new

.gitattributes

@@ -33,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-Tutorial.xlsx filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,31 +1,30 @@
-FROM python:3.10-slim-bullseye
+FROM python:3.9-slim-bullseye
 
-# 1) System dependencies (minimal)
+# 1) System deps (as root)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     curl \
     git \
  && rm -rf /var/lib/apt/lists/*
 
-# 2) Create non-root user
+# 2) Create a non-root user for runtime
 RUN useradd -m -u 1000 appuser
 
 # 3) App setup
 WORKDIR /app
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
+COPY requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt
 COPY . .
 
-# 4) Permissions
+# 4) Make sure the runtime user can write where needed
 RUN chown -R appuser:appuser /app /home/appuser
 
-# 5) Streamlit config
+# 5) Streamlit config in a writable home
 RUN mkdir -p /home/appuser/.streamlit && \
-    printf "[general]\nemail = \"\"\n" > /home/appuser/.streamlit/credentials.toml && \
-    printf "[server]\nheadless = true\nenableCORS = false\n" > /home/appuser/.streamlit/config.toml && \
+    printf "[general]\nbrowser.gatherUsageStats = false\n" > /home/appuser/.streamlit/config.toml && \
     chown -R appuser:appuser /home/appuser/.streamlit
 
-# 6) Environment variables & non-root
+# 6) Env for Streamlit + switch to non-root
 ENV HOME=/home/appuser
 ENV STREAMLIT_CONFIG_DIR=/home/appuser/.streamlit
 USER appuser
@@ -33,5 +32,4 @@ USER appuser
 EXPOSE 8501
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health || exit 1
 
-# 7) Run Streamlit app
-ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

Lucky For Life.csv

@@ -1,661 +0,0 @@
-date,b1,b2,b3,b4,b5,lucky_ball
-1/29/2026,14,24,25,39,40,17
-1/28/2026,19,24,26,27,47,14
-1/27/2026,1,10,32,37,48,9
-1/26/2026,3,21,22,42,44,9
-1/25/2026,2,25,27,29,31,13
-1/24/2026,8,17,25,40,44,7
-1/23/2026,6,16,17,18,29,4
-1/22/2026,8,20,30,42,46,15
-1/21/2026,3,10,22,32,38,11
-1/20/2026,6,9,28,41,45,8
-1/19/2026,5,17,22,42,48,16
-1/18/2026,11,18,21,42,48,17
-1/17/2026,10,17,24,33,34,17
-1/16/2026,4,6,9,14,17,17
-1/15/2026,3,24,32,39,41,18
-1/14/2026,14,17,21,30,36,3
-1/13/2026,21,32,34,35,38,4
-1/12/2026,21,23,24,28,39,1
-1/11/2026,5,6,12,14,24,12
-1/10/2026,17,24,36,38,43,17
-1/9/2026,19,24,40,42,44,5
-1/8/2026,5,12,13,39,48,13
-1/7/2026,5,14,15,21,39,10
-1/6/2026,10,13,24,27,31,8
-1/5/2026,2,7,8,21,45,15
-1/4/2026,3,8,13,38,47,2
-1/3/2026,1,2,28,30,43,7
-1/2/2026,9,15,20,21,25,2
-1/1/2026,2,8,17,32,45,15
-12/31/2025,26,30,41,43,47,12
-12/30/2025,3,7,15,24,30,16
-12/29/2025,1,8,16,17,26,12
-12/28/2025,12,17,25,34,42,9
-12/27/2025,8,12,24,26,42,17
-12/26/2025,2,9,15,20,24,3
-12/25/2025,23,29,31,37,45,16
-12/24/2025,3,5,7,17,34,9
-12/23/2025,2,4,12,37,42,10
-12/22/2025,9,16,23,34,46,7
-12/21/2025,11,24,27,38,46,15
-12/20/2025,8,21,30,41,47,15
-12/19/2025,8,13,19,34,48,14
-12/18/2025,2,9,24,25,44,15
-12/17/2025,11,13,20,40,41,7
-12/16/2025,3,4,19,24,39,11
-12/15/2025,12,16,27,34,41,12
-12/14/2025,8,23,32,33,34,15
-12/13/2025,12,18,19,24,35,17
-12/12/2025,6,20,23,30,36,11
-12/11/2025,7,20,24,30,39,18
-12/10/2025,5,7,14,16,45,11
-12/9/2025,19,24,33,39,40,6
-12/8/2025,11,14,28,30,41,11
-12/7/2025,5,8,11,12,34,4
-12/6/2025,11,12,14,34,48,13
-12/5/2025,4,35,38,40,41,3
-12/4/2025,1,10,21,35,47,4
-12/3/2025,20,21,22,41,43,17
-12/2/2025,1,15,17,24,29,2
-12/1/2025,10,16,18,30,43,18
-11/30/2025,3,8,13,17,18,17
-11/29/2025,4,8,9,34,39,13
-11/28/2025,19,28,32,41,47,16
-11/27/2025,8,12,13,16,45,13
-11/26/2025,8,12,15,23,43,5
-11/25/2025,7,11,32,37,44,14
-11/24/2025,3,11,18,24,38,2
-11/23/2025,3,4,13,28,41,9
-11/22/2025,4,8,24,28,47,16
-11/21/2025,19,29,39,41,48,18
-11/20/2025,5,8,37,39,40,16
-11/19/2025,2,4,12,34,38,16
-11/18/2025,4,8,30,31,37,3
-11/17/2025,8,12,16,24,37,8
-11/16/2025,3,11,26,32,45,2
-11/15/2025,16,29,32,33,37,16
-11/14/2025,14,19,34,42,43,13
-11/13/2025,3,9,16,20,42,11
-11/12/2025,20,28,30,33,44,15
-11/11/2025,12,25,30,40,42,15
-11/10/2025,11,17,32,39,44,13
-11/9/2025,17,19,33,46,47,10
-11/8/2025,27,31,41,46,47,15
-11/7/2025,5,9,16,30,41,2
-11/6/2025,9,15,32,39,41,11
-11/5/2025,9,12,29,38,43,15
-11/4/2025,3,13,17,27,44,12
-11/3/2025,1,31,32,34,37,13
-11/2/2025,8,14,19,25,38,15
-11/1/2025,6,19,28,38,46,8
-10/31/2025,3,27,37,40,42,1
-10/30/2025,1,10,23,29,34,16
-10/29/2025,3,4,33,36,43,2
-10/28/2025,14,15,21,24,45,8
-10/26/2025,2,8,11,24,30,10
-10/25/2025,21,32,34,35,44,5
-10/24/2025,8,9,28,31,46,6
-10/23/2025,12,30,33,39,40,3
-10/22/2025,1,20,30,37,46,1
-10/21/2025,8,9,15,31,32,12
-10/20/2025,3,5,23,26,28,4
-10/19/2025,11,31,35,42,45,3
-10/18/2025,13,20,24,31,45,12
-10/17/2025,7,24,34,45,47,11
-10/16/2025,4,7,42,43,46,11
-10/15/2025,13,25,27,31,46,17
-10/14/2025,2,5,15,34,37,1
-10/13/2025,3,9,19,28,46,5
-10/12/2025,5,11,15,22,45,14
-10/11/2025,10,37,40,42,45,8
-10/10/2025,3,35,39,40,45,6
-10/9/2025,9,11,27,42,46,17
-10/8/2025,9,13,14,35,46,6
-10/7/2025,8,32,42,44,46,8
-10/6/2025,6,11,30,34,39,10
-10/5/2025,4,23,25,32,40,16
-10/4/2025,8,17,18,24,35,1
-10/3/2025,1,22,23,25,38,12
-10/2/2025,16,21,26,34,48,7
-10/1/2025,1,4,5,16,47,7
-9/30/2025,8,15,17,30,39,14
-9/29/2025,1,25,29,40,43,1
-9/28/2025,8,9,27,31,36,6
-9/27/2025,4,7,8,34,48,1
-9/26/2025,22,30,33,37,43,14
-9/25/2025,5,7,19,28,34,14
-9/24/2025,3,26,29,40,45,3
-9/23/2025,18,19,38,42,44,1
-9/22/2025,6,9,15,42,43,15
-9/21/2025,9,11,14,26,33,11
-9/20/2025,11,16,31,34,38,18
-9/19/2025,9,16,23,25,26,17
-9/18/2025,14,29,41,44,46,4
-9/17/2025,3,11,29,40,41,2
-9/16/2025,7,17,22,27,32,8
-9/15/2025,14,21,23,24,43,1
-9/14/2025,23,33,34,38,40,17
-9/13/2025,20,21,23,29,39,11
-9/12/2025,28,34,35,36,43,11
-9/11/2025,5,40,42,47,48,10
-9/10/2025,11,12,35,37,45,11
-9/9/2025,2,4,7,34,45,7
-9/8/2025,5,9,21,22,36,18
-9/7/2025,13,29,34,37,40,9
-9/6/2025,4,12,14,15,21,9
-9/5/2025,18,25,35,47,48,2
-9/4/2025,17,20,23,25,39,2
-9/3/2025,11,15,19,40,48,3
-9/2/2025,4,5,24,29,40,11
-9/1/2025,15,18,39,46,47,2
-8/31/2025,13,14,19,25,28,6
-8/30/2025,6,12,38,43,45,7
-8/29/2025,8,14,22,24,30,17
-8/28/2025,8,10,17,23,33,2
-8/27/2025,6,15,26,38,48,8
-8/26/2025,5,6,8,17,36,12
-8/25/2025,1,4,12,17,20,6
-8/24/2025,9,16,18,25,42,15
-8/23/2025,9,11,17,25,42,11
-8/22/2025,8,19,26,27,29,15
-8/21/2025,23,27,32,41,46,15
-8/20/2025,1,5,18,25,28,4
-8/19/2025,1,4,30,46,48,7
-8/18/2025,3,12,24,30,40,2
-8/17/2025,8,15,20,25,28,3
-8/16/2025,1,3,8,26,32,10
-8/15/2025,2,8,19,26,32,18
-8/14/2025,3,10,17,25,37,1
-8/13/2025,13,23,30,31,38,2
-8/12/2025,1,11,18,29,34,15
-8/11/2025,18,22,26,40,46,3
-8/10/2025,6,11,25,40,46,7
-8/9/2025,9,19,35,44,45,17
-8/8/2025,20,23,32,40,46,10
-8/7/2025,16,25,26,27,36,16
-8/6/2025,7,22,38,39,40,3
-8/5/2025,17,27,32,37,39,15
-8/4/2025,25,26,30,37,45,16
-8/3/2025,4,9,25,33,43,6
-8/2/2025,8,10,16,18,36,8
-8/1/2025,8,20,22,24,36,15
-7/31/2025,14,25,33,39,40,10
-7/30/2025,2,5,22,33,40,12
-7/29/2025,2,4,15,18,42,7
-7/28/2025,4,9,13,23,34,6
-7/27/2025,4,6,9,25,47,4
-7/26/2025,4,8,9,22,23,8
-7/25/2025,19,20,31,37,41,2
-7/24/2025,1,11,22,26,29,18
-7/23/2025,5,9,11,30,47,8
-7/22/2025,18,19,22,30,48,2
-7/21/2025,1,12,19,38,48,10
-7/20/2025,26,31,37,41,43,1
-7/19/2025,12,23,33,35,36,8
-7/18/2025,10,12,18,22,39,9
-7/17/2025,1,7,9,10,32,8
-7/16/2025,17,21,23,25,47,9
-7/15/2025,21,25,26,39,48,2
-7/14/2025,19,21,26,40,48,16
-7/13/2025,4,7,20,35,40,2
-7/12/2025,3,6,17,42,46,4
-7/11/2025,1,6,8,18,47,11
-7/10/2025,7,9,11,17,32,3
-7/9/2025,9,17,38,43,47,3
-7/8/2025,16,26,27,34,43,15
-7/7/2025,3,12,24,40,42,13
-7/6/2025,6,15,16,30,45,12
-7/5/2025,9,17,26,27,41,1
-7/4/2025,9,26,27,30,46,5
-7/3/2025,12,29,30,42,45,18
-7/2/2025,3,6,16,22,42,17
-7/1/2025,1,2,19,30,33,2
-6/30/2025,7,11,26,37,41,17
-6/29/2025,12,24,29,34,48,4
-6/28/2025,9,11,40,46,47,8
-6/27/2025,5,12,33,43,47,17
-6/26/2025,5,7,37,41,42,15
-6/25/2025,7,28,33,43,48,9
-6/24/2025,1,4,27,40,45,11
-6/23/2025,13,22,23,26,47,13
-6/22/2025,12,19,21,23,38,6
-6/21/2025,8,10,22,26,28,4
-6/20/2025,5,9,31,33,45,8
-6/19/2025,2,5,8,18,45,1
-6/18/2025,6,16,25,26,44,14
-6/17/2025,4,7,28,36,46,2
-6/16/2025,17,27,34,38,41,10
-6/15/2025,12,17,25,40,44,7
-6/14/2025,6,22,31,35,37,9
-6/13/2025,4,12,18,22,29,15
-6/12/2025,2,4,6,37,40,5
-6/11/2025,7,9,30,36,43,4
-6/10/2025,10,26,30,41,44,17
-6/9/2025,3,7,17,29,46,15
-6/8/2025,5,11,20,42,43,10
-6/7/2025,2,4,28,34,45,2
-6/6/2025,10,15,38,41,45,18
-6/5/2025,1,14,19,28,41,7
-6/4/2025,11,12,14,40,41,10
-6/3/2025,1,21,32,34,48,1
-6/2/2025,1,10,22,29,40,15
-6/1/2025,28,29,38,39,42,16
-5/31/2025,11,18,22,27,31,13
-5/30/2025,13,17,30,35,48,9
-5/29/2025,9,14,20,31,46,7
-5/28/2025,3,11,35,43,47,11
-5/27/2025,10,12,18,43,46,18
-5/26/2025,12,15,19,22,33,3
-5/25/2025,12,20,30,35,47,2
-5/24/2025,9,10,32,36,44,12
-5/23/2025,4,11,15,19,38,4
-5/22/2025,12,16,28,31,37,3
-5/21/2025,8,23,32,40,45,18
-5/20/2025,5,6,16,29,34,8
-5/19/2025,22,23,32,35,39,15
-5/18/2025,1,3,4,18,30,8
-5/17/2025,1,4,27,38,46,13
-5/16/2025,14,24,25,29,35,4
-5/15/2025,7,16,17,20,23,4
-5/14/2025,14,23,37,41,46,18
-5/13/2025,4,14,17,43,44,12
-5/12/2025,9,13,15,16,48,11
-5/11/2025,16,26,30,34,43,6
-5/10/2025,5,12,19,43,47,14
-5/9/2025,4,9,22,41,46,13
-5/8/2025,14,18,23,34,35,17
-5/7/2025,5,7,37,39,46,15
-5/6/2025,15,31,33,35,46,17
-5/5/2025,3,26,30,32,39,8
-5/4/2025,12,26,31,35,43,14
-5/3/2025,2,13,18,21,31,9
-5/2/2025,2,17,18,33,38,15
-5/1/2025,17,32,36,41,46,4
-4/30/2025,3,5,22,23,44,4
-4/29/2025,24,25,39,43,45,13
-4/28/2025,16,19,20,33,40,11
-4/27/2025,4,19,35,36,41,5
-4/26/2025,15,38,40,45,48,6
-4/25/2025,9,15,40,41,48,5
-4/24/2025,13,15,20,31,38,14
-4/23/2025,8,14,15,23,24,15
-4/22/2025,14,31,36,39,44,8
-4/21/2025,12,25,29,36,47,3
-4/20/2025,3,6,17,30,42,15
-4/19/2025,3,22,39,41,43,11
-4/18/2025,29,34,39,42,46,16
-4/17/2025,4,18,22,26,44,15
-4/16/2025,1,34,38,43,47,3
-4/15/2025,10,19,26,30,48,11
-4/14/2025,10,11,23,35,40,13
-4/13/2025,2,29,30,43,45,9
-4/12/2025,1,14,16,19,41,12
-4/11/2025,7,9,10,31,34,10
-4/10/2025,9,18,38,39,45,13
-4/9/2025,1,14,24,29,46,14
-4/8/2025,3,28,32,44,48,12
-4/7/2025,21,25,31,37,38,18
-4/6/2025,3,6,27,37,40,11
-4/5/2025,8,15,29,37,47,6
-4/4/2025,1,4,11,22,32,6
-4/3/2025,2,5,11,14,28,18
-4/2/2025,18,22,35,36,43,8
-4/1/2025,9,20,29,36,41,8
-3/31/2025,8,31,39,40,42,4
-3/30/2025,19,20,27,36,39,6
-3/29/2025,4,8,13,18,41,12
-3/28/2025,10,15,23,31,40,18
-3/27/2025,7,20,27,35,46,5
-3/26/2025,8,12,15,39,44,15
-3/25/2025,9,16,27,30,35,7
-3/24/2025,14,20,30,31,39,1
-3/23/2025,16,19,21,39,47,6
-3/22/2025,13,14,32,46,47,10
-3/21/2025,7,25,28,40,45,7
-3/20/2025,7,14,25,35,40,14
-3/19/2025,17,21,36,40,45,3
-3/18/2025,8,20,37,39,46,15
-3/17/2025,6,12,25,29,32,15
-3/16/2025,4,14,16,28,34,7
-3/15/2025,9,12,30,39,41,12
-3/14/2025,7,16,28,40,48,18
-3/13/2025,19,24,27,32,38,12
-3/12/2025,5,8,10,20,44,1
-3/11/2025,2,7,17,18,28,14
-3/10/2025,7,8,13,21,42,8
-3/9/2025,6,14,18,40,46,6
-3/8/2025,9,20,31,40,44,10
-3/7/2025,2,7,25,28,36,8
-3/6/2025,20,28,30,31,38,10
-3/5/2025,4,12,21,22,40,17
-3/4/2025,2,11,25,30,31,7
-3/3/2025,10,15,21,27,45,1
-3/2/2025,4,24,26,32,42,12
-3/1/2025,12,25,28,30,43,3
-2/28/2025,9,16,18,23,42,13
-2/27/2025,2,18,24,26,45,12
-2/26/2025,5,18,27,33,38,10
-2/25/2025,6,10,14,16,25,11
-2/24/2025,7,16,23,33,40,8
-2/23/2025,1,18,43,44,46,7
-2/22/2025,2,6,29,35,44,7
-2/21/2025,19,35,44,45,47,10
-2/20/2025,15,39,40,42,47,7
-2/19/2025,7,21,30,41,42,2
-2/18/2025,2,5,16,19,46,7
-2/17/2025,2,7,42,43,47,6
-2/16/2025,3,15,16,19,32,3
-2/15/2025,21,34,38,40,48,10
-2/14/2025,7,11,12,22,34,8
-2/13/2025,1,21,25,37,45,11
-2/12/2025,8,29,34,36,42,11
-2/11/2025,8,25,28,41,46,5
-2/10/2025,1,2,16,18,30,6
-2/9/2025,8,13,22,28,39,12
-2/8/2025,1,7,15,17,40,18
-2/7/2025,14,18,21,29,31,10
-2/6/2025,18,21,32,39,41,7
-2/5/2025,7,9,25,37,39,3
-2/4/2025,2,5,23,29,47,8
-2/3/2025,3,24,28,33,35,16
-2/2/2025,5,6,17,27,36,12
-2/1/2025,4,34,36,42,47,2
-1/31/2025,3,7,34,39,44,13
-1/30/2025,9,13,18,23,40,4
-1/29/2025,1,20,25,30,34,11
-1/28/2025,7,20,24,39,43,9
-1/27/2025,7,16,41,42,48,5
-1/26/2025,1,10,21,28,40,11
-1/25/2025,8,26,28,38,46,6
-1/24/2025,14,26,35,39,40,10
-1/23/2025,9,13,18,24,46,6
-1/22/2025,24,25,37,44,45,9
-1/21/2025,18,27,30,40,44,15
-1/20/2025,4,8,12,22,35,15
-1/19/2025,8,24,35,43,46,4
-1/18/2025,4,12,13,32,43,17
-1/17/2025,1,4,6,9,46,4
-1/16/2025,13,20,29,32,37,6
-1/15/2025,19,31,33,36,46,7
-1/14/2025,3,6,17,26,39,4
-1/13/2025,13,17,35,41,44,5
-1/12/2025,2,10,22,26,47,8
-1/11/2025,21,22,26,27,48,12
-1/10/2025,3,9,21,33,36,1
-1/9/2025,2,4,14,17,28,11
-1/8/2025,13,14,24,37,38,13
-1/7/2025,16,24,30,32,44,2
-1/6/2025,6,22,31,39,44,3
-1/5/2025,6,27,31,33,47,13
-1/4/2025,3,9,27,29,33,6
-1/3/2025,14,15,20,23,28,12
-1/2/2025,12,14,27,44,46,6
-1/1/2025,7,15,17,39,40,16
-12/31/2024,19,27,37,41,48,15
-12/30/2024,7,14,18,25,47,18
-12/29/2024,7,18,26,35,38,1
-12/28/2024,14,19,21,25,30,9
-12/27/2024,15,21,24,32,43,11
-12/26/2024,9,10,12,30,47,9
-12/25/2024,4,10,35,42,45,2
-12/24/2024,16,22,24,43,47,11
-12/23/2024,10,20,22,23,43,1
-12/22/2024,4,7,37,43,47,8
-12/21/2024,2,9,10,41,42,9
-12/20/2024,9,20,21,35,36,3
-12/19/2024,2,5,13,18,29,16
-12/18/2024,19,26,30,31,41,16
-12/17/2024,4,18,29,36,37,18
-12/16/2024,3,16,29,31,33,9
-12/15/2024,9,12,22,36,45,3
-12/14/2024,10,16,35,40,42,16
-12/13/2024,3,15,32,34,37,18
-12/12/2024,5,7,17,19,32,12
-12/11/2024,10,19,32,44,46,1
-12/10/2024,6,12,30,39,46,10
-12/9/2024,1,13,19,22,28,11
-12/8/2024,1,2,39,40,42,4
-12/7/2024,1,17,34,41,45,14
-12/6/2024,1,3,33,36,39,1
-12/5/2024,4,13,25,44,47,18
-12/4/2024,1,13,25,33,46,6
-12/3/2024,6,11,28,30,37,9
-12/2/2024,5,13,14,31,42,15
-12/1/2024,1,7,25,33,46,7
-11/30/2024,21,22,32,36,48,5
-11/29/2024,19,21,31,38,39,5
-11/28/2024,18,33,42,44,45,2
-11/27/2024,5,16,22,25,45,15
-11/26/2024,27,29,32,33,47,2
-11/25/2024,7,10,14,33,36,1
-11/24/2024,7,11,14,26,48,15
-11/23/2024,11,20,21,26,31,7
-11/22/2024,17,31,33,38,46,17
-11/21/2024,4,11,13,45,47,18
-11/20/2024,3,29,30,39,45,13
-11/19/2024,7,10,17,24,26,13
-11/18/2024,4,9,10,28,29,1
-11/17/2024,10,20,26,28,42,2
-11/16/2024,6,11,18,20,29,4
-11/15/2024,5,28,34,38,44,13
-11/14/2024,5,22,30,33,44,3
-11/13/2024,18,24,27,43,45,8
-11/12/2024,11,21,22,24,48,8
-11/11/2024,5,11,17,19,30,11
-11/10/2024,11,18,32,38,40,3
-11/9/2024,4,7,19,36,39,1
-11/8/2024,2,7,19,42,47,4
-11/7/2024,5,10,30,37,40,5
-11/6/2024,4,7,12,14,43,5
-11/5/2024,1,9,14,38,45,12
-11/4/2024,8,18,28,36,43,6
-11/3/2024,5,13,18,21,42,8
-11/2/2024,21,25,30,34,35,9
-11/1/2024,15,37,39,45,47,16
-10/31/2024,29,30,31,33,36,4
-10/30/2024,14,17,27,28,43,13
-10/29/2024,4,8,9,25,48,10
-10/28/2024,3,17,21,35,39,8
-10/27/2024,1,4,8,27,42,1
-10/26/2024,6,12,32,35,41,13
-10/25/2024,1,3,15,33,36,5
-10/24/2024,2,4,9,29,32,8
-10/23/2024,9,12,22,25,44,9
-10/22/2024,7,12,22,37,48,9
-10/21/2024,3,14,23,37,38,2
-10/20/2024,3,15,21,37,38,15
-10/19/2024,10,14,24,45,46,9
-10/18/2024,10,31,32,36,38,6
-10/17/2024,23,26,29,36,47,14
-10/16/2024,5,29,32,45,46,7
-10/15/2024,15,20,21,24,38,5
-10/14/2024,1,12,25,32,35,7
-10/13/2024,2,6,14,25,45,9
-10/12/2024,6,17,20,22,46,13
-10/11/2024,3,18,29,33,36,12
-10/10/2024,7,8,26,27,47,13
-10/9/2024,11,15,31,36,45,2
-10/8/2024,5,17,22,26,32,11
-10/7/2024,8,21,22,28,47,16
-10/6/2024,1,8,10,26,34,10
-10/5/2024,3,17,31,32,35,18
-10/4/2024,1,4,34,39,42,6
-10/3/2024,2,5,29,42,48,18
-10/2/2024,6,30,33,42,44,13
-10/1/2024,5,13,22,31,48,18
-9/30/2024,21,28,29,40,42,18
-9/29/2024,7,15,27,31,38,14
-9/28/2024,7,20,23,38,48,11
-9/27/2024,4,7,9,24,36,1
-9/26/2024,4,8,27,37,40,8
-9/25/2024,4,7,15,21,31,13
-9/24/2024,6,9,18,36,38,4
-9/23/2024,1,21,24,27,48,18
-9/22/2024,5,13,27,35,48,14
-9/21/2024,7,21,31,41,44,5
-9/20/2024,2,9,17,18,27,2
-9/19/2024,11,20,28,35,43,13
-9/18/2024,10,13,28,43,47,9
-9/17/2024,10,16,23,29,35,18
-9/16/2024,1,2,15,17,39,14
-9/15/2024,1,2,10,22,27,11
-9/14/2024,5,13,27,28,44,6
-9/13/2024,14,15,18,33,40,9
-9/12/2024,23,32,38,41,44,18
-9/11/2024,12,19,37,43,48,1
-9/10/2024,30,39,42,45,48,6
-9/9/2024,16,26,30,35,46,6
-9/8/2024,9,17,27,42,45,12
-9/7/2024,3,20,29,34,39,13
-9/6/2024,3,23,24,25,30,5
-9/5/2024,2,3,18,23,25,12
-9/4/2024,4,12,14,40,47,11
-9/3/2024,25,36,38,39,48,8
-9/2/2024,3,4,8,28,29,5
-9/1/2024,17,22,27,35,42,17
-8/31/2024,2,15,37,45,46,18
-8/30/2024,3,24,25,30,43,11
-8/29/2024,7,13,18,23,42,12
-8/28/2024,4,7,8,17,34,6
-8/27/2024,1,3,18,23,42,16
-8/26/2024,12,18,24,40,44,9
-8/25/2024,8,17,19,29,31,12
-8/24/2024,13,19,26,33,38,15
-8/23/2024,17,24,28,34,39,2
-8/22/2024,2,5,21,45,47,18
-8/21/2024,9,16,26,42,45,11
-8/20/2024,8,12,24,39,40,6
-8/19/2024,15,17,35,40,45,6
-8/18/2024,2,4,11,32,39,18
-8/17/2024,22,24,27,42,47,4
-8/16/2024,5,12,17,21,45,8
-8/15/2024,3,7,19,24,38,11
-8/14/2024,7,19,29,30,39,4
-8/13/2024,6,30,37,42,47,3
-8/12/2024,3,6,17,24,35,2
-8/11/2024,3,5,10,12,32,16
-8/10/2024,3,26,30,37,43,2
-8/9/2024,19,26,36,42,43,17
-8/8/2024,3,4,9,33,44,12
-8/7/2024,3,9,30,45,46,1
-8/6/2024,4,15,21,22,35,3
-8/5/2024,20,26,28,33,44,9
-8/4/2024,10,17,19,29,46,10
-8/3/2024,8,10,15,17,21,18
-8/2/2024,11,13,16,27,33,16
-8/1/2024,3,25,36,41,42,14
-7/31/2024,10,16,20,31,44,12
-7/30/2024,19,22,34,41,45,12
-7/29/2024,18,28,30,32,33,11
-7/28/2024,2,4,10,26,29,3
-7/27/2024,9,32,37,40,43,15
-7/26/2024,1,4,21,37,41,13
-7/25/2024,2,11,33,46,47,8
-7/24/2024,15,18,21,25,36,16
-7/23/2024,1,4,15,25,31,17
-7/22/2024,17,19,20,28,29,11
-7/21/2024,2,5,20,36,39,7
-7/20/2024,14,19,20,35,46,11
-7/19/2024,4,7,20,26,34,8
-7/18/2024,9,22,25,35,45,10
-7/17/2024,7,18,20,39,46,10
-7/16/2024,21,26,31,34,40,15
-7/15/2024,1,2,3,20,24,18
-7/14/2024,9,13,16,20,23,11
-7/13/2024,8,16,27,33,34,10
-7/12/2024,1,2,27,34,44,14
-7/11/2024,3,4,9,17,37,10
-7/10/2024,2,14,19,22,36,9
-7/9/2024,25,31,40,41,44,4
-7/8/2024,2,9,27,37,48,1
-7/7/2024,7,13,15,30,34,4
-7/6/2024,3,13,21,29,37,6
-7/5/2024,7,15,23,41,48,17
-7/4/2024,3,4,22,33,48,4
-7/3/2024,10,11,23,35,42,16
-7/2/2024,9,15,18,28,34,3
-7/1/2024,13,22,31,47,48,5
-6/30/2024,6,9,12,24,32,14
-6/29/2024,10,11,22,25,44,9
-6/28/2024,10,21,41,43,48,4
-6/27/2024,5,14,34,46,48,8
-6/26/2024,5,12,36,39,40,6
-6/25/2024,15,20,23,33,45,5
-6/24/2024,20,26,27,29,33,14
-6/23/2024,3,5,23,43,46,8
-6/22/2024,12,14,22,38,46,4
-6/21/2024,4,7,13,29,46,1
-6/20/2024,22,24,25,28,35,4
-6/19/2024,10,16,18,19,31,10
-6/18/2024,5,14,18,37,48,5
-6/17/2024,15,26,32,38,46,3
-6/16/2024,1,12,20,38,43,10
-6/15/2024,2,7,8,12,21,16
-6/14/2024,6,21,25,33,45,6
-6/13/2024,1,12,18,23,38,1
-6/12/2024,3,12,15,19,34,6
-6/11/2024,12,23,31,44,48,8
-6/10/2024,7,9,14,23,47,17
-6/9/2024,2,3,33,39,41,7
-6/8/2024,3,17,29,31,33,11
-6/7/2024,3,12,15,25,32,2
-6/6/2024,21,28,30,31,37,12
-6/5/2024,1,2,12,30,33,6
-6/4/2024,8,13,39,42,48,11
-6/3/2024,8,21,23,39,40,8
-6/2/2024,8,16,19,20,25,6
-6/1/2024,22,29,33,36,40,15
-5/31/2024,10,31,34,42,46,17
-5/30/2024,9,11,12,14,24,5
-5/29/2024,9,12,15,41,46,4
-5/28/2024,9,18,21,37,46,1
-5/27/2024,2,9,17,19,46,4
-5/26/2024,2,17,25,26,43,2
-5/25/2024,2,4,21,26,42,18
-5/24/2024,13,17,24,29,33,7
-5/23/2024,4,8,9,28,29,11
-5/22/2024,5,8,15,17,37,4
-5/21/2024,5,13,24,41,48,15
-5/20/2024,12,15,19,20,47,16
-5/19/2024,6,16,32,34,41,12
-5/18/2024,18,21,34,37,40,13
-5/17/2024,2,22,31,34,37,9
-5/16/2024,12,19,34,39,45,14
-5/15/2024,12,18,24,38,40,5
-5/14/2024,9,27,43,44,48,9
-5/13/2024,13,16,20,39,43,11
-5/12/2024,8,14,26,29,47,15
-5/11/2024,3,9,20,23,37,2
-5/10/2024,24,30,32,35,41,11
-5/9/2024,3,6,7,22,41,4
-5/8/2024,17,30,31,33,44,16
-5/7/2024,9,21,22,33,48,18
-5/6/2024,10,32,35,43,47,6
-5/5/2024,1,6,10,16,27,8
-5/4/2024,1,4,5,6,33,1
-5/3/2024,15,19,32,34,36,7
-5/2/2024,7,14,16,37,41,17
-5/1/2024,2,9,19,21,46,13
-4/30/2024,7,8,19,36,41,1
-4/29/2024,12,14,16,25,46,16
-4/28/2024,4,25,32,35,40,9
-4/27/2024,16,22,26,31,34,12
-4/26/2024,11,15,27,28,46,7
-4/25/2024,3,9,21,31,41,8
-4/24/2024,4,40,41,45,46,6
-4/23/2024,11,31,32,36,44,8
-4/22/2024,33,36,39,40,47,15
-4/21/2024,23,24,31,33,40,10
-4/20/2024,17,23,28,33,37,10
-4/19/2024,5,8,24,28,34,5
-4/18/2024,4,10,16,44,45,14
-4/17/2024,6,9,19,27,42,2
-4/16/2024,20,22,28,41,45,18
-4/15/2024,11,24,25,44,46,4
-4/14/2024,6,20,30,37,44,18
-4/13/2024,15,20,34,36,43,9
-4/12/2024,1,19,20,34,44,4
-4/11/2024,4,10,27,33,40,8
-4/10/2024,2,4,7,12,39,14
-4/9/2024,1,11,12,19,45,3

Pick3eve.csv

@@ -1,1020 +0,0 @@
-DrawDate,1,2,3
-3/9/2023,0,9,3
-3/10/2023,3,5,3
-3/11/2023,8,3,1
-3/12/2023,9,5,5
-3/13/2023,6,4,9
-3/14/2023,5,7,0
-3/15/2023,7,5,9
-3/16/2023,9,1,6
-3/17/2023,0,9,0
-3/18/2023,1,6,6
-3/19/2023,1,4,6
-3/20/2023,5,6,1
-3/21/2023,7,9,2
-3/22/2023,0,3,1
-3/23/2023,4,1,4
-3/24/2023,0,6,5
-3/25/2023,8,0,6
-3/26/2023,4,9,9
-3/27/2023,1,9,4
-3/28/2023,6,2,9
-3/29/2023,1,6,0
-3/30/2023,1,9,0
-3/31/2023,2,1,5
-4/1/2023,8,8,6
-4/2/2023,9,2,3
-4/3/2023,3,1,9
-4/4/2023,3,8,9
-4/5/2023,3,6,3
-4/6/2023,1,3,6
-4/7/2023,8,1,9
-4/8/2023,5,4,5
-4/9/2023,8,9,6
-4/10/2023,4,1,5
-4/11/2023,6,8,0
-4/12/2023,0,5,9
-4/13/2023,5,6,2
-4/14/2023,5,4,6
-4/15/2023,3,9,4
-4/16/2023,7,1,0
-4/17/2023,8,9,9
-4/18/2023,1,5,7
-4/19/2023,6,4,5
-4/20/2023,2,8,7
-4/21/2023,9,9,9
-4/22/2023,7,0,7
-4/23/2023,3,8,4
-4/24/2023,6,9,5
-4/25/2023,7,5,1
-4/26/2023,1,1,7
-4/27/2023,7,9,3
-4/28/2023,6,8,6
-4/29/2023,4,1,8
-4/30/2023,7,9,3
-5/1/2023,4,9,4
-5/2/2023,9,7,5
-5/3/2023,1,1,1
-5/4/2023,4,2,6
-5/5/2023,7,9,1
-5/6/2023,8,8,2
-5/7/2023,7,6,5
-5/8/2023,2,0,4
-5/9/2023,0,9,0
-5/10/2023,1,9,4
-5/11/2023,8,6,9
-5/12/2023,3,2,8
-5/13/2023,8,7,7
-5/14/2023,2,1,2
-5/15/2023,3,5,9
-5/16/2023,1,9,1
-5/17/2023,2,2,0
-5/18/2023,2,7,5
-5/19/2023,4,6,9
-5/20/2023,3,1,2
-5/21/2023,3,9,0
-5/22/2023,0,3,0
-5/23/2023,2,4,8
-5/24/2023,5,0,9
-5/25/2023,6,6,7
-5/26/2023,1,7,3
-5/27/2023,0,1,9
-5/28/2023,3,2,3
-5/29/2023,6,5,9
-5/30/2023,4,1,3
-5/31/2023,5,4,4
-6/1/2023,6,7,9
-6/2/2023,6,6,6
-6/3/2023,0,2,1
-6/4/2023,3,8,0
-6/5/2023,1,5,2
-6/6/2023,1,8,0
-6/7/2023,7,3,5
-6/8/2023,1,4,5
-6/9/2023,4,6,8
-6/10/2023,9,9,7
-6/11/2023,7,1,4
-6/12/2023,7,7,9
-6/13/2023,1,1,0
-6/14/2023,0,8,0
-6/15/2023,9,8,9
-6/16/2023,0,3,4
-6/17/2023,8,8,0
-6/18/2023,6,1,9
-6/19/2023,6,7,0
-6/20/2023,4,8,0
-6/21/2023,9,5,9
-6/22/2023,9,9,1
-6/23/2023,9,6,8
-6/24/2023,7,4,7
-6/25/2023,0,1,8
-6/26/2023,6,3,6
-6/27/2023,1,5,0
-6/28/2023,0,9,5
-6/29/2023,0,6,3
-6/30/2023,3,4,2
-7/1/2023,2,6,0
-7/2/2023,9,2,1
-7/3/2023,0,2,7
-7/4/2023,6,3,9
-7/5/2023,0,7,9
-7/6/2023,5,8,2
-7/7/2023,2,2,7
-7/8/2023,0,9,9
-7/9/2023,1,1,0
-7/10/2023,8,0,3
-7/11/2023,3,2,2
-7/12/2023,9,6,8
-7/13/2023,8,1,8
-7/14/2023,2,0,8
-7/15/2023,2,3,1
-7/16/2023,9,0,5
-7/17/2023,4,6,8
-7/18/2023,8,9,0
-7/19/2023,9,5,9
-7/20/2023,3,5,1
-7/21/2023,4,6,4
-7/22/2023,9,2,4
-7/23/2023,2,5,6
-7/24/2023,0,4,6
-7/25/2023,1,8,3
-7/26/2023,1,7,1
-7/27/2023,2,5,9
-7/28/2023,6,6,2
-7/29/2023,6,8,1
-7/30/2023,6,1,5
-7/31/2023,9,8,8
-8/1/2023,0,2,1
-8/2/2023,8,1,1
-8/3/2023,9,7,1
-8/4/2023,4,7,0
-8/5/2023,2,7,5
-8/6/2023,8,0,4
-8/7/2023,1,1,3
-8/8/2023,2,0,5
-8/9/2023,2,1,9
-8/10/2023,9,3,0
-8/11/2023,6,7,0
-8/12/2023,7,5,1
-8/13/2023,1,2,5
-8/14/2023,8,8,4
-8/15/2023,0,0,5
-8/16/2023,3,8,9
-8/17/2023,0,1,4
-8/18/2023,0,8,1
-8/19/2023,4,5,4
-8/20/2023,6,0,1
-8/21/2023,1,7,9
-8/22/2023,4,2,1
-8/23/2023,4,2,8
-8/24/2023,3,7,1
-8/25/2023,4,3,7
-8/26/2023,4,5,8
-8/27/2023,0,4,5
-8/28/2023,8,3,2
-8/29/2023,6,1,0
-8/30/2023,3,1,0
-8/31/2023,7,9,2
-9/1/2023,8,5,4
-9/2/2023,5,1,1
-9/3/2023,2,9,2
-9/4/2023,7,7,3
-9/5/2023,2,2,5
-9/6/2023,4,3,5
-9/7/2023,7,4,2
-9/8/2023,0,6,7
-9/9/2023,7,8,3
-9/10/2023,7,0,2
-9/11/2023,0,4,3
-9/12/2023,7,1,7
-9/13/2023,1,6,0
-9/14/2023,3,0,0
-9/15/2023,9,7,4
-9/16/2023,6,8,7
-9/17/2023,6,1,6
-9/18/2023,0,8,4
-9/19/2023,9,5,1
-9/20/2023,8,9,1
-9/21/2023,7,7,9
-9/22/2023,6,6,0
-9/23/2023,2,5,9
-9/24/2023,8,9,1
-9/25/2023,2,8,8
-9/26/2023,3,5,4
-9/27/2023,1,7,4
-9/28/2023,6,5,4
-9/29/2023,4,6,7
-9/30/2023,3,2,0
-10/1/2023,2,2,0
-10/2/2023,7,0,5
-10/3/2023,7,0,1
-10/4/2023,5,6,9
-10/5/2023,2,4,5
-10/6/2023,8,3,8
-10/7/2023,3,3,8
-10/8/2023,5,6,9
-10/9/2023,3,3,1
-10/10/2023,7,6,2
-10/11/2023,8,7,3
-10/12/2023,4,1,4
-10/13/2023,8,5,6
-10/14/2023,0,1,2
-10/15/2023,3,6,4
-10/16/2023,1,5,6
-10/17/2023,9,8,9
-10/18/2023,9,2,6
-10/19/2023,0,3,8
-10/20/2023,6,5,4
-10/21/2023,2,6,4
-10/22/2023,1,2,6
-10/23/2023,8,5,0
-10/24/2023,0,8,9
-10/25/2023,9,1,6
-10/26/2023,9,3,0
-10/27/2023,0,3,5
-10/28/2023,9,7,0
-10/29/2023,1,6,2
-10/30/2023,6,3,9
-10/31/2023,3,8,0
-11/1/2023,1,9,8
-11/2/2023,5,6,9
-11/3/2023,0,6,6
-11/4/2023,2,9,9
-11/5/2023,0,2,4
-11/6/2023,0,1,7
-11/7/2023,2,3,4
-11/8/2023,6,4,3
-11/9/2023,5,6,7
-11/10/2023,8,3,0
-11/11/2023,0,8,8
-11/12/2023,7,0,0
-11/13/2023,6,1,3
-11/14/2023,9,7,0
-11/15/2023,8,4,4
-11/16/2023,0,5,0
-11/17/2023,4,8,0
-11/18/2023,3,3,3
-11/19/2023,6,7,4
-11/20/2023,2,6,9
-11/21/2023,3,0,5
-11/22/2023,4,1,2
-11/23/2023,0,4,7
-11/24/2023,1,2,6
-11/25/2023,9,0,5
-11/26/2023,2,3,0
-11/27/2023,6,3,2
-11/28/2023,0,3,1
-11/29/2023,3,8,2
-11/30/2023,7,8,5
-12/1/2023,4,1,1
-12/2/2023,2,8,0
-12/3/2023,2,7,9
-12/4/2023,1,4,6
-12/5/2023,4,4,6
-12/6/2023,1,7,2
-12/7/2023,2,0,0
-12/8/2023,1,2,9
-12/9/2023,6,8,3
-12/10/2023,4,9,7
-12/11/2023,6,3,5
-12/12/2023,4,0,8
-12/13/2023,0,0,0
-12/14/2023,3,8,6
-12/15/2023,3,4,6
-12/16/2023,6,6,6
-12/17/2023,8,1,7
-12/18/2023,2,5,6
-12/19/2023,0,3,2
-12/20/2023,6,0,4
-12/21/2023,7,8,2
-12/22/2023,3,2,5
-12/23/2023,4,2,3
-12/24/2023,3,7,6
-12/25/2023,3,1,1
-12/26/2023,1,9,8
-12/27/2023,0,2,9
-12/28/2023,4,4,7
-12/29/2023,4,9,7
-12/30/2023,8,9,4
-12/31/2023,1,9,5
-1/1/2024,0,6,5
-1/2/2024,5,7,2
-1/3/2024,2,7,9
-1/4/2024,5,7,9
-1/5/2024,6,2,9
-1/6/2024,4,8,5
-1/7/2024,0,3,1
-1/8/2024,8,9,8
-1/9/2024,6,7,6
-1/10/2024,4,9,8
-1/11/2024,0,9,5
-1/12/2024,8,8,7
-1/13/2024,8,8,0
-1/14/2024,5,1,9
-1/15/2024,7,7,3
-1/16/2024,5,1,6
-1/17/2024,8,7,7
-1/18/2024,9,8,4
-1/19/2024,1,3,3
-1/20/2024,1,0,6
-1/21/2024,1,4,9
-1/22/2024,2,3,3
-1/23/2024,5,4,4
-1/24/2024,1,6,7
-1/25/2024,0,0,5
-1/26/2024,8,9,6
-1/27/2024,2,8,1
-1/28/2024,9,9,5
-1/29/2024,7,6,8
-1/30/2024,4,2,3
-1/31/2024,7,4,7
-2/1/2024,1,5,0
-2/2/2024,7,9,1
-2/3/2024,2,4,3
-2/4/2024,2,0,5
-2/5/2024,8,1,7
-2/6/2024,8,8,1
-2/7/2024,6,3,5
-2/8/2024,8,6,4
-2/9/2024,8,9,6
-2/10/2024,5,1,5
-2/11/2024,7,3,6
-2/12/2024,7,7,9
-2/13/2024,1,1,5
-2/14/2024,6,0,8
-2/15/2024,2,4,3
-2/16/2024,2,3,3
-2/17/2024,4,7,8
-2/18/2024,7,0,4
-2/19/2024,9,0,2
-2/20/2024,7,1,1
-2/21/2024,9,3,4
-2/22/2024,7,1,8
-2/23/2024,0,6,5
-2/24/2024,2,9,3
-2/25/2024,2,8,3
-2/26/2024,1,3,5
-2/27/2024,4,6,1
-2/28/2024,1,7,2
-2/29/2024,9,9,1
-3/1/2024,6,3,2
-3/2/2024,9,2,5
-3/3/2024,8,2,4
-3/4/2024,9,2,6
-3/5/2024,2,3,4
-3/6/2024,5,3,5
-3/7/2024,3,9,2
-3/8/2024,9,7,2
-3/9/2024,9,4,9
-3/10/2024,1,3,4
-3/11/2024,2,6,5
-3/12/2024,0,0,9
-3/13/2024,3,1,5
-3/14/2024,2,9,0
-3/15/2024,0,9,2
-3/16/2024,5,3,3
-3/17/2024,1,3,4
-3/18/2024,1,1,7
-3/19/2024,2,8,9
-3/20/2024,7,9,6
-3/21/2024,7,6,5
-3/22/2024,5,7,7
-3/23/2024,6,3,3
-3/24/2024,5,1,4
-3/25/2024,2,7,5
-3/26/2024,7,7,1
-3/27/2024,9,3,7
-3/28/2024,2,5,0
-3/29/2024,3,8,9
-3/30/2024,1,1,8
-3/31/2024,5,6,1
-4/1/2024,2,4,3
-4/2/2024,7,3,6
-4/3/2024,8,9,3
-4/4/2024,8,4,8
-4/5/2024,3,4,9
-4/6/2024,6,7,5
-4/7/2024,0,7,6
-4/8/2024,3,7,6
-4/9/2024,5,1,4
-4/10/2024,8,6,4
-4/11/2024,4,6,0
-4/12/2024,3,8,8
-4/13/2024,6,1,7
-4/14/2024,4,6,9
-4/15/2024,5,1,7
-4/16/2024,3,8,5
-4/17/2024,6,7,9
-4/18/2024,1,6,0
-4/19/2024,7,9,6
-4/20/2024,9,3,0
-4/21/2024,2,0,3
-4/22/2024,7,9,0
-4/23/2024,9,4,3
-4/24/2024,1,8,9
-4/25/2024,4,4,9
-4/26/2024,7,2,0
-4/27/2024,6,5,9
-4/28/2024,1,7,6
-4/29/2024,6,9,9
-4/30/2024,6,5,0
-5/1/2024,6,6,7
-5/2/2024,6,8,8
-5/3/2024,0,2,0
-5/4/2024,1,3,8
-5/5/2024,4,6,5
-5/6/2024,3,5,5
-5/7/2024,4,6,0
-5/8/2024,7,8,7
-5/9/2024,3,5,9
-5/10/2024,9,3,9
-5/11/2024,7,7,8
-5/12/2024,7,8,0
-5/13/2024,8,1,2
-5/14/2024,7,7,2
-5/15/2024,6,4,8
-5/16/2024,4,9,2
-5/17/2024,9,0,0
-5/18/2024,3,7,0
-5/19/2024,7,4,8
-5/20/2024,9,0,5
-5/21/2024,0,4,9
-5/22/2024,5,2,4
-5/23/2024,2,1,7
-5/24/2024,7,3,2
-5/25/2024,9,3,5
-5/26/2024,1,6,5
-5/27/2024,6,6,3
-5/28/2024,9,5,6
-5/29/2024,7,1,5
-5/30/2024,2,3,1
-5/31/2024,8,7,4
-6/1/2024,6,0,4
-6/2/2024,4,0,8
-6/3/2024,7,4,5
-6/4/2024,8,4,6
-6/5/2024,9,2,7
-6/6/2024,6,3,8
-6/7/2024,7,4,0
-6/8/2024,7,0,3
-6/9/2024,6,0,6
-6/10/2024,8,9,9
-6/11/2024,6,1,3
-6/12/2024,8,3,9
-6/13/2024,5,3,1
-6/14/2024,7,5,0
-6/15/2024,4,0,0
-6/16/2024,5,0,0
-6/17/2024,2,1,6
-6/18/2024,5,0,8
-6/19/2024,6,9,3
-6/20/2024,1,9,6
-6/21/2024,5,6,5
-6/22/2024,8,4,0
-6/23/2024,8,4,9
-6/24/2024,3,2,5
-6/25/2024,2,3,9
-6/26/2024,7,3,2
-6/27/2024,7,1,9
-6/28/2024,4,6,1
-6/29/2024,5,5,2
-6/30/2024,1,5,2
-7/1/2024,1,4,8
-7/2/2024,0,3,1
-7/3/2024,5,3,0
-7/4/2024,5,3,4
-7/5/2024,7,4,3
-7/6/2024,4,4,2
-7/7/2024,0,6,5
-7/8/2024,2,4,4
-7/9/2024,5,3,4
-7/10/2024,5,9,8
-7/11/2024,8,7,0
-7/12/2024,2,9,2
-7/13/2024,9,3,7
-7/14/2024,5,1,9
-7/15/2024,0,9,6
-7/16/2024,9,6,4
-7/17/2024,7,7,1
-7/18/2024,5,7,4
-7/19/2024,4,5,6
-7/20/2024,8,5,4
-7/21/2024,9,6,4
-7/22/2024,9,9,1
-7/23/2024,4,7,2
-7/24/2024,0,4,0
-7/25/2024,7,5,5
-7/26/2024,9,3,5
-7/27/2024,7,8,0
-7/28/2024,3,9,2
-7/29/2024,0,8,8
-7/30/2024,4,4,9
-7/31/2024,1,1,3
-8/1/2024,8,8,4
-8/2/2024,7,5,5
-8/3/2024,7,2,7
-8/4/2024,5,3,8
-8/5/2024,5,7,5
-8/6/2024,6,2,8
-8/7/2024,4,7,3
-8/8/2024,5,1,7
-8/9/2024,4,5,4
-8/10/2024,8,9,9
-8/11/2024,9,8,2
-8/12/2024,7,1,9
-8/13/2024,7,9,6
-8/14/2024,6,2,6
-8/15/2024,0,2,8
-8/16/2024,8,5,7
-8/17/2024,9,7,7
-8/18/2024,3,5,6
-8/19/2024,1,0,4
-8/20/2024,3,5,8
-8/21/2024,0,4,7
-8/22/2024,6,9,2
-8/23/2024,6,2,4
-8/24/2024,5,7,6
-8/25/2024,0,6,5
-8/26/2024,0,1,2
-8/27/2024,7,0,1
-8/28/2024,9,2,2
-8/29/2024,3,4,5
-8/30/2024,8,9,0
-8/31/2024,0,1,4
-9/1/2024,9,7,5
-9/2/2024,6,2,6
-9/3/2024,7,0,2
-9/4/2024,1,0,4
-9/5/2024,6,8,6
-9/6/2024,0,0,5
-9/7/2024,7,5,3
-9/8/2024,8,4,7
-9/9/2024,0,4,4
-9/10/2024,5,9,5
-9/11/2024,2,6,2
-9/12/2024,0,7,7
-9/13/2024,9,3,8
-9/14/2024,7,5,5
-9/15/2024,8,0,3
-9/16/2024,7,1,2
-9/17/2024,3,8,2
-9/18/2024,7,6,4
-9/19/2024,4,5,7
-9/20/2024,9,7,8
-9/21/2024,2,2,6
-9/22/2024,8,1,9
-9/23/2024,4,9,7
-9/24/2024,7,5,8
-9/25/2024,6,7,5
-9/26/2024,4,6,6
-9/27/2024,4,0,6
-9/28/2024,8,2,9
-9/29/2024,0,1,4
-9/30/2024,4,3,4
-10/1/2024,3,7,2
-10/2/2024,4,4,1
-10/3/2024,1,0,3
-10/4/2024,1,1,4
-10/5/2024,9,2,6
-10/6/2024,8,2,8
-10/7/2024,2,9,1
-10/8/2024,2,6,9
-10/9/2024,0,5,7
-10/10/2024,1,1,7
-10/11/2024,7,5,3
-10/12/2024,7,2,2
-10/13/2024,4,9,2
-10/14/2024,2,5,7
-10/15/2024,7,1,3
-10/16/2024,2,8,2
-10/17/2024,5,4,7
-10/18/2024,6,1,9
-10/19/2024,6,2,2
-10/20/2024,8,7,6
-10/21/2024,0,4,3
-10/22/2024,7,8,3
-10/23/2024,6,2,0
-10/24/2024,4,8,7
-10/25/2024,1,6,7
-10/26/2024,2,6,9
-10/27/2024,1,4,2
-10/28/2024,9,0,4
-10/29/2024,5,1,1
-10/30/2024,7,4,1
-10/31/2024,3,6,8
-11/1/2024,4,4,2
-11/2/2024,4,8,5
-11/3/2024,2,7,7
-11/4/2024,1,1,6
-11/5/2024,4,2,6
-11/6/2024,3,5,4
-11/7/2024,3,3,3
-11/8/2024,0,3,2
-11/9/2024,7,2,9
-11/10/2024,5,3,8
-11/11/2024,5,2,5
-11/12/2024,8,3,8
-11/13/2024,7,5,8
-11/14/2024,9,8,4
-11/15/2024,7,6,0
-11/16/2024,0,0,7
-11/17/2024,5,5,6
-11/18/2024,4,0,8
-11/19/2024,0,8,1
-11/20/2024,5,8,6
-11/21/2024,0,0,2
-11/22/2024,6,1,9
-11/23/2024,2,5,4
-11/24/2024,6,7,4
-11/25/2024,7,3,3
-11/26/2024,0,4,7
-11/27/2024,3,2,1
-11/28/2024,8,2,7
-11/29/2024,2,8,7
-11/30/2024,5,2,2
-12/1/2024,7,8,7
-12/2/2024,4,6,7
-12/3/2024,4,3,2
-12/4/2024,1,8,8
-12/5/2024,5,9,9
-12/6/2024,1,2,5
-12/7/2024,6,3,0
-12/8/2024,3,3,3
-12/9/2024,3,4,5
-12/10/2024,6,7,4
-12/11/2024,6,9,3
-12/12/2024,9,5,8
-12/13/2024,5,2,9
-12/14/2024,5,7,0
-12/15/2024,3,9,1
-12/16/2024,3,1,2
-12/17/2024,1,7,0
-12/18/2024,4,6,2
-12/19/2024,7,9,1
-12/20/2024,3,3,2
-12/21/2024,2,6,1
-12/22/2024,5,5,9
-12/23/2024,9,1,2
-12/24/2024,6,7,3
-12/25/2024,4,1,6
-12/26/2024,0,8,8
-12/27/2024,6,2,5
-12/28/2024,5,8,5
-12/29/2024,0,3,8
-12/30/2024,9,4,1
-12/31/2024,2,2,8
-1/1/2025,3,0,6
-1/2/2025,4,7,5
-1/3/2025,0,8,4
-1/4/2025,4,0,4
-1/5/2025,8,9,9
-1/6/2025,5,5,1
-1/7/2025,0,4,1
-1/8/2025,8,5,2
-1/9/2025,7,5,5
-1/10/2025,1,3,3
-1/11/2025,1,4,7
-1/12/2025,0,8,2
-1/13/2025,6,1,9
-1/14/2025,3,9,1
-1/15/2025,7,6,1
-1/16/2025,1,9,3
-1/17/2025,5,5,1
-1/18/2025,6,1,3
-1/19/2025,6,2,6
-1/20/2025,6,7,2
-1/21/2025,4,2,8
-1/22/2025,9,7,9
-1/23/2025,9,8,4
-1/24/2025,4,8,2
-1/25/2025,4,5,1
-1/26/2025,3,6,9
-1/27/2025,2,2,2
-1/28/2025,9,9,6
-1/29/2025,4,0,5
-1/30/2025,0,9,8
-1/31/2025,9,1,7
-2/1/2025,2,5,8
-2/2/2025,7,5,9
-2/3/2025,1,0,0
-2/4/2025,2,5,2
-2/5/2025,9,8,8
-2/6/2025,1,9,1
-2/7/2025,0,3,3
-2/8/2025,0,6,1
-2/9/2025,5,0,2
-2/10/2025,1,7,8
-2/11/2025,5,9,8
-2/12/2025,1,4,7
-2/13/2025,4,5,9
-2/14/2025,5,2,3
-2/15/2025,1,4,7
-2/16/2025,1,6,2
-2/17/2025,3,8,7
-2/18/2025,6,8,5
-2/19/2025,8,3,3
-2/20/2025,7,0,4
-2/21/2025,6,3,5
-2/22/2025,0,4,2
-2/23/2025,3,1,9
-2/24/2025,2,4,3
-2/25/2025,0,1,7
-2/26/2025,2,1,4
-2/27/2025,1,1,0
-2/28/2025,7,4,0
-3/1/2025,9,6,7
-3/2/2025,3,4,4
-3/3/2025,5,3,9
-3/4/2025,7,5,3
-3/5/2025,7,0,3
-3/6/2025,1,6,1
-3/7/2025,1,9,4
-3/8/2025,2,8,9
-3/9/2025,6,9,4
-3/10/2025,8,2,9
-3/11/2025,2,5,9
-3/12/2025,8,0,3
-3/13/2025,7,9,5
-3/14/2025,8,2,5
-3/15/2025,3,6,6
-3/16/2025,1,1,0
-3/17/2025,0,0,5
-3/18/2025,1,0,0
-3/19/2025,2,6,3
-3/20/2025,3,1,2
-3/21/2025,4,6,2
-3/22/2025,4,0,7
-3/23/2025,2,6,1
-3/24/2025,9,6,9
-3/25/2025,6,4,4
-3/26/2025,4,0,7
-3/27/2025,2,7,5
-3/28/2025,9,4,7
-3/29/2025,5,1,2
-3/30/2025,7,6,6
-3/31/2025,5,4,5
-4/1/2025,3,1,7
-4/2/2025,4,0,1
-4/3/2025,3,2,8
-4/4/2025,0,3,4
-4/5/2025,7,9,2
-4/6/2025,8,1,3
-4/7/2025,0,2,1
-4/8/2025,7,8,3
-4/9/2025,2,7,2
-4/10/2025,1,3,5
-4/11/2025,7,4,4
-4/12/2025,9,6,5
-4/13/2025,4,6,4
-4/14/2025,9,0,5
-4/15/2025,9,2,2
-4/16/2025,8,0,6
-4/17/2025,0,8,9
-4/18/2025,5,1,7
-4/19/2025,5,0,5
-4/20/2025,6,6,3
-4/21/2025,6,2,1
-4/22/2025,6,4,3
-4/23/2025,4,3,0
-4/24/2025,4,7,0
-4/25/2025,4,3,5
-4/26/2025,5,5,0
-4/27/2025,4,8,4
-4/28/2025,6,8,5
-4/29/2025,2,2,3
-4/30/2025,2,9,4
-5/1/2025,1,3,9
-5/2/2025,3,9,7
-5/3/2025,9,6,6
-5/4/2025,3,5,7
-5/5/2025,6,6,8
-5/6/2025,2,7,1
-5/7/2025,5,5,4
-5/8/2025,1,7,9
-5/9/2025,7,3,3
-5/10/2025,5,1,3
-5/11/2025,9,6,6
-5/12/2025,7,4,2
-5/13/2025,3,7,2
-5/14/2025,2,6,2
-5/15/2025,8,2,7
-5/16/2025,2,6,8
-5/17/2025,8,3,9
-5/18/2025,1,0,6
-5/19/2025,0,7,4
-5/20/2025,2,7,4
-5/21/2025,4,6,4
-5/22/2025,9,0,0
-5/23/2025,5,8,4
-5/24/2025,6,6,4
-5/25/2025,3,4,1
-5/26/2025,9,7,6
-5/27/2025,9,3,5
-5/28/2025,0,5,9
-5/29/2025,8,9,2
-5/30/2025,7,1,0
-5/31/2025,5,9,6
-6/1/2025,2,2,4
-6/2/2025,3,2,4
-6/3/2025,0,6,2
-6/4/2025,6,9,2
-6/5/2025,2,4,0
-6/6/2025,2,8,2
-6/7/2025,2,5,6
-6/8/2025,7,9,2
-6/9/2025,3,9,9
-6/10/2025,7,0,3
-6/11/2025,7,2,6
-6/12/2025,9,3,4
-6/13/2025,0,7,5
-6/14/2025,1,1,7
-6/15/2025,8,7,0
-6/16/2025,2,7,8
-6/17/2025,7,9,2
-6/18/2025,8,1,4
-6/19/2025,4,6,3
-6/20/2025,0,2,9
-6/21/2025,3,4,9
-6/22/2025,2,1,0
-6/23/2025,8,2,7
-6/24/2025,2,7,9
-6/25/2025,3,3,5
-6/26/2025,1,1,8
-6/27/2025,6,4,1
-6/28/2025,4,8,5
-6/29/2025,4,8,6
-6/30/2025,9,3,0
-7/1/2025,3,8,6
-7/2/2025,6,0,4
-7/3/2025,2,4,5
-7/4/2025,6,1,8
-7/5/2025,6,2,0
-7/6/2025,2,0,6
-7/7/2025,3,0,2
-7/8/2025,5,0,8
-7/9/2025,2,6,2
-7/10/2025,4,3,3
-7/11/2025,7,3,3
-7/12/2025,1,7,1
-7/13/2025,9,4,8
-7/14/2025,9,9,6
-7/15/2025,2,4,6
-7/16/2025,0,1,1
-7/17/2025,8,3,6
-7/18/2025,9,3,1
-7/19/2025,2,3,8
-7/20/2025,6,9,7
-7/21/2025,2,4,3
-7/22/2025,8,2,7
-7/23/2025,3,7,3
-7/24/2025,8,7,9
-7/25/2025,2,1,3
-7/26/2025,9,4,5
-7/27/2025,8,5,2
-7/28/2025,2,9,7
-7/29/2025,8,9,5
-7/30/2025,0,4,9
-7/31/2025,3,5,5
-8/1/2025,9,0,6
-8/2/2025,5,7,3
-8/3/2025,9,1,7
-8/4/2025,6,0,4
-8/5/2025,6,1,9
-8/6/2025,3,5,6
-8/7/2025,8,5,2
-8/8/2025,4,7,7
-8/9/2025,3,9,8
-8/10/2025,0,4,6
-8/11/2025,1,2,1
-8/12/2025,8,3,6
-8/13/2025,3,9,5
-8/14/2025,7,5,1
-8/15/2025,6,8,5
-8/16/2025,3,6,8
-8/17/2025,8,3,2
-8/18/2025,7,2,2
-8/19/2025,8,7,9
-8/20/2025,4,6,8
-8/21/2025,3,8,2
-8/22/2025,0,2,5
-8/23/2025,8,9,6
-8/24/2025,3,6,3
-8/25/2025,4,8,6
-8/26/2025,8,2,2
-8/27/2025,6,8,4
-8/28/2025,3,7,0
-8/29/2025,5,4,6
-8/30/2025,2,3,9
-8/31/2025,5,8,5
-9/1/2025,1,5,3
-9/2/2025,3,2,5
-9/3/2025,4,1,0
-9/4/2025,6,5,8
-9/5/2025,9,5,6
-9/6/2025,3,3,7
-9/7/2025,1,2,1
-9/8/2025,6,5,0
-9/9/2025,9,0,6
-9/10/2025,3,2,8
-9/11/2025,6,9,5
-9/12/2025,0,5,3
-9/13/2025,9,8,3
-9/14/2025,0,9,9
-9/15/2025,7,0,8
-9/16/2025,8,0,7
-9/17/2025,8,2,4
-9/18/2025,2,0,0
-9/19/2025,1,1,5
-9/20/2025,5,5,9
-9/21/2025,5,5,5
-9/22/2025,5,5,1
-9/23/2025,2,3,2
-9/24/2025,9,5,7
-9/25/2025,9,4,5
-9/26/2025,1,6,2
-9/27/2025,5,7,2
-9/28/2025,9,9,1
-9/29/2025,8,5,9
-9/30/2025,3,4,6
-10/1/2025,0,7,7
-10/2/2025,4,9,8
-10/3/2025,9,0,8
-10/4/2025,5,2,1
-10/5/2025,7,3,4
-10/6/2025,5,2,5
-10/7/2025,8,2,1
-10/8/2025,6,2,0
-10/9/2025,5,1,1
-10/10/2025,4,0,6
-10/11/2025,1,2,6
-10/12/2025,9,5,1
-10/13/2025,8,6,3
-10/14/2025,2,6,5
-10/15/2025,8,6,2
-10/16/2025,5,5,4
-10/17/2025,1,1,7
-10/18/2025,3,1,0
-10/19/2025,2,0,0
-10/20/2025,2,1,5
-10/21/2025,2,1,9
-10/22/2025,8,6,7
-10/23/2025,9,4,9
-10/24/2025,6,5,2
-10/25/2025,3,0,6
-10/26/2025,3,0,3
-10/27/2025,0,0,7
-10/28/2025,2,7,0
-10/29/2025,0,6,0
-10/30/2025,1,7,5
-10/31/2025,3,5,5
-11/1/2025,6,3,4
-11/2/2025,9,6,0
-11/3/2025,6,5,0
-11/4/2025,4,6,6
-11/5/2025,8,4,9
-11/6/2025,5,0,1
-11/7/2025,4,5,8
-11/8/2025,3,8,3
-11/9/2025,7,5,7
-11/10/2025,9,2,9
-11/11/2025,9,2,7
-11/12/2025,7,3,3
-11/13/2025,0,0,6
-11/14/2025,9,9,9
-11/15/2025,6,4,3
-11/16/2025,7,4,9
-11/17/2025,2,0,4
-11/18/2025,7,8,1
-11/19/2025,6,4,6
-11/20/2025,3,4,0
-11/21/2025,8,2,5
-11/22/2025,3,1,4
-11/23/2025,0,6,3
-11/24/2025,1,7,2
-11/25/2025,8,5,8
-11/26/2025,0,6,6
-11/27/2025,9,7,8
-11/28/2025,8,4,4
-11/29/2025,2,6,5
-11/30/2025,2,6,5
-12/1/2025,5,6,3
-12/2/2025,3,9,3
-12/3/2025,6,1,3
-12/4/2025,4,5,4
-12/5/2025,0,7,0
-12/6/2025,8,9,6
-12/7/2025,9,5,4
-12/8/2025,4,1,5
-12/9/2025,4,3,4
-12/10/2025,7,6,3
-12/11/2025,5,6,3
-12/12/2025,2,2,6
-12/13/2025,3,8,3
-12/14/2025,3,3,8
-12/15/2025,3,9,2
-12/16/2025,0,0,5
-12/17/2025,8,5,6
-12/18/2025,9,7,2
-12/19/2025,9,4,0
-12/20/2025,3,9,8
-12/21/2025,5,5,8

Pick4eve (1).csv

@@ -1,1520 +0,0 @@
-DrawDate,1,2,3,4
-10/25/2021,4,0,3,0
-10/26/2021,9,3,3,7
-10/27/2021,2,1,7,1
-10/28/2021,8,3,7,2
-10/29/2021,8,6,4,4
-10/30/2021,1,7,9,4
-10/31/2021,3,4,3,6
-11/1/2021,6,8,1,0
-11/2/2021,7,1,0,5
-11/3/2021,2,5,7,9
-11/4/2021,1,2,2,3
-11/5/2021,6,1,3,9
-11/6/2021,0,6,3,3
-11/7/2021,9,6,4,8
-11/8/2021,7,1,9,6
-11/9/2021,7,0,0,8
-11/10/2021,1,6,3,6
-11/11/2021,0,5,3,6
-11/12/2021,6,5,0,0
-11/13/2021,9,3,4,8
-11/14/2021,5,8,5,6
-11/15/2021,2,6,4,0
-11/16/2021,2,0,8,5
-11/17/2021,1,7,3,9
-11/18/2021,1,1,0,6
-11/19/2021,4,5,8,6
-11/20/2021,4,2,4,4
-11/21/2021,0,7,7,7
-11/22/2021,8,2,0,4
-11/23/2021,5,4,9,4
-11/24/2021,3,5,6,3
-11/25/2021,8,9,2,0
-11/26/2021,0,7,3,5
-11/27/2021,4,0,1,9
-11/28/2021,2,0,6,9
-11/29/2021,6,1,3,4
-11/30/2021,5,0,4,8
-12/1/2021,9,9,0,1
-12/2/2021,9,2,9,2
-12/3/2021,2,3,1,5
-12/4/2021,0,3,0,7
-12/5/2021,5,9,6,3
-12/6/2021,1,1,4,4
-12/7/2021,2,9,2,9
-12/8/2021,7,4,5,2
-12/9/2021,4,6,2,5
-12/10/2021,4,7,5,6
-12/11/2021,4,0,1,9
-12/12/2021,3,0,6,2
-12/13/2021,6,1,7,6
-12/14/2021,2,7,7,7
-12/15/2021,8,8,4,6
-12/16/2021,8,9,1,6
-12/17/2021,8,6,9,8
-12/18/2021,3,0,0,1
-12/19/2021,2,3,8,5
-12/20/2021,3,0,4,6
-12/21/2021,5,5,8,7
-12/22/2021,8,3,1,4
-12/23/2021,7,6,3,3
-12/24/2021,5,6,0,5
-12/25/2021,0,8,1,4
-12/26/2021,8,3,5,2
-12/27/2021,0,6,6,7
-12/28/2021,0,4,9,6
-12/29/2021,7,1,9,6
-12/30/2021,4,6,8,0
-12/31/2021,4,8,8,6
-1/1/2022,0,4,1,7
-1/2/2022,1,6,1,5
-1/3/2022,1,1,5,2
-1/4/2022,2,0,0,2
-1/5/2022,6,8,0,5
-1/6/2022,4,6,9,8
-1/7/2022,7,4,8,8
-1/8/2022,7,9,3,5
-1/9/2022,2,5,1,8
-1/10/2022,7,4,7,8
-1/11/2022,9,2,8,2
-1/12/2022,4,2,4,3
-1/13/2022,0,6,1,8
-1/14/2022,1,2,7,5
-1/15/2022,6,4,7,0
-1/16/2022,8,3,0,5
-1/17/2022,1,5,9,3
-1/18/2022,0,9,5,6
-1/19/2022,2,1,5,9
-1/20/2022,7,6,0,6
-1/21/2022,3,1,0,7
-1/22/2022,2,8,2,4
-1/23/2022,8,2,7,9
-1/24/2022,0,4,2,7
-1/25/2022,5,1,9,7
-1/26/2022,9,6,4,1
-1/27/2022,5,9,3,2
-1/28/2022,8,3,6,6
-1/29/2022,8,3,4,9
-1/30/2022,8,5,9,2
-1/31/2022,7,8,3,5
-2/1/2022,1,0,8,9
-2/2/2022,9,3,5,5
-2/3/2022,9,3,4,2
-2/4/2022,6,8,7,4
-2/5/2022,8,2,1,6
-2/6/2022,6,9,0,2
-2/7/2022,5,3,0,6
-2/8/2022,7,9,3,5
-2/9/2022,5,8,6,2
-2/10/2022,8,8,3,7
-2/11/2022,9,3,5,5
-2/12/2022,1,2,7,0
-2/13/2022,4,1,9,0
-2/14/2022,0,5,7,0
-2/15/2022,6,0,8,4
-2/16/2022,8,3,1,0
-2/17/2022,8,2,4,3
-2/18/2022,9,0,7,1
-2/19/2022,2,6,0,0
-2/20/2022,6,3,9,7
-2/21/2022,8,0,9,1
-2/22/2022,4,1,3,7
-2/23/2022,5,1,7,0
-2/24/2022,1,5,1,4
-2/25/2022,2,5,3,6
-2/26/2022,0,2,1,8
-2/27/2022,3,0,7,0
-2/28/2022,3,9,9,5
-3/1/2022,6,7,4,2
-3/2/2022,0,0,5,3
-3/3/2022,6,5,4,9
-3/4/2022,2,1,1,4
-3/5/2022,0,7,2,0
-3/6/2022,5,4,4,1
-3/7/2022,1,7,9,3
-3/8/2022,0,1,4,4
-3/9/2022,4,6,6,1
-3/10/2022,9,6,8,1
-3/11/2022,7,4,3,1
-3/12/2022,9,6,4,4
-3/13/2022,9,8,8,1
-3/14/2022,7,5,4,8
-3/15/2022,1,6,1,4
-3/16/2022,8,3,9,1
-3/17/2022,3,8,7,1
-3/18/2022,7,0,5,5
-3/19/2022,0,7,4,7
-3/20/2022,1,3,8,3
-3/21/2022,1,2,4,9
-3/22/2022,9,4,5,8
-3/23/2022,2,8,1,1
-3/24/2022,6,5,2,4
-3/25/2022,9,9,2,1
-3/26/2022,7,2,9,1
-3/27/2022,7,3,2,9
-3/28/2022,7,9,4,2
-3/29/2022,9,3,6,6
-3/30/2022,6,8,9,1
-3/31/2022,3,1,4,5
-4/1/2022,2,7,9,3
-4/2/2022,6,6,9,5
-4/3/2022,8,7,7,3
-4/4/2022,8,4,5,8
-4/5/2022,4,6,3,6
-4/6/2022,4,0,0,1
-4/7/2022,2,2,4,5
-4/8/2022,7,8,7,3
-4/9/2022,3,7,4,1
-4/10/2022,3,1,5,8
-4/11/2022,3,8,0,0
-4/12/2022,0,9,5,6
-4/13/2022,8,5,4,3
-4/14/2022,4,5,4,3
-4/15/2022,8,7,5,7
-4/16/2022,1,2,0,6
-4/17/2022,1,3,0,3
-4/18/2022,6,7,7,4
-4/19/2022,3,1,7,8
-4/20/2022,1,7,3,2
-4/21/2022,9,2,0,0
-4/22/2022,3,7,4,9
-4/23/2022,6,3,0,2
-4/24/2022,6,6,8,2
-4/25/2022,6,7,1,9
-4/26/2022,2,8,0,0
-4/27/2022,3,6,4,2
-4/28/2022,8,6,7,2
-4/29/2022,3,4,1,1
-4/30/2022,6,4,3,7
-5/1/2022,2,8,1,4
-5/2/2022,7,5,0,3
-5/3/2022,9,1,4,5
-5/4/2022,3,0,7,8
-5/5/2022,2,7,4,1
-5/6/2022,9,5,9,1
-5/7/2022,4,6,7,9
-5/8/2022,1,5,2,8
-5/9/2022,1,2,9,6
-5/10/2022,5,2,7,9
-5/11/2022,6,5,2,0
-5/12/2022,8,4,2,5
-5/13/2022,0,0,2,8
-5/14/2022,9,5,0,9
-5/15/2022,0,1,0,5
-5/16/2022,7,7,0,0
-5/17/2022,2,4,3,6
-5/18/2022,9,2,5,4
-5/19/2022,2,5,4,7
-5/20/2022,7,6,0,5
-5/21/2022,2,5,4,7
-5/22/2022,0,1,0,3
-5/23/2022,6,6,3,0
-5/24/2022,8,2,9,8
-5/25/2022,5,7,6,1
-5/26/2022,1,3,1,8
-5/27/2022,4,5,5,6
-5/28/2022,6,1,4,3
-5/29/2022,4,5,0,0
-5/30/2022,7,4,3,2
-5/31/2022,3,4,2,8
-6/1/2022,2,5,3,3
-6/2/2022,9,0,3,1
-6/3/2022,1,2,9,6
-6/4/2022,4,5,0,7
-6/5/2022,1,6,6,8
-6/6/2022,7,6,9,9
-6/7/2022,3,5,9,9
-6/8/2022,2,5,9,4
-6/9/2022,5,1,9,9
-6/10/2022,7,8,2,9
-6/11/2022,1,3,8,6
-6/12/2022,0,8,7,3
-6/13/2022,6,4,1,0
-6/14/2022,6,0,8,7
-6/15/2022,3,6,5,9
-6/16/2022,4,7,7,9
-6/17/2022,3,6,8,9
-6/18/2022,1,2,5,4
-6/19/2022,5,7,4,4
-6/20/2022,2,2,4,0
-6/21/2022,1,5,9,8
-6/22/2022,3,3,5,5
-6/23/2022,2,2,2,2
-6/24/2022,2,6,6,7
-6/25/2022,8,0,7,9
-6/26/2022,8,8,2,8
-6/27/2022,5,1,4,2
-6/28/2022,0,1,0,7
-6/29/2022,1,1,0,0
-6/30/2022,8,4,0,5
-7/1/2022,0,0,6,7
-7/2/2022,5,0,1,6
-7/3/2022,2,9,7,4
-7/4/2022,5,4,2,2
-7/5/2022,4,3,9,0
-7/6/2022,2,5,5,3
-7/7/2022,4,6,2,3
-7/8/2022,7,7,6,3
-7/9/2022,9,6,8,2
-7/10/2022,6,5,0,7
-7/11/2022,1,3,0,3
-7/12/2022,1,8,0,5
-7/13/2022,8,3,0,7
-7/14/2022,4,0,8,5
-7/15/2022,4,7,9,1
-7/16/2022,8,4,8,0
-7/17/2022,3,8,9,1
-7/18/2022,6,1,2,8
-7/19/2022,5,6,1,1
-7/20/2022,8,6,9,0
-7/21/2022,2,4,7,8
-7/22/2022,9,4,5,9
-7/23/2022,0,2,2,5
-7/24/2022,4,4,7,0
-7/25/2022,2,5,4,9
-7/26/2022,6,8,2,3
-7/27/2022,9,0,2,3
-7/28/2022,8,8,3,5
-7/29/2022,7,5,3,4
-7/30/2022,2,4,4,2
-7/31/2022,3,7,4,2
-8/1/2022,5,8,6,2
-8/2/2022,2,8,7,5
-8/3/2022,2,9,5,1
-8/4/2022,4,6,8,0
-8/5/2022,6,6,6,7
-8/6/2022,9,2,8,6
-8/7/2022,1,0,0,8
-8/8/2022,2,4,8,4
-8/9/2022,4,4,6,1
-8/10/2022,0,3,0,3
-8/11/2022,3,6,0,3
-8/12/2022,9,8,1,4
-8/13/2022,1,7,0,4
-8/14/2022,6,0,6,8
-8/15/2022,9,5,8,3
-8/16/2022,8,6,4,3
-8/17/2022,3,0,8,7
-8/18/2022,2,1,9,2
-8/19/2022,6,5,8,4
-8/20/2022,6,9,8,8
-8/21/2022,5,6,0,2
-8/22/2022,6,4,4,9
-8/23/2022,2,7,1,4
-8/24/2022,7,5,6,4
-8/25/2022,4,6,5,6
-8/26/2022,6,2,5,7
-8/27/2022,4,6,6,5
-8/28/2022,0,4,1,1
-8/29/2022,1,6,0,9
-8/30/2022,9,3,1,9
-8/31/2022,0,7,8,9
-9/1/2022,5,2,1,8
-9/2/2022,8,7,0,0
-9/3/2022,3,7,7,3
-9/4/2022,2,0,5,2
-9/5/2022,8,8,8,5
-9/6/2022,5,8,5,8
-9/7/2022,2,5,1,1
-9/8/2022,7,0,3,3
-9/9/2022,7,7,4,6
-9/10/2022,5,6,3,8
-9/11/2022,0,4,7,7
-9/12/2022,6,9,0,3
-9/13/2022,9,3,5,8
-9/14/2022,9,8,9,9
-9/15/2022,7,9,0,6
-9/16/2022,3,7,5,6
-9/17/2022,3,2,9,9
-9/18/2022,1,4,9,0
-9/19/2022,3,4,5,1
-9/20/2022,1,0,4,6
-9/21/2022,5,7,8,5
-9/22/2022,7,8,5,9
-9/23/2022,1,2,2,8
-9/24/2022,2,5,2,7
-9/25/2022,2,2,2,6
-9/26/2022,1,7,3,1
-9/27/2022,2,5,7,9
-9/28/2022,8,1,7,4
-9/29/2022,8,8,4,9
-9/30/2022,3,1,9,3
-10/1/2022,4,3,4,4
-10/2/2022,8,6,4,0
-10/3/2022,9,7,1,2
-10/4/2022,3,5,7,3
-10/5/2022,0,2,3,6
-10/6/2022,5,4,7,7
-10/7/2022,3,8,5,6
-10/8/2022,1,2,6,5
-10/9/2022,8,1,0,9
-10/10/2022,9,4,3,5
-10/11/2022,1,4,5,0
-10/12/2022,5,3,1,1
-10/13/2022,6,6,4,2
-10/14/2022,2,4,4,7
-10/15/2022,7,1,1,4
-10/16/2022,1,1,0,7
-10/17/2022,1,0,5,3
-10/18/2022,3,7,6,9
-10/19/2022,8,2,2,4
-10/20/2022,8,1,3,4
-10/21/2022,7,7,4,9
-10/22/2022,5,9,2,6
-10/23/2022,0,3,4,3
-10/24/2022,8,2,1,4
-10/25/2022,5,4,6,9
-10/26/2022,1,7,8,7
-10/27/2022,3,6,4,1
-10/28/2022,2,8,1,8
-10/29/2022,6,1,3,8
-10/30/2022,6,0,9,8
-10/31/2022,7,0,8,7
-11/1/2022,1,3,6,8
-11/2/2022,0,5,1,4
-11/3/2022,2,3,6,1
-11/4/2022,8,2,6,1
-11/5/2022,8,6,3,7
-11/6/2022,5,4,7,1
-11/7/2022,3,3,4,2
-11/8/2022,8,2,8,4
-11/9/2022,8,7,9,4
-11/10/2022,5,7,3,4
-11/11/2022,1,1,9,0
-11/12/2022,9,2,4,9
-11/13/2022,2,7,7,7
-11/14/2022,6,8,9,1
-11/15/2022,7,0,3,3
-11/16/2022,3,0,2,6
-11/17/2022,1,3,3,3
-11/18/2022,9,1,0,6
-11/19/2022,7,2,2,0
-11/20/2022,9,4,0,1
-11/21/2022,8,7,6,1
-11/22/2022,6,6,8,6
-11/23/2022,9,0,6,6
-11/24/2022,5,7,2,2
-11/25/2022,2,7,7,6
-11/26/2022,4,6,7,5
-11/27/2022,3,1,2,5
-11/28/2022,1,6,3,1
-11/29/2022,8,7,3,7
-11/30/2022,9,7,8,3
-12/1/2022,8,3,7,0
-12/2/2022,7,8,7,4
-12/3/2022,2,2,6,2
-12/4/2022,3,5,2,5
-12/5/2022,7,8,3,4
-12/6/2022,7,1,4,1
-12/7/2022,3,3,0,9
-12/8/2022,8,8,9,2
-12/9/2022,2,4,7,8
-12/10/2022,6,0,2,2
-12/11/2022,7,0,2,7
-12/12/2022,2,5,3,4
-12/13/2022,1,2,1,4
-12/14/2022,3,5,7,8
-12/15/2022,4,2,8,3
-12/16/2022,9,6,3,8
-12/17/2022,9,2,6,9
-12/18/2022,1,4,3,2
-12/19/2022,6,8,4,9
-12/20/2022,0,1,0,2
-12/21/2022,9,2,9,4
-12/22/2022,4,7,5,5
-12/23/2022,2,3,0,7
-12/24/2022,2,5,2,4
-12/25/2022,4,1,5,6
-12/26/2022,8,9,3,5
-12/27/2022,2,1,4,7
-12/28/2022,7,9,0,2
-12/29/2022,0,6,3,7
-12/30/2022,8,2,5,9
-12/31/2022,9,9,6,4
-1/1/2023,9,2,0,5
-1/2/2023,7,4,3,7
-1/3/2023,6,7,4,4
-1/4/2023,4,0,8,1
-1/5/2023,4,9,0,7
-1/6/2023,9,4,4,2
-1/7/2023,8,0,3,1
-1/8/2023,4,0,3,9
-1/9/2023,4,6,3,8
-1/10/2023,4,2,2,8
-1/11/2023,8,5,0,9
-1/12/2023,3,5,1,2
-1/13/2023,5,6,6,3
-1/14/2023,0,8,6,2
-1/15/2023,4,9,8,4
-1/16/2023,4,0,5,7
-1/17/2023,0,8,2,3
-1/18/2023,8,0,4,4
-1/19/2023,9,0,8,2
-1/20/2023,9,5,9,3
-1/21/2023,6,3,3,6
-1/22/2023,5,9,5,5
-1/23/2023,1,7,2,7
-1/24/2023,9,7,5,9
-1/25/2023,7,7,1,0
-1/26/2023,0,5,2,0
-1/27/2023,8,9,2,4
-1/28/2023,6,1,2,8
-1/29/2023,4,2,9,8
-1/30/2023,5,7,5,7
-1/31/2023,1,0,8,8
-2/1/2023,5,4,5,8
-2/2/2023,2,2,7,7
-2/3/2023,9,0,8,2
-2/4/2023,7,7,9,4
-2/5/2023,2,1,4,6
-2/6/2023,6,6,2,6
-2/7/2023,4,3,1,7
-2/8/2023,9,2,0,4
-2/9/2023,0,3,2,7
-2/10/2023,6,0,2,6
-2/11/2023,9,0,4,2
-2/12/2023,1,2,7,8
-2/13/2023,9,1,2,1
-2/14/2023,0,4,3,8
-2/15/2023,2,8,5,6
-2/16/2023,9,2,6,9
-2/17/2023,0,8,1,5
-2/18/2023,8,7,3,4
-2/19/2023,4,0,8,9
-2/20/2023,3,0,0,3
-2/21/2023,6,9,4,6
-2/22/2023,5,4,3,8
-2/23/2023,1,2,9,5
-2/24/2023,4,3,0,4
-2/25/2023,1,8,5,0
-2/26/2023,8,3,6,5
-2/27/2023,3,1,2,3
-2/28/2023,8,7,9,2
-3/1/2023,3,0,6,7
-3/2/2023,8,8,6,5
-3/3/2023,9,3,5,7
-3/4/2023,8,2,6,6
-3/5/2023,3,8,6,1
-3/6/2023,7,4,2,4
-3/7/2023,3,5,8,9
-3/8/2023,2,5,7,0
-3/9/2023,6,5,5,1
-3/10/2023,5,8,0,5
-3/11/2023,8,1,3,8
-3/12/2023,5,3,1,4
-3/13/2023,5,0,1,8
-3/14/2023,6,0,2,7
-3/15/2023,2,8,3,3
-3/16/2023,8,4,3,1
-3/17/2023,0,1,3,2
-3/18/2023,8,7,2,2
-3/19/2023,5,2,3,7
-3/20/2023,1,7,0,9
-3/21/2023,8,2,0,8
-3/22/2023,5,2,3,0
-3/23/2023,4,1,7,2
-3/24/2023,7,1,8,0
-3/25/2023,2,7,3,4
-3/26/2023,2,5,8,2
-3/27/2023,7,8,3,8
-3/28/2023,3,2,0,5
-3/29/2023,4,8,5,4
-3/30/2023,7,4,8,5
-3/31/2023,1,4,1,0
-4/1/2023,1,1,0,1
-4/2/2023,6,0,5,6
-4/3/2023,7,3,9,6
-4/4/2023,5,1,7,6
-4/5/2023,2,3,4,9
-4/6/2023,5,9,7,1
-4/7/2023,2,9,2,0
-4/8/2023,5,2,8,5
-4/9/2023,3,9,9,6
-4/10/2023,8,4,7,6
-4/11/2023,3,9,0,3
-4/12/2023,2,4,8,2
-4/13/2023,1,9,0,7
-4/14/2023,7,5,5,9
-4/15/2023,6,7,9,5
-4/16/2023,5,8,2,7
-4/17/2023,4,7,3,2
-4/18/2023,1,2,3,5
-4/19/2023,6,2,3,7
-4/20/2023,0,0,7,5
-4/21/2023,9,1,8,8
-4/22/2023,2,8,2,4
-4/23/2023,7,9,3,5
-4/24/2023,6,1,5,0
-4/25/2023,6,5,6,3
-4/26/2023,5,4,2,7
-4/27/2023,1,7,3,1
-4/28/2023,9,1,8,4
-4/29/2023,0,5,7,5
-4/30/2023,9,5,0,2
-5/1/2023,8,5,9,0
-5/2/2023,5,6,1,9
-5/3/2023,1,5,9,6
-5/4/2023,2,5,4,2
-5/5/2023,4,2,0,5
-5/6/2023,3,1,5,7
-5/7/2023,1,9,8,7
-5/8/2023,4,3,8,2
-5/9/2023,4,7,7,9
-5/10/2023,3,8,7,7
-5/11/2023,8,3,6,0
-5/12/2023,8,0,4,6
-5/13/2023,0,4,5,8
-5/14/2023,3,4,7,7
-5/15/2023,0,3,8,3
-5/16/2023,8,1,9,0
-5/17/2023,1,8,8,7
-5/18/2023,1,6,5,5
-5/19/2023,8,4,1,0
-5/20/2023,5,6,0,3
-5/21/2023,5,0,8,8
-5/22/2023,0,5,1,9
-5/23/2023,4,3,4,6
-5/24/2023,6,7,1,0
-5/25/2023,3,6,8,9
-5/26/2023,9,9,0,0
-5/27/2023,0,7,0,0
-5/28/2023,2,5,1,2
-5/29/2023,3,9,9,4
-5/30/2023,0,4,8,6
-5/31/2023,0,0,3,5
-6/1/2023,6,6,4,8
-6/2/2023,2,5,2,5
-6/3/2023,7,2,7,6
-6/4/2023,1,4,9,8
-6/5/2023,0,9,4,0
-6/6/2023,3,8,6,5
-6/7/2023,9,5,2,3
-6/8/2023,1,7,6,7
-6/9/2023,3,8,5,3
-6/10/2023,2,1,6,0
-6/11/2023,4,1,2,1
-6/12/2023,5,8,6,8
-6/13/2023,7,4,6,7
-6/14/2023,7,8,3,8
-6/15/2023,0,3,7,5
-6/16/2023,3,1,8,4
-6/17/2023,5,5,2,5
-6/18/2023,5,7,9,2
-6/19/2023,8,8,8,1
-6/20/2023,6,7,9,0
-6/21/2023,5,6,4,3
-6/22/2023,8,3,9,7
-6/23/2023,1,9,5,5
-6/24/2023,2,6,3,9
-6/25/2023,4,2,1,5
-6/26/2023,5,1,6,7
-6/27/2023,6,3,5,6
-6/28/2023,6,4,4,7
-6/29/2023,7,0,3,6
-6/30/2023,3,8,5,9
-7/1/2023,7,2,8,5
-7/2/2023,9,3,8,9
-7/3/2023,6,9,4,4
-7/4/2023,8,5,4,6
-7/5/2023,8,9,3,1
-7/6/2023,5,5,5,9
-7/7/2023,4,9,7,2
-7/8/2023,5,1,1,8
-7/9/2023,9,6,0,0
-7/10/2023,2,0,8,4
-7/11/2023,7,4,8,4
-7/12/2023,4,9,0,8
-7/13/2023,6,7,6,6
-7/14/2023,2,0,3,7
-7/15/2023,0,2,5,8
-7/16/2023,8,6,9,5
-7/17/2023,1,2,7,0
-7/18/2023,3,3,5,9
-7/19/2023,4,6,0,2
-7/20/2023,5,0,4,3
-7/21/2023,9,6,1,3
-7/22/2023,9,8,1,7
-7/23/2023,0,5,8,9
-7/24/2023,0,3,6,6
-7/25/2023,4,3,3,4
-7/26/2023,5,7,6,9
-7/27/2023,3,0,4,1
-7/28/2023,1,3,4,8
-7/29/2023,4,8,2,5
-7/30/2023,8,7,8,1
-7/31/2023,1,0,5,7
-8/1/2023,9,0,4,5
-8/2/2023,4,1,3,9
-8/3/2023,4,5,8,0
-8/4/2023,3,0,9,9
-8/5/2023,4,9,3,9
-8/6/2023,7,1,9,1
-8/7/2023,7,5,7,3
-8/8/2023,5,7,8,0
-8/9/2023,9,4,4,6
-8/10/2023,9,0,7,1
-8/11/2023,7,2,2,1
-8/12/2023,4,0,0,4
-8/13/2023,6,0,4,7
-8/14/2023,6,7,8,6
-8/15/2023,6,5,8,9
-8/16/2023,7,6,4,5
-8/17/2023,6,9,6,1
-8/18/2023,6,7,0,3
-8/19/2023,9,9,6,1
-8/20/2023,2,8,6,6
-8/21/2023,9,1,9,5
-8/22/2023,2,9,6,8
-8/23/2023,4,5,8,3
-8/24/2023,5,0,6,5
-8/25/2023,9,8,9,7
-8/26/2023,4,5,5,2
-8/27/2023,2,8,9,0
-8/28/2023,7,6,1,9
-8/29/2023,0,0,4,6
-8/30/2023,4,6,9,1
-8/31/2023,0,8,2,7
-9/1/2023,6,6,8,4
-9/2/2023,4,6,1,7
-9/3/2023,6,2,6,6
-9/4/2023,4,7,7,8
-9/5/2023,2,8,2,9
-9/6/2023,8,0,7,6
-9/7/2023,6,7,7,6
-9/8/2023,4,1,5,9
-9/9/2023,1,2,7,9
-9/10/2023,2,0,4,9
-9/11/2023,2,0,2,1
-9/12/2023,6,6,7,5
-9/13/2023,9,9,3,6
-9/14/2023,0,0,4,0
-9/15/2023,4,7,0,7
-9/16/2023,5,5,4,9
-9/17/2023,1,7,3,9
-9/18/2023,7,0,3,2
-9/19/2023,5,8,0,0
-9/20/2023,7,6,4,4
-9/21/2023,0,7,4,5
-9/22/2023,8,2,6,7
-9/23/2023,8,5,2,5
-9/24/2023,2,5,6,8
-9/25/2023,0,6,7,0
-9/26/2023,5,1,9,1
-9/27/2023,0,7,0,2
-9/28/2023,2,2,4,5
-9/29/2023,2,3,6,3
-9/30/2023,6,9,2,4
-10/1/2023,0,0,4,7
-10/2/2023,7,6,4,9
-10/3/2023,0,1,7,8
-10/4/2023,8,8,4,6
-10/5/2023,7,6,3,6
-10/6/2023,6,4,2,5
-10/7/2023,0,0,9,1
-10/8/2023,3,7,5,2
-10/9/2023,2,7,0,8
-10/10/2023,8,5,5,9
-10/11/2023,1,1,3,8
-10/12/2023,2,9,3,3
-10/13/2023,6,5,6,8
-10/14/2023,3,4,5,1
-10/15/2023,9,5,7,6
-10/16/2023,0,1,9,1
-10/17/2023,7,9,1,6
-10/18/2023,5,4,6,7
-10/19/2023,0,4,7,7
-10/20/2023,1,4,8,9
-10/21/2023,7,8,3,2
-10/22/2023,9,0,2,9
-10/23/2023,3,0,4,0
-10/24/2023,2,6,2,2
-10/25/2023,5,6,8,1
-10/26/2023,3,6,7,6
-10/27/2023,6,3,2,8
-10/28/2023,8,1,1,3
-10/29/2023,5,0,0,1
-10/30/2023,6,0,0,1
-10/31/2023,5,0,7,0
-11/1/2023,9,6,0,2
-11/2/2023,5,0,0,9
-11/3/2023,2,1,9,5
-11/4/2023,9,5,1,4
-11/5/2023,6,1,7,1
-11/6/2023,7,9,8,2
-11/7/2023,2,1,1,0
-11/8/2023,0,6,5,0
-11/9/2023,7,0,4,0
-11/10/2023,6,1,3,4
-11/11/2023,1,8,3,6
-11/12/2023,9,0,2,7
-11/13/2023,5,0,5,5
-11/14/2023,4,4,1,1
-11/15/2023,1,4,0,2
-11/16/2023,4,1,5,9
-11/17/2023,5,8,9,1
-11/18/2023,7,4,4,9
-11/19/2023,2,2,0,9
-11/20/2023,9,4,4,7
-11/21/2023,4,8,4,4
-11/22/2023,9,0,5,2
-11/23/2023,5,7,1,0
-11/24/2023,4,5,1,7
-11/25/2023,2,4,8,1
-11/26/2023,4,1,2,4
-11/27/2023,6,2,7,7
-11/28/2023,1,8,3,8
-11/29/2023,8,1,2,9
-11/30/2023,3,3,2,8
-12/1/2023,3,1,7,0
-12/2/2023,7,4,4,1
-12/3/2023,9,4,0,4
-12/4/2023,7,3,1,2
-12/5/2023,7,7,0,9
-12/6/2023,6,9,4,7
-12/7/2023,4,0,3,7
-12/8/2023,6,0,0,2
-12/9/2023,5,4,7,5
-12/10/2023,0,4,6,4
-12/11/2023,5,0,3,1
-12/12/2023,1,4,1,4
-12/13/2023,9,1,8,3
-12/14/2023,2,3,9,7
-12/15/2023,2,6,8,2
-12/16/2023,3,9,6,1
-12/17/2023,3,9,0,1
-12/18/2023,6,2,5,3
-12/19/2023,5,6,1,6
-12/20/2023,7,8,8,8
-12/21/2023,0,3,4,5
-12/22/2023,0,0,7,7
-12/23/2023,2,0,7,3
-12/24/2023,0,6,5,2
-12/25/2023,4,6,7,2
-12/26/2023,1,6,9,4
-12/27/2023,8,7,9,1
-12/28/2023,4,2,2,7
-12/29/2023,6,0,8,8
-12/30/2023,7,7,4,8
-12/31/2023,9,8,8,7
-1/1/2024,2,3,6,6
-1/2/2024,8,1,5,8
-1/3/2024,2,9,9,2
-1/4/2024,3,7,1,4
-1/5/2024,1,1,4,5
-1/6/2024,0,9,5,4
-1/7/2024,7,5,6,4
-1/8/2024,5,9,1,1
-1/9/2024,3,6,7,9
-1/10/2024,8,9,8,1
-1/11/2024,1,6,4,2
-1/12/2024,2,3,5,0
-1/13/2024,4,2,1,7
-1/14/2024,8,9,1,9
-1/15/2024,3,8,0,1
-1/16/2024,0,4,8,3
-1/17/2024,9,5,4,5
-1/18/2024,0,8,1,4
-1/19/2024,5,1,6,1
-1/20/2024,6,2,4,6
-1/21/2024,1,6,0,3
-1/22/2024,2,1,0,9
-1/23/2024,3,5,2,1
-1/24/2024,8,8,0,9
-1/25/2024,9,1,2,4
-1/26/2024,4,6,1,3
-1/27/2024,7,0,4,4
-1/28/2024,0,6,6,2
-1/29/2024,6,4,5,4
-1/30/2024,6,7,3,1
-1/31/2024,9,4,3,2
-2/1/2024,9,3,2,1
-2/2/2024,3,7,7,1
-2/3/2024,9,0,6,3
-2/4/2024,3,6,3,4
-2/5/2024,5,9,3,5
-2/6/2024,4,4,3,1
-2/7/2024,1,6,1,6
-2/8/2024,9,1,9,1
-2/9/2024,0,8,7,4
-2/10/2024,2,9,2,8
-2/11/2024,0,1,5,7
-2/12/2024,1,5,8,0
-2/13/2024,9,9,1,6
-2/14/2024,8,9,2,7
-2/15/2024,6,0,0,2
-2/16/2024,6,6,3,4
-2/17/2024,0,0,8,1
-2/18/2024,4,6,4,1
-2/19/2024,8,5,7,8
-2/20/2024,4,2,7,1
-2/21/2024,9,3,3,0
-2/22/2024,9,3,4,2
-2/23/2024,2,2,3,7
-2/24/2024,9,7,8,0
-2/25/2024,8,5,6,8
-2/26/2024,4,1,4,5
-2/27/2024,8,4,4,5
-2/28/2024,3,0,3,7
-2/29/2024,0,9,3,3
-3/1/2024,7,8,2,7
-3/2/2024,2,5,6,4
-3/3/2024,3,2,4,5
-3/4/2024,3,0,1,8
-3/5/2024,5,7,1,7
-3/6/2024,7,0,4,1
-3/7/2024,1,1,0,1
-3/8/2024,7,3,8,2
-3/9/2024,9,5,3,0
-3/10/2024,0,4,3,7
-3/11/2024,5,3,6,0
-3/12/2024,0,9,5,8
-3/13/2024,2,0,5,9
-3/14/2024,3,1,5,9
-3/15/2024,7,0,4,1
-3/16/2024,0,6,5,6
-3/17/2024,8,8,3,2
-3/18/2024,3,3,5,8
-3/19/2024,2,8,1,2
-3/20/2024,7,6,1,9
-3/21/2024,5,0,9,3
-3/22/2024,1,8,4,2
-3/23/2024,2,0,8,5
-3/24/2024,5,3,6,2
-3/25/2024,6,0,5,2
-3/26/2024,6,3,0,7
-3/27/2024,1,7,8,3
-3/28/2024,6,0,7,3
-3/29/2024,7,4,3,6
-3/30/2024,4,7,5,2
-3/31/2024,9,7,8,4
-4/1/2024,7,4,8,4
-4/2/2024,2,0,9,2
-4/3/2024,9,4,0,9
-4/4/2024,3,9,1,8
-4/5/2024,9,0,3,7
-4/6/2024,4,9,3,3
-4/7/2024,8,8,6,5
-4/8/2024,3,6,1,7
-4/9/2024,6,2,2,4
-4/10/2024,3,8,8,0
-4/11/2024,3,4,0,4
-4/12/2024,3,8,9,2
-4/13/2024,8,7,8,3
-4/14/2024,6,8,4,9
-4/15/2024,7,7,2,9
-4/16/2024,1,7,7,0
-4/17/2024,1,9,2,4
-4/18/2024,4,0,4,5
-4/19/2024,7,4,0,1
-4/20/2024,0,5,6,4
-4/21/2024,7,7,6,0
-4/22/2024,3,3,2,6
-4/23/2024,3,4,1,8
-4/24/2024,8,4,6,2
-4/25/2024,1,3,6,5
-4/26/2024,8,9,0,1
-4/27/2024,6,2,7,7
-4/28/2024,5,7,0,3
-4/29/2024,5,8,3,0
-4/30/2024,8,9,8,4
-5/1/2024,6,9,9,4
-5/2/2024,5,2,7,5
-5/3/2024,3,0,9,4
-5/4/2024,3,7,1,1
-5/5/2024,5,8,0,6
-5/6/2024,6,1,5,0
-5/7/2024,9,1,0,9
-5/8/2024,2,7,6,7
-5/9/2024,4,3,5,5
-5/10/2024,6,5,9,3
-5/11/2024,5,6,3,9
-5/12/2024,2,4,5,1
-5/13/2024,1,3,3,1
-5/14/2024,7,7,3,1
-5/15/2024,0,5,7,1
-5/16/2024,4,9,1,6
-5/17/2024,8,8,4,5
-5/18/2024,7,7,1,8
-5/19/2024,3,5,0,0
-5/20/2024,0,9,3,0
-5/21/2024,1,6,1,9
-5/22/2024,2,5,7,0
-5/23/2024,7,0,6,2
-5/24/2024,8,7,7,9
-5/25/2024,7,6,3,4
-5/26/2024,0,2,3,9
-5/27/2024,6,1,9,9
-5/28/2024,7,1,2,8
-5/29/2024,9,1,3,8
-5/30/2024,2,2,2,6
-5/31/2024,6,7,1,9
-6/1/2024,0,2,7,5
-6/2/2024,9,5,7,5
-6/3/2024,3,7,3,2
-6/4/2024,1,1,1,2
-6/5/2024,5,5,5,4
-6/6/2024,9,6,6,7
-6/7/2024,1,1,0,8
-6/8/2024,7,9,7,8
-6/9/2024,8,8,5,5
-6/10/2024,5,6,4,3
-6/11/2024,2,7,2,2
-6/12/2024,8,9,1,5
-6/13/2024,4,5,7,2
-6/14/2024,9,4,1,7
-6/15/2024,6,9,1,4
-6/16/2024,7,8,5,0
-6/17/2024,8,4,1,2
-6/18/2024,8,0,3,3
-6/19/2024,6,6,5,2
-6/20/2024,8,9,3,6
-6/21/2024,4,9,9,8
-6/22/2024,0,2,7,0
-6/23/2024,7,7,8,5
-6/24/2024,9,9,6,7
-6/25/2024,5,3,5,9
-6/26/2024,8,8,1,0
-6/27/2024,0,6,2,2
-6/28/2024,9,5,0,5
-6/29/2024,0,5,9,2
-6/30/2024,1,8,2,3
-7/1/2024,5,8,5,8
-7/2/2024,9,5,4,0
-7/3/2024,4,1,9,9
-7/4/2024,9,1,5,0
-7/5/2024,0,9,0,8
-7/6/2024,4,8,5,8
-7/7/2024,0,8,8,3
-7/8/2024,6,1,0,5
-7/9/2024,7,4,2,2
-7/10/2024,3,8,2,1
-7/11/2024,1,0,1,9
-7/12/2024,5,2,8,7
-7/13/2024,7,4,5,7
-7/14/2024,0,2,6,6
-7/15/2024,5,7,4,8
-7/16/2024,6,2,9,6
-7/17/2024,4,8,1,5
-7/18/2024,7,0,9,2
-7/19/2024,6,7,0,8
-7/20/2024,3,4,3,2
-7/21/2024,2,5,9,5
-7/22/2024,4,9,1,5
-7/23/2024,8,7,6,5
-7/24/2024,5,6,6,5
-7/25/2024,6,2,0,4
-7/26/2024,0,3,8,8
-7/27/2024,6,8,3,9
-7/28/2024,1,3,9,8
-7/29/2024,6,6,0,9
-7/30/2024,8,5,5,0
-7/31/2024,8,3,0,3
-8/1/2024,6,6,4,3
-8/2/2024,5,5,5,0
-8/3/2024,8,2,4,3
-8/4/2024,4,9,5,3
-8/5/2024,6,2,0,5
-8/6/2024,6,6,3,0
-8/7/2024,6,0,0,2
-8/8/2024,6,1,6,7
-8/9/2024,2,6,2,9
-8/10/2024,6,0,6,9
-8/11/2024,0,6,2,2
-8/12/2024,1,2,1,3
-8/13/2024,3,1,9,9
-8/14/2024,6,6,2,1
-8/15/2024,6,4,2,3
-8/16/2024,3,0,7,0
-8/17/2024,6,0,0,1
-8/18/2024,8,5,6,9
-8/19/2024,4,1,4,2
-8/20/2024,3,9,8,9
-8/21/2024,4,5,9,9
-8/22/2024,8,9,4,1
-8/23/2024,2,9,9,5
-8/24/2024,0,7,2,6
-8/25/2024,5,2,5,8
-8/26/2024,0,7,1,3
-8/27/2024,6,4,9,3
-8/28/2024,3,5,9,6
-8/29/2024,3,4,7,0
-8/30/2024,9,0,7,0
-8/31/2024,4,9,8,1
-9/1/2024,0,8,1,2
-9/2/2024,3,2,6,7
-9/3/2024,3,9,1,8
-9/4/2024,4,9,4,0
-9/5/2024,0,8,1,7
-9/6/2024,9,0,1,5
-9/7/2024,6,3,0,6
-9/8/2024,0,4,8,6
-9/9/2024,4,4,5,2
-9/10/2024,4,8,7,2
-9/11/2024,9,0,2,7
-9/12/2024,4,2,0,6
-9/13/2024,0,5,2,4
-9/14/2024,6,9,6,6
-9/15/2024,9,9,4,1
-9/16/2024,4,3,1,3
-9/17/2024,2,3,2,4
-9/18/2024,7,6,6,1
-9/19/2024,5,4,8,4
-9/20/2024,7,2,8,1
-9/21/2024,1,7,9,1
-9/22/2024,5,8,7,0
-9/23/2024,3,4,3,0
-9/24/2024,8,0,5,1
-9/25/2024,8,5,8,0
-9/26/2024,4,3,8,1
-9/27/2024,5,9,3,3
-9/28/2024,7,4,5,4
-9/29/2024,1,2,1,5
-9/30/2024,5,6,9,7
-10/1/2024,3,4,6,4
-10/2/2024,8,3,5,9
-10/3/2024,2,5,8,9
-10/4/2024,5,0,1,9
-10/5/2024,6,0,7,8
-10/6/2024,1,6,0,4
-10/7/2024,3,7,5,2
-10/8/2024,0,5,4,0
-10/9/2024,1,4,7,3
-10/10/2024,1,5,8,9
-10/11/2024,2,6,3,6
-10/12/2024,9,5,6,3
-10/13/2024,6,3,0,7
-10/14/2024,3,8,0,5
-10/15/2024,5,1,4,5
-10/16/2024,8,5,6,1
-10/17/2024,5,0,5,4
-10/18/2024,2,5,4,1
-10/19/2024,5,9,2,9
-10/20/2024,3,4,8,8
-10/21/2024,1,3,9,9
-10/22/2024,0,4,4,5
-10/23/2024,6,5,5,1
-10/24/2024,8,8,4,6
-10/25/2024,3,5,2,9
-10/26/2024,0,3,0,1
-10/27/2024,0,5,7,0
-10/28/2024,9,0,1,3
-10/29/2024,2,6,3,3
-10/30/2024,6,6,3,3
-10/31/2024,7,2,2,0
-11/1/2024,7,4,2,5
-11/2/2024,5,3,6,2
-11/3/2024,3,7,5,6
-11/4/2024,6,0,2,1
-11/5/2024,4,2,3,7
-11/6/2024,6,3,4,8
-11/7/2024,1,0,4,9
-11/8/2024,2,7,4,9
-11/9/2024,7,1,3,1
-11/10/2024,5,9,1,5
-11/11/2024,3,3,3,0
-11/12/2024,6,2,9,4
-11/13/2024,5,7,0,6
-11/14/2024,8,9,8,4
-11/15/2024,6,7,4,0
-11/16/2024,3,1,3,3
-11/17/2024,8,9,9,6
-11/18/2024,6,9,1,1
-11/19/2024,9,8,0,1
-11/20/2024,5,0,7,4
-11/21/2024,7,5,4,7
-11/22/2024,6,7,6,3
-11/23/2024,5,3,9,7
-11/24/2024,0,8,6,6
-11/25/2024,0,4,9,3
-11/26/2024,3,3,2,4
-11/27/2024,4,2,1,0
-11/28/2024,2,3,0,9
-11/29/2024,0,4,7,7
-11/30/2024,1,2,5,5
-12/1/2024,7,2,6,8
-12/2/2024,8,0,2,7
-12/3/2024,6,4,7,6
-12/4/2024,2,9,1,5
-12/5/2024,3,5,4,0
-12/6/2024,0,8,8,3
-12/7/2024,6,7,4,1
-12/8/2024,3,5,4,1
-12/9/2024,6,8,8,6
-12/10/2024,1,9,1,1
-12/11/2024,7,3,1,1
-12/12/2024,9,2,6,9
-12/13/2024,6,5,9,9
-12/14/2024,4,5,4,8
-12/15/2024,1,1,1,3
-12/16/2024,8,7,1,5
-12/17/2024,9,1,4,5
-12/18/2024,1,3,1,0
-12/19/2024,3,0,1,5
-12/20/2024,1,4,6,1
-12/21/2024,0,1,3,5
-12/22/2024,4,8,4,2
-12/23/2024,0,9,3,7
-12/24/2024,9,3,0,2
-12/25/2024,6,3,5,0
-12/26/2024,9,9,3,0
-12/27/2024,0,1,8,6
-12/28/2024,5,3,7,3
-12/29/2024,2,0,1,9
-12/30/2024,6,9,5,2
-12/31/2024,3,6,2,0
-1/1/2025,3,0,7,4
-1/2/2025,3,8,3,0
-1/3/2025,4,0,1,6
-1/4/2025,3,7,7,9
-1/5/2025,3,8,0,6
-1/6/2025,8,3,3,2
-1/7/2025,0,9,7,5
-1/8/2025,0,7,4,6
-1/9/2025,0,8,3,8
-1/10/2025,2,1,9,8
-1/11/2025,4,1,7,2
-1/12/2025,5,3,6,7
-1/13/2025,4,5,3,8
-1/14/2025,1,0,8,3
-1/15/2025,2,0,6,8
-1/16/2025,5,3,3,8
-1/17/2025,2,6,3,9
-1/18/2025,5,2,2,0
-1/19/2025,7,3,8,4
-1/20/2025,5,7,0,4
-1/21/2025,6,2,1,4
-1/22/2025,2,8,9,9
-1/23/2025,3,2,7,9
-1/24/2025,9,3,1,1
-1/25/2025,9,5,0,6
-1/26/2025,8,5,0,2
-1/27/2025,9,0,7,5
-1/28/2025,4,4,5,1
-1/29/2025,6,0,9,0
-1/30/2025,3,1,6,8
-1/31/2025,0,4,0,2
-2/1/2025,7,5,3,8
-2/2/2025,3,4,8,7
-2/3/2025,7,1,1,5
-2/4/2025,0,8,7,6
-2/5/2025,8,4,5,8
-2/6/2025,9,6,7,5
-2/7/2025,7,6,4,8
-2/8/2025,1,5,0,6
-2/9/2025,3,3,6,7
-2/10/2025,1,1,9,9
-2/11/2025,4,1,4,5
-2/12/2025,6,6,9,0
-2/13/2025,9,0,9,1
-2/14/2025,4,1,6,7
-2/15/2025,1,4,0,2
-2/16/2025,7,1,7,9
-2/17/2025,2,2,6,2
-2/18/2025,1,4,9,8
-2/19/2025,6,1,9,2
-2/20/2025,5,4,7,1
-2/21/2025,5,8,3,9
-2/22/2025,0,9,0,7
-2/23/2025,7,1,2,0
-2/24/2025,7,2,1,4
-2/25/2025,7,8,8,7
-2/26/2025,5,8,2,7
-2/27/2025,8,7,0,6
-2/28/2025,8,2,8,9
-3/1/2025,4,7,4,7
-3/2/2025,5,4,7,4
-3/3/2025,8,8,0,3
-3/4/2025,7,6,5,7
-3/5/2025,0,2,7,9
-3/6/2025,1,9,6,0
-3/7/2025,2,4,4,5
-3/8/2025,2,0,7,1
-3/9/2025,2,9,8,4
-3/10/2025,9,4,5,0
-3/11/2025,1,0,0,0
-3/12/2025,4,1,7,5
-3/13/2025,5,4,6,8
-3/14/2025,1,5,0,7
-3/15/2025,4,8,2,5
-3/16/2025,2,6,7,5
-3/17/2025,1,2,9,5
-3/18/2025,6,7,0,4
-3/19/2025,5,7,9,6
-3/20/2025,1,7,7,3
-3/21/2025,6,0,0,7
-3/22/2025,2,8,2,4
-3/23/2025,0,0,0,6
-3/24/2025,3,7,1,5
-3/25/2025,6,9,9,2
-3/26/2025,5,6,7,5
-3/27/2025,9,1,5,0
-3/28/2025,4,1,1,4
-3/29/2025,7,1,4,8
-3/30/2025,5,6,9,1
-3/31/2025,8,8,4,7
-4/1/2025,4,2,3,6
-4/2/2025,7,8,4,2
-4/3/2025,9,9,0,9
-4/4/2025,1,2,6,7
-4/5/2025,7,4,8,6
-4/6/2025,2,8,9,5
-4/7/2025,3,5,8,7
-4/8/2025,9,8,3,6
-4/9/2025,4,6,2,8
-4/10/2025,8,1,0,1
-4/11/2025,5,8,0,5
-4/12/2025,7,0,0,4
-4/13/2025,8,8,5,8
-4/14/2025,5,4,0,8
-4/15/2025,7,8,4,6
-4/16/2025,7,6,8,2
-4/17/2025,1,0,6,3
-4/18/2025,8,5,9,4
-4/19/2025,8,2,6,3
-4/20/2025,6,8,2,1
-4/21/2025,4,6,5,1
-4/22/2025,9,2,2,9
-4/23/2025,2,9,1,9
-4/24/2025,0,8,1,7
-4/25/2025,8,4,7,1
-4/26/2025,8,1,1,8
-4/27/2025,7,6,2,6
-4/28/2025,5,3,7,8
-4/29/2025,9,2,4,0
-4/30/2025,7,6,4,6
-5/1/2025,8,1,0,5
-5/2/2025,7,2,1,3
-5/3/2025,0,4,2,5
-5/4/2025,9,3,2,0
-5/5/2025,0,5,8,9
-5/6/2025,4,7,7,1
-5/7/2025,1,1,9,8
-5/8/2025,6,4,1,8
-5/9/2025,7,2,6,6
-5/10/2025,6,6,5,2
-5/11/2025,0,1,1,1
-5/12/2025,6,3,8,1
-5/13/2025,1,3,3,0
-5/14/2025,4,6,6,5
-5/15/2025,2,3,6,3
-5/16/2025,8,2,8,7
-5/17/2025,1,5,2,7
-5/18/2025,4,6,7,1
-5/19/2025,2,3,0,3
-5/20/2025,3,8,0,6
-5/21/2025,9,8,8,8
-5/22/2025,7,4,9,1
-5/23/2025,7,2,0,5
-5/24/2025,5,9,2,3
-5/25/2025,6,6,4,7
-5/26/2025,3,2,8,6
-5/27/2025,3,3,8,0
-5/28/2025,2,5,3,0
-5/29/2025,4,7,7,1
-5/30/2025,2,2,5,9
-5/31/2025,9,4,6,3
-6/1/2025,3,1,8,5
-6/2/2025,6,5,2,4
-6/3/2025,4,0,2,5
-6/4/2025,7,8,3,1
-6/5/2025,3,7,4,3
-6/6/2025,1,5,3,6
-6/7/2025,6,8,8,2
-6/8/2025,7,2,4,2
-6/9/2025,3,0,9,4
-6/10/2025,7,4,8,0
-6/11/2025,3,9,8,8
-6/12/2025,0,1,9,1
-6/13/2025,5,9,4,7
-6/14/2025,8,5,1,6
-6/15/2025,1,0,9,3
-6/16/2025,4,2,1,1
-6/17/2025,8,0,9,3
-6/18/2025,4,4,9,7
-6/19/2025,6,7,7,3
-6/20/2025,3,9,7,2
-6/21/2025,7,3,9,0
-6/22/2025,7,4,2,2
-6/23/2025,8,4,4,9
-6/24/2025,9,8,2,0
-6/25/2025,4,3,8,1
-6/26/2025,1,0,3,8
-6/27/2025,4,4,2,6
-6/28/2025,8,5,8,8
-6/29/2025,2,6,9,9
-6/30/2025,6,6,7,5
-7/1/2025,7,8,3,1
-7/2/2025,6,5,0,4
-7/3/2025,2,6,2,5
-7/4/2025,6,7,5,9
-7/5/2025,9,6,2,2
-7/6/2025,8,2,0,2
-7/7/2025,1,3,5,4
-7/8/2025,7,1,1,0
-7/9/2025,6,1,5,8
-7/10/2025,0,7,1,5
-7/11/2025,0,3,6,5
-7/12/2025,6,9,6,1
-7/13/2025,8,1,2,0
-7/14/2025,1,6,1,5
-7/15/2025,4,9,2,8
-7/16/2025,6,6,0,9
-7/17/2025,8,0,6,0
-7/18/2025,7,2,7,2
-7/19/2025,1,3,4,8
-7/20/2025,4,8,8,7
-7/21/2025,7,5,7,1
-7/22/2025,3,4,8,9
-7/23/2025,0,7,5,1
-7/24/2025,9,4,0,9
-7/25/2025,1,8,7,9
-7/26/2025,3,2,8,4
-7/27/2025,8,6,5,2
-7/28/2025,0,6,4,7
-7/29/2025,3,0,7,1
-7/30/2025,4,7,8,3
-7/31/2025,1,1,7,5
-8/1/2025,2,2,4,7
-8/2/2025,1,1,3,4
-8/3/2025,5,6,3,2
-8/4/2025,0,0,1,0
-8/5/2025,7,1,7,2
-8/6/2025,5,6,8,0
-8/7/2025,4,4,5,1
-8/8/2025,1,5,8,1
-8/9/2025,0,8,9,7
-8/10/2025,4,3,8,0
-8/11/2025,2,4,0,2
-8/12/2025,4,1,0,8
-8/13/2025,2,1,9,3
-8/14/2025,4,2,4,6
-8/15/2025,2,6,3,2
-8/16/2025,2,7,3,4
-8/17/2025,0,7,3,8
-8/18/2025,9,4,4,3
-8/19/2025,3,7,7,9
-8/20/2025,3,0,3,0
-8/21/2025,4,7,8,2
-8/22/2025,0,3,6,8
-8/23/2025,0,0,7,3
-8/24/2025,7,1,2,0
-8/25/2025,0,8,4,8
-8/26/2025,1,3,5,3
-8/27/2025,5,4,0,4
-8/28/2025,8,1,7,3
-8/29/2025,0,9,9,3
-8/30/2025,2,3,5,4
-8/31/2025,3,9,6,3
-9/1/2025,1,6,4,4
-9/2/2025,4,6,4,6
-9/3/2025,0,3,4,6
-9/4/2025,3,0,6,4
-9/5/2025,0,1,3,6
-9/6/2025,4,8,5,8
-9/7/2025,9,2,1,4
-9/8/2025,1,2,2,3
-9/9/2025,7,9,7,8
-9/10/2025,5,3,6,7
-9/11/2025,9,1,3,8
-9/12/2025,4,0,2,9
-9/13/2025,1,8,0,7
-9/14/2025,4,4,8,6
-9/15/2025,2,7,0,1
-9/16/2025,4,7,6,1
-9/17/2025,9,3,2,3
-9/18/2025,5,9,3,9
-9/19/2025,7,5,0,7
-9/20/2025,3,9,6,6
-9/21/2025,5,2,9,1
-9/22/2025,0,3,4,4
-9/23/2025,6,2,0,4
-9/24/2025,7,0,9,4
-9/25/2025,8,1,6,0
-9/26/2025,4,5,4,8
-9/27/2025,2,7,2,0
-9/28/2025,8,7,2,6
-9/29/2025,2,4,5,9
-9/30/2025,4,0,0,7
-10/1/2025,2,9,3,2
-10/2/2025,3,8,9,7
-10/3/2025,4,9,4,9
-10/4/2025,4,2,9,9
-10/5/2025,0,2,1,6
-10/6/2025,8,9,8,9
-10/7/2025,8,2,1,0
-10/8/2025,8,9,0,5
-10/9/2025,0,9,0,9
-10/10/2025,1,0,4,8
-10/11/2025,8,3,2,1
-10/12/2025,6,4,8,0
-10/13/2025,4,4,1,2
-10/14/2025,2,4,6,9
-10/15/2025,3,1,3,3
-10/16/2025,1,3,0,3
-10/17/2025,7,6,4,5
-10/18/2025,4,3,7,6
-10/19/2025,8,5,6,2
-10/20/2025,7,0,1,3
-10/21/2025,1,0,3,8
-10/22/2025,6,2,4,0
-10/23/2025,4,2,4,9
-10/24/2025,9,4,8,4
-10/25/2025,6,1,2,1
-10/26/2025,1,3,5,2
-10/27/2025,9,9,7,0
-10/28/2025,6,3,0,4
-10/29/2025,2,7,2,2
-10/30/2025,9,0,3,8
-10/31/2025,3,3,9,6
-11/1/2025,6,0,9,1
-11/2/2025,6,4,4,2
-11/3/2025,0,0,0,5
-11/4/2025,6,9,9,0
-11/5/2025,8,8,5,0
-11/6/2025,6,6,8,4
-11/7/2025,0,2,6,0
-11/8/2025,6,3,3,0
-11/9/2025,7,9,4,9
-11/10/2025,2,6,0,7
-11/11/2025,5,6,8,8
-11/12/2025,3,4,5,9
-11/13/2025,7,7,9,9
-11/14/2025,8,4,8,0
-11/15/2025,4,2,3,6
-11/16/2025,7,3,3,7
-11/17/2025,6,2,9,8
-11/18/2025,3,5,9,3
-11/19/2025,3,7,1,7
-11/20/2025,9,5,5,0
-11/21/2025,0,1,0,2
-11/22/2025,3,6,0,1
-11/23/2025,9,3,4,9
-11/24/2025,6,1,9,2
-11/25/2025,8,0,1,3
-11/26/2025,3,4,0,2
-11/27/2025,6,8,9,2
-11/28/2025,4,0,8,4
-11/29/2025,2,9,4,6
-11/30/2025,7,5,1,3
-12/1/2025,1,2,0,6
-12/2/2025,7,2,4,3
-12/3/2025,3,6,1,8
-12/4/2025,4,1,4,1
-12/5/2025,9,3,1,7
-12/6/2025,2,9,8,6
-12/7/2025,2,0,9,9
-12/8/2025,3,6,0,9
-12/9/2025,8,8,4,8
-12/10/2025,5,4,9,5
-12/11/2025,6,4,0,1
-12/12/2025,7,7,0,7
-12/13/2025,3,6,1,6
-12/14/2025,0,7,9,6
-12/15/2025,3,8,1,4
-12/16/2025,4,7,8,1
-12/17/2025,9,5,4,9
-12/18/2025,3,6,5,6
-12/19/2025,5,0,8,1
-12/20/2025,0,8,8,8
-12/21/2025,9,3,8,1

Tutorial.xlsx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f0ca6108f5e4fad95d38c2a057f4a428fa5fa945443aa7f717c60457d3094100
-size 1786171

app (20).py

@@ -1,266 +0,0 @@
-#!/usr/bin/env python3
-import importlib
-from pathlib import Path
-import streamlit as st
-import pandas as pd
-
-from datetime import datetime
-# ===============================
-# CONFIG
-# ===============================
-
-ENGINE_MODULE = "lotto_predictor"
-
-DATA_PATHS = {
-    "G5 (Gimme 5)": "gimme5_results.csv",
-    "LA (Lotto America)": "la_results.csv",
-    "L4L (Lucky for Life)": "Lucky For Life.csv",
-    "MB (Megabucks)": "mb_results.csv",
-    "MM (Mega Millions)": "mm_results.csv",
-    "PB (Powerball)": "pb_results.csv",
-    "P3 (Pick 3 Evening)": "Pick3eve.csv",
-    "P4 (Pick 4 Evening)": "Pick4eve (1).csv",
-}
-
-GAME_KEY_MAP = {
-    "G5 (Gimme 5)": "gimme5",
-    "LA (Lotto America)": "la",
-    "L4L (Lucky for Life)": "l4l",
-    "MB (Megabucks)": "mb",
-    "MM (Mega Millions)": "mm",
-    "PB (Powerball)": "pb",
-}
-
-PICK3_KEY = "P3 (Pick 3 Evening)"
-PICK4_KEY = "P4 (Pick 4 Evening)"
-
-# ===============================
-# HELPERS
-# ===============================
-
-@st.cache_resource
-def load_engine():
-    return importlib.import_module(ENGINE_MODULE)
-
-@st.cache_data
-def csv_rows(path):
-    try:
-        return len(pd.read_csv(path))
-    except Exception:
-        return 0
-
-def fmt_ticket(nums, star=None):
-    if not nums:
-        return ""
-    s = "-".join(str(int(x)) for x in nums)
-    if star is not None:
-        return f"{s} ({int(star)})"
-    return s
-
-
-def build_ticket_text(game_name, result, cfg):
-    lines = []
-    lines.append(f"GAME: {game_name}")
-    lines.append("")
-
-    # Primary
-    if result.get("numbers"):
-        lines.append("PRIMARY:")
-        lines.append(
-            fmt_ticket(
-                result.get("numbers"),
-                result.get("star") if cfg.star_col else None
-            )
-        )
-        lines.append("")
-
-    # GOD MODE sets (support multiple key names)
-    god_sets = (
-        result.get("god_sets")
-        or result.get("godmode_sets")
-        or result.get("god_mode_sets")
-        or []
-    )
-    if god_sets:
-        lines.append("GOD MODE SETS:")
-        for s in god_sets:
-            lines.append(
-                f"- {s.get('style','Set')}: "
-                f"{fmt_ticket(s.get('numbers'), s.get('star') if cfg.star_col else None)}"
-            )
-        lines.append("")
-
-    # Strike tickets
-    strike = result.get("strike_tickets", {}) or {}
-    if strike:
-        lines.append("STRIKE TICKETS:")
-        for k, v in strike.items():
-            lines.append(
-                f"- {k}: "
-                f"{fmt_ticket(v.get('numbers'), v.get('star') if cfg.star_col else None)}"
-            )
-        lines.append("")
-
-    # Wildcard (if present)
-    wc = result.get("wildcard")
-    if wc:
-        lines.append("WILDCARD:")
-        lines.append(
-            fmt_ticket(
-                wc.get("numbers"),
-                wc.get("star") if cfg.star_col else None
-            )
-        )
-
-    return "\n".join(lines)
-
-# ===============================
-# UI
-# ===============================
-
-st.set_page_config(page_title="God Mode", layout="centered")
-st.title("🎯 GOD MODE Lottery Engine")
-
-engine = load_engine()
-
-game = st.selectbox("Select Game", list(DATA_PATHS.keys()))
-csv_path = Path(DATA_PATHS[game])
-
-if not csv_path.exists():
-    st.error(f"CSV not found in HF repo: {csv_path.name}")
-    st.stop()
-
-top_k = st.number_input("How many predictions?", 3, 30, 5, 1)
-st.caption(f"Using CSV: `{csv_path.name}` ({csv_rows(csv_path)} rows)")
-
-# ===============================
-# PICK 3 / PICK 4
-# ===============================
-
-if game == PICK3_KEY:
-    from pick3_ultra_predictor import Pick3UltraPredictor
-    if st.button("Generate Pick 3", use_container_width=True):
-        with st.spinner("Training Pick 3..."):
-            p = Pick3UltraPredictor(str(csv_path))
-            p.load_and_prepare()
-            p.train_models()
-
-        preds = []
-        hot = p.hot_digits(50)
-        import numpy as np
-
-        for _ in range(top_k):
-            for __ in range(500):
-                a = int(p.predict_digit(0))
-                b = int(p.predict_digit(1))
-                c = int(p.predict_digit(2))
-                if np.random.rand() < 0.4: a = int(np.random.choice(hot))
-                if np.random.rand() < 0.3: b = int(np.random.choice(hot))
-                if not p.is_bad_pattern(a, b, c):
-                    preds.append(f"{a}-{b}-{c}")
-                    break
-
-        st.success("Pick 3 Results")
-        for i, v in enumerate(preds, 1):
-            st.write(f"{i}) **{v}**")
-    st.stop()
-
-if game == PICK4_KEY:
-    from pick4_catboost_ultra import Pick4CatBoostUltra
-    if st.button("Generate Pick 4", use_container_width=True):
-        with st.spinner("Training Pick 4..."):
-            p = Pick4CatBoostUltra(str(csv_path))
-            p.load()
-            p.train()
-
-        preds = []
-        import numpy as np
-        from collections import Counter
-        hot = [d for d, _ in Counter(
-            p.data[["d1","d2","d3","d4"]].tail(60).values.flatten()
-        ).most_common(7)]
-
-        for _ in range(top_k):
-            for __ in range(500):
-                d1 = int(p.predict_digit(0))
-                d2 = int(p.predict_digit(1))
-                d3 = int(p.predict_digit(2))
-                d4 = int(p.predict_digit(3))
-                if np.random.rand() < 0.8: d1 = int(np.random.choice(hot))
-                if np.random.rand() < 0.7: d2 = int(np.random.choice(hot))
-                if len({d1,d2,d3,d4}) >= 2:
-                    preds.append(f"{d1}-{d2}-{d3}-{d4}")
-                    break
-
-        st.success("Pick 4 Results")
-        for i, v in enumerate(preds, 1):
-            st.write(f"{i}) **{v}**")
-    st.stop()
-
-# ===============================
-# LOTTO ENGINE
-# ===============================
-
-st.subheader("Lotto Predictions")
-
-enable_wildcard = st.checkbox("Wildcard Strike", True)
-
-try:
-    engine.PATCH_UI_FLAGS["wildcard_strike"] = bool(enable_wildcard)
-except Exception:
-    pass
-
-game_key = GAME_KEY_MAP[game]
-cfg = engine.GAME_CONFIGS[game_key]
-
-if st.button("Generate Lotto Prediction", type="primary", use_container_width=True):
-    with st.spinner("Running GOD MODE..."):
-        result = engine.predict_for_game_v3(
-            csv_path=csv_path,
-            game_key=game_key,
-            run_backtest=False
-        )
-
-    if result.get("error"):
-        st.error(result["error"])
-        st.stop()
-
-    st.subheader("Primary Prediction")
-    st.success(fmt_ticket(result.get("numbers"), result.get("star") if cfg.star_col else None))
-
-    god_sets = (
-        result.get("god_sets")
-        or result.get("godmode_sets")
-        or result.get("god_mode_sets")
-        or []
-    )
-
-    if god_sets:
-        st.subheader("🎲 GOD MODE Sets")
-        for s in god_sets:
-            st.write(
-                f"**{s.get('style','Set')}:** "
-                f"{fmt_ticket(s.get('numbers'), s.get('star') if cfg.star_col else None)}"
-            )
-
-    strike = result.get("strike_tickets", {}) or {}
-    if strike:
-        st.subheader("🎯 Strike Tickets")
-        for k, v in strike.items():
-            st.write(
-                f"**{k}:** "
-                f"{fmt_ticket(v.get('numbers'), v.get('star') if cfg.star_col else None)}"
-            )
-
-    # -------------------------------
-    # Download tickets (timestamped)
-    # -------------------------------
-    ticket_text = build_ticket_text(game, result, cfg)
-    timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
-    st.download_button(
-        label="⬇️ Download Tickets",
-        data=ticket_text,
-        file_name=f"{game.replace(' ', '_')}_tickets_{timestamp}.txt",
-        mime="text/plain",
-        use_container_width=True,
-    )

app.py

@@ -1,1412 +0,0 @@
-import streamlit as st
-import pandas as pd
-from pathlib import Path
-import re
-import json
-from collections import Counter
-
-from datetime import datetime
-import random
-
-import os
-import time
-
-# -------------------------
-# CSV freshness guardrails (UI-only, no layout/color changes)
-# -------------------------
-def _human_age(seconds: float) -> str:
-    try:
-        s = int(max(0, seconds))
-    except Exception:
-        return "unknown"
-    if s < 60:
-        return f"{s}s"
-    m, s = divmod(s, 60)
-    if m < 60:
-        return f"{m}m {s}s"
-    h, m = divmod(m, 60)
-    if h < 24:
-        return f"{h}h {m}m"
-    d, h = divmod(h, 24)
-    return f"{d}d {h}h"
-
-def _csv_signature(path: str):
-    """Fast CSV signature: (exists, mtime_ns, size)."""
-    try:
-        stat = os.stat(path)
-        return (True, stat.st_mtime_ns, stat.st_size)
-    except FileNotFoundError:
-        return (False, None, None)
-    except Exception:
-        return (False, None, None)
-
-def _csv_age_seconds(path: str):
-    try:
-        stat = os.stat(path)
-        return max(0.0, time.time() - float(stat.st_mtime))
-    except Exception:
-        return None
-
-def csv_changed_warning(csv_paths, label="CSV"):
-    """
-    Show a warning if any CSV changed since last run (session_state).
-    Returns (changed_any, changed_list).
-    """
-    if "csv_sigs" not in st.session_state:
-        st.session_state["csv_sigs"] = {}
-
-    changed_any = False
-    changed_list = []
-
-    for p in csv_paths:
-        sig = _csv_signature(p)
-        old = st.session_state["csv_sigs"].get(p)
-
-        if old is None:
-            # First time this session — just store it
-            st.session_state["csv_sigs"][p] = sig
-            continue
-
-        if sig != old:
-            changed_any = True
-            changed_list.append(p)
-            st.session_state["csv_sigs"][p] = sig
-
-    if changed_any:
-        st.warning(
-            f"⚠️ {label} updated since last run. "
-            f"Soft restart recommended for clean recency windows.\n\n"
-            + "\n".join(f"• {os.path.basename(x)}" for x in changed_list)
-        )
-
-    return changed_any, changed_list
-
-def soft_restart_app():
-    """Best-effort 'restart' inside Streamlit: clears caches + session state then reruns."""
-    try:
-        st.cache_data.clear()
-    except Exception:
-        pass
-    try:
-        # Clear all session state keys (widgets will reinitialize)
-        for k in list(st.session_state.keys()):
-            del st.session_state[k]
-    except Exception:
-        pass
-    try:
-        st.rerun()
-    except Exception:
-        pass
-
-
-# --- Gimme5 Default Mode (UI-only, safe) ---
-g5_default_mode = False
-def fmt_ticket(nums, star=None, cfg=None):
-    """Format a ticket for display.
-    Accepts:
-      - list/tuple of numbers
-      - dict with keys like {'numbers':[...], 'star':...} (or bonus/power)
-      - pre-formatted string
-    Clamps bonus range using cfg.star_min/star_max when cfg is provided.
-    """
-    if nums is None:
-        return ""
-
-    # If dict ticket, prefer its own star/bonus/power unless an explicit star was provided
-    if isinstance(nums, dict):
-        if star is None:
-            for k in ("star", "bonus", "power", "pb", "mb", "sb", "lucky"):
-                if k in nums and isinstance(nums.get(k), (int, str)):
-                    star = nums.get(k)
-                    break
-        nums = nums.get("numbers") or nums.get("nums") or nums.get("main") or []
-
-    # If already a string (rare but supported), just attach star if valid
-    if isinstance(nums, str):
-        s = nums.strip()
-        if not s:
-            return ""
-        if star is not None:
-            try:
-                st = int(star)
-                if cfg is not None and getattr(cfg, "star_min", None) is not None and getattr(cfg, "star_max", None) is not None:
-                    if not (int(cfg.star_min) <= st <= int(cfg.star_max)):
-                        st = None
-                if st is not None:
-                    return f"{s} (⭐ {st})"
-            except Exception:
-                pass
-        return s
-
-    # Normalize numbers list
-    clean = []
-    for x in (nums or []):
-        try:
-            clean.append(int(x))
-        except Exception:
-            continue
-
-    # Clamp main range if cfg provided (safe-guard)
-    if cfg is not None and getattr(cfg, "main_min", None) is not None and getattr(cfg, "main_max", None) is not None:
-        try:
-            mn, mx = int(cfg.main_min), int(cfg.main_max)
-            clean = [n for n in clean if mn <= n <= mx]
-        except Exception:
-            pass
-
-    s = "-".join(str(n) for n in clean)
-
-    # Attach bonus ball if present (and in-range for this game)
-    if star is not None and s:
-        try:
-            st = int(star)
-            if cfg is not None and getattr(cfg, "star_min", None) is not None and getattr(cfg, "star_max", None) is not None:
-                if not (int(cfg.star_min) <= st <= int(cfg.star_max)):
-                    st = None
-            if st is not None:
-                return f"{s} (⭐ {st})"
-        except Exception:
-            pass
-
-    return s
-
-
-def _is_bad_run(nums, run_len=4):
-    s = sorted(set(int(x) for x in nums))
-    streak = 1
-    for i in range(1, len(s)):
-        if s[i] == s[i-1] + 1:
-            streak += 1
-            if streak >= run_len:
-                return True
-        else:
-            streak = 1
-    return False
-
-def build_anchor_spread_ticket(god_sets, *, main_min:int, main_max:int, anchor_min:int, anchor_max:int, seed:int=0):
-    from collections import Counter
-    rnd = random.Random(int(seed) if seed is not None else 0)
-    pool = []
-    for s in (god_sets or []):
-        for n in (s.get("numbers") or []):
-            try:
-                n = int(n)
-                if main_min <= n <= main_max:
-                    pool.append(n)
-            except Exception:
-                pass
-    freq = Counter(pool)
-    core = set([n for n, _ in freq.most_common(7)])
-
-    a0 = max(main_min, anchor_min)
-    a1 = min(main_max, anchor_max)
-    if a0 > a1:
-        return None
-    anchor_band = list(range(a0, a1 + 1))
-    anchor_choices = sorted(anchor_band, key=lambda n: (freq.get(n, 0), n))
-    anchor = next((n for n in anchor_choices if n not in core), anchor_choices[0])
-
-    rest = sorted(set(pool), key=lambda n: (freq.get(n, 0), n))
-    rest = [n for n in rest if n not in core and n != anchor]
-    if len(rest) < 10:
-        rest = [n for n in range(main_min, main_max + 1) if n not in core and n != anchor]
-
-    mid = [n for n in rest if 10 <= n <= 19]
-    hi  = [n for n in rest if n >= 20]
-    any10 = [n for n in rest if n >= 10]
-
-    picked = [anchor]
-
-    def pick_from(band, k):
-        band2 = [n for n in band if n not in picked]
-        rnd.shuffle(band2)
-        for n in band2:
-            picked.append(n)
-            if len(picked) >= 1 + k:
-                break
-
-    pick_from(mid, 2)
-    remaining = 5 - len(picked)
-    if remaining > 0:
-        pick_from(hi, remaining)
-    if len(picked) < 5:
-        pick_from(any10, 5 - len(picked))
-
-    if len(picked) < 5:
-        fb = [n for n in range(main_min, main_max + 1) if n not in picked]
-        rnd.shuffle(fb)
-        for n in fb:
-            picked.append(n)
-            if len(picked) >= 5:
-                break
-
-    picked = sorted(picked[:5])
-
-    if _is_bad_run(picked, run_len=4):
-        fb = [n for n in range(main_min, main_max + 1) if n not in picked and n not in core]
-        fb = sorted(fb, reverse=True)
-        for swap_in in fb[:40]:
-            for idx in range(1, 5):
-                trial = sorted(picked[:idx] + [swap_in] + picked[idx+1:])
-                if not _is_bad_run(trial, run_len=4):
-                    return trial
-    return picked
-
-def build_low_anchor(god_sets, *, main_min:int, main_max:int, seed:int=0):
-    return build_anchor_spread_ticket(god_sets, main_min=main_min, main_max=main_max,
-                                     anchor_min=main_min, anchor_max=min(9, main_max), seed=seed)
-
-def build_mid_anchor(god_sets, *, main_min:int, main_max:int, seed:int=0):
-    return build_anchor_spread_ticket(god_sets, main_min=main_min, main_max=main_max,
-                                     anchor_min=max(10, main_min), anchor_max=min(19, main_max), seed=seed)
-
-
-# Import V3.0 backend
-from lotto_predictor import (
-    predict_for_game_v3,
-    GAME_CONFIGS,
-    NumpyEncoder,
-    clean_powerball_df,
-    load_csv_for_game
-)
-
-# Data paths (adjust if your files live in a data/ subfolder)
-DATA_PATHS = {
-    "G5 (Gimme 5)": "gimme5_results.csv",
-    "LA (Lotto America)": "la_results.csv",
-    "L4L (Lucky for Life)": "Lucky For Life.csv",   # ✅ NEW
-    "MB (Megabucks)": "mb_results.csv",
-    "MM (Mega Millions)": "mm_results.csv",
-    "PB (Powerball)": "pb_results.csv",
-    "wheel_template": "wheel.txt",
-}
-
-st.set_page_config(page_title="Multi Lotto AI Engine V6.0", layout="centered")
-st.title("🎯 Lotto AI Engine (V6.0)")
-
-# -------------------------
-# Helper functions for V3.0
-# -------------------------
-
-def get_hot_and_cold_numbers(df: pd.DataFrame, cfg, top_n: int = 10):
-    """Calculate hot and cold numbers from the dataframe"""
-    # Count frequency of each number across all main columns
-    all_numbers = []
-    for col in cfg.main_cols:
-        all_numbers.extend(df[col].astype(int).tolist())
-    
-    freq_counter = Counter(all_numbers)
-    
-    # Get all possible numbers for this game
-    all_possible = list(range(cfg.main_min, cfg.main_max + 1))
-    
-    # Create frequency list with zeros for missing numbers
-    freq_list = [(num, freq_counter.get(num, 0)) for num in all_possible]
-    
-    # Sort by frequency
-    sorted_by_freq = sorted(freq_list, key=lambda x: x[1], reverse=True)
-    
-    # Hot numbers (most frequent)
-    hot = sorted_by_freq[:top_n]
-    
-    # Cold numbers (least frequent) 
-    cold = sorted_by_freq[-top_n:]
-    cold.reverse()  # Show coldest first
-    
-    return hot, cold
-
-@st.cache_data
-def load_wheel_raw_text(path: str) -> str:
-    """
-    Read wheel template as raw text using latin-1 fallback (robust to special bytes).
-    Returns empty string if missing or unreadable.
-    """
-    p = Path(path)
-    if not p.exists():
-        return ""
-    try:
-        # latin-1 will never fail for single-byte encodings; errors='replace' for safety
-        text = p.read_text(encoding="latin-1", errors="replace")
-        return text
-    except Exception:
-        return ""
-
-def select_20_wheel_numbers(hot: list, cold: list):
-    """Select 20 numbers for wheeling using hot/cold analysis"""
-    wheel_map = {}
-    wheel_labels = list("ABCDEFGHIJKLMNOPQRST")
-    
-    # Take top 10 hot numbers
-    hot_numbers = [num for num, freq in hot[:10]]
-    
-    # Take bottom 10 cold numbers 
-    cold_numbers = [num for num, freq in cold[:10]]
-    
-    # Combine them
-    selected_numbers = hot_numbers + cold_numbers
-    
-    # Map to letters A-T
-    for i, letter in enumerate(wheel_labels):
-        if i < len(selected_numbers):
-            wheel_map[letter] = selected_numbers[i]
-    
-    return wheel_map
-
-def convert_numeric_wheel_to_letter_template(raw_text: str, wheel_size: int = 20) -> str:
-    """
-    Convert numeric wheel lines like:
-      1-01-02-06-18-19-46
-    into letter-template lines:
-      A B C D E
-    """
-    if not raw_text:
-        return ""
-
-    lines = raw_text.splitlines()
-    out_lines = []
-    for line in lines:
-        # Detect lines that start with an index + dash (e.g. " 1-01-02-06-18-19-46")
-        if re.match(r'^\s*\d+\s*-', line):
-            # extract all integer tokens (1 or 2 digits)
-            nums = re.findall(r'\d{1,2}', line)
-            if not nums:
-                continue
-            # Many files start the line with the ticket index; drop it if present and equals first num
-            first_num_match = re.match(r'^\s*(\d+)', line)
-            if first_num_match and nums and nums[0] == first_num_match.group(1):
-                nums = nums[1:]
-            if len(nums) < 5:
-                # skip if fewer than 5 picks found
-                continue
-            picks = nums[:5]  # take the first five numbers
-            letters = []
-            for n_str in picks:
-                n = int(n_str)
-                # Map 1->A, 2->B, ... wrap/clamp if needed
-                idx = (n - 1) % 26
-                letters.append(chr(ord('A') + idx))
-            if len(letters) >= 5:
-                out_lines.append(" ".join(letters))
-    return "\n".join(out_lines)
-
-def expand_wheel_with_template(wheel_map: dict, template: str):
-    """Expand wheel template into actual number combinations"""
-    combos = []
-    lines = template.strip().split('\n')
-    
-    for line in lines:
-        letters = line.strip().split()
-        if len(letters) >= 5:
-            combo = []
-            for letter in letters[:5]:  # Take first 5 letters
-                if letter in wheel_map:
-                    combo.append(wheel_map[letter])
-            if len(combo) == 5:
-                combos.append(sorted(combo))
-    
-    return combos
-
-# -------------------------
-# Display helpers
-# -------------------------
-def display_hot_cold_tables(hot_df: pd.DataFrame, cold_df: pd.DataFrame):
-    hot_df.index = range(1, len(hot_df) + 1)
-    hot_df.index.name = "No"
-    cold_df.index = range(1, len(cold_df) + 1)
-    cold_df.index.name = "No"
-    with st.expander("🔥 Hot Numbers (Top 10)"):
-        st.table(hot_df)
-    with st.expander("❄️ Cold Numbers (Bottom 10)"):
-        st.table(cold_df)
-
-def display_wheel_table_from_hotcold(hot_df: pd.DataFrame, cold_df: pd.DataFrame):
-    """
-    Build the 20-number wheel mapping and show the table in the UI. 
-    Returns wheel_map (dict letter->number).
-    """
-    hot = [(int(n), f) for n, f in hot_df.values]
-    cold = [(int(n), f) for n, f in cold_df.values]
-    wheel_map = select_20_wheel_numbers(hot, cold)
-    wheel_labels = list("ABCDEFGHIJKLMNOPQRST")
-    ordered_numbers = [wheel_map.get(l, None) for l in wheel_labels]
-    wheel_df = pd.DataFrame([ordered_numbers], columns=wheel_labels)
-    with st.expander("🎡 Your 20 Numbers to Wheel"):
-        st.table(wheel_df)
-    return wheel_map
-
-def display_wheel_combinations_from_raw(wheel_map: dict, raw_template_text: str):
-    """
-    Convert numeric wheel template to letter-template, then expand and display combos.
-    """
-    if not raw_template_text:
-        st.warning("Wheel template file is empty or not found.")
-        return
-
-    letter_template = convert_numeric_wheel_to_letter_template(raw_template_text)
-    if not letter_template:
-        st.warning("Wheel template parsing found no valid ticket lines.")
-        return
-
-    combos = expand_wheel_with_template(wheel_map, letter_template)
-    if not combos:
-        st.warning("No combinations produced after expansion.")
-        return
-
-    df = pd.DataFrame(combos, columns=["Num1", "Num2", "Num3", "Num4", "Num5"])
-    df.index = [f"Ticket{i+1}" for i in range(len(df))]
-    df.index.name = "No"
-    with st.expander(f"🎟️ Wheel Combinations ({len(df)} tickets)"):
-        st.dataframe(df)
-
-# -------------------------
-
-# -------------------------
-# Results parsing + hit tracking (UI-only, no layout/color changes)
-# -------------------------
-def _parse_results_text(txt: str):
-    """Parse results like '1-2-3-4-5 (6)' or '1 2 3 4 5 ⭐6'. Returns (main_set, star_int_or_None)."""
-    if not txt:
-        return set(), None
-    s = str(txt).strip()
-    if not s:
-        return set(), None
-    # Extract numbers; first 5 are main, last (optional) treated as star/bonus if present
-    nums = re.findall(r"\d+", s)
-    if len(nums) < 5:
-        return set(), None
-    main = [int(x) for x in nums[:5]]
-    star = None
-    if len(nums) >= 6:
-        try:
-            star = int(nums[5])
-        except Exception:
-            star = None
-    return set(main), star
-
-def _ticket_main_set(tk):
-    """Return main numbers set from a ticket dict/list/string."""
-    if tk is None:
-        return set()
-    if isinstance(tk, dict):
-        cand = tk.get('numbers') or tk.get('nums') or tk.get('main') or []
-        return set(int(x) for x in cand if str(x).isdigit() or isinstance(x, int))
-    if isinstance(tk, (list, tuple, set)):
-        return set(int(x) for x in tk if str(x).isdigit() or isinstance(x, int))
-    if isinstance(tk, str):
-        nums = re.findall(r"\d+", tk)
-        return set(int(x) for x in nums[:5]) if len(nums) >= 5 else set()
-    return set()
-
-def _ticket_star(tk):
-    if isinstance(tk, dict):
-        for k in ('star','bonus','power','pb','mb','sb','lucky'):
-            if k in tk and tk.get(k) is not None:
-                try:
-                    return int(tk.get(k))
-                except Exception:
-                    return None
-    return None
-
-def _calc_hits(ticket, results_main:set, results_star, cfg=None):
-    main = _ticket_main_set(ticket)
-    main_hits = len(main & (results_main or set()))
-    star_hit = None
-    if results_star is not None:
-        stv = _ticket_star(ticket)
-        if stv is None and isinstance(ticket, dict):
-            # fmt_ticket supports pulling star from dict; mirror that behavior loosely
-            stv = ticket.get('star') if isinstance(ticket.get('star'), (int,str)) else None
-            try:
-                stv = int(stv) if stv is not None else None
-            except Exception:
-                stv = None
-        if stv is not None:
-            # Clamp against cfg star range (safety)
-            if cfg is not None and getattr(cfg,'star_min',None) is not None and getattr(cfg,'star_max',None) is not None:
-                try:
-                    smin, smax = int(cfg.star_min), int(cfg.star_max)
-                    if not (smin <= int(stv) <= smax):
-                        stv = None
-                except Exception:
-                    pass
-            star_hit = (stv == results_star) if stv is not None else None
-    return main_hits, star_hit
-
-def _get_named_ticket(god_sets_list, wanted):
-    w = (wanted or '').strip().lower()
-    for _s in (god_sets_list or []):
-        nm = (_s.get('style') or _s.get('name') or '').strip().lower()
-        if nm == w:
-            return _s
-    return None
-
-def _build_recommended_plays(*, game_key:str, primary_nums, primary_star, god_sets_list, collapse_t, neighbor_t):
-    """Default 5-ticket recipe per game (UI-only): balanced + tight + wide + collapse + neighbor."""
-    picks = []
-    # Prefer the engine-provided 'balanced' style; fall back to PRIMARY
-    balanced = _get_named_ticket(god_sets_list, 'balanced')
-    if balanced:
-        picks.append(('balanced', balanced))
-    else:
-        picks.append(('primary', {'numbers': primary_nums or [], 'star': primary_star}))
-
-    tight = _get_named_ticket(god_sets_list, 'tight_cluster')
-    if tight:
-        picks.append(('tight_cluster', tight))
-    wide = _get_named_ticket(god_sets_list, 'wide_spread')
-    if wide:
-        picks.append(('wide_spread', wide))
-
-    if collapse_t:
-        picks.append(('collapse', collapse_t))
-    if neighbor_t:
-        picks.append(('neighbor', neighbor_t))
-
-    # Fill to 5 from remaining god sets (keeps variety)
-    if len(picks) < 5:
-        used = set()
-        for lbl, tk in picks:
-            used.add(tuple(sorted(_ticket_main_set(tk))))
-        for s in (god_sets_list or []):
-            key = tuple(sorted(_ticket_main_set(s)))
-            if key and key not in used:
-                picks.append((s.get('style') or s.get('name') or 'set', s))
-                used.add(key)
-            if len(picks) >= 5:
-                break
-
-    # Final de-dupe + cap
-    seen = set()
-    out = []
-    for lbl, tk in picks:
-        key = tuple(sorted(_ticket_main_set(tk)))
-        if not key or key in seen:
-            continue
-        seen.add(key)
-        out.append((lbl, tk))
-        if len(out) >= 5:
-            break
-    return out
-
-def _scorecard_key(game_key: str):
-    return f"scorecard_{game_key}"
-# UI & main logic
-# -------------------------
-lotto_options = [
-    "G5 (Gimme 5)",
-    "LA (Lotto America)", 
-    "L4L (Lucky for Life)",  # ✅ NEW
-    "MB (Megabucks)",
-    "MM (Mega Millions)",
-    "PB (Powerball)",
-]
-lotto_type = st.selectbox("Select Lotto Type:", options=lotto_options, index=0)
-
-# Map display names -> keys used in GAME_CONFIGS and predict_for_game_v3
-GAME_KEY_MAP = {
-    "G5 (Gimme 5)": "gimme5",
-    "LA (Lotto America)": "la",
-    "L4L (Lucky for Life)": "l4l",  # ✅ NEW
-    "MB (Megabucks)": "mb", 
-    "MM (Mega Millions)": "mm",
-    "PB (Powerball)": "pb",
-}
-
-try:
-    game_key = GAME_KEY_MAP[lotto_type]
-    data_path = DATA_PATHS[lotto_type]
-    cfg = GAME_CONFIGS[game_key]
-
-    # --- CSV change detection + age indicator (sidebar, no layout impact) ---
-    csv_file = str(Path(data_path))
-    with st.sidebar:
-        age_s = _csv_age_seconds(csv_file)
-        if age_s is None:
-            st.caption("📄 CSV age: unknown")
-        else:
-            st.caption(f"📄 CSV age: {_human_age(age_s)} ago")
-
-        changed, changed_list = csv_changed_warning([csv_file], label="Draw history CSV")
-
-        # Soft restart button (clears caches + reloads this session)
-        if st.button("🔁 Restart (soft reload)"):
-            soft_restart_app()
-
-        # Optional extra nudge if a change was detected
-        if changed:
-            st.info("Tip: Soft restart reloads the app session; for a full process restart, stop and re-run Streamlit.")
-
-    # Optional: clear cached data if CSV changed
-    if changed:
-        try:
-            st.cache_data.clear()
-        except Exception:
-            pass
-
-
-    # Load dataset using V3.0 loader
-    df, _ = load_csv_for_game(Path(data_path), game_key)
-
-    # Hot/cold numbers computed using our helper
-    hot, cold = get_hot_and_cold_numbers(df, cfg)
-    hot_df = pd.DataFrame(hot, columns=["Number", "Frequency"])
-    cold_df = pd.DataFrame(cold, columns=["Number", "Frequency"])
-
-    # UI options - simplified for V3.0
-    run_backtest = st.checkbox("🧪 Run Backtest (slower but shows model performance)", value=False)
-    use_wheel = st.checkbox("🎡 Generate Wheel Combinations (if wheel.txt available)", value=False)
-
-    wheel_raw_text = load_wheel_raw_text(DATA_PATHS["wheel_template"]) if use_wheel else ""
-
-    # Styling
-    st.markdown(
-        """
-        <style>
-        table { margin-left:auto; margin-right:auto; }
-        th, td { text-align:center !important; vertical-align: middle !important; }
-        </style>
-        """,
-        unsafe_allow_html=True,
-    )
-
-    if st.button("🎰 Generate Prediction" if not run_backtest else "🧪 Run Backtest"):
-        with st.spinner("Building ensemble models and generating results..."):
-            # Run V3.0 predictor 
-            result = predict_for_game_v3(
-                csv_path=Path(data_path),
-                game_key=game_key,
-                run_backtest=run_backtest
-            )
-
-            if run_backtest:
-                # Display backtest results
-                if 'error' in result:
-                    st.error(f"❌ Backtest Error: {result['error']}")
-                else:
-                    st.success("✅ Backtest Complete!")
-                    
-                    # Show summary metrics
-                    st.subheader("📊 Backtest Summary")
-                    col1, col2, col3 = st.columns(3)
-                    
-                    with col1:
-                        st.metric("Model 3+ Matches", f"{result.get('model_3plus_rate', 0)}%")
-                    with col2:
-                        st.metric("Random 3+ Matches", f"{result.get('random_3plus_rate', 0)}%")
-                    with col3:
-                        st.metric("Even Count Accuracy", f"{result.get('even_count_accuracy', 0)}%")
-                    
-                    # Detailed hit rates
-                    st.subheader("🎯 Hit Rate Comparison")
-                    hit_data = []
-                    for i in range(6):
-                        model_rate = result.get(f'model_hit_{i}_rate', 0)
-                        random_rate = result.get(f'random_hit_{i}_rate', 0)
-                        hit_data.append({
-                            'Matches': i,
-                            'Model Rate (%)': model_rate,
-                            'Random Rate (%)': random_rate,
-                            'Improvement': f"+{model_rate - random_rate:.1f}%" if model_rate > random_rate else f"{model_rate - random_rate:.1f}%"
-                        })
-                    
-                    hit_df = pd.DataFrame(hit_data)
-                    st.table(hit_df)
-                    
-                    # Raw results
-                    with st.expander("📋 Full Backtest Results"):
-                        st.json(result)
-                        
-            else:
-                # Display prediction results
-                st.success(f"🧠 Predicted Numbers: {result['numbers']}")
-                if result.get("star") is not None:
-                    star_col_name = cfg.star_col or 'Star'
-                    st.success(f"🌟 Predicted {star_col_name}: {result['star']}")
-                else:
-                    st.info("ℹ️ No bonus number for this game")
-                
-                # Show additional info
-                st.info(f"🔢 Total Sum: {sum(result['numbers'])} (Expected Range: {cfg.sum_min}–{cfg.sum_max})")
-                
-                model_info = result.get('model_info', {})
-                st.info(f"🤖 Models built for {model_info.get('numbers_modeled', 0)}/{model_info.get('total_possible', 0)} numbers")
-                
-                # -------------------------
-                # GOD MODE + CONSENSUS + ANCHORS (UI only)
-                # -------------------------
-                god_sets = result.get("god_sets") or result.get("god_mode_sets") or result.get("godmode_sets") or []
-                strike = result.get("strike_tickets") or result.get("strike") or {}
-
-                if god_sets:
-                    st.info("🎲 Lotto Cash Predictions")
-                    for s in god_sets:
-                        name = s.get("name", "set")
-                        nums = s.get("numbers") or []
-                        st.info(f"{name}: {fmt_ticket({'numbers': nums, 'star': s.get('star', None)})}")
-
-
-
-                # APPEND PATCH: EXTRA_PREDICTIONS_UI_V1 (APPEND-ONLY / NO DELETIONS)
-                # Shows the two extra engine predictions (if present) without changing layout/colors.
-                try:
-                    _extra = result.get("extra_predictions")
-                    if isinstance(_extra, dict) and (_extra.get("ml_ensemble") or _extra.get("dl_sequence")):
-                        st.info("➕ Extra Predictions")
-                        mlp = _extra.get("ml_ensemble") if isinstance(_extra.get("ml_ensemble"), dict) else None
-                        dlp = _extra.get("dl_sequence") if isinstance(_extra.get("dl_sequence"), dict) else None
-                        if mlp:
-                            st.info(f"ML Ensemble (RF/XGB): {fmt_ticket(mlp, cfg=cfg)}")
-                        if dlp:
-                            st.info(f"DL Sequence (LSTM/Transformer): {fmt_ticket(dlp, cfg=cfg)}")
-                except Exception:
-                    pass
-
-                collapse = None
-                neighbor = None
-                # Convergence tickets (engine may provide these directly)
-                convergence_core = result.get("convergence_core")
-                convergence_cooccur = result.get("convergence_cooccur")
-
-                if isinstance(strike, dict):
-                    collapse = strike.get("collapse") or strike.get("consensus_collapse") or strike.get("CONSENSUS_COLLAPSE")
-                    neighbor = strike.get("neighbor") or strike.get("consensus_neighbor") or strike.get("CONSENSUS_NEIGHBOR")
-                    # If engine didn't supply these, allow them to come from strike payloads too
-                    if not convergence_core:
-                        convergence_core = strike.get("convergence_core") or strike.get("CONVERGENCE_CORE")
-                    if not convergence_cooccur:
-                        convergence_cooccur = strike.get("convergence_cooccur") or strike.get("CONVERGENCE_COOCCUR") or strike.get("CONVERGENCE_CO-OCCUR")
-
-                if collapse or neighbor or convergence_core or convergence_cooccur:
-                    st.info("🎯 Consensus Tickets")
-                    if collapse:
-                        st.info(f"Consensus (Collapse): {fmt_ticket(collapse, cfg=cfg)}")
-                    if neighbor:
-                        st.info(f"Neighbor Consensus: {fmt_ticket(neighbor, cfg=cfg)}")
-                    if convergence_core:
-                        st.info(f"Convergence Core: {fmt_ticket(convergence_core, cfg=cfg)}")
-                    if convergence_cooccur:
-                        st.info(f"Convergence Co-Occur: {fmt_ticket(convergence_cooccur, cfg=cfg)}")
-
-                main_min = int(getattr(cfg, "main_min", 1))
-                main_max = int(getattr(cfg, "main_max", 99))
-                seed = int(result.get("seed", 0) or 0)
-                low_anchor = build_low_anchor(god_sets, main_min=main_min, main_max=main_max, seed=seed)
-                mid_anchor = build_mid_anchor(god_sets, main_min=main_min, main_max=main_max, seed=seed)
-                # Per-ticket Star Ball display (prevents the same star being shown for every line)
-                def _pick_star_for_display(offset:int=0):
-                    try:
-                        if not getattr(cfg, "star_col", None):
-                            return None
-                        smin = int(getattr(cfg, "star_min", 1))
-                        smax = int(getattr(cfg, "star_max", 1))
-                        if smax < smin:
-                            return None
-                        rnd = random.Random(int(seed) + int(offset))
-                        # Frequency weights: all-time + last-80 (recency boosted)
-                        series_all = pd.to_numeric(df[cfg.star_col], errors="coerce").dropna().astype(int).tolist()
-                        if not series_all:
-                            return rnd.randint(smin, smax)
-                        series_80 = pd.to_numeric(df[cfg.star_col].tail(80), errors="coerce").dropna().astype(int).tolist()
-                        from collections import Counter
-                        fa = Counter(series_all)
-                        f8 = Counter(series_80)
-                        candidates = list(range(smin, smax + 1))
-                        weights = []
-                        for b in candidates:
-                            w = 1.0 + float(fa.get(b, 0)) + 2.0 * float(f8.get(b, 0))
-                            # gentle low-zone preference for LA / MM (matches engine intent)
-                            if getattr(cfg, "name", "") in ("Lotto America", "Mega Millions") and b <= (smin + 4):
-                                w *= 1.10
-                            weights.append(w)
-                        return int(rnd.choices(candidates, weights=weights, k=1)[0])
-                    except Exception:
-                        return None
-
-
-
-                # -------------------------
-                # Recommended Plays (per-game, UI-only)
-                # -------------------------
-                recommended = None
-                if game_key == "gimme5":
-                    # If G5 play5 was built above, reuse it; else fall back to default recipe
-                    try:
-                        recommended = play5 if 'play5' in locals() else None
-                    except Exception:
-                        recommended = None
-                if not recommended:
-                    recommended = _build_recommended_plays(
-                        game_key=game_key,
-                        primary_nums=result.get("numbers") or [],
-                        primary_star=result.get("star"),
-                        god_sets_list=god_sets,
-                        collapse_t=collapse,
-                        neighbor_t=neighbor,
-                    )
-
-                if recommended:
-                    st.info("🏷️ Recommended Plays (5-ticket recipe)")
-                    for lbl, tk in recommended:
-                        st.info(f"{lbl}: {fmt_ticket(tk, cfg=cfg)}")
-
-                # -------------------------
-                # Optional: Results entry + hit highlight + rolling 30-draw scorecard (silent)
-                # -------------------------
-                with st.expander("✅ Results & Hit Tracking (optional)"):
-                    results_input = st.text_input(
-                        "Paste official results (ex: 12-17-25-34-42 (9))",
-                        key=f"results_input_{game_key}",
-                    )
-                    if st.button("Apply Results", key=f"apply_results_{game_key}"):
-                        main_set, star_val = _parse_results_text(results_input)
-                        if not main_set:
-                            st.warning("Couldn’t parse results. Example: 12-17-25-34-42 (9)")
-                        else:
-                            # Store last results in session
-                            st.session_state[f"last_results_{game_key}"] = {"main": sorted(main_set), "star": star_val, "ts": datetime.now().isoformat()}
-                            # Update rolling scorecard (30)
-                            sk = _scorecard_key(game_key)
-                            sc = st.session_state.get(sk, [])
-                            # Score recommended plays
-                            scored = []
-                            for lbl, tk in (recommended or []):
-                                mh, sh = _calc_hits(tk, main_set, star_val, cfg=cfg)
-                                scored.append({"label": lbl, "main_hits": mh, "star_hit": sh})
-                            sc.append({
-                                "time": datetime.now().strftime('%Y-%m-%d %H:%M'),
-                                "results": "-".join(str(x) for x in sorted(main_set)) + (f" (⭐ {star_val})" if star_val is not None else ""),
-                                "best_main_hits": max([x["main_hits"] for x in scored], default=0),
-                            })
-                            st.session_state[sk] = sc[-30:]
-                            st.success("Saved. Scroll down for highlights and scorecard.")
-
-                    # Show highlight if we have stored results
-                    stored = st.session_state.get(f"last_results_{game_key}")
-                    if stored:
-                        rmain = set(stored.get("main") or [])
-                        rstar = stored.get("star")
-                        st.write(f"**Last results:** {'-'.join(str(x) for x in sorted(rmain))}" + (f" (⭐ {rstar})" if rstar is not None else ""))
-                        if recommended:
-                            st.write("**Auto-highlight hits (Recommended Plays):**")
-                            for lbl, tk in recommended:
-                                mh, sh = _calc_hits(tk, rmain, rstar, cfg=cfg)
-                                hit_note = f"{mh} hit" + ("s" if mh != 1 else "")
-                                if sh is True:
-                                    hit_note += " + ⭐"
-                                st.write(f"- {lbl}: {fmt_ticket(tk, cfg=cfg)}  →  {hit_note}")
-
-                        # Silent rolling 30-draw scorecard
-                        sk = _scorecard_key(game_key)
-                        sc = st.session_state.get(sk, [])
-                        if sc:
-                            st.write("**Rolling scorecard (last 30 saves):**")
-                            st.dataframe(pd.DataFrame(sc), use_container_width=True)
-                st.info("🎟️ Anchor Tickets")
-                st.info(f"LOW Anchor (1–9): {fmt_ticket({'numbers': low_anchor, 'star': _pick_star_for_display(101)})}")
-                st.info(f"MID Anchor (10–19): {fmt_ticket({'numbers': mid_anchor, 'star': _pick_star_for_display(202)})}")
-
-                lines = []
-                lines.append(f"GAME: {game_key}")
-                lines.append(f"GENERATED: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
-                lines.append("")
-                lines.append(f"PRIMARY: {fmt_ticket(result.get('numbers') or [], result.get('star'))}")
-                if god_sets:
-                    lines.append("")
-                    lines.append("LOTTO CASH SETS:")
-                    for s in god_sets:
-                        lines.append(f"- {s.get('name','set')}: {fmt_ticket(s, cfg=cfg)}")
-                if collapse or neighbor or (convergence_core is not None) or (convergence_cooccur is not None):
-                    lines.append("")
-                    lines.append("CONSENSUS:")
-                    if collapse:
-                        lines.append(f"- collapse: {fmt_ticket(collapse, cfg=cfg)}")
-                    if neighbor:
-                        lines.append(f"- neighbor: {fmt_ticket(neighbor, cfg=cfg)}")
-                    if convergence_core is not None:
-                        lines.append(f"- convergence_core: {fmt_ticket(convergence_core, cfg=cfg)}")
-                    if convergence_cooccur is not None:
-                        lines.append(f"- convergence_cooccur: {fmt_ticket(convergence_cooccur, cfg=cfg)}")
-                lines.append("")
-                lines.append(f"LOW ANCHOR (1–9): {fmt_ticket({'numbers': low_anchor, 'star': _pick_star_for_display(101)})}")
-                lines.append(f"MID ANCHOR (10–19): {fmt_ticket({'numbers': mid_anchor, 'star': _pick_star_for_display(202)})}")
-                content = "\n".join(lines).strip() + "\n"
-                fname = f"{game_key}_tickets_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt"
-                st.download_button("⬇️ Download tickets (timestamped)", data=content.encode("utf-8"),
-                                   file_name=fname, mime="text/plain")
-
-                # ------------------------------------------------------------
-                # NITRO PACK download add-on (append-only; does not change layout)
-                # Creates an additional download option that includes Nitro Pack tickets
-                # if the engine provided them in the result payload.
-                # ------------------------------------------------------------
-                try:
-                    nitro_pack = (
-                        result.get("nitro_pack")
-                        or result.get("nitro")
-                        or result.get("nitro_pack_tickets")
-                        or result.get("nitro_tickets")
-                    )
-                    if isinstance(nitro_pack, dict):
-                        # allow {"tickets":[...]} or {"sets":[...]}
-                        nitro_pack = nitro_pack.get("tickets") or nitro_pack.get("sets") or nitro_pack.get("pack") or []
-                    if nitro_pack and isinstance(nitro_pack, (list, tuple)):
-                        lines2 = list(lines)
-                        lines2.append("")
-                        lines2.append("NITRO PACK:")
-                        for i_np, tk_np in enumerate(nitro_pack, start=1):
-                            try:
-                                lines2.append(f"- nitro_{i_np}: {fmt_ticket(tk_np, cfg=cfg)}")
-                            except Exception:
-                                # fall back if tk_np is just a list of numbers
-                                try:
-                                    lines2.append(f"- nitro_{i_np}: {fmt_ticket({'numbers': tk_np, 'star': None}, cfg=cfg)}")
-                                except Exception:
-                                    pass
-                        content2 = "\n".join(lines2).strip() + "\n"
-                        fname2 = f"{game_key}_tickets_NITRO_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt"
-                        st.download_button(
-                            "⬇️ Download tickets + Nitro Pack",
-                            data=content2.encode("utf-8"),
-                            file_name=fname2,
-                            mime="text/plain",
-                        )
-                except Exception:
-                    pass
-
-
-                # Wheel (if requested)
-                if use_wheel and wheel_raw_text:
-                    # Build and show wheel table (A..T mapping)
-                    wheel_map = display_wheel_table_from_hotcold(hot_df, cold_df)
-
-                    # Expand numeric wheel.txt to letter-template and display combos
-                    display_wheel_combinations_from_raw(wheel_map, wheel_raw_text)
-                elif use_wheel:
-                    st.warning("⚠️ Wheel template file (wheel.txt) not found or empty")
-
-except FileNotFoundError:
-    st.error(f"❌ File not found: `{data_path}`")
-except Exception as e:
-    st.error(f"⚠️ Error: {str(e)}")
-    import traceback
-    st.error(f"Details: {traceback.format_exc()}")
-
-# ============================================================
-# APPEND PATCH: NITRO_PACK_UI_V2 (APPEND-ONLY / NO DELETIONS)
-# - Patches lotto_predictor.predict_for_game_v3 inside sys.modules so that
-#   future Streamlit reruns import the wrapped function automatically.
-# - Stores last engine result in st.session_state.
-# - Renders 4 additional prediction lines below existing UI.
-# ============================================================
-
-def _NITRO_UI__patch_engine_predictor():
-    try:
-        import sys as _sys
-        _mod = _sys.modules.get("lotto_predictor")
-        if _mod is None:
-            return
-        _orig = getattr(_mod, "predict_for_game_v3", None)
-        if _orig is None or getattr(_orig, "_nitro_wrapped", False):
-            return
-
-        def _wrapped_predict_for_game_v3(*args, **kwargs):
-            res = _orig(*args, **kwargs)
-            try:
-                st.session_state["_nitro_last_result"] = res
-                gk = None
-                if "game_key" in kwargs:
-                    gk = kwargs.get("game_key")
-                elif len(args) >= 2:
-                    gk = args[1]
-                st.session_state["_nitro_last_game_key"] = gk
-            except Exception:
-                pass
-            return res
-
-        _wrapped_predict_for_game_v3._nitro_wrapped = True  # type: ignore
-        setattr(_mod, "predict_for_game_v3", _wrapped_predict_for_game_v3)
-    except Exception:
-        return
-
-def _NITRO_UI__get_ticket(res: dict, key: str):
-    if not isinstance(res, dict):
-        return None
-    tk = res.get(key)
-    if tk:
-        return tk
-    npk = res.get("nitro_pack")
-    if isinstance(npk, dict):
-        return npk.get(key)
-    return None
-
-def _NITRO_UI__render():
-    res = st.session_state.get("_nitro_last_result")
-    if not isinstance(res, dict) or ("error" in res):
-        return
-
-    gk = st.session_state.get("_nitro_last_game_key")
-    try:
-        if "game_key" in globals():
-            gk = globals().get("game_key")
-    except Exception:
-        pass
-
-    cfg_local = None
-    try:
-        if gk and "GAME_CONFIGS" in globals():
-            cfg_local = GAME_CONFIGS.get(gk)
-    except Exception:
-        cfg_local = None
-
-    mk = _NITRO_UI__get_ticket(res, "markov_addon")
-    rf = _NITRO_UI__get_ticket(res, "rf_line")
-    jc = _NITRO_UI__get_ticket(res, "jackpot_chase")
-
-    st.info("⚡ Nitro Pack (4 extra lines)")
-    st.info(f"🔁 Markov Add-on: {fmt_ticket(mk, cfg=cfg_local) if mk else '(not available for this run)'}")
-    st.info(f"🌲 RF-only ML Line: {fmt_ticket(rf, cfg=cfg_local) if rf else '(not available for this run)'}")
-
-    if jc:
-        label = None
-        try:
-            label = jc.get("mode")
-        except Exception:
-            label = None
-        prefix = "🚀 Jackpot Chase Mode (optional)" if not label else f"🚀 {label}"
-        st.info(f"{prefix}: {fmt_ticket(jc, cfg=cfg_local)}")
-    else:
-        st.info("🚀 Jackpot Chase Mode (optional): (not available for this run)")
-
-    try:
-        pasted = ""
-        if gk:
-            pasted = st.session_state.get(f"results_input_{gk}", "")
-        main_set, _star = _parse_results_text(pasted)
-        if main_set:
-            engine_primary = {"numbers": res.get("numbers") or [], "star": res.get("star")}
-            eng_hits = len(_ticket_main_set(engine_primary) & main_set)
-            rf_hits = len(_ticket_main_set(rf) & main_set) if rf else 0
-            mk_hits = len(_ticket_main_set(mk) & main_set) if mk else 0
-            jc_hits = len(_ticket_main_set(jc) & main_set) if jc else 0
-            st.info(f"⚖️ Live compare vs pasted results: Engine={eng_hits}/5 • RF={rf_hits}/5 • Markov={mk_hits}/5 • Chase={jc_hits}/5")
-        else:
-            st.info("⚖️ Live compare (paste official results to score Engine vs RF vs Markov vs Chase)")
-    except Exception:
-        st.info("⚖️ Live compare (paste official results to score Engine vs RF vs Markov vs Chase)")
-
-# Patch engine module for future reruns, then render any stored output
-try:
-    _NITRO_UI__patch_engine_predictor()
-except Exception:
-    pass
-
-try:
-    _NITRO_UI__render()
-except Exception:
-    pass
-
-
-# =========================
-# NITRO PATCH v3 (append-only)
-# Adds an explicit checkbox/tickbox for Live Compare display.
-# Does NOT change any layout above; this renders at the very bottom.
-# =========================
-def _NITRO_UI__live_compare_checkbox_panel():
-    try:
-        import streamlit as st
-    except Exception:
-        return
-    try:
-        # Show a small optional panel at the bottom so user has a clear tickbox.
-        with st.expander("⚖️ Live Compare (optional)", expanded=False):
-            enabled = st.checkbox(
-                "Enable Live compare (paste official results to score Engine vs RF vs Markov vs Chase)",
-                value=False,
-                key="nitro_live_compare_enabled",
-                help="If enabled, this panel will show the live hit counts based on the last saved results.",
-            )
-            st.caption("Tip: Use the existing '✅ Results & Hit Tracking (optional)' expander above, paste official results, then click 'Apply Results'.")
-            if not enabled:
-                return
-
-            # Try to infer the active game_key from session by looking for a last_results_* entry.
-            # This is safe and does not require changing any code above.
-            last_keys = [k for k in st.session_state.keys() if isinstance(k, str) and k.startswith("last_results_")]
-            if not last_keys:
-                st.info("No saved results yet. Paste official results above and click 'Apply Results' first.")
-                return
-
-            # Prefer the most recently updated key if multiple exist.
-            def _ts(k):
-                try:
-                    v = st.session_state.get(k) or {}
-                    return v.get("ts") or ""
-                except Exception:
-                    return ""
-            last_keys_sorted = sorted(last_keys, key=_ts, reverse=True)
-            game_key = last_keys_sorted[0].replace("last_results_", "", 1)
-
-            stored = st.session_state.get(f"last_results_{game_key}") or {}
-            main = set(stored.get("main") or [])
-            if not main:
-                st.info("Saved results found but could not parse main numbers.")
-                return
-
-            # Try to fetch the last predictions we rendered for this game from session (if present),
-            # else do a best-effort pull from commonly used session keys.
-            # We will display 'N/A' if we can't find them; still satisfies checkbox presence.
-            pred = st.session_state.get(f"nitro_last_predictions_{game_key}") or st.session_state.get("nitro_last_predictions") or {}
-            eng = pred.get("engine") or pred.get("primary") or pred.get("balanced")
-            rf  = pred.get("rf")
-            mk  = pred.get("markov")
-            jc  = pred.get("chase") or pred.get("jackpot_chase")
-
-            def _main_set(tk):
-                try:
-                    if tk is None:
-                        return set()
-                    if isinstance(tk, dict):
-                        nums = tk.get("numbers") or tk.get("nums") or tk.get("main") or []
-                    elif isinstance(tk, (list, tuple)):
-                        nums = list(tk)
-                    else:
-                        nums = [int(x) for x in re.findall(r"\d+", str(tk))][:5]
-                    return set(int(x) for x in nums if str(x).strip() != "")
-                except Exception:
-                    return set()
-
-            eng_hits = len(_main_set(eng) & main) if eng else None
-            rf_hits  = len(_main_set(rf) & main) if rf else None
-            mk_hits  = len(_main_set(mk) & main) if mk else None
-            jc_hits  = len(_main_set(jc) & main) if jc else None
-
-            # Display in a clear card-like info line
-            parts = []
-            parts.append(f"Engine={'N/A' if eng_hits is None else str(eng_hits) + '/5'}")
-            parts.append(f"RF={'N/A' if rf_hits is None else str(rf_hits) + '/5'}")
-            parts.append(f"Markov={'N/A' if mk_hits is None else str(mk_hits) + '/5'}")
-            parts.append(f"Chase={'N/A' if jc_hits is None else str(jc_hits) + '/5'}")
-            st.success(" • ".join(parts))
-
-            st.caption("If any are N/A, it means that line wasn't cached in session for this run (the main UI line still works).")
-    except Exception:
-        # Never break the app
-        return
-
-# Render the checkbox panel last
-try:
-    _NITRO_UI__live_compare_checkbox_panel()
-except Exception:
-    pass
-
-
-
-# ======================================================================================
-# NITRO PACK V4 ADD-ON (append-only)
-# - Performance memory: keep last N scored results for Engine/RF/Markov/Chase
-# - Auto Chase helper: optional checkbox + additional download that includes
-#   a "recommended" bundle when the engine has been cold
-# - RF confidence display (if provided by engine)
-# NOTE: This block is strictly append-only and does not modify any code above.
-# ======================================================================================
-
-def _nitro__safe_fmt_nums(nums):
-    try:
-        if nums is None:
-            return ""
-        if isinstance(nums, dict):
-            nums = nums.get("numbers") or nums.get("nums") or nums.get("main") or []
-        if isinstance(nums, (tuple, list)):
-            return "-".join(str(int(x)) for x in nums)
-        return "-".join(re.findall(r"\d+", str(nums))[:5])
-    except Exception:
-        return ""
-
-def _nitro__hits(pred_ticket, result_main_set):
-    try:
-        if pred_ticket is None:
-            return None
-        if isinstance(pred_ticket, dict):
-            nums = pred_ticket.get("numbers") or pred_ticket.get("nums") or pred_ticket.get("main") or []
-        elif isinstance(pred_ticket, (list, tuple)):
-            nums = list(pred_ticket)
-        else:
-            nums = [int(x) for x in re.findall(r"\d+", str(pred_ticket))][:5]
-        s = set(int(x) for x in nums if str(x).strip() != "")
-        return int(len(s & set(result_main_set)))
-    except Exception:
-        return None
-
-def _NITRO_UI__cache_last_predictions():
-    """Cache the last rendered predictions so Live Compare + performance scoring can work."""
-    try:
-        res = st.session_state.get("_nitro_last_result")
-        gk = st.session_state.get("_nitro_last_game_key")
-        if not isinstance(res, dict) or not gk:
-            return
-
-        # Extract best-known tickets
-        engine_ticket = (
-            res.get("primary")
-            or (res.get("god_mode", {}) or {}).get("balanced")
-            or (res.get("god_mode_sets", {}) or {}).get("balanced")
-        )
-
-        nitro_pack = res.get("nitro_pack") if isinstance(res.get("nitro_pack"), dict) else {}
-        mk = res.get("markov_addon") or (nitro_pack.get("markov_addon") if isinstance(nitro_pack, dict) else None)
-        rf = res.get("rf_line") or (nitro_pack.get("rf_line") if isinstance(nitro_pack, dict) else None)
-        jc = res.get("jackpot_chase") or (nitro_pack.get("jackpot_chase") if isinstance(nitro_pack, dict) else None)
-
-        st.session_state[f"nitro_last_predictions_{gk}"] = {
-            "engine": engine_ticket,
-            "rf": rf,
-            "markov": mk,
-            "chase": jc,
-            "rf_confidence": res.get("rf_confidence") or (rf.get("confidence") if isinstance(rf, dict) else None),
-            "ts": datetime.now().isoformat(),
-        }
-        # Also keep a generic last snapshot for safety
-        st.session_state["nitro_last_predictions"] = st.session_state[f"nitro_last_predictions_{gk}"]
-    except Exception:
-        return
-
-def _NITRO_UI__score_if_new_results():
-    """If the user saved official results, score the cached lines and append to history."""
-    try:
-        last_keys = [k for k in st.session_state.keys() if isinstance(k, str) and k.startswith("last_results_")]
-        if not last_keys:
-            return
-
-        def _ts(k):
-            try:
-                v = st.session_state.get(k) or {}
-                return v.get("ts") or ""
-            except Exception:
-                return ""
-
-        last_key = sorted(last_keys, key=_ts, reverse=True)[0]
-        gk = last_key.replace("last_results_", "", 1)
-        stored = st.session_state.get(last_key) or {}
-        main = stored.get("main") or []
-        rts = stored.get("ts") or ""
-
-        if not main or not rts:
-            return
-
-        pred = st.session_state.get(f"nitro_last_predictions_{gk}") or {}
-        scored_key = f"nitro_last_scored_ts_{gk}"
-        if st.session_state.get(scored_key) == rts:
-            return
-
-        entry = {
-            "ts": rts,
-            "engine": _nitro__hits(pred.get("engine"), main),
-            "rf": _nitro__hits(pred.get("rf"), main),
-            "markov": _nitro__hits(pred.get("markov"), main),
-            "chase": _nitro__hits(pred.get("chase"), main),
-        }
-
-        hist_key = f"nitro_score_history_{gk}"
-        hist = st.session_state.get(hist_key) or []
-        if not isinstance(hist, list):
-            hist = []
-        hist.append(entry)
-        st.session_state[hist_key] = hist[-12:]
-        st.session_state[scored_key] = rts
-    except Exception:
-        return
-
-def _NITRO_UI__performance_panel():
-    try:
-        _NITRO_UI__cache_last_predictions()
-        _NITRO_UI__score_if_new_results()
-
-        gk = st.session_state.get("_nitro_last_game_key")
-        if not gk:
-            hist_keys = [k for k in st.session_state.keys() if isinstance(k, str) and k.startswith("nitro_score_history_")]
-            if not hist_keys:
-                return
-            gk = hist_keys[-1].replace("nitro_score_history_", "", 1)
-
-        hist = st.session_state.get(f"nitro_score_history_{gk}") or []
-        if not isinstance(hist, list):
-            hist = []
-
-        with st.expander("📈 Nitro Pack Performance (optional)", expanded=False):
-            st.caption("Scores update automatically after you paste official results and click 'Apply Results'.")
-            if not hist:
-                st.info("No scored results yet. Paste official results above and click 'Apply Results' to start tracking.")
-                return
-
-            def _avg(field):
-                vals = [h.get(field) for h in hist if isinstance(h.get(field), int)]
-                return (sum(vals) / len(vals)) if vals else None
-
-            a_eng = _avg("engine")
-            a_rf = _avg("rf")
-            a_mk = _avg("markov")
-            a_jc = _avg("chase")
-
-            st.success(
-                "Averages (last {}): Engine={}  RF={}  Markov={}  Chase={}".format(
-                    len(hist),
-                    "N/A" if a_eng is None else f"{a_eng:.2f}/5",
-                    "N/A" if a_rf is None else f"{a_rf:.2f}/5",
-                    "N/A" if a_mk is None else f"{a_mk:.2f}/5",
-                    "N/A" if a_jc is None else f"{a_jc:.2f}/5",
-                )
-            )
-
-            pred = st.session_state.get(f"nitro_last_predictions_{gk}") or {}
-            rf_conf = pred.get("rf_confidence")
-            if rf_conf is not None:
-                try:
-                    st.info(f"RF Confidence: {float(rf_conf):.1f}% (heuristic from RF probabilities)")
-                except Exception:
-                    st.info(f"RF Confidence: {rf_conf}")
-
-            for h in reversed(hist[-10:]):
-                st.write(
-                    f"{h.get('ts','')[:19]}  •  Engine={h.get('engine','N/A')}/5  •  RF={h.get('rf','N/A')}/5  •  Markov={h.get('markov','N/A')}/5  •  Chase={h.get('chase','N/A')}/5"
-                )
-
-            cold = (a_eng is not None and a_eng < 1.0)
-            auto = st.checkbox(
-                "🚀 Auto-suggest Jackpot Chase when Engine is cold (avg < 1.0 hit)",
-                value=bool(st.session_state.get("nitro_auto_chase", False)),
-                key="nitro_auto_chase",
-                help="Does not change your main output; it only adds a helper suggestion + a separate download option below.",
-            )
-
-            if auto and cold:
-                st.warning("Engine has been cold recently. Jackpot Chase is suggested for upside (optional).")
-
-            try:
-                pred2 = st.session_state.get(f"nitro_last_predictions_{gk}") or {}
-                lines = []
-                lines.append(f"GAME: {gk}")
-                lines.append(f"GENERATED: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
-                lines.append("")
-                lines.append(f"ENGINE: {_nitro__safe_fmt_nums(pred2.get('engine'))}")
-                lines.append(f"MARKOV: {_nitro__safe_fmt_nums(pred2.get('markov'))}")
-                lines.append(f"RF: {_nitro__safe_fmt_nums(pred2.get('rf'))}")
-                lines.append(f"CHASE: {_nitro__safe_fmt_nums(pred2.get('chase'))}")
-                lines.append("")
-                if auto and cold:
-                    lines.append("RECOMMENDED: ENGINE + CHASE (Engine cold; Chase optional)")
-                content = "\n".join(lines).strip() + "\n"
-                st.download_button(
-                    "⬇️ Download Nitro Lines (Engine/RF/Markov/Chase)",
-                    data=content.encode("utf-8"),
-                    file_name=f"{gk}_nitro_lines_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt",
-                    mime="text/plain",
-                )
-            except Exception:
-                pass
-    except Exception:
-        return
-
-try:
-    _NITRO_UI__performance_panel()
-except Exception:
-    pass

app.txt

@@ -1,376 +0,0 @@
-import streamlit as st
-import pandas as pd
-from pathlib import Path
-import re
-import json
-from collections import Counter
-
-# Import V3.0 backend
-from lotto_predictor import (
-    predict_for_game_v3,
-    GAME_CONFIGS,
-    NumpyEncoder,
-    clean_powerball_df,
-    load_csv_for_game
-)
-
-# Data paths (adjust if your files live in a data/ subfolder)
-DATA_PATHS = {
-    "G5 (Gimme 5)": "gimme5_results.csv",
-    "LA (Lotto America)": "la_results.csv",
-    "L4L (Lucky for Life)": "Lucky For Life.csv",   # ✅ NEW
-    "MB (Megabucks)": "mb_results.csv",
-    "MM (Mega Millions)": "mm_results.csv",
-    "PB (Powerball)": "pb_results.csv",
-    "wheel_template": "wheel.txt",
-}
-
-st.set_page_config(page_title="Multi Lotto AI Engine V5.0", layout="centered")
-st.title("🎯 Lotto AI Engine (V5.0)")
-
-# -------------------------
-# Helper functions for V3.0
-# -------------------------
-
-def get_hot_and_cold_numbers(df: pd.DataFrame, cfg, top_n: int = 10):
-    """Calculate hot and cold numbers from the dataframe"""
-    # Count frequency of each number across all main columns
-    all_numbers = []
-    for col in cfg.main_cols:
-        all_numbers.extend(df[col].astype(int).tolist())
-    
-    freq_counter = Counter(all_numbers)
-    
-    # Get all possible numbers for this game
-    all_possible = list(range(cfg.main_min, cfg.main_max + 1))
-    
-    # Create frequency list with zeros for missing numbers
-    freq_list = [(num, freq_counter.get(num, 0)) for num in all_possible]
-    
-    # Sort by frequency
-    sorted_by_freq = sorted(freq_list, key=lambda x: x[1], reverse=True)
-    
-    # Hot numbers (most frequent)
-    hot = sorted_by_freq[:top_n]
-    
-    # Cold numbers (least frequent) 
-    cold = sorted_by_freq[-top_n:]
-    cold.reverse()  # Show coldest first
-    
-    return hot, cold
-
-@st.cache_data
-def load_wheel_raw_text(path: str) -> str:
-    """
-    Read wheel template as raw text using latin-1 fallback (robust to special bytes).
-    Returns empty string if missing or unreadable.
-    """
-    p = Path(path)
-    if not p.exists():
-        return ""
-    try:
-        # latin-1 will never fail for single-byte encodings; errors='replace' for safety
-        text = p.read_text(encoding="latin-1", errors="replace")
-        return text
-    except Exception:
-        return ""
-
-def select_20_wheel_numbers(hot: list, cold: list):
-    """Select 20 numbers for wheeling using hot/cold analysis"""
-    wheel_map = {}
-    wheel_labels = list("ABCDEFGHIJKLMNOPQRST")
-    
-    # Take top 10 hot numbers
-    hot_numbers = [num for num, freq in hot[:10]]
-    
-    # Take bottom 10 cold numbers 
-    cold_numbers = [num for num, freq in cold[:10]]
-    
-    # Combine them
-    selected_numbers = hot_numbers + cold_numbers
-    
-    # Map to letters A-T
-    for i, letter in enumerate(wheel_labels):
-        if i < len(selected_numbers):
-            wheel_map[letter] = selected_numbers[i]
-    
-    return wheel_map
-
-def convert_numeric_wheel_to_letter_template(raw_text: str, wheel_size: int = 20) -> str:
-    """
-    Convert numeric wheel lines like:
-      1-01-02-06-18-19-46
-    into letter-template lines:
-      A B C D E
-    """
-    if not raw_text:
-        return ""
-
-    lines = raw_text.splitlines()
-    out_lines = []
-    for line in lines:
-        # Detect lines that start with an index + dash (e.g. " 1-01-02-06-18-19-46")
-        if re.match(r'^\s*\d+\s*-', line):
-            # extract all integer tokens (1 or 2 digits)
-            nums = re.findall(r'\d{1,2}', line)
-            if not nums:
-                continue
-            # Many files start the line with the ticket index; drop it if present and equals first num
-            first_num_match = re.match(r'^\s*(\d+)', line)
-            if first_num_match and nums and nums[0] == first_num_match.group(1):
-                nums = nums[1:]
-            if len(nums) < 5:
-                # skip if fewer than 5 picks found
-                continue
-            picks = nums[:5]  # take the first five numbers
-            letters = []
-            for n_str in picks:
-                n = int(n_str)
-                # Map 1->A, 2->B, ... wrap/clamp if needed
-                idx = (n - 1) % 26
-                letters.append(chr(ord('A') + idx))
-            if len(letters) >= 5:
-                out_lines.append(" ".join(letters))
-    return "\n".join(out_lines)
-
-def expand_wheel_with_template(wheel_map: dict, template: str):
-    """Expand wheel template into actual number combinations"""
-    combos = []
-    lines = template.strip().split('\n')
-    
-    for line in lines:
-        letters = line.strip().split()
-        if len(letters) >= 5:
-            combo = []
-            for letter in letters[:5]:  # Take first 5 letters
-                if letter in wheel_map:
-                    combo.append(wheel_map[letter])
-            if len(combo) == 5:
-                combos.append(sorted(combo))
-    
-    return combos
-
-# -------------------------
-# Display helpers
-# -------------------------
-def display_hot_cold_tables(hot_df: pd.DataFrame, cold_df: pd.DataFrame):
-    hot_df.index = range(1, len(hot_df) + 1)
-    hot_df.index.name = "No"
-    cold_df.index = range(1, len(cold_df) + 1)
-    cold_df.index.name = "No"
-    with st.expander("🔥 Hot Numbers (Top 10)"):
-        st.table(hot_df)
-    with st.expander("❄️ Cold Numbers (Bottom 10)"):
-        st.table(cold_df)
-
-def display_wheel_table_from_hotcold(hot_df: pd.DataFrame, cold_df: pd.DataFrame):
-    """
-    Build the 20-number wheel mapping and show the table in the UI. 
-    Returns wheel_map (dict letter->number).
-    """
-    hot = [(int(n), f) for n, f in hot_df.values]
-    cold = [(int(n), f) for n, f in cold_df.values]
-    wheel_map = select_20_wheel_numbers(hot, cold)
-    wheel_labels = list("ABCDEFGHIJKLMNOPQRST")
-    ordered_numbers = [wheel_map.get(l, None) for l in wheel_labels]
-    wheel_df = pd.DataFrame([ordered_numbers], columns=wheel_labels)
-    with st.expander("🎡 Your 20 Numbers to Wheel"):
-        st.table(wheel_df)
-    return wheel_map
-
-def display_wheel_combinations_from_raw(wheel_map: dict, raw_template_text: str):
-    """
-    Convert numeric wheel template to letter-template, then expand and display combos.
-    """
-    if not raw_template_text:
-        st.warning("Wheel template file is empty or not found.")
-        return
-
-    letter_template = convert_numeric_wheel_to_letter_template(raw_template_text)
-    if not letter_template:
-        st.warning("Wheel template parsing found no valid ticket lines.")
-        return
-
-    combos = expand_wheel_with_template(wheel_map, letter_template)
-    if not combos:
-        st.warning("No combinations produced after expansion.")
-        return
-
-    df = pd.DataFrame(combos, columns=["Num1", "Num2", "Num3", "Num4", "Num5"])
-    df.index = [f"Ticket{i+1}" for i in range(len(df))]
-    df.index.name = "No"
-    with st.expander(f"🎟️ Wheel Combinations ({len(df)} tickets)"):
-        st.dataframe(df)
-
-# -------------------------
-# UI & main logic
-# -------------------------
-lotto_options = [
-    "G5 (Gimme 5)",
-    "LA (Lotto America)", 
-    "L4L (Lucky for Life)",  # ✅ NEW
-    "MB (Megabucks)",
-    "MM (Mega Millions)",
-    "PB (Powerball)",
-]
-lotto_type = st.selectbox("Select Lotto Type:", options=lotto_options, index=0)
-
-# Map display names -> keys used in GAME_CONFIGS and predict_for_game_v3
-GAME_KEY_MAP = {
-    "G5 (Gimme 5)": "gimme5",
-    "LA (Lotto America)": "la",
-    "L4L (Lucky for Life)": "l4l",  # ✅ NEW
-    "MB (Megabucks)": "mb", 
-    "MM (Mega Millions)": "mm",
-    "PB (Powerball)": "pb",
-}
-
-try:
-    game_key = GAME_KEY_MAP[lotto_type]
-    data_path = DATA_PATHS[lotto_type]
-    cfg = GAME_CONFIGS[game_key]
-
-    # Load dataset using V3.0 loader
-    df, _ = load_csv_for_game(Path(data_path), game_key)
-
-    # Hot/cold numbers computed using our helper
-    hot, cold = get_hot_and_cold_numbers(df, cfg)
-    hot_df = pd.DataFrame(hot, columns=["Number", "Frequency"])
-    cold_df = pd.DataFrame(cold, columns=["Number", "Frequency"])
-
-    # UI options - simplified for V3.0
-    run_backtest = st.checkbox("🧪 Run Backtest (slower but shows model performance)", value=False)
-    use_wheel = st.checkbox("🎡 Generate Wheel Combinations (if wheel.txt available)", value=False)
-
-    wheel_raw_text = load_wheel_raw_text(DATA_PATHS["wheel_template"]) if use_wheel else ""
-
-    # Styling
-    st.markdown(
-        """
-        <style>
-        table { margin-left:auto; margin-right:auto; }
-        th, td { text-align:center !important; vertical-align: middle !important; }
-        </style>
-        """,
-        unsafe_allow_html=True,
-    )
-
-    if st.button("🎰 Generate Prediction" if not run_backtest else "🧪 Run Backtest"):
-        with st.spinner("Building ensemble models and generating results..."):
-            # Run V3.0 predictor 
-            result = predict_for_game_v3(
-                csv_path=Path(data_path),
-                game_key=game_key,
-                run_backtest=run_backtest
-            )
-
-            if run_backtest:
-                # Display backtest results
-                if 'error' in result:
-                    st.error(f"❌ Backtest Error: {result['error']}")
-                else:
-                    st.success("✅ Backtest Complete!")
-                    
-                    # Show summary metrics
-                    st.subheader("📊 Backtest Summary")
-                    col1, col2, col3 = st.columns(3)
-                    
-                    with col1:
-                        st.metric("Model 3+ Matches", f"{result.get('model_3plus_rate', 0)}%")
-                    with col2:
-                        st.metric("Random 3+ Matches", f"{result.get('random_3plus_rate', 0)}%")
-                    with col3:
-                        st.metric("Even Count Accuracy", f"{result.get('even_count_accuracy', 0)}%")
-                    
-                    # Detailed hit rates
-                    st.subheader("🎯 Hit Rate Comparison")
-                    hit_data = []
-                    for i in range(6):
-                        model_rate = result.get(f'model_hit_{i}_rate', 0)
-                        random_rate = result.get(f'random_hit_{i}_rate', 0)
-                        hit_data.append({
-                            'Matches': i,
-                            'Model Rate (%)': model_rate,
-                            'Random Rate (%)': random_rate,
-                            'Improvement': f"+{model_rate - random_rate:.1f}%" if model_rate > random_rate else f"{model_rate - random_rate:.1f}%"
-                        })
-                    
-                    hit_df = pd.DataFrame(hit_data)
-                    st.table(hit_df)
-                    
-                    # Raw results
-                    with st.expander("📋 Full Backtest Results"):
-                        st.json(result)
-                        
-            else:
-                # -------------------------------
-                # Display prediction results
-                # -------------------------------
-                primary_numbers = result.get("numbers", [])
-                primary_star = result.get("star", None)
-
-                # Primary pick (same look as before, just a bit safer)
-                if primary_numbers:
-                    st.success(f"🧠 Predicted Numbers: {primary_numbers}")
-                else:
-                    st.warning("No primary numbers returned from engine.")
-
-                if primary_star is not None:
-                    star_col_name = cfg.star_col or 'Star'
-                    st.success(f"🌟 Predicted {star_col_name}: {primary_star}")
-                else:
-                    st.info("ℹ️ No bonus number for this game")
-                
-                # 👉 NEW: Show up to 5 GOD MODE sets (if present)
-                god_sets = result.get("godmode_sets", [])
-                if god_sets:
-                    st.subheader("🎲 GOD MODE Sets (up to 5)")
-                    for i, s in enumerate(god_sets[:5], start=1):
-                        style = s.get("style", "unknown").replace("_", " ").title()
-                        nums = s.get("numbers", [])
-                        star = s.get("star", None)
-                        label = f"{i}) {style}"
-                        if nums:
-                            nums_str = "-".join(str(n) for n in nums)
-                        else:
-                            nums_str = "(none)"
-
-                        if star is not None:
-                            st.write(f"**{label}:** {nums_str}  | ⭐ {star}")
-                        else:
-                            st.write(f"**{label}:** {nums_str}")
-                else:
-                    st.info("No GOD MODE sets available in this result.")
-
-                # Show additional info (same as before)
-                if primary_numbers:
-                    st.info(f"🔢 Total Sum: {sum(primary_numbers)} (Expected Range: {cfg.sum_min}–{cfg.sum_max})")
-                else:
-                    st.info(f"🔢 Expected Sum Range: {cfg.sum_min}–{cfg.sum_max}")
-
-                model_info = result.get('model_info', {})
-                st.info(f"🤖 Models built for {model_info.get('numbers_modeled', 0)}/{model_info.get('total_possible', 0)} numbers")
-
-                # Show hot/cold tables
-                display_hot_cold_tables(hot_df, cold_df)
-
-                # Wheel (if requested)
-                if use_wheel and wheel_raw_text:
-                    # Build and show wheel table (A..T mapping)
-                    wheel_map = display_wheel_table_from_hotcold(hot_df, cold_df)
-
-                    # Expand numeric wheel.txt to letter-template and display combos
-                    display_wheel_combinations_from_raw(wheel_map, wheel_raw_text)
-                elif use_wheel:
-                    st.warning("⚠️ Wheel template file (wheel.txt) not found or empty")
-                
-                # Raw prediction results
-                with st.expander("📋 Full Prediction Details"):
-                    st.json(result)
-
-except FileNotFoundError:
-    st.error(f"❌ File not found: `{data_path}`")
-except Exception as e:
-    st.error(f"⚠️ Error: {str(e)}")
-    import traceback
-    st.error(f"Details: {traceback.format_exc()}")

gimme5_predictor.py

@@ -1,230 +0,0 @@
-#!/usr/bin/env python3
-"""Gimme5 wrapper ONLY (NO engine edits).
-
-Adds (wrapper-side only):
-- Diversified Ticket (escapes consensus collapse by mixing sets)
-- Counter-Ticket when collapse ~= top_cluster (anti-stagnation)
-- De-dup strike tickets in printed output
-- Timestamped outputs written to pred_outputs/
-
-This file calls your existing lotto_predictor.predict_for_game_v3().
-"""
-
-import argparse
-import importlib
-import random
-from collections import Counter
-from datetime import datetime
-from pathlib import Path
-
-import numpy as np
-
-
-def set_seed(seed: int) -> None:
-    random.seed(seed)
-    np.random.seed(seed)
-
-
-def _get_god_sets(res: dict):
-    return res.get("god_sets") or res.get("godmode_sets") or res.get("god_mode_sets") or []
-
-
-def _pick_style(sets, style_name: str):
-    for s in sets:
-        if (s.get("style") or "").lower() == style_name.lower():
-            return s
-    return None
-
-
-def _norm_nums(nums):
-    if not nums:
-        return None
-    try:
-        return tuple(int(x) for x in nums)
-    except Exception:
-        return tuple(nums)
-
-
-def _fmt(nums):
-    return "-".join(str(int(x)) for x in nums)
-
-
-def build_diversified_ticket(god_sets):
-    if not god_sets:
-        return None
-
-    top = _pick_style(god_sets, "top_cluster") or god_sets[0]
-    high = _pick_style(god_sets, "high_cluster") or _pick_style(god_sets, "wide_spread") or (god_sets[1] if len(god_sets) > 1 else top)
-    low = _pick_style(god_sets, "low_cluster") or (god_sets[2] if len(god_sets) > 2 else high)
-
-    picked = []
-
-    def add_from(src, upto):
-        for n in (src.get("numbers") or []):
-            n = int(n)
-            if n not in picked:
-                picked.append(n)
-            if len(picked) >= upto:
-                break
-
-    # 2 from top, 2 from high/wide, 1 from low
-    add_from(top, 2)
-    add_from(high, 4)
-    add_from(low, 5)
-
-    # If still short, fill from global freq
-    if len(picked) < 5:
-        freq = Counter()
-        for s in god_sets:
-            for n in (s.get("numbers") or []):
-                freq[int(n)] += 1
-        for n, _ in freq.most_common():
-            if n not in picked:
-                picked.append(n)
-            if len(picked) >= 5:
-                break
-
-    return sorted(picked[:5])
-
-
-def build_counter_ticket(god_sets):
-    """Choose numbers that are least represented across sets (anti-collapse)."""
-    if not god_sets:
-        return None
-    freq = Counter()
-    pool = set()
-    for s in god_sets:
-        for n in (s.get("numbers") or []):
-            n = int(n)
-            freq[n] += 1
-            pool.add(n)
-
-    least = sorted(pool, key=lambda n: (freq[n], n))
-
-    pref = []
-    for style in ("high_cluster", "wide_spread"):
-        s = _pick_style(god_sets, style)
-        if s:
-            for n in (s.get("numbers") or []):
-                n = int(n)
-                if n not in pref:
-                    pref.append(n)
-
-    combined = []
-    for n in pref + least:
-        if n not in combined:
-            combined.append(n)
-        if len(combined) >= 5:
-            break
-    return sorted(combined[:5]) if len(combined) >= 5 else None
-
-
-def collapse_similarity(a, b):
-    if not a or not b:
-        return 0
-    sa, sb = set(a), set(b)
-    return len(sa & sb)
-
-
-def build_text(res: dict):
-    lines = []
-    lines.append(\"WRAPPER BUILD: FORCE_ANCHORS_v1\")
-    lines.append(\"\")
-    lines.append("GAME: G5 (Gimme 5)")
-    lines.append(f"GENERATED: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
-    lines.append("")
-
-    if res.get("numbers"):
-        lines.append("PRIMARY:")
-        lines.append(_fmt(res["numbers"]))
-        lines.append("")
-
-    god_sets = _get_god_sets(res)
-    if god_sets:
-        lines.append("GOD MODE SETS:")
-        for s in god_sets:
-            nums = s.get("numbers") or []
-            if nums:
-                lines.append(f"- {s.get('style','set')}: {_fmt(nums)}")
-        lines.append("")
-
-    strike = res.get("strike_tickets") or {}
-    collapse_nums = None
-    top_nums = None
-    if isinstance(strike, dict) and strike:
-        lines.append("STRIKE TICKETS:")
-        seen = set()
-        for k, v in strike.items():
-            if not isinstance(v, dict):
-                continue
-            nums = v.get("numbers") or []
-            t = _norm_nums(nums)
-            if t and t in seen:
-                continue
-            if t:
-                seen.add(t)
-            if (k or "").lower() == "collapse":
-                collapse_nums = [int(x) for x in nums] if nums else None
-            lines.append(f"- {k}: {_fmt(nums)}")
-        lines.append("")
-
-    top = _pick_style(god_sets, "top_cluster")
-    if top and top.get("numbers"):
-        top_nums = [int(x) for x in (top.get("numbers") or [])]
-
-    div = build_diversified_ticket(god_sets)
-    if div:
-        lines.append("DIVERSIFIED TICKET (wrapper-generated):")
-        lines.append(_fmt(div))
-        lines.append("")
-
-    if collapse_nums and top_nums:
-        sim = collapse_similarity(collapse_nums, top_nums)
-        if sim >= 4:
-            counter = build_counter_ticket(god_sets)
-            if counter:
-                lines.append("COUNTER-TICKET (anti-collapse, wrapper-generated):")
-                lines.append(_fmt(counter))
-                lines.append("")
-
-    return "\n".join(lines)
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--csv", default="gimme5_results.csv", help="CSV file in repo or full local path")
-    ap.add_argument("--seed", type=int, default=5105, help="Repro seed (wrapper-level, G5 default)")
-    ap.add_argument("--out-dir", default="pred_outputs", help="Write timestamped results here")
-    ap.add_argument("--no-deep-low", action="store_true")
-    ap.add_argument("--no-tight-relax", action="store_true")
-    ap.add_argument("--no-mid-carry", action="store_true")
-    ap.add_argument("--no-wildcard", action="store_true")
-    args = ap.parse_args()
-
-    set_seed(args.seed)
-
-    engine = importlib.import_module("lotto_predictor")
-
-    if hasattr(engine, "PATCH_UI_FLAGS") and isinstance(getattr(engine, "PATCH_UI_FLAGS"), dict):
-        engine.PATCH_UI_FLAGS.update({
-            "deep_low_patch": not args.no_deep_low,
-            "tight_relax_patch": not args.no_tight_relax,
-            "mid_carry_patch": not args.no_mid_carry,
-            "wildcard_strike": not args.no_wildcard,
-        })
-
-    res = engine.predict_for_game_v3(Path(args.csv), "gimme5", run_backtest=False)
-
-    text = build_text(res)
-
-    outp = Path(args.out_dir)
-    outp.mkdir(parents=True, exist_ok=True)
-    ts = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
-    out_file = outp / f"g5_godmode_{ts}.txt"
-    out_file.write_text(text, encoding="utf-8")
-
-    print(text)
-
-
-if __name__ == "__main__":
-    main()

gimme5_results.csv

@@ -1,443 +0,0 @@
-Date,b1,b2,b3,b4,b5
-1/29/2026,3,16,18,21,33
-1/28/2026,4,14,16,32,37
-1/27/2026,3,9,11,17,39
-1/26/2026,3,19,24,32,39
-1/23/2026,4,5,13,26,32
-1/22/2026,16,19,22,23,27
-1/21/2026,3,9,13,14,20
-1/20/2026,11,14,23,31,38
-1/19/2026,5,10,29,34,38
-1/16/2026,3,6,11,20,28
-1/15/2026,9,16,17,22,31
-1/14/2026,1,15,19,26,28
-1/13/2026,3,11,16,24,27
-1/12/2026,7,26,27,34,36
-1/9/2026,6,17,21,25,32
-1/8/2026,1,7,28,33,34
-1/7/2026,16,19,21,25,34
-1/6/2026,1,10,11,36,37
-1/5/2026,10,14,18,22,30
-1/1/2026,9,13,17,24,28
-12/31/2025,1,3,20,33,34
-12/30/2025,2,14,24,29,31
-12/29/2025,6,18,21,22,27
-12/26/2025,4,8,23,26,30
-12/25/2025,14,16,18,25,31
-12/24/2025,3,7,18,23,39
-12/23/2025,21,25,31,36,39
-12/22/2025,21,26,27,38,39
-12/19/2025,4,12,17,20,30
-12/18/2025,8,9,27,28,30
-12/17/2025,9,17,24,28,32
-12/16/2025,8,21,36,38,39
-12/15/2025,6,8,10,36,39
-12/12/2025,9,11,12,30,37
-12/11/2025,1,3,14,21,38
-12/10/2025,10,11,18,26,30
-12/9/2025,9,11,27,33,37
-12/8/2025,3,14,19,28,31
-12/5/2025,3,10,30,31,34
-12/4/2025,3,24,29,37,39
-12/3/2025,12,13,16,20,35
-12/2/2025,6,11,13,16,26
-12/1/2025,9,20,30,32,35
-11/28/2025,6,23,25,29,31
-11/27/2025,5,10,25,31,35
-11/26/2025,9,12,28,33,34
-11/25/2025,10,16,18,19,30
-11/24/2025,2,4,15,19,25
-11/21/2025,6,15,22,29,30
-11/20/2025,3,11,17,22,24
-11/19/2025,2,16,17,21,28
-11/18/2025,16,21,26,34,35
-11/17/2025,13,21,23,28,29
-11/14/2025,3,13,16,34,35
-11/13/2025,3,7,19,24,26
-11/12/2025,7,11,23,33,35
-11/11/2025,3,16,17,23,36
-11/10/2025,4,9,11,20,30
-11/7/2025,4,12,13,34,36
-11/6/2025,11,16,18,28,31
-11/5/2025,7,15,18,23,30
-11/4/2025,15,17,28,29,38
-11/3/2025,1,5,11,22,26
-10/31/2025,5,8,15,16,34
-10/30/2025,1,10,13,18,33
-10/29/2025,3,11,22,23,38
-10/28/2025,2,6,22,25,35
-10/27/2025,2,3,8,13,35
-10/24/2025,2,14,18,27,29
-10/23/2025,2,4,18,20,26
-10/22/2025,8,13,23,27,29
-10/21/2025,8,18,21,31,35
-10/20/2025,6,19,20,23,30
-10/17/2025,14,18,20,24,37
-10/16/2025,1,11,20,29,39
-10/15/2025,10,12,24,26,33
-10/14/2025,6,17,18,26,34
-10/13/2025,1,7,18,31,37
-10/10/2025,7,10,19,22,30
-10/9/2025,11,15,18,24,25
-10/8/2025,7,10,16,30,32
-10/7/2025,14,17,20,28,33
-10/6/2025,2,25,29,31,35
-10/3/2025,15,29,36,38,39
-10/2/2025,5,10,25,29,38
-10/1/2025,9,14,25,27,31
-9/30/2025,11,13,14,33,37
-9/29/2025,3,14,15,17,28
-9/26/2025,19,21,23,30,34
-9/25/2025,3,9,32,33,39
-9/24/2025,23,25,26,31,35
-9/23/2025,1,5,20,32,36
-9/22/2025,7,22,26,31,34
-9/19/2025,2,15,23,34,39
-9/18/2025,16,22,23,32,37
-9/17/2025,5,12,14,16,32
-9/16/2025,5,6,16,23,33
-9/15/2025,2,5,17,35,37
-9/12/2025,5,14,23,25,28
-9/11/2025,15,25,30,31,33
-9/10/2025,3,12,20,28,36
-9/9/2025,3,9,21,26,27
-9/8/2025,11,15,17,22,27
-9/5/2025,2,5,11,27,37
-9/4/2025,3,5,22,30,35
-9/3/2025,5,12,18,27,38
-9/2/2025,7,19,22,25,26
-9/1/2025,2,12,19,28,29
-8/29/2025,3,11,18,19,34
-8/28/2025,15,18,31,33,38
-8/27/2025,4,10,12,15,35
-8/26/2025,11,23,26,31,39
-8/25/2025,4,12,16,28,31
-8/22/2025,2,17,27,34,37
-8/21/2025,6,9,30,34,37
-8/20/2025,5,7,9,35,38
-8/19/2025,6,11,15,21,25
-8/18/2025,11,16,21,34,35
-8/15/2025,6,16,24,30,37
-8/14/2025,1,3,12,21,26
-8/13/2025,5,7,17,22,24
-8/12/2025,4,5,13,15,17
-8/11/2025,9,10,21,23,39
-8/8/2025,19,20,26,35,39
-8/7/2025,19,22,23,29,37
-8/6/2025,2,14,17,32,38
-8/5/2025,4,13,26,30,37
-8/4/2025,6,9,20,22,23
-8/1/2025,16,17,20,22,35
-7/31/2025,19,23,24,32,38
-7/30/2025,7,14,15,18,26
-7/29/2025,11,13,14,15,25
-7/28/2025,8,10,23,30,38
-7/25/2025,2,10,15,30,39
-7/24/2025,10,14,19,31,33
-7/23/2025,1,14,23,30,37
-7/22/2025,1,14,19,29,31
-7/21/2025,4,14,18,33,39
-7/18/2025,3,7,20,21,27
-7/17/2025,11,18,21,31,34
-7/16/2025,12,13,31,36,37
-7/15/2025,1,21,22,28,37
-7/14/2025,6,19,23,25,38
-7/11/2025,9,10,21,25,32
-7/10/2025,13,16,23,33,34
-7/9/2025,8,14,18,38,39
-7/8/2025,4,18,20,31,32
-7/7/2025,19,20,24,33,38
-7/4/2025,8,26,27,34,39
-7/3/2025,5,6,14,19,25
-7/2/2025,9,11,20,24,39
-7/1/2025,3,5,7,18,38
-6/30/2025,1,7,16,24,39
-6/27/2025,2,6,11,15,35
-6/26/2025,16,19,23,24,36
-6/25/2025,22,25,29,33,38
-6/24/2025,6,9,32,37,39
-6/23/2025,16,22,24,28,34
-6/20/2025,1,2,3,27,30
-6/19/2025,6,9,14,16,21
-6/18/2025,3,13,16,19,24
-6/17/2025,7,9,24,26,33
-6/16/2025,4,8,14,18,33
-6/13/2025,1,2,9,25,33
-6/12/2025,7,9,13,16,26
-6/11/2025,14,18,25,36,37
-6/10/2025,3,16,18,20,22
-6/9/2025,8,12,20,26,35
-6/6/2025,7,11,16,20,35
-6/5/2025,2,3,5,22,33
-6/4/2025,10,24,25,26,38
-6/3/2025,2,7,21,23,36
-6/2/2025,11,25,28,29,36
-5/30/2025,9,13,28,33,37
-5/29/2025,1,14,16,17,22
-5/28/2025,16,21,25,27,28
-5/27/2025,6,9,20,26,33
-5/26/2025,12,22,23,25,37
-5/23/2025,4,8,12,19,27
-5/22/2025,2,4,15,29,34
-5/21/2025,6,11,13,24,26
-5/20/2025,12,18,20,23,37
-5/19/2025,9,10,25,34,35
-5/16/2025,2,9,13,18,24
-5/15/2025,5,9,11,26,34
-5/14/2025,21,27,31,32,33
-5/13/2025,9,12,13,26,35
-5/12/2025,4,7,21,33,36
-5/9/2025,1,18,22,23,26
-5/8/2025,4,10,18,19,28
-5/7/2025,20,22,27,33,39
-5/6/2025,5,13,19,29,34
-5/5/2025,3,4,29,30,33
-5/2/2025,3,5,8,15,19
-5/1/2025,11,22,24,25,30
-4/30/2025,13,23,29,36,38
-4/29/2025,1,18,20,28,35
-4/28/2025,7,12,24,26,28
-4/25/2025,2,8,12,22,24
-4/24/2025,16,22,28,33,39
-4/23/2025,3,8,18,23,37
-4/22/2025,1,9,14,18,25
-4/21/2025,10,11,24,26,29
-4/18/2025,3,11,19,31,36
-4/17/2025,1,2,10,14,15
-4/16/2025,9,14,20,38,39
-4/15/2025,3,4,14,22,38
-4/14/2025,1,8,19,20,28
-4/11/2025,6,9,21,24,39
-4/10/2025,3,17,26,35,37
-4/9/2025,5,6,12,15,35
-4/8/2025,15,25,28,34,36
-4/7/2025,7,10,18,32,37
-4/4/2025,10,14,18,24,34
-4/3/2025,1,11,15,33,39
-4/2/2025,17,21,23,29,39
-4/1/2025,5,9,22,26,29
-3/31/2025,12,22,26,31,35
-3/28/2025,10,18,19,21,34
-3/27/2025,4,6,15,32,37
-3/26/2025,9,17,32,34,36
-3/25/2025,9,18,28,30,35
-3/24/2025,15,20,22,31,34
-3/21/2025,1,2,4,25,34
-3/20/2025,2,3,24,30,34
-3/19/2025,9,13,15,17,28
-3/18/2025,4,12,13,15,33
-3/17/2025,2,3,20,34,38
-3/14/2025,17,22,23,25,39
-3/13/2025,2,13,15,23,32
-3/12/2025,3,9,12,19,23
-3/11/2025,1,9,15,30,33
-3/10/2025,9,12,16,26,30
-3/7/2025,8,21,26,28,34
-3/6/2025,8,19,28,35,39
-3/5/2025,1,25,31,32,37
-3/4/2025,1,17,30,35,39
-3/3/2025,3,6,13,33,34
-2/28/2025,5,8,13,26,39
-2/27/2025,9,13,31,33,38
-2/26/2025,1,3,8,17,27
-2/25/2025,20,21,26,27,30
-2/24/2025,2,15,18,19,25
-2/21/2025,1,15,18,27,29
-2/20/2025,3,8,11,36,38
-2/19/2025,9,10,18,19,29
-2/18/2025,6,8,9,18,24
-2/17/2025,7,20,23,24,39
-2/14/2025,7,19,30,35,39
-2/13/2025,9,14,16,17,19
-2/12/2025,20,21,23,29,39
-2/11/2025,1,6,9,14,39
-2/10/2025,8,11,12,29,30
-2/7/2025,8,20,25,31,34
-2/6/2025,17,19,29,31,39
-2/5/2025,5,11,20,27,36
-2/4/2025,1,3,6,21,24
-2/3/2025,1,18,33,35,39
-1/31/2025,15,16,18,19,20
-1/30/2025,8,20,28,29,31
-1/29/2025,6,13,15,16,36
-1/28/2025,1,6,17,29,38
-1/27/2025,7,10,27,33,38
-1/24/2025,11,14,15,22,27
-1/23/2025,5,7,19,34,39
-1/22/2025,10,25,27,35,38
-1/21/2025,10,14,22,32,33
-1/20/2025,7,28,29,32,35
-1/17/2025,9,15,20,34,36
-1/16/2025,1,6,10,24,33
-1/15/2025,10,13,15,19,32
-1/14/2025,5,16,18,23,38
-1/13/2025,8,22,26,31,34
-1/10/2025,1,4,8,15,38
-1/9/2025,3,8,27,31,32
-1/8/2025,14,16,26,30,36
-1/7/2025,6,11,18,36,39
-1/6/2025,15,16,18,21,25
-1/3/2025,1,9,19,24,31
-1/2/2025,12,15,21,26,36
-1/1/2025,5,8,20,24,27
-12/31/2024,2,4,12,27,29
-12/30/2024,8,10,20,25,27
-12/27/2024,2,14,21,34,38
-12/26/2024,6,13,22,32,34
-12/25/2024,2,24,27,30,36
-12/24/2024,9,13,17,29,35
-12/23/2024,6,9,15,19,22
-12/20/2024,10,19,27,28,31
-12/19/2024,13,25,28,29,31
-12/18/2024,7,14,21,22,27
-12/17/2024,2,14,19,24,38
-12/16/2024,4,5,25,26,33
-12/13/2024,3,23,24,25,29
-12/12/2024,18,21,24,27,30
-12/11/2024,2,18,19,25,37
-12/10/2024,10,16,23,25,26
-12/9/2024,18,26,29,33,35
-12/6/2024,1,5,13,15,20
-12/5/2024,8,24,27,28,37
-12/4/2024,2,15,18,23,24
-12/3/2024,2,7,20,30,37
-12/2/2024,5,7,9,26,31
-11/29/2024,5,7,9,10,11
-11/28/2024,24,26,27,28,31
-11/27/2024,13,15,23,27,34
-11/26/2024,14,18,22,26,32
-11/25/2024,9,15,20,25,38
-11/22/2024,1,10,21,24,38
-11/21/2024,6,17,18,22,27
-11/20/2024,5,13,20,30,32
-11/19/2024,10,20,23,24,25
-11/18/2024,20,23,33,37,39
-11/15/2024,8,14,33,35,37
-11/14/2024,4,7,10,17,20
-11/13/2024,10,11,23,27,34
-11/12/2024,12,14,25,37,38
-11/11/2024,12,17,20,23,30
-11/8/2024,2,8,13,19,36
-11/7/2024,2,14,22,23,37
-11/6/2024,2,6,22,23,30
-11/5/2024,10,14,17,19,23
-11/4/2024,7,9,18,19,27
-11/1/2024,10,12,19,23,38
-10/31/2024,14,20,25,32,36
-10/30/2024,9,10,11,27,34
-10/29/2024,12,26,28,32,38
-10/28/2024,6,13,16,25,32
-10/25/2024,21,27,29,32,39
-10/24/2024,11,13,17,33,38
-10/23/2024,10,11,18,25,28
-10/22/2024,1,4,21,28,37
-10/21/2024,16,25,29,32,37
-10/18/2024,3,4,19,23,29
-10/17/2024,2,18,28,33,39
-10/16/2024,10,14,15,17,23
-10/15/2024,14,17,20,31,39
-10/14/2024,4,9,11,16,31
-10/11/2024,1,13,27,29,30
-10/10/2024,12,14,15,19,22
-10/9/2024,6,15,22,32,33
-10/8/2024,18,21,30,33,34
-10/7/2024,1,5,15,33,36
-10/4/2024,4,5,12,17,20
-10/3/2024,6,8,24,29,32
-10/2/2024,11,22,23,26,35
-10/1/2024,8,19,21,36,39
-9/30/2024,2,8,19,26,31
-9/27/2024,1,5,9,34,37
-9/26/2024,19,20,22,23,39
-9/25/2024,1,5,7,9,19
-9/24/2024,5,7,8,19,37
-9/23/2024,2,5,7,14,31
-9/20/2024,2,16,29,32,35
-9/19/2024,5,7,18,20,29
-9/18/2024,1,19,22,30,35
-9/17/2024,3,8,13,34,35
-9/16/2024,12,18,22,37,39
-9/13/2024,2,23,30,32,36
-9/12/2024,3,12,16,26,29
-9/11/2024,2,15,22,24,28
-9/10/2024,2,7,22,27,28
-9/9/2024,4,8,27,29,30
-9/6/2024,7,8,14,20,30
-9/5/2024,3,27,28,30,34
-9/4/2024,18,19,22,26,39
-9/3/2024,7,11,29,34,39
-9/2/2024,2,9,17,19,34
-8/30/2024,5,6,19,28,38
-8/29/2024,11,20,29,30,32
-8/28/2024,3,5,8,14,35
-8/27/2024,3,8,9,24,26
-8/26/2024,16,23,28,32,36
-8/23/2024,18,25,27,35,36
-8/22/2024,12,28,30,31,37
-8/21/2024,3,6,17,26,30
-8/20/2024,5,6,9,14,20
-8/19/2024,14,26,29,34,39
-8/16/2024,20,27,33,35,37
-8/15/2024,4,11,18,19,33
-8/14/2024,6,15,20,26,32
-8/13/2024,4,9,23,31,33
-8/12/2024,2,12,14,27,29
-8/9/2024,5,16,31,34,36
-8/8/2024,3,4,21,35,38
-8/7/2024,4,13,16,20,31
-8/6/2024,1,4,30,33,37
-8/5/2024,2,5,12,21,25
-8/2/2024,5,9,14,16,38
-8/1/2024,15,16,18,31,34
-7/31/2024,7,12,15,30,31
-7/30/2024,3,4,8,30,35
-7/29/2024,4,12,16,23,30
-7/26/2024,4,14,18,34,36
-7/25/2024,13,24,30,32,34
-7/24/2024,7,13,15,33,37
-7/23/2024,6,9,13,21,32
-7/22/2024,20,25,31,33,34
-7/19/2024,30,33,34,35,39
-7/18/2024,6,10,19,24,26
-7/17/2024,1,3,13,16,18
-7/16/2024,2,8,9,26,36
-7/15/2024,4,10,13,32,35
-7/12/2024,2,15,19,26,28
-7/11/2024,6,21,24,38,39
-7/10/2024,15,16,22,25,26
-7/9/2024,9,15,23,32,36
-7/8/2024,10,19,20,25,26
-7/5/2024,1,4,5,12,27
-7/4/2024,2,7,10,14,31
-7/3/2024,3,10,13,27,35
-7/2/2024,2,17,21,36,39
-7/1/2024,5,7,26,28,39
-6/28/2024,1,21,22,25,31
-6/27/2024,3,17,20,35,36
-6/26/2024,6,13,16,19,26
-6/25/2024,7,12,22,30,37
-6/24/2024,17,27,31,32,36
-6/21/2024,8,14,16,17,21
-6/20/2024,18,20,24,31,38
-6/19/2024,1,3,6,10,35
-6/18/2024,2,9,29,38,39
-6/17/2024,13,26,29,38,39
-6/14/2024,5,8,10,18,36
-6/13/2024,7,8,11,14,20
-6/12/2024,1,12,17,23,32
-6/11/2024,10,18,29,31,38
-6/10/2024,1,7,17,18,30
-6/7/2024,23,25,28,35,36
-6/6/2024,6,18,24,35,36
-6/5/2024,11,18,22,34,37
-6/4/2024,6,15,17,22,28
-6/3/2024,6,12,18,19,23
-5/31/2024,8,13,20,30,32
-5/30/2024,7,13,18,22,25
-5/29/2024,6,11,20,22,27
-5/28/2024,1,7,8,11,26
-5/27/2024,1,3,6,20,33
-5/24/2024,5,9,18,29,39
-5/23/2024,1,6,10,12,17
-5/22/2024,4,8,20,24,35
-5/21/2024,5,8,11,33,34

l4l_predictor.py

@@ -1,32 +0,0 @@
-import json
-from pathlib import Path
-from lotto_predictor import predict_for_game_v3, NumpyEncoder
-
-def main():
-    # Lucky for Life CSV path
-    csv_path = Path("Lucky For Life.csv")
-    
-    try:
-        # Run prediction for Lucky for Life (game key "l4l")
-        print("Generating Lucky for Life prediction...")
-        res = predict_for_game_v3(csv_path, "l4l", run_backtest=False)
-        
-        print("Prediction:")
-        print(json.dumps(res, indent=2, cls=NumpyEncoder))
-        
-        print(f"\nPredicted Numbers: {res['numbers']}")
-        if res.get('star'):
-            print(f"Lucky Ball: {res['star']}")
-        
-        # Print model info if present
-        model_info = res.get('model_info', {})
-        print(f"\nModel built for {model_info.get('numbers_modeled', 0)} "
-              f"out of {model_info.get('total_possible', 0)} possible numbers")
-        
-    except Exception as e:
-        print(f"Prediction failed: {str(e)}")
-        import traceback
-        traceback.print_exc()
-
-if __name__ == "__main__":
-    main()

la_predictor.py

@@ -1,2050 +0,0 @@
-#!/usr/bin/env python3
-"""
-LOTTO PREDICTOR V5.3 ULTRA - GOD MODE
-
-Upgrades vs V5.2:
-- New GOD-MODE style: "top_cluster"
-  * Explicitly packs the top 3 highest-score numbers (not banned)
-    into one hyper-focused combo, then fills the rest.
-- Gimme5-specific tuning:
-  * Short-window ML weights increased for Gimme5
-  * Agent weights adjusted to favor recency / hot/cold / clusters more
-    for Gimme5, while other games keep the older balanced mix.
-- V5.3 ULTRA layer:
-  * Regime & trend-aware adjustment (low/flat/high volatility, high_run/low_run)
-  * Low-zone boost + cold-burst correction
-  * Anti-lock usage limiter across sets + coverage optimizer
-  * Mega Millions specific refinements for main numbers
-  * Lotto America specific main-range + Star Ball tweaks + neighbor-chaser
-  * Megabucks specific main-range tweaks (mid/high band support, soften 1–3)
-  * Powerball specific main-range tweaks (core band support, soften extremes)
-  * Lucky for Life specific main-range tweaks (central band support, soften extremes + neighbor-chaser)
-  * Gimme 5 neighbor-chaser with micro-boost around recent hot core numbers
-  * Mega Millions legacy Megaball 25→1–24 remap so all history fits MB 1–24
-  * Enhanced star/bonus picker (V5.3.1) with low-zone + cold-burst logic
-
-Features:
-- Multi-game, multi-agent, multi-window prediction engine
-- Games supported:
-    * gimme5 (Gimme 5)
-    * la (Lotto America)
-    * mb (Megabucks)
-    * mm (Mega Millions)
-    * pb (Powerball)
-    * l4l (Lucky for Life)
-- Multi-window ML:
-    * Short (20 draws), Medium (80 draws), Long (400 draws or all)
-- Agents per number:
-    * ML agent (RF + ET + GB + XGB + MLP ensemble)
-    * Hot/Cold frequency agent
-    * Bayesian frequency agent
-    * Recency agent
-    * RL-style "good draw" agent
-    * Pattern agent (sum/odd-even/high-low/range)
-    * Cluster compression agent (recent density bands)
-    * Drift agent (low/high sum shifts)
-    * Parity drift agent (odd/even imbalance)
-- Combination search:
-    * GOD-MODE Monte Carlo over agent scores + pattern scoring
-    * LAST-4 repeater ban rule (YOUR CUSTOM RULE):
-        - If a number appears in EACH of the last 4 consecutive draws,
-          it is banned from prediction. (We do NOT ban all numbers
-          that simply appeared in the last 4 once.)
-    * Generates multiple GOD MODE combos with different pattern styles:
-        - top_cluster (hyper-focused, forced top-3 core)
-        - balanced
-        - low_cluster
-        - high_cluster
-        - tight_cluster
-        - wide_spread
-- API:
-    * predict_for_game_v3(csv_path, game_key, run_backtest=False)
-    * predict_for_game(csv_path, game_key, run_backtest=False)
-    * generate_wheel_numbers(...)
-    * get_wheel_for_game(...)
-    * get_hot_cold_analysis(...)
-    * load_and_prepare_data(...)
-"""
-
-from __future__ import annotations
-
-import json
-import random
-from collections import Counter
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Dict, List, Optional, Tuple
-
-import numpy as np
-import pandas as pd
-import warnings
-
-warnings.filterwarnings("ignore")
-
-
-# ============================================================
-# JSON encoder for numpy types
-# ============================================================
-
-class NumpyEncoder(json.JSONEncoder):
-    def default(self, obj):
-        if isinstance(obj, (np.integer, np.int64)):
-            return int(obj)
-        if isinstance(obj, (np.floating, np.float64)):
-            return float(obj)
-        if isinstance(obj, np.ndarray):
-            return obj.tolist()
-        return super().default(obj)
-
-
-# ============================================================
-# Game configuration
-# ============================================================
-
-@dataclass
-class GameConfig:
-    name: str
-    csv_date_col: str
-    main_cols: List[str]
-    star_col: Optional[str]
-    main_min: int
-    main_max: int
-    star_min: Optional[int] = None
-    star_max: Optional[int] = None
-    sum_min: int = 0
-    sum_max: int = 1000
-    clean_func: Optional[str] = None
-    draw_frequency: str = "Unknown"  # used by engine/app
-
-
-GAME_CONFIGS: Dict[str, GameConfig] = {
-    "gimme5": GameConfig(
-        name="Gimme 5",
-        csv_date_col="Date",
-        main_cols=["1", "2", "3", "4", "5"],
-        star_col=None,
-        main_min=1,
-        main_max=39,
-        sum_min=40,
-        sum_max=160,
-        draw_frequency="5x/week",
-    ),
-    "la": GameConfig(
-        name="Lotto America",
-        csv_date_col="DrawDate",
-        main_cols=["1", "2", "3", "4", "5"],
-        star_col="SB",
-        main_min=1,
-        main_max=52,
-        star_min=1,
-        star_max=10,
-        sum_min=70,
-        sum_max=210,
-        draw_frequency="3x/week",
-    ),
-    "mb": GameConfig(
-        name="Megabucks",
-        csv_date_col="Date",
-        main_cols=["1", "2", "3", "4", "5"],
-        star_col="Megaball",
-        main_min=1,
-        main_max=41,
-        star_min=1,
-        star_max=6,
-        sum_min=45,
-        sum_max=165,
-        draw_frequency="3x/week",
-    ),
-    "mm": GameConfig(
-        name="Mega Millions",
-        csv_date_col="Date",
-        main_cols=["1", "2", "3", "4", "5"],
-        star_col="MB",
-        main_min=1,
-        main_max=70,
-        star_min=1,
-        star_max=24,  # modern format (Megaball 1–24, legacy 25 remapped below)
-        sum_min=75,
-        sum_max=280,
-        draw_frequency="2x/week",
-    ),
-    "pb": GameConfig(
-        name="Powerball",
-        csv_date_col="DrawDate",
-        main_cols=["1", "2", "3", "4", "5"],
-        star_col="PB",
-        main_min=1,
-        main_max=69,
-        star_min=1,
-        star_max=26,
-        sum_min=65,
-        sum_max=265,
-        clean_func="clean_powerball_df",
-        draw_frequency="3x/week",
-    ),
-    "l4l": GameConfig(
-        name="Lucky for Life",
-        csv_date_col="Draw Date",
-        main_cols=["Ball 1", "Ball 2", "Ball 3", "Ball 4", "Ball 5"],
-        star_col="Lucky Ball",
-        main_min=1,
-        main_max=48,
-        star_min=1,
-        star_max=18,
-        sum_min=60,
-        sum_max=200,
-        draw_frequency="Daily",
-    ),
-}
-
-
-# ============================================================
-# Cleaning / Date / Recency helpers
-# ============================================================
-
-def clean_powerball_df(raw_df: pd.DataFrame) -> pd.DataFrame:
-    """
-    Example cleanup for Powerball: drop Double Play / malformed rows.
-    Adapt if your PB CSV has extra columns.
-    """
-    df = raw_df.copy()
-    if "DrawDate" in df.columns:
-        mask = ~df["DrawDate"].astype(str).str.contains("Double Play", na=False)
-        df = df[mask]
-    return df.reset_index(drop=True)
-
-
-def _ensure_datetime(df: pd.DataFrame, date_col: str) -> pd.DataFrame:
-    df = df.copy()
-    df[date_col] = pd.to_datetime(df[date_col], errors="coerce")
-    invalid = df[date_col].isna().sum()
-    if invalid > 0:
-        df = df.dropna(subset=[date_col])
-    df = df.sort_values(date_col).reset_index(drop=True)
-
-    df["Date"] = pd.to_datetime(df[date_col], errors="coerce")
-    df["DayOfWeek"] = df["Date"].dt.dayofweek
-    df["Month"] = df["Date"].dt.month
-    df["Year"] = df["Date"].dt.year
-    df["DayOfYear"] = df["Date"].dt.dayofyear
-    return df
-
-
-def _limit_history(df: pd.DataFrame, max_rows: int) -> pd.DataFrame:
-    if len(df) > max_rows:
-        return df.tail(max_rows).reset_index(drop=True)
-    return df.reset_index(drop=True)
-
-
-# ============================================================
-# Structural features per draw
-# ============================================================
-
-def calculate_structural_features(df: pd.DataFrame, cfg: GameConfig) -> pd.DataFrame:
-    df = df.copy()
-    df["sum_total"] = df[cfg.main_cols].sum(axis=1)
-    df["mean_val"] = df[cfg.main_cols].mean(axis=1)
-    df["std_val"] = df[cfg.main_cols].std(axis=1)
-
-    df["even_count"] = df[cfg.main_cols].apply(
-        lambda row: sum(1 for v in row if v % 2 == 0), axis=1
-    )
-    df["odd_count"] = len(cfg.main_cols) - df["even_count"]
-
-    df["range_span"] = df[cfg.main_cols].max(axis=1) - df[cfg.main_cols].min(axis=1)
-
-    midpoint = (cfg.main_min + cfg.main_max) / 2.0
-    df["high_count"] = df[cfg.main_cols].apply(
-        lambda row: sum(1 for v in row if v > midpoint), axis=1
-    )
-    df["low_count"] = len(cfg.main_cols) - df["high_count"]
-
-    def count_consecutive(values):
-        s = sorted(values)
-        return sum(1 for i in range(len(s) - 1) if s[i + 1] - s[i] == 1)
-
-    def avg_gap(values):
-        s = sorted(values)
-        gaps = [s[i + 1] - s[i] for i in range(len(s) - 1)]
-        return float(np.mean(gaps)) if gaps else 0.0
-
-    df["consecutive_count"] = df[cfg.main_cols].apply(count_consecutive, axis=1)
-    df["avg_gap"] = df[cfg.main_cols].apply(avg_gap, axis=1)
-
-    return df
-
-
-def create_frequency_features(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    windows: List[int] = [20, 80, 400],
-) -> Dict[int, Dict[str, float]]:
-    freq: Dict[int, Dict[str, float]] = {}
-    for num in range(cfg.main_min, cfg.main_max + 1):
-        freq[num] = {}
-        total_hits = (df[cfg.main_cols] == num).sum().sum()
-        freq[num]["overall_freq"] = total_hits / max(len(df), 1)
-
-        for w in windows:
-            sub = df.tail(w) if len(df) >= w else df
-            hits = (sub[cfg.main_cols] == num).sum().sum()
-            freq[num][f"freq_{w}"] = hits / max(len(sub), 1)
-
-        last_idx = -1
-        for i in range(len(df) - 1, -1, -1):
-            if num in df.iloc[i][cfg.main_cols].values:
-                last_idx = i
-                break
-        if last_idx == -1:
-            freq[num]["days_since_last"] = float(len(df))
-        else:
-            freq[num]["days_since_last"] = float(len(df) - 1 - last_idx)
-    return freq
-
-
-# ============================================================
-# Multi-window ML ensemble
-# ============================================================
-
-try:
-    from xgboost import XGBClassifier
-    _HAS_XGB = True
-except ImportError:
-    from sklearn.ensemble import GradientBoostingClassifier as XGBClassifier
-    _HAS_XGB = False
-
-from sklearn.ensemble import (
-    RandomForestClassifier,
-    ExtraTreesClassifier,
-    GradientBoostingClassifier,
-    VotingClassifier,
-)
-from sklearn.neural_network import MLPClassifier
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import accuracy_score
-
-
-def _build_window_ml_models(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    window: int,
-) -> Dict[int, Dict]:
-    """
-    Train a per-number ML ensemble for a given window size.
-    Returns {num: {"model": VotingClassifier, "scaler": StandardScaler, "feature_cols": [...], "accuracy": float}}
-    """
-    if len(df) < 40:
-        return {}
-
-    sub = df.tail(window) if len(df) > window else df
-    feats = calculate_structural_features(sub, cfg)
-
-    base_cols = [
-        "DayOfWeek",
-        "Month",
-        "sum_total",
-        "even_count",
-        "odd_count",
-        "range_span",
-        "consecutive_count",
-        "avg_gap",
-        "high_count",
-    ]
-    feature_cols = [c for c in base_cols if c in feats.columns]
-    X = feats[feature_cols].fillna(0.0)
-
-    scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-
-    models: Dict[int, Dict] = {}
-
-    for num in range(cfg.main_min, cfg.main_max + 1):
-        y = (sub[cfg.main_cols] == num).any(axis=1).astype(int)
-        if y.sum() < 4:
-            continue
-
-        try:
-            X_train, X_test, y_train, y_test = train_test_split(
-                X_scaled, y, test_size=0.2, random_state=42, stratify=y
-            )
-
-            rf = RandomForestClassifier(
-                n_estimators=120,
-                max_depth=7,
-                random_state=42,
-                class_weight="balanced",
-            )
-            et = ExtraTreesClassifier(
-                n_estimators=120,
-                max_depth=7,
-                random_state=42,
-                class_weight="balanced",
-            )
-            gb = GradientBoostingClassifier(
-                n_estimators=120,
-                max_depth=3,
-                learning_rate=0.08,
-                random_state=42,
-            )
-            if _HAS_XGB:
-                xgb = XGBClassifier(
-                    n_estimators=120,
-                    max_depth=3,
-                    learning_rate=0.08,
-                    subsample=0.9,
-                    colsample_bytree=0.9,
-                    eval_metric="logloss",
-                    random_state=42,
-                )
-            else:
-                xgb = XGBClassifier(
-                    n_estimators=120,
-                    max_depth=3,
-                    random_state=42,
-                )
-
-            mlp = MLPClassifier(
-                hidden_layer_sizes=(32, 16),
-                max_iter=600,
-                random_state=42,
-                alpha=0.0005,
-            )
-
-            ensemble = VotingClassifier(
-                estimators=[
-                    ("rf", rf),
-                    ("et", et),
-                    ("gb", gb),
-                    ("xgb", xgb),
-                    ("mlp", mlp),
-                ],
-                voting="soft",
-            )
-
-            ensemble.fit(X_train, y_train)
-            y_pred = ensemble.predict(X_test)
-            acc = accuracy_score(y_test, y_pred)
-
-            if acc >= 0.52:
-                models[num] = {
-                    "model": ensemble,
-                    "scaler": scaler,
-                    "feature_cols": feature_cols,
-                    "accuracy": acc,
-                }
-
-        except Exception:
-            continue
-
-    return models
-
-
-def build_multiwindow_ml(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    windows: List[int] = [20, 80, 400],
-) -> Dict[int, Dict[str, object]]:
-    """
-    Train ML models in multiple history windows and store them per number.
-    result[num] = {"short": {...}, "medium": {...}, "long": {...}}
-    """
-    models_by_window: Dict[int, Dict[str, object]] = {}
-
-    if len(df) < 40:
-        return {}
-
-    for w in windows:
-        label = "short" if w <= 20 else ("medium" if w <= 120 else "long")
-        mw = _build_window_ml_models(df, cfg, w)
-        for num, info in mw.items():
-            if num not in models_by_window:
-                models_by_window[num] = {}
-            models_by_window[num][label] = info
-
-    return models_by_window
-
-
-# ============================================================
-# Multi-agent per-number scoring (V5.2 + Gimme5 tuning)
-# ============================================================
-
-def compute_agent_scores(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    ml_models: Dict[int, Dict[str, object]],
-    freq_features: Dict[int, Dict[str, float]],
-) -> Dict[int, Dict[str, float]]:
-    """
-    Compute scores from multiple agents for each number:
-      - ml_agent
-      - hotcold_agent
-      - bayes_agent
-      - recency_agent
-      - rl_agent
-      - pattern_agent
-      - cluster_agent
-      - drift_agent
-      - parity_agent
-    """
-    scores: Dict[int, Dict[str, float]] = {}
-
-    df_struct = calculate_structural_features(df, cfg)
-    latest_feat = df_struct.iloc[[-1]].copy()
-
-    base_cols = [
-        "DayOfWeek",
-        "Month",
-        "sum_total",
-        "even_count",
-        "odd_count",
-        "range_span",
-        "consecutive_count",
-        "avg_gap",
-        "high_count",
-    ]
-    latest_feat = latest_feat.reindex(columns=base_cols, fill_value=0.0)
-
-    # Global stats for drift / cluster
-    sums = df[cfg.main_cols].sum(axis=1)
-    sum_mean = float(sums.mean())
-    sum_std = float(sums.std()) if sums.std() > 0 else 1.0
-
-    total_draws = len(df)
-
-    # Good draws mask for RL (sums near mean)
-    good_mask = (abs(sums - sum_mean) <= sum_std)
-    good_indices = df.index[good_mask]
-
-    # RL rewards
-    rl_rewards: Dict[int, float] = {}
-    for num in range(cfg.main_min, cfg.main_max + 1):
-        if total_draws <= 0:
-            rl_rewards[num] = 0.5
-            continue
-        good_hits = 0
-        for idx in good_indices:
-            if num in df.loc[idx, cfg.main_cols].values:
-                good_hits += 1
-        rl_rewards[num] = good_hits / max(len(good_indices), 1)
-
-    # Cluster agent: based on recent 40 draws, density in +/-2 window
-    recent_n = min(40, len(df))
-    recent = df.tail(recent_n) if recent_n > 0 else df
-    cluster_counts: Dict[int, float] = {}
-    if recent_n > 0:
-        all_recent_nums = recent[cfg.main_cols].values.flatten()
-        all_recent_nums = [int(v) for v in all_recent_nums if not pd.isna(v)]
-        hist = Counter(all_recent_nums)
-        for num in range(cfg.main_min, cfg.main_max + 1):
-            window_sum = 0
-            for k in range(num - 2, num + 3):
-                if cfg.main_min <= k <= cfg.main_max:
-                    window_sum += hist.get(k, 0)
-            cluster_counts[num] = window_sum
-        if cluster_counts:
-            max_cluster = max(cluster_counts.values()) or 1
-            for num in cluster_counts.keys():
-                cluster_counts[num] = cluster_counts[num] / max_cluster
-    else:
-        for num in range(cfg.main_min, cfg.main_max + 1):
-            cluster_counts[num] = 0.5
-
-    # Drift agent: compare recent sums vs older sums (20 vs 80)
-    recent_window = min(20, len(df))
-    mid_window = min(80, len(df))
-    if mid_window > recent_window >= 5:
-        recent_sums = sums.tail(recent_window)
-        older_sums = sums.tail(mid_window).head(mid_window - recent_window)
-        recent_mean = float(recent_sums.mean())
-        older_mean = float(older_sums.mean()) if len(older_sums) > 0 else recent_mean
-        if older_mean > 0:
-            drift_ratio = (recent_mean - older_mean) / older_mean
-        else:
-            drift_ratio = 0.0
-    else:
-        drift_ratio = 0.0
-
-    # Parity drift: even/odd balance in last 40 draws
-    if len(df) >= 10:
-        last_k = df.tail(min(40, len(df)))
-        even_counts = last_k[cfg.main_cols].apply(
-            lambda row: sum(1 for v in row if v % 2 == 0), axis=1
-        )
-        even_mean_recent = float(even_counts.mean())
-        expected_even = len(cfg.main_cols) / 2.0
-        parity_delta = even_mean_recent - expected_even
-    else:
-        parity_delta = 0.0
-
-    # Pre-calc uniform position mapping for drift
-    span = cfg.main_max - cfg.main_min if cfg.main_max > cfg.main_min else 1
-
-    # Is this Gimme5? (name is "Gimme 5")
-    is_gimme5 = cfg.name.lower().startswith("gimme")
-
-    for num in range(cfg.main_min, cfg.main_max + 1):
-        scores[num] = {}
-
-        # ML agent
-        ml_score = 0.5
-        if num in ml_models:
-            cfg_models = ml_models[num]
-            probs = []
-            weights = []
-            for label, info in cfg_models.items():
-                model = info["model"]
-                scaler = info["scaler"]
-                feature_cols = info["feature_cols"]
-                X_latest = latest_feat[feature_cols].fillna(0.0)
-                X_scaled = scaler.transform(X_latest)
-                if hasattr(model, "predict_proba"):
-                    p = model.predict_proba(X_scaled)[0][1]
-                else:
-                    p = 0.5
-                probs.append(p)
-                # V5.2: Gimme5 → stronger short-window weighting
-                if is_gimme5:
-                    if label == "short":
-                        weights.append(0.6)
-                    elif label == "medium":
-                        weights.append(0.25)
-                    else:
-                        weights.append(0.15)
-                else:
-                    if label == "short":
-                        weights.append(0.5)
-                    elif label == "medium":
-                        weights.append(0.3)
-                    else:
-                        weights.append(0.2)
-            if probs:
-                p_arr = np.array(probs)
-                w_arr = np.array(weights)
-                ml_score = float((p_arr * w_arr).sum() / w_arr.sum())
-        scores[num]["ml_agent"] = float(np.clip(ml_score, 0.0, 1.0))
-
-        # Hot/cold agent
-        fdata = freq_features[num]
-        f_20 = fdata.get("freq_20", 0.0)
-        f_80 = fdata.get("freq_80", 0.0)
-        f_400 = fdata.get("freq_400", fdata.get("overall_freq", 0.0))
-        hot_score = 0.5 * f_20 + 0.3 * f_80 + 0.2 * f_400
-        scores[num]["hotcold_agent"] = float(np.clip(hot_score * 5.0, 0.0, 1.0))
-
-        # Bayesian agent
-        hits = (df[cfg.main_cols] == num).sum().sum()
-        bayes_mean = (hits + 1.0) / (total_draws + 2.0)
-        scores[num]["bayes_agent"] = float(np.clip(bayes_mean * 8.0, 0.0, 1.0))
-
-        # Recency agent
-        days_since_last = fdata.get("days_since_last", float(total_draws))
-        recency_score = 1.0 / (1.0 + 0.08 * days_since_last)
-        scores[num]["recency_agent"] = float(np.clip(recency_score, 0.0, 1.0))
-
-        # RL agent
-        rl_raw = rl_rewards[num]
-        scores[num]["rl_agent"] = float(np.clip(rl_raw * 5.0, 0.0, 1.0))
-
-        # Pattern agent: how well this number participates in "good" patterns
-        pattern_hits = 0
-        pattern_total = 0
-        for idx in range(total_draws):
-            row_nums = df.loc[idx, cfg.main_cols].values
-            if num not in row_nums:
-                continue
-            row_sum = row_nums.sum()
-            even_cnt = sum(1 for v in row_nums if v % 2 == 0)
-            in_range = (cfg.sum_min <= row_sum <= cfg.sum_max)
-            balanced = even_cnt in (2, 3)
-            if in_range and balanced:
-                pattern_hits += 1
-            pattern_total += 1
-        pattern_score = (pattern_hits / pattern_total) if pattern_total > 0 else 0.5
-        scores[num]["pattern_agent"] = float(np.clip(pattern_score, 0.0, 1.0))
-
-        # Cluster agent (recent density in +/-2 around num)
-        scores[num]["cluster_agent"] = float(
-            np.clip(cluster_counts.get(num, 0.5), 0.0, 1.0)
-        )
-
-        # Drift agent: if sums drifting lower, prefer low; if higher, prefer high
-        if drift_ratio < -0.03:  # trending lower
-            pos = (num - cfg.main_min) / span
-            drift_score = 1.0 - pos  # low numbers ~1, high ~0
-        elif drift_ratio > 0.03:  # trending higher
-            pos = (num - cfg.main_min) / span
-            drift_score = pos  # high numbers ~1, low ~0
-        else:
-            drift_score = 0.5
-        scores[num]["drift_agent"] = float(np.clip(drift_score, 0.0, 1.0))
-
-        # Parity drift agent: favor even or odd depending on recent imbalance
-        if abs(parity_delta) < 0.2:
-            parity_score = 0.5
-        else:
-            is_even = (num % 2 == 0)
-            if parity_delta > 0:  # more evens recently
-                parity_score = 0.8 if is_even else 0.2
-            else:  # more odds recently
-                parity_score = 0.8 if not is_even else 0.2
-        scores[num]["parity_agent"] = float(np.clip(parity_score, 0.0, 1.0))
-
-    # Normalize each agent across all numbers (0..1)
-    if scores:
-        agent_names = list(next(iter(scores.values())).keys())
-        for agent in agent_names:
-            vals = np.array([scores[n][agent] for n in scores.keys()])
-            vmin, vmax = vals.min(), vals.max()
-            if vmax > vmin:
-                for n in scores.keys():
-                    scores[n][agent] = float(
-                        (scores[n][agent] - vmin) / (vmax - vmin)
-                    )
-            else:
-                for n in scores.keys():
-                    scores[n][agent] = 0.5
-
-    return scores
-
-
-def combine_agent_scores(
-    agent_scores: Dict[int, Dict[str, float]],
-    cfg: GameConfig,
-) -> Dict[int, float]:
-    """
-    Combine multi-agent scores into a single score per number.
-    V5.2: uses a different profile for Gimme5 vs other games.
-    """
-    is_gimme5 = cfg.name.lower().startswith("gimme")
-
-    if is_gimme5:
-        # Gimme5: faster game, lean more on short-window / recency / clusters
-        weights = {
-            "ml_agent":      0.20,
-            "hotcold_agent": 0.20,
-            "bayes_agent":   0.10,
-            "recency_agent": 0.15,
-            "rl_agent":      0.10,
-            "pattern_agent": 0.05,
-            "cluster_agent": 0.12,
-            "drift_agent":   0.04,
-            "parity_agent":  0.04,
-        }
-    else:
-        # Other games: more balanced
-        weights = {
-            "ml_agent":      0.25,
-            "hotcold_agent": 0.18,
-            "bayes_agent":   0.12,
-            "recency_agent": 0.08,
-            "rl_agent":      0.12,
-            "pattern_agent": 0.08,
-            "cluster_agent": 0.08,
-            "drift_agent":   0.05,
-            "parity_agent":  0.04,
-        }
-
-    final_scores: Dict[int, float] = {}
-    for num, agents in agent_scores.items():
-        total = 0.0
-        for name, w in weights.items():
-            total += w * agents.get(name, 0.5)
-        final_scores[num] = float(total)
-
-    if final_scores:
-        vals = np.array(list(final_scores.values()))
-        vmin, vmax = vals.min(), vals.max()
-        if vmax > vmin:
-            for n in final_scores.keys():
-                final_scores[n] = float((final_scores[n] - vmin) / (vmax - vmin))
-        else:
-            for n in final_scores.keys():
-                final_scores[n] = 0.5
-
-    return final_scores
-
-
-# ============================================================
-# Combination scoring & generation
-# ============================================================
-
-def score_combo_pattern(
-    combo: List[int],
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    style: str = "balanced",
-) -> float:
-    """
-    Score a candidate combination:
-    - Sum vs history & config
-    - Even/odd mix
-    - Range & gaps
-    plus style-specific tweaks for multi-style GOD MODE.
-    """
-    combo = sorted(combo)
-    score = 0.0
-
-    sums = df[cfg.main_cols].sum(axis=1)
-    sum_mean = float(sums.mean())
-    sum_std = float(sums.std()) if sums.std() > 0 else 1.0
-
-    combo_sum = sum(combo)
-    if cfg.sum_min <= combo_sum <= cfg.sum_max:
-        score += 1.0
-        z = abs(combo_sum - sum_mean) / sum_std
-        score += max(0.0, 1.5 - z)
-    else:
-        score -= 1.0
-
-    even_count = sum(1 for v in combo if v % 2 == 0)
-    if even_count in (2, 3):
-        score += 1.0
-    elif even_count in (1, 4):
-        score += 0.2
-    else:
-        score -= 0.5
-
-    combo_range = max(combo) - min(combo)
-    hist_range = df[cfg.main_cols].max(axis=1) - df[cfg.main_cols].min(axis=1)
-    mean_r = float(hist_range.mean()) if len(hist_range) > 0 else combo_range
-    if mean_r > 0:
-        diff = abs(combo_range - mean_r) / mean_r
-        if diff < 0.3:
-            score += 0.7
-        elif diff < 0.6:
-            score += 0.2
-        else:
-            score -= 0.2
-
-    gaps = [combo[i + 1] - combo[i] for i in range(len(combo) - 1)]
-    avg_gap = float(np.mean(gaps)) if gaps else 0.0
-
-    midpoint = (cfg.main_min + cfg.main_max) / 2.0
-    low_count = sum(1 for v in combo if v <= midpoint)
-    high_count = len(combo) - low_count
-
-    if style == "low_cluster":
-        if low_count >= 3:
-            score += 0.7
-        if combo_range <= (cfg.main_max - cfg.main_min) * 0.5:
-            score += 0.3
-    elif style == "high_cluster":
-        if high_count >= 3:
-            score += 0.7
-        if combo_range <= (cfg.main_max - cfg.main_min) * 0.5:
-            score += 0.3
-    elif style == "tight_cluster":
-        if combo_range <= (cfg.main_max - cfg.main_min) * 0.4:
-            score += 0.8
-        if avg_gap <= 8:
-            score += 0.4
-    elif style == "wide_spread":
-        if combo_range >= (cfg.main_max - cfg.main_min) * 0.6:
-            score += 0.8
-        if avg_gap >= 6:
-            score += 0.4
-    elif style == "top_cluster":
-        # Reward combos staying fairly central and not too extreme
-        if combo_range <= (cfg.main_max - cfg.main_min) * 0.6:
-            score += 0.5
-        if avg_gap <= 10:
-            score += 0.3
-
-    return score
-
-
-def generate_godmode_combo(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    final_scores: Dict[int, float],
-    banned_nums: Optional[set] = None,
-    n_candidates: int = 6000,
-    style: str = "balanced",
-) -> Tuple[List[int], float]:
-    """
-    Monte Carlo search for best combination for a given style.
-    style ∈ {"balanced", "low_cluster", "high_cluster", "tight_cluster", "wide_spread", "top_cluster"}
-    (for "top_cluster" a separate helper is usually used, but style is kept
-    here for consistency).
-    """
-    if banned_nums is None:
-        banned_nums = set()
-
-    filtered_scores = {n: s for n, s in final_scores.items() if n not in banned_nums}
-    if not filtered_scores:
-        filtered_scores = final_scores.copy()
-
-    numbers = list(filtered_scores.keys())
-    weights = np.array(list(filtered_scores.values()), dtype=float)
-    if weights.sum() <= 0:
-        weights = np.ones_like(weights)
-    weights /= weights.sum()
-
-    best_combo: Optional[List[int]] = None
-    best_score = -1e9
-
-    for _ in range(n_candidates):
-        combo = list(
-            np.random.choice(numbers, size=len(cfg.main_cols), replace=False, p=weights)
-        )
-        combo.sort()
-        pat_score = score_combo_pattern(combo, df, cfg, style=style)
-        synergy = float(np.mean([filtered_scores[n] for n in combo]))
-        total_score = pat_score + synergy * 2.0
-        if total_score > best_score:
-            best_score = total_score
-            best_combo = combo
-
-    if best_combo is None:
-        best_combo = sorted(
-            np.random.choice(numbers, size=len(cfg.main_cols), replace=False).tolist()
-        )
-
-    return best_combo, float(best_score)
-
-
-def generate_top_cluster_combo(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    final_scores: Dict[int, float],
-    banned_nums: Optional[set] = None,
-    top_n_core: int = 3,
-    n_candidates: int = 3000,
-) -> Tuple[List[int], float]:
-    """
-    Hyper-focused combo that forces top K highest-score numbers together
-    in a single line, then fills the remaining spots with other strong numbers.
-    """
-    if banned_nums is None:
-        banned_nums = set()
-
-    sorted_nums = sorted(
-        ((n, s) for n, s in final_scores.items() if n not in banned_nums),
-        key=lambda kv: kv[1],
-        reverse=True,
-    )
-    if not sorted_nums:
-        sorted_nums = sorted(final_scores.items(), key=lambda kv: kv[1], reverse=True)
-
-    core = [n for n, _ in sorted_nums[:top_n_core]]
-    core = core[: len(cfg.main_cols)]  # safety
-
-    remaining_pool = [n for n, _ in sorted_nums if n not in core]
-    if len(remaining_pool) < (len(cfg.main_cols) - len(core)):
-        # not enough left, just fall back
-        return generate_godmode_combo(
-            df, cfg, final_scores, banned_nums=banned_nums, n_candidates=n_candidates, style="top_cluster"
-        )
-
-    remaining_weights = np.array([final_scores[n] for n in remaining_pool], dtype=float)
-    if remaining_weights.sum() <= 0:
-        remaining_weights = np.ones_like(remaining_weights)
-    remaining_weights /= remaining_weights.sum()
-
-    best_combo: Optional[List[int]] = None
-    best_score = -1e9
-
-    needed = len(cfg.main_cols) - len(core)
-
-    for _ in range(n_candidates):
-        support = list(
-            np.random.choice(
-                remaining_pool,
-                size=needed,
-                replace=False,
-                p=remaining_weights,
-            )
-        )
-        combo = sorted(core + support)
-        pat_score = score_combo_pattern(combo, df, cfg, style="top_cluster")
-        synergy = float(np.mean([final_scores[n] for n in combo]))
-        total_score = pat_score + synergy * 2.0
-        if total_score > best_score:
-            best_score = total_score
-            best_combo = combo
-
-    if best_combo is None:
-        # extreme fallback
-        return generate_godmode_combo(
-            df, cfg, final_scores, banned_nums=banned_nums, n_candidates=n_candidates, style="top_cluster"
-        )
-
-    return best_combo, float(best_score)
-
-
-def _compute_sum_regime_and_trend(df: pd.DataFrame, cfg: GameConfig) -> Dict[str, object]:
-    """
-    Analyze recent sums to detect:
-      - volatility regime: low / flat / high
-      - short-term trend: high_run / low_run / none
-    """
-    sums = df[cfg.main_cols].sum(axis=1)
-    if len(sums) == 0:
-        return {
-            "regime": "unknown",
-            "volatility": 0.0,
-            "trend": "none",
-            "mean": 0.0,
-            "std": 1.0,
-        }
-
-    recent = sums.tail(40) if len(sums) > 40 else sums
-    mean = float(recent.mean())
-    std = float(recent.std()) if recent.std() > 0 else 1.0
-
-    z = (recent - mean) / std
-    vol = float(np.mean(np.abs(z)))
-
-    if vol < 0.8:
-        regime = "low"
-    elif vol > 1.2:
-        regime = "high"
-    else:
-        regime = "flat"
-
-    last_k = min(6, len(recent))
-    tail = recent.tail(last_k)
-    hi_th = mean + 0.5 * std
-    lo_th = mean - 0.5 * std
-
-    last3 = tail.tail(3)
-    if all(v > hi_th for v in last3):
-        trend = "high_run"
-    elif all(v < lo_th for v in last3):
-        trend = "low_run"
-    else:
-        trend = "none"
-
-    return {
-        "regime": regime,
-        "volatility": vol,
-        "trend": trend,
-        "mean": mean,
-        "std": std,
-    }
-
-
-def _compute_coldness(df: pd.DataFrame, cfg: GameConfig) -> Dict[int, float]:
-    """
-    Coldness score per number in [0,1], where 1 = very cold, 0 = very hot.
-    """
-    all_nums = df[cfg.main_cols].values.flatten()
-    all_nums = [int(v) for v in all_nums if not pd.isna(v)]
-    if not all_nums:
-        return {n: 0.5 for n in range(cfg.main_min, cfg.main_max + 1)}
-
-    freq = Counter(all_nums)
-    values = list(freq.values())
-    if not values:
-        return {n: 0.5 for n in range(cfg.main_min, cfg.main_max + 1)}
-
-    f_min = min(values)
-    f_max = max(values)
-    denom = max(f_max - f_min, 1)
-
-    coldness: Dict[int, float] = {}
-    for n in range(cfg.main_min, cfg.main_max + 1):
-        f = freq.get(n, 0)
-        cold = (f_max - f) / denom  # high when f is small
-        coldness[n] = float(np.clip(cold, 0.0, 1.0))
-    return coldness
-
-
-def _adjust_scores_v5_3(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    base_scores: Dict[int, float],
-) -> Tuple[Dict[int, float], Dict[str, object], Dict[int, float]]:
-    """
-    V5.3 ULTRA correction layer:
-      1) Dynamic regime detection (low/flat/high volatility).
-      2) Low-zone boost (roughly bottom 1/3rd of the range).
-      3) Inverse-trend feature (reversal agent).
-      4) Cold-burst: slight boost to colder numbers, dampen over-hot.
-      5) Mega Millions specific high-band refinements.
-      6) Lotto America specific main-range tweaks + neighbor-chaser.
-      7) Megabucks specific main-range tweaks.
-      8) Powerball specific main-range tweaks.
-      9) Lucky for Life specific main-range tweaks + neighbor-chaser for mids.
-     10) Gimme 5 neighbor-chaser with micro-boost around recent hot core numbers.
-    Returns:
-      adjusted_scores, regime_info, coldness_map
-    """
-    if not base_scores:
-        return base_scores, {"regime": "unknown"}, {
-            n: 0.5 for n in range(cfg.main_min, cfg.main_max + 1)
-        }
-
-    regime_info = _compute_sum_regime_and_trend(df, cfg)
-    regime = regime_info.get("regime", "flat")
-    trend = regime_info.get("trend", "none")
-
-    span = max(cfg.main_max - cfg.main_min, 1)
-    mid = cfg.main_min + span / 2.0
-    low_cut = cfg.main_min + int(span * 0.33)
-    regime_info["low_zone_cut"] = low_cut
-
-    coldness = _compute_coldness(df, cfg)
-
-    vals = np.array(list(base_scores.values()), dtype=float)
-    vmin, vmax = float(vals.min()), float(vals.max())
-    norm_scores: Dict[int, float] = {}
-    if vmax > vmin:
-        for n, s in base_scores.items():
-            norm_scores[n] = float((s - vmin) / (vmax - vmin))
-    else:
-        for n in base_scores.keys():
-            norm_scores[n] = 0.5
-
-    # Lucky for Life neighbor-chaser: identify recent hot mids (11–38)
-    l4l_hot_mids: set = set()
-    if cfg.name == "Lucky for Life":
-        recent_draws = df[cfg.main_cols].tail(30)
-        vals_mid = recent_draws.values.flatten()
-        mids = [
-            int(v)
-            for v in vals_mid
-            if not pd.isna(v) and 11 <= int(v) <= 38
-        ]
-        if mids:
-            freq_mid = Counter(mids)
-            l4l_hot_mids = {
-                n for n, _ in sorted(
-                    freq_mid.items(), key=lambda kv: kv[1], reverse=True
-                )[:6]
-            }
-
-    # Gimme 5 neighbor-chaser: identify recent hot core numbers (5–35)
-    g5_hot_core: set = set()
-    if cfg.name == "Gimme 5":
-        recent_g5 = df[cfg.main_cols].tail(25)
-        vals_g = recent_g5.values.flatten()
-        gnums = [int(v) for v in vals_g if not pd.isna(v)]
-        if gnums:
-            freq_g = Counter(gnums)
-            ordered = sorted(freq_g.items(), key=lambda kv: kv[1], reverse=True)
-            core_list: List[int] = []
-            for n, _ in ordered:
-                if 5 <= n <= 35:
-                    core_list.append(n)
-                if len(core_list) >= 6:
-                    break
-            g5_hot_core = set(core_list)
-
-    # Lotto America neighbor-chaser: identify recent hot core band numbers (15–45)
-    la_hot_core: set = set()
-    if cfg.name == "Lotto America":
-        recent_la = df[cfg.main_cols].tail(30)
-        vals_la = recent_la.values.flatten()
-        lans = [int(v) for v in vals_la if not pd.isna(v)]
-        if lans:
-            freq_la = Counter(lans)
-            ordered_la = sorted(
-                freq_la.items(), key=lambda kv: kv[1], reverse=True
-            )
-            core_la: List[int] = []
-            for n, _ in ordered_la:
-                if 15 <= n <= 45:
-                    core_la.append(n)
-                if len(core_la) >= 6:
-                    break
-            la_hot_core = set(core_la)
-
-    adjusted: Dict[int, float] = {}
-    for n, s in norm_scores.items():
-        m = 1.0
-        pos = (n - cfg.main_min) / span
-        in_low_zone = n <= low_cut
-
-        # Low-zone boost
-        if in_low_zone:
-            m *= 1.18  # low-zone probability boost
-
-        # Regime-specific tweaks
-        if regime == "high":
-            if s > 0.7:
-                m *= 0.92
-            elif s < 0.4:
-                m *= 1.08
-        elif regime == "low":
-            if s > 0.7:
-                m *= 1.05
-            elif s < 0.3:
-                m *= 0.90
-        else:
-            if s > 0.8:
-                m *= 0.97
-            elif s < 0.2:
-                m *= 1.03
-
-        # Trend inversion: favor reversal side a bit
-        if trend == "high_run":
-            if n <= mid:
-                m *= 1.10
-            else:
-                m *= 0.90
-        elif trend == "low_run":
-            if n >= mid:
-                m *= 1.10
-            else:
-                m *= 0.90
-
-        # Cold-burst factor
-        c = coldness.get(n, 0.5)
-        if regime == "high":
-            m *= (1.0 + 0.25 * c)
-        else:
-            m *= (1.0 + 0.15 * c)
-
-        # Mega Millions specific high-band refinements
-        if cfg.name == "Mega Millions":
-            # Boost 34–36 band
-            if 34 <= n <= 36:
-                m *= 1.06
-            # Boost 37–39 ridge
-            if 37 <= n <= 39:
-                m *= 1.05
-            # Soften extreme high cooling 65+ so 69-style hits are not suppressed
-            if n >= 65:
-                m *= 1.03
-
-        # Lotto America specific main-range tweaks (V5.3 ULTRA + neighbor-chaser)
-        if cfg.name == "Lotto America":
-            # Slight boost to mid-band 20–40
-            if 20 <= n <= 40:
-                m *= 1.04
-            # Mild damp on extreme ends to avoid overshooting
-            if n <= 5 or n >= 50:
-                m *= 0.96
-            # Tiny neighbor-chaser boost: ±1 around recent hot core numbers
-            if la_hot_core:
-                if (n - 1 in la_hot_core) or (n + 1 in la_hot_core):
-                    m *= 1.03
-
-        # Megabucks specific main-range tweaks (V5.3 ULTRA)
-        if cfg.name == "Megabucks":
-            # Slight boost to mid-band 18–32 (common MB hit zone)
-            if 18 <= n <= 32:
-                m *= 1.04
-            # Soft boost for upper range 35–41 so high numbers like 41 don't get over-cooled
-            if 35 <= n <= 41:
-                m *= 1.03
-            # Mild dampening on ultra-low extremes 1–3
-            if n <= 3:
-                m *= 0.96
-
-        # Powerball specific main-range tweaks (V5.3 ULTRA)
-        if cfg.name == "Powerball":
-            # Slight boost to core mid-band 20–45 (heavy PB activity zone)
-            if 20 <= n <= 45:
-                m *= 1.04
-            # Soft support for secondary band 10–19 and 46–59
-            if (10 <= n <= 19) or (46 <= n <= 59):
-                m *= 1.02
-            # Mild dampening on extreme ends 1–3 and 65–69
-            if n <= 3 or n >= 65:
-                m *= 0.96
-
-        # Lucky for Life specific main-range tweaks (V5.3 ULTRA, stronger + neighbor-chaser)
-        if cfg.name == "Lucky for Life":
-            # Stronger boost to core central band 14–36 where many hits cluster
-            if 14 <= n <= 36:
-                m *= 1.06
-            # Secondary soft support for broader mid band 11–38
-            if 11 <= n <= 38:
-                m *= 1.02
-            # Slightly stronger dampening on outer extremes 1–4 and 45–48
-            if n <= 4 or n >= 45:
-                m *= 0.95
-            # Tiny neighbor-chaser boost: ±1 around recent hot mids
-            if l4l_hot_mids:
-                if (n - 1 in l4l_hot_mids) or (n + 1 in l4l_hot_mids):
-                    m *= 1.03  # ~3% nudge, just enough to surface neighbors
-
-        # Gimme 5 neighbor-chaser with micro-boost: tiny nudge around recent hot core numbers
-        if cfg.name == "Gimme 5" and g5_hot_core:
-            if (n - 1 in g5_hot_core) or (n + 1 in g5_hot_core):
-                m *= 1.05  # micro-boosted neighbor effect
-
-        adjusted[n] = float(max(m * s, 0.0))
-
-    vals = np.array(list(adjusted.values()), dtype=float)
-    vmin, vmax = float(vals.min()), float(vals.max())
-    if vmax > vmin:
-        for n in adjusted.keys():
-            adjusted[n] = float((adjusted[n] - vmin) / (vmax - vmin))
-    else:
-        for n in adjusted.keys():
-            adjusted[n] = 0.5
-
-    return adjusted, regime_info, coldness
-
-
-def pick_star_ball(df: pd.DataFrame, cfg: GameConfig) -> Optional[int]:
-    """
-    V5.3.1 Mega / bonus ball picker.
-
-    Improvements over V5.2:
-    - Uses all-time + medium-term + short-term frequencies.
-    - Adds a cold-burst factor (prefer colder balls slightly).
-    - Favors low-zone bonus numbers a bit more (good for Mega Millions MB 1–12).
-    - Respects cfg.star_min / cfg.star_max for all games.
-    - Lotto America: extra boost for SB 1–5.
-    - Powerball: mild preference for PB 1–15.
-    - Lucky for Life: mild mid-band Lucky Ball tilt (7–15).
-    """
-    if not cfg.star_col:
-        return None
-
-    df = df.copy()
-    df[cfg.star_col] = pd.to_numeric(df[cfg.star_col], errors="coerce")
-    df = df.dropna(subset=[cfg.star_col])
-    if df.empty:
-        return None
-
-    series = df[cfg.star_col].astype(int)
-    freq_all = Counter(series)
-
-    recent_med = series.tail(40) if len(series) > 40 else series
-    freq_med = Counter(recent_med)
-
-    recent_short = series.tail(15) if len(series) > 15 else series
-    freq_short = Counter(recent_short)
-
-    # Build base weights from multiple horizons
-    weights: Dict[int, float] = {}
-    all_vals = []
-    for s in range(cfg.star_min, cfg.star_max + 1):
-        w = (
-            0.50 * freq_med.get(s, 0)
-            + 0.30 * freq_all.get(s, 0)
-            + 0.20 * freq_short.get(s, 0)
-        )
-        weights[s] = float(w)
-        all_vals.append(w)
-
-    # Avoid degenerate case
-    if not all_vals or max(all_vals) == 0:
-        return int(random.randint(cfg.star_min, cfg.star_max))
-
-    # Coldness (for cold-burst boosting)
-    vals = [freq_all.get(s, 0) for s in range(cfg.star_min, cfg.star_max + 1)]
-    f_min, f_max = min(vals), max(vals)
-    denom = max(f_max - f_min, 1)
-    coldness: Dict[int, float] = {}
-    for s in range(cfg.star_min, cfg.star_max + 1):
-        f = freq_all.get(s, 0)
-        cold = (f_max - f) / denom  # high when f is small
-        coldness[s] = float(np.clip(cold, 0.0, 1.0))
-
-    # Low-zone boost (e.g., MB 1–12)
-    span = cfg.star_max - cfg.star_min
-    low_cut = cfg.star_min + int(span * 0.5)  # bottom half considered "low zone"
-
-    adjusted: Dict[int, float] = {}
-    for s in range(cfg.star_min, cfg.star_max + 1):
-        base = weights.get(s, 0.0)
-        c = coldness.get(s, 0.5)
-        m = 1.0
-
-        # Low-zone preference
-        if s <= low_cut:
-            m *= 1.12  # +12% for low-zone stars
-
-        # Lotto America: extra preference for SB 1–5
-        if cfg.name == "Lotto America" and s <= 5:
-            m *= 1.08
-
-        # Powerball: mild preference for PB 1–15 zone
-        if cfg.name == "Powerball" and s <= 15:
-            m *= 1.05
-
-        # Lucky for Life: mid-band preference for Lucky Ball 7–15
-        if cfg.name == "Lucky for Life" and 7 <= s <= 15:
-            m *= 1.05
-
-        # Cold-burst
-        m *= (1.0 + 0.25 * c)  # up to +25% for very cold bonus balls
-
-        adjusted[s] = max(base * m, 0.0)
-
-    # Normalize to probabilities
-    stars = list(adjusted.keys())
-    wts = [adjusted[s] for s in stars]
-    total = float(sum(wts))
-    if total <= 0:
-        return int(random.randint(cfg.star_min, cfg.star_max))
-
-    probs = [w / total for w in wts]
-    choice = int(np.random.choice(stars, p=probs))
-    return choice
-
-
-# ============================================================
-# Last-4 repeater ban rule (your custom rule)
-# ============================================================
-
-def get_last4_repeater_ban(df: pd.DataFrame, cfg: GameConfig) -> set:
-    """
-    Your rule:
-    - Look at the most recent 4 draws.
-    - If a number appears in EACH of those 4 draws,
-      it is banned from prediction.
-    - We do NOT ban all numbers that just appeared once or twice.
-    """
-    if len(df) < 4:
-        return set()
-
-    last4 = df[cfg.main_cols].tail(4).values
-    cnt = Counter()
-    for row in last4:
-        unique_nums = {int(v) for v in row if not pd.isna(v)}
-        for n in unique_nums:
-            cnt[n] += 1
-
-    banned = {n for n, c in cnt.items() if c == 4}
-    return banned
-
-
-# ============================================================
-# GOD MODE V5.3 prediction (multi-style, including top_cluster)
-# ============================================================
-
-def generate_prediction_v4_god(  # name kept for compatibility
-    raw_df: pd.DataFrame,
-    cfg: GameConfig,
-) -> Dict[str, object]:
-    """
-    Main GOD MODE engine (V5.3.1 ULTRA behavior on top of V5.2).
-    - Builds multi-window ML models
-    - Computes multi-agent scores (including cluster/drift/parity)
-    - Applies last-4 repeater ban (your consecutive rule)
-    - Applies V5.3.1 corrections:
-        * regime detection (low/flat/high)
-        * low-zone boost
-        * inverse trend correction
-        * cold-burst correction
-        * anti-lock rule (prevent over-using same number across sets)
-        * coverage optimizer across the 5–6 styles
-    - Generates styled combos:
-        top_cluster, balanced, low_cluster, high_cluster, tight_cluster, wide_spread
-    """
-    df = _ensure_datetime(raw_df, cfg.csv_date_col)
-    if cfg.clean_func and cfg.clean_func in globals():
-        df = globals()[cfg.clean_func](df)
-
-    if len(df) < 40:
-        raise ValueError("Insufficient history (<40 draws) for GOD-MODE engine.")
-
-    df_long = _limit_history(df, 400)
-
-    # Core multi-window ML + agent scoring
-    ml_models = build_multiwindow_ml(df_long, cfg, windows=[20, 80, 400])
-    freq_features = create_frequency_features(df_long, cfg, windows=[20, 80, 400])
-    agent_scores = compute_agent_scores(df_long, cfg, ml_models, freq_features)
-
-    base_scores = combine_agent_scores(agent_scores, cfg)
-
-    # V5.3.1 correction layer (regime, low-zone, inverse trend, cold-burst)
-    final_scores, regime_info, coldness = _adjust_scores_v5_3(df_long, cfg, base_scores)
-
-    # Last-4 repeater ban (your rule)
-    banned_nums = get_last4_repeater_ban(df_long, cfg)
-
-    god_sets: List[Dict[str, object]] = []
-    usage_counts: Counter = Counter()  # track usage across all styles
-
-    def _make_style_scores(style_name: str, scores: Dict[int, float]) -> Dict[int, float]:
-        """
-        Per-style adjustment:
-        - Anti-lock rule (cap over-used numbers).
-        - Extra cold-burst compensation if a lock is happening.
-        - Micro-clustering: boost neighbors of strong numbers a bit.
-        """
-        adjusted_style: Dict[int, float] = {}
-        # Detect whether any number has been used twice already
-        max_used = max(usage_counts.values()) if usage_counts else 0
-        lock_phase = (max_used >= 2)
-
-        # Precompute which numbers are "strong" for micro-clustering
-        vals = np.array(list(scores.values()), dtype=float)
-        if vals.size == 0:
-            return scores
-        vmin, vmax = float(vals.min()), float(vals.max())
-        thresh = vmin + 0.75 * (vmax - vmin) if vmax > vmin else vmin
-        strong_numbers = {n for n, s in scores.items() if s >= thresh}
-
-        for n, s in scores.items():
-            m = 1.0
-            used = usage_counts.get(n, 0)
-
-            # Anti-lock across sets
-            if used >= 2:
-                m *= 0.25
-            elif used == 1:
-                m *= 0.65
-
-            # Extra cold compensation in lock phase
-            if lock_phase:
-                c = coldness.get(n, 0.5)
-                m *= (1.0 + 0.40 * c)
-
-            # Micro-clustering: if this number neighbors a strong number, give it a nudge
-            if (n - 1 in strong_numbers) or (n + 1 in strong_numbers):
-                m *= 1.08
-
-            adjusted_style[n] = max(m * s, 0.0)
-
-        # Normalize to [0,1]
-        vals = np.array(list(adjusted_style.values()), dtype=float)
-        if vals.size == 0:
-            return scores
-        vmin, vmax = float(vals.min()), float(vals.max())
-        if vmax > vmin:
-            for k in adjusted_style.keys():
-                adjusted_style[k] = float((adjusted_style[k] - vmin) / (vmax - vmin))
-        else:
-            for k in adjusted_style.keys():
-                adjusted_style[k] = 0.5
-
-        return adjusted_style
-
-    # 1) TOP-CLUSTER combo: force highest-score core together
-    top_combo, top_score = generate_top_cluster_combo(
-        df_long,
-        cfg,
-        final_scores,
-        banned_nums=banned_nums,
-        top_n_core=3,
-        n_candidates=3000,
-    )
-    top_star = pick_star_ball(df_long, cfg)
-    god_sets.append(
-        {
-            "style": "top_cluster",
-            "numbers": [int(x) for x in sorted(top_combo)],
-            "star": int(top_star) if top_star is not None else None,
-            "score": float(top_score),
-        }
-    )
-    usage_counts.update(int(x) for x in top_combo)
-
-    # 2) Other main styles
-    styles = [
-        "balanced",
-        "low_cluster",
-        "high_cluster",
-        "tight_cluster",
-        "wide_spread",
-    ]
-
-    for style in styles:
-        style_scores = _make_style_scores(style, final_scores)
-        combo, combo_score = generate_godmode_combo(
-            df_long,
-            cfg,
-            style_scores,
-            banned_nums=banned_nums,
-            n_candidates=4000,
-            style=style,
-        )
-        star = pick_star_ball(df_long, cfg)
-        god_sets.append(
-            {
-                "style": style,
-                "numbers": [int(x) for x in sorted(combo)],
-                "star": int(star) if star is not None else None,
-                "score": float(combo_score),
-            }
-        )
-        usage_counts.update(int(x) for x in combo)
-
-    # Coverage optimizer: adjust last 1–2 sets if coverage is weak
-    if len(god_sets) >= 4:
-        # Compute global coverage & high-score candidates
-        all_used = set()
-        for s in god_sets:
-            all_used.update(int(x) for x in s["numbers"])
-
-        # Target extra numbers: high-score but not yet used
-        sorted_nums = sorted(final_scores.items(), key=lambda kv: kv[1], reverse=True)
-        coverage_targets = [int(n) for n, sc in sorted_nums if int(n) not in all_used][:15]
-
-        def _rebuild_for_coverage(style_name: str, base_scores: Dict[int, float]) -> Tuple[List[int], float]:
-            coverage_scores: Dict[int, float] = {}
-            for n, s in base_scores.items():
-                m = 1.0
-                if n in coverage_targets:
-                    m *= 1.25  # strong push for uncovered high-score numbers
-                # small micro-cluster around coverage targets
-                if (n - 1 in coverage_targets) or (n + 1 in coverage_targets):
-                    m *= 1.08
-                coverage_scores[n] = max(m * s, 0.0)
-
-            vals = np.array(list(coverage_scores.values()), dtype=float)
-            if vals.size == 0:
-                coverage_scores = base_scores
-            else:
-                vmin, vmax = float(vals.min()), float(vals.max())
-                if vmax > vmin:
-                    for k in coverage_scores.keys():
-                        coverage_scores[k] = float((coverage_scores[k] - vmin) / (vmax - vmin))
-                else:
-                    coverage_scores[k] = 0.5
-
-            combo, score = generate_godmode_combo(
-                df_long,
-                cfg,
-                coverage_scores,
-                banned_nums=banned_nums,
-                n_candidates=4000,
-                style=style_name,
-            )
-            return [int(x) for x in sorted(combo)], float(score)
-
-        # Rebuild last 1–2 styles for better coverage (usually tight_cluster & wide_spread)
-        for idx in range(len(god_sets) - 2, len(god_sets)):
-            style_name = god_sets[idx]["style"]
-            if style_name in ("tight_cluster", "wide_spread", "high_cluster"):
-                new_nums, new_score = _rebuild_for_coverage(style_name, final_scores)
-                god_sets[idx]["numbers"] = new_nums
-                god_sets[idx]["score"] = new_score
-
-    # Select primary combo: prefer balanced, else fall back to top_cluster
-    primary = next((s for s in god_sets if s["style"] == "balanced"), god_sets[0])
-
-    sorted_nums = sorted(final_scores.items(), key=lambda kv: kv[1], reverse=True)
-    top_explain = sorted_nums[:10]
-
-    explanation = {
-        "top_numbers": [
-            {"num": int(n), "score": float(round(s, 4))} for n, s in top_explain
-        ],
-        "banned_last4_repeater": sorted(int(x) for x in banned_nums),
-        "regime": regime_info,
-        "usage_counts": {int(k): int(v) for k, v in usage_counts.items()},
-    }
-
-    model_info = {
-        "numbers_modeled": len(ml_models),
-        "total_possible": cfg.main_max - cfg.main_min + 1,
-    }
-
-    result = {
-        "game": cfg.name,
-        "numbers": primary["numbers"],
-        "star": primary["star"],
-        "meta": {
-            "numbers_scored": len(final_scores),
-            "history_used": len(df_long),
-            "styles": [s["style"] for s in god_sets],
-        },
-        "godmode_sets": god_sets,
-        "explanation": explanation,
-        "model_info": model_info,
-    }
-    return result
-
-
-# ============================================================
-# Backtesting
-# ============================================================
-
-def enhanced_backtest(
-    df: pd.DataFrame,
-    cfg: GameConfig,
-    n_tests: int = 200,
-) -> Dict[str, float]:
-    df = _ensure_datetime(df, cfg.csv_date_col)
-    if cfg.clean_func and cfg.clean_func in globals():
-        df = globals()[cfg.clean_func](df)
-
-    if len(df) < 80:
-        return {"error": "Insufficient data for backtest (need >80 draws)"}
-
-    total_tests = min(n_tests, len(df) - 60)
-    print(f"[BACKTEST] {cfg.name}: running {total_tests} tests...")
-
-    stats = {
-        "hit_0": 0,
-        "hit_1": 0,
-        "hit_2": 0,
-        "hit_3": 0,
-        "hit_4": 0,
-        "hit_5": 0,
-        "rnd_0": 0,
-        "rnd_1": 0,
-        "rnd_2": 0,
-        "rnd_3": 0,
-        "rnd_4": 0,
-        "rnd_5": 0,
-        "sum_errors": [],
-        "even_match": 0,
-    }
-
-    for idx in range(60, 60 + total_tests):
-        if (idx - 59) % 30 == 0:
-            print(f"  progress: {idx - 59}/{total_tests}")
-
-        train_df = df.iloc[:idx].copy()
-        actual_row = df.iloc[idx]
-        actual_nums = sorted(int(x) for x in actual_row[cfg.main_cols].values)
-
-        try:
-            pred = generate_prediction_v4_god(train_df, cfg)
-            pred_nums = sorted(pred["numbers"])
-        except Exception:
-            pred_nums = sorted(
-                random.sample(
-                    range(cfg.main_min, cfg.main_max + 1),
-                    len(cfg.main_cols),
-                )
-            )
-
-        hits = len(set(pred_nums) & set(actual_nums))
-        stats[f"hit_{hits}"] += 1
-
-        rnd_nums = sorted(
-            random.sample(
-                range(cfg.main_min, cfg.main_max + 1),
-                len(cfg.main_cols),
-            )
-        )
-        rnd_hits = len(set(rnd_nums) & set(actual_nums))
-        stats[f"rnd_{rnd_hits}"] += 1
-
-        stats["sum_errors"].append(abs(sum(pred_nums) - sum(actual_nums)))
-        if sum(v % 2 == 0 for v in pred_nums) == sum(
-            v % 2 == 0 for v in actual_nums
-        ):
-            stats["even_match"] += 1
-
-    out: Dict[str, float] = {}
-    for i in range(6):
-        out[f"model_hit_{i}_rate"] = round(
-            stats[f"hit_{i}"] / max(total_tests, 1) * 100.0, 2
-        )
-        out[f"random_hit_{i}_rate"] = round(
-            stats[f"rnd_{i}"] / max(total_tests, 1) * 100.0, 2
-        )
-
-    out["avg_sum_error"] = round(float(np.mean(stats["sum_errors"])), 2)
-    out["even_count_accuracy"] = round(
-        stats["even_match"] / max(total_tests, 1) * 100.0, 2
-    )
-    out["model_3plus_rate"] = round(
-        sum(stats[f"hit_{i}"] for i in range(3, 6)) / max(total_tests, 1) * 100.0, 2
-    )
-    out["random_3plus_rate"] = round(
-        sum(stats[f"rnd_{i}"] for i in range(3, 6)) / max(total_tests, 1) * 100.0, 2
-    )
-    return out
-
-
-# ============================================================
-# CSV loading + public API
-# ============================================================
-
-def load_csv_for_game(csv_path: Path, game_key: str) -> Tuple[pd.DataFrame, GameConfig]:
-    cfg = GAME_CONFIGS[game_key]
-    df = pd.read_csv(csv_path)
-
-    # Basic main number cleaning
-    for col in cfg.main_cols:
-        if col not in df.columns:
-            raise ValueError(f"Expected column '{col}' in CSV for {cfg.name}")
-        df[col] = pd.to_numeric(df[col], errors="coerce")
-        mask_bad = (df[col].isna()) | (df[col] < cfg.main_min) | (df[col] > cfg.main_max)
-        if mask_bad.any():
-            df = df[~mask_bad]
-
-    # Bonus/Star cleaning
-    if cfg.star_col and cfg.star_col in df.columns:
-        df[cfg.star_col] = pd.to_numeric(df[cfg.star_col], errors="coerce")
-
-        # Mega Millions legacy Megaball patch:
-        # Before April 2025 many CSVs still have MB 1–25.
-        # We remap any values > star_max back into 1–star_max cyclically,
-        # so old draws are kept but MB is always in 1–24.
-        if cfg.name == "Mega Millions":
-            legacy_mask = df[cfg.star_col] > cfg.star_max
-            if legacy_mask.any():
-                df.loc[legacy_mask, cfg.star_col] = (
-                    (df.loc[legacy_mask, cfg.star_col] - 1) % cfg.star_max
-                ) + 1
-
-        mask_bad_star = (
-            df[cfg.star_col].isna()
-            | (df[cfg.star_col] < cfg.star_min)
-            | (df[cfg.star_col] > cfg.star_max)
-        )
-        if mask_bad_star.any():
-            df = df[~mask_bad_star]
-
-    if cfg.csv_date_col not in df.columns:
-        raise ValueError(f"Expected date column '{cfg.csv_date_col}' in CSV for {cfg.name}")
-
-    df[cfg.csv_date_col] = pd.to_datetime(df[cfg.csv_date_col], errors="coerce")
-    df = df.dropna(subset=[cfg.csv_date_col])
-    df = df.sort_values(cfg.csv_date_col).reset_index(drop=True)
-
-    if cfg.clean_func and cfg.clean_func in globals():
-        df = globals()[cfg.clean_func](df)
-
-    return df, cfg
-
-
-def predict_for_game_v3(
-    csv_path: Path,
-    game_key: str,
-    run_backtest: bool = False,
-) -> Dict[str, object]:
-    """
-    Public API (same name/signature as earlier versions).
-    If run_backtest=True -> run enhanced_backtest.
-    Else -> run GOD-MODE prediction (V5.3 ULTRA).
-    """
-    df, cfg = load_csv_for_game(Path(csv_path), game_key)
-    if run_backtest:
-        return enhanced_backtest(df, cfg)
-    return generate_prediction_v4_god(df, cfg)
-
-
-def predict_for_game(
-    csv_path: Path,
-    game_key: str,
-    run_backtest: bool = False,
-):
-    """
-    Backwards-compatible wrapper for older code that imports `predict_for_game`.
-    """
-    return predict_for_game_v3(csv_path=Path(csv_path), game_key=game_key, run_backtest=run_backtest)
-
-
-# ============================================================
-# Wheel generation + hot/cold analysis
-# ============================================================
-
-def generate_wheel_numbers(raw_df: pd.DataFrame, cfg: GameConfig) -> Dict[str, object]:
-    """
-    Generate a 20-number wheel using frequency, recency, and multi-agent ranking.
-    """
-    df = _ensure_datetime(raw_df, cfg.csv_date_col)
-    if cfg.clean_func and cfg.clean_func in globals():
-        df = globals()[cfg.clean_func](df)
-
-    if len(df) < 40:
-        return {"error": "Insufficient history (<40) for wheel generation"}
-
-    df_long = _limit_history(df, 400)
-
-    ml_models = build_multiwindow_ml(df_long, cfg, windows=[20, 80, 400])
-    freq_features = create_frequency_features(df_long, cfg, windows=[20, 80, 400])
-    agent_scores = compute_agent_scores(df_long, cfg, ml_models, freq_features)
-    final_scores = combine_agent_scores(agent_scores, cfg)
-
-    banned = get_last4_repeater_ban(df_long, cfg)
-    wheel_pool = {n: s for n, s in final_scores.items() if n not in banned}
-    if len(wheel_pool) < 20:
-        wheel_pool = final_scores.copy()
-
-    sorted_nums = sorted(wheel_pool.items(), key=lambda x: x[1], reverse=True)
-    wheel_nums = [n for n, _ in sorted_nums[:20]]
-
-    freq_all = Counter(df_long[cfg.main_cols].values.flatten())
-    hot = [n for n, _ in freq_all.most_common(10)]
-    cold = [n for n, _ in freq_all.most_common()[-10:]]
-
-    return {
-        "wheel_numbers": wheel_nums,
-        "hot_count": len(set(wheel_nums) & set(hot)),
-        "cold_count": len(set(wheel_nums) & set(cold)),
-        "warm_count": len(wheel_nums) - len(set(wheel_nums) & set(hot)) - len(set(wheel_nums) & set(cold)),
-        "banned_last4_repeater": sorted(banned),
-        "hot_cold_analysis": {
-            "hot": hot,
-            "cold": cold,
-        },
-    }
-
-
-def get_wheel_for_game(csv_path: Path, game_key: str) -> Dict[str, object]:
-    df, cfg = load_csv_for_game(Path(csv_path), game_key)
-    return generate_wheel_numbers(df, cfg)
-
-
-def get_hot_cold_analysis(
-    csv_path: Path,
-    game_key: str,
-    top_n: int = 10,
-) -> Dict[str, object]:
-    """
-    Helper for app/engine: top-N hottest and coldest numbers for the given game,
-    plus full frequency table.
-    """
-    df, cfg = load_csv_for_game(Path(csv_path), game_key)
-
-    all_nums = []
-    for col in cfg.main_cols:
-        all_nums.extend(df[col].tolist())
-    all_nums = [int(x) for x in all_nums if not pd.isna(x)]
-
-    freq = Counter(all_nums)
-    sorted_freq = sorted(freq.items(), key=lambda kv: kv[1], reverse=True)
-    hot = [n for n, _ in sorted_freq[:top_n]]
-    cold = [n for n, _ in sorted(freq.items(), key=lambda kv: kv[1])[:top_n]]
-
-    return {
-        "hot": hot,
-        "cold": cold,
-        "frequency": {int(n): int(c) for n, c in freq.items()},
-    }
-
-
-def load_and_prepare_data(csv_path: Path, game_key: str) -> Tuple[pd.DataFrame, GameConfig]:
-    """
-    Backwards-compatible wrapper for older engine code.
-    Loads CSV, cleans & validates it, and returns (DataFrame, GameConfig).
-    """
-    csv_path = Path(csv_path)
-    df, cfg = load_csv_for_game(csv_path, game_key)
-    return df, cfg
-
-
-# ============================================================
-# CLI (pretty output)
-# ============================================================
-
-if __name__ == "__main__":
-    import argparse
-    import os
-
-    parser = argparse.ArgumentParser(
-        description="Lotto Predictor V5.3 ULTRA GOD MODE (multi-agent, multi-window, cluster-aware, top_cluster style)"
-    )
-    parser.add_argument(
-        "--game",
-        required=True,
-        choices=list(GAME_CONFIGS.keys()),
-        help="Game key: " + ", ".join(GAME_CONFIGS.keys()),
-    )
-    parser.add_argument("--csv", required=True, help="Path to CSV for the game")
-    parser.add_argument(
-        "--backtest",
-        action="store_true",
-        help="Run backtest instead of prediction",
-    )
-    parser.add_argument(
-        "--save-json",
-        action="store_true",
-        help="Also save full JSON result to godmode_last_result_<game>.json",
-    )
-    args = parser.parse_args()
-
-    result = predict_for_game_v3(
-        csv_path=Path(args.csv),
-        game_key=args.game,
-        run_backtest=args.backtest,
-    )
-
-    # -------------------------------
-    # Backtest mode: pretty summary
-    # -------------------------------
-    if args.backtest:
-        if "error" in result:
-            print(f"\n[BACKTEST ERROR] {result['error']}")
-        else:
-            print("\n==============================================")
-            print(f"  BACKTEST RESULTS - {GAME_CONFIGS[args.game].name}")
-            print("==============================================\n")
-
-            print(f"  Model 3+ hits rate : {result.get('model_3plus_rate', 0)} %")
-            print(f"  Random 3+ hits rate: {result.get('random_3plus_rate', 0)} %")
-            print(f"  Avg sum error      : {result.get('avg_sum_error', 0)}")
-            print(f"  Even-count accuracy: {result.get('even_count_accuracy', 0)} %")
-            print("\n  Hit-rate table (Model vs Random):")
-            print("    Matches |  Model %   | Random %")
-            print("   ---------+-----------+----------")
-            for i in range(6):
-                m = result.get(f"model_hit_{i}_rate", 0)
-                r = result.get(f"random_hit_{i}_rate", 0)
-                print(f"      {i:1d}     | {m:7.2f} % | {r:7.2f} %")
-            print("\n==============================================\n")
-    else:
-        # -------------------------------
-        # Prediction mode: nice compact view
-        # -------------------------------
-        game_name = result.get("game", GAME_CONFIGS[args.game].name)
-        numbers = result.get("numbers", [])
-        star = result.get("star", None)
-        meta = result.get("meta", {})
-        god_sets = result.get("godmode_sets", [])
-        expl = result.get("explanation", {})
-        top_nums = expl.get("top_numbers", [])
-        banned = expl.get("banned_last4_repeater", [])
-        model_info = result.get("model_info", {})
-
-        print("\n==============================================")
-        print(f"   V5.3 ULTRA GOD MODE RESULT - {game_name}")
-        print("==============================================\n")
-
-        # Primary combo
-        nums_str = "-".join(str(n) for n in numbers)
-        if star is not None:
-            print(f"  PRIMARY PICK : {nums_str}  (Star: {star})")
-        else:
-            print(f"  PRIMARY PICK : {nums_str}")
-        print()
-
-        # Multi-style sets
-        if god_sets:
-            print("  GOD MODE SETS (multi-style):\n")
-            for i, s in enumerate(god_sets, start=1):
-                s_nums = "-".join(str(n) for n in s.get("numbers", []))
-                s_style = s.get("style", "unknown").replace("_", " ").title()
-                s_star = s.get("star", None)
-                if s_star is not None:
-                    print(f"    {i}) {s_style:<12} -> {s_nums}  (Star: {s_star})")
-                else:
-                    print(f"    {i}) {s_style:<12} -> {s_nums}")
-            print()
-
-        # Top-10 favorite numbers
-        if top_nums:
-            fav_str = ", ".join(f"{t['num']} ({t['score']:.3f})" for t in top_nums)
-            just_nums = ", ".join(str(t["num"]) for t in top_nums)
-            print("  TOP 10 FAVORITE NUMBERS (by score):")
-            print(f"    Numbers: {just_nums}")
-            print(f"    Detail : {fav_str}")
-            print()
-
-        # Banned last-4 repeaters
-        if banned:
-            print("  BANNED (4-in-a-row repeaters):")
-            print(f"    {', '.join(str(b) for b in banned)}")
-            print()
-        else:
-            print("  BANNED (4-in-a-row repeaters): none")
-            print()
-
-        # Meta / model info
-        print(f"  Numbers scored   : {meta.get('numbers_scored', 'N/A')}")
-        print(f"  History used     : {meta.get('history_used', 'N/A')} draws")
-        print(
-            f"  ML coverage      : {model_info.get('numbers_modeled', 0)}/"
-            f"{model_info.get('total_possible', 0)} numbers"
-        )
-        if meta.get("styles"):
-            print(f"  Styles evaluated : {', '.join(meta['styles'])}")
-        print("\n==============================================\n")
-
-    # Optional: save full JSON snapshot for debugging / records
-    if args.save_json:
-        out_name = f"godmode_last_result_{args.game}.json"
-        try:
-            with open(out_name, "w", encoding="utf-8") as f:
-                json.dump(result, f, indent=2, cls=NumpyEncoder)
-            print(f"[INFO] Full JSON result saved to: {os.path.abspath(out_name)}")
-        except Exception as e:
-            print(f"[WARN] Could not save JSON result: {e}")

la_results.csv

@@ -1,526 +0,0 @@
-date,b1,b2,b3,b4,b5,star_ball
-1/28/2026,25,31,33,36,41,2
-1/26/2026,2,12,15,27,48,9
-1/24/2026,4,11,16,33,42,6
-1/21/2026,11,30,39,48,51,4
-1/19/2026,2,10,15,18,31,9
-1/17/2026,7,28,29,35,39,8
-1/14/2026,1,10,23,33,35,6
-1/12/2026,9,20,25,30,51,10
-1/10/2026,6,15,20,22,25,10
-1/7/2026,3,18,25,45,50,4
-1/5/2026,12,19,21,30,47,5
-1/3/2026,3,4,5,25,42,3
-12/31/2025,12,13,37,42,51,8
-12/29/2025,1,5,24,35,51,4
-12/27/2025,8,10,20,47,50,4
-12/24/2025,1,18,27,41,49,9
-12/22/2025,1,9,18,19,44,2
-12/20/2025,9,12,34,45,50,1
-12/17/2025,14,30,38,40,47,6
-12/15/2025,8,11,29,36,50,7
-12/13/2025,20,26,27,32,46,8
-12/10/2025,3,13,37,42,44,1
-12/8/2025,7,10,32,33,35,3
-12/6/2025,7,8,14,23,41,9
-12/3/2025,14,19,27,30,41,10
-12/1/2025,5,27,37,43,47,5
-11/29/2025,1,15,18,21,46,6
-11/26/2025,7,19,25,26,28,7
-11/24/2025,1,5,8,19,50,6
-11/22/2025,4,12,19,20,50,4
-11/19/2025,12,31,39,40,42,8
-11/17/2025,2,20,28,36,46,2
-11/15/2025,14,21,40,43,48,8
-11/12/2025,9,30,31,34,39,2
-11/10/2025,6,14,17,26,28,3
-11/8/2025,15,21,23,37,52,5
-11/5/2025,1,26,35,50,51,5
-11/3/2025,7,11,19,25,50,10
-11/1/2025,8,11,23,31,47,6
-10/29/2025,21,33,40,42,50,5
-10/27/2025,12,21,27,35,39,2
-10/25/2025,2,31,33,35,50,7
-10/22/2025,4,15,28,33,35,6
-10/20/2025,20,32,35,43,51,4
-10/18/2025,12,26,27,32,35,2
-10/15/2025,8,24,33,46,47,4
-10/13/2025,5,8,10,39,47,9
-10/11/2025,1,17,31,35,39,3
-10/8/2025,4,10,15,17,19,10
-10/6/2025,3,11,21,25,32,6
-10/4/2025,9,27,28,45,51,6
-10/1/2025,12,28,42,44,48,3
-9/29/2025,5,38,49,51,52,8
-9/27/2025,2,12,20,34,43,7
-9/24/2025,6,24,27,35,46,2
-9/22/2025,2,5,34,41,44,10
-9/20/2025,2,13,17,36,42,8
-9/17/2025,8,33,36,45,51,2
-9/15/2025,14,16,17,33,43,3
-9/13/2025,20,24,25,28,46,1
-9/10/2025,14,24,38,49,50,5
-9/8/2025,3,9,37,44,47,4
-9/6/2025,3,9,35,39,48,1
-9/3/2025,15,31,34,51,52,5
-9/1/2025,4,10,11,23,32,3
-8/30/2025,10,16,19,21,45,2
-8/27/2025,12,13,25,40,52,9
-8/25/2025,1,4,5,10,28,8
-8/23/2025,1,6,11,28,31,10
-8/20/2025,3,12,27,35,39,6
-8/18/2025,2,7,26,30,49,2
-8/16/2025,9,15,34,45,47,4
-8/13/2025,17,23,27,45,52,3
-8/11/2025,1,9,23,25,42,3
-8/9/2025,1,9,24,37,40,1
-8/6/2025,26,29,30,33,40,1
-8/4/2025,1,8,18,22,42,8
-8/2/2025,7,16,22,31,39,6
-7/30/2025,9,13,26,43,51,4
-7/28/2025,8,12,23,25,31,10
-7/26/2025,8,16,20,35,48,8
-7/23/2025,4,32,36,39,52,1
-7/21/2025,5,7,13,47,52,6
-7/19/2025,4,25,32,42,51,10
-7/16/2025,5,35,37,46,50,9
-7/14/2025,9,30,35,43,49,8
-7/12/2025,2,10,12,21,45,3
-7/9/2025,2,10,27,30,50,5
-7/7/2025,8,18,27,31,41,9
-7/5/2025,8,10,36,43,45,9
-7/2/2025,8,19,20,21,39,7
-6/30/2025,5,8,18,32,46,4
-6/28/2025,6,25,26,37,45,1
-6/25/2025,12,14,25,30,42,4
-6/23/2025,16,18,26,40,46,7
-6/21/2025,4,6,14,37,43,2
-6/18/2025,11,18,25,29,32,9
-6/16/2025,4,19,35,43,51,1
-6/14/2025,19,22,26,31,51,9
-6/11/2025,4,12,13,20,26,4
-6/9/2025,6,14,35,44,49,5
-6/7/2025,1,17,19,36,43,3
-6/4/2025,1,6,26,41,51,8
-6/2/2025,5,7,20,28,35,3
-5/31/2025,5,11,23,40,47,10
-5/28/2025,4,6,8,33,35,5
-5/26/2025,2,13,25,37,42,1
-5/24/2025,8,19,24,28,49,1
-5/21/2025,1,14,15,19,31,9
-5/19/2025,4,24,25,45,47,2
-5/17/2025,16,18,24,25,34,2
-5/14/2025,8,17,38,42,50,5
-5/12/2025,2,8,9,20,42,3
-5/10/2025,10,12,27,45,51,1
-5/7/2025,3,6,9,13,17,8
-5/5/2025,5,13,20,22,28,5
-5/3/2025,21,23,39,45,50,1
-4/30/2025,5,22,23,24,36,7
-4/28/2025,18,19,32,44,50,10
-4/26/2025,1,9,14,31,34,2
-4/23/2025,18,24,34,40,42,8
-4/21/2025,2,4,13,21,44,8
-4/19/2025,4,11,23,29,36,9
-4/16/2025,2,5,45,47,48,8
-4/14/2025,7,10,13,21,42,10
-4/12/2025,16,24,42,50,52,8
-4/9/2025,12,19,30,42,46,7
-4/7/2025,4,8,13,27,37,7
-4/5/2025,17,26,37,40,51,9
-4/2/2025,12,28,39,41,44,1
-3/31/2025,11,24,33,38,47,1
-3/29/2025,2,21,33,46,52,8
-3/26/2025,16,19,30,37,47,6
-3/24/2025,14,34,35,40,44,4
-3/22/2025,6,21,43,47,52,3
-3/19/2025,4,8,26,34,36,6
-3/17/2025,11,12,20,29,33,8
-3/15/2025,16,39,41,44,51,7
-3/12/2025,4,17,21,28,48,4
-3/10/2025,13,15,34,36,39,10
-3/8/2025,1,30,31,36,43,9
-3/5/2025,10,15,23,35,41,4
-3/3/2025,12,25,29,40,49,3
-3/1/2025,8,9,13,33,41,6
-2/26/2025,8,11,21,27,39,5
-2/24/2025,1,21,30,35,41,3
-2/22/2025,3,24,26,34,35,6
-2/19/2025,3,22,23,35,41,2
-2/17/2025,20,22,24,37,48,5
-2/15/2025,17,29,39,41,52,3
-2/12/2025,6,16,23,27,30,1
-2/10/2025,7,10,13,31,50,5
-2/8/2025,2,5,6,30,50,6
-2/5/2025,4,13,17,44,45,5
-2/3/2025,10,33,35,49,51,3
-2/1/2025,14,15,21,35,52,6
-1/29/2025,9,20,23,42,45,2
-1/27/2025,3,7,21,33,45,2
-1/25/2025,8,31,35,44,46,10
-1/22/2025,8,16,27,32,43,4
-1/20/2025,2,4,22,23,32,5
-1/18/2025,16,28,41,47,52,3
-1/15/2025,2,11,28,40,47,3
-1/13/2025,5,11,37,49,50,4
-1/11/2025,7,10,16,47,52,1
-1/8/2025,4,15,33,39,41,7
-1/6/2025,15,34,45,50,51,8
-1/4/2025,1,3,17,21,34,4
-1/1/2025,1,2,8,14,30,6
-12/30/2024,12,16,38,45,50,8
-12/28/2024,12,17,22,30,42,2
-12/25/2024,4,5,40,42,52,10
-12/23/2024,4,21,28,42,52,1
-12/21/2024,9,19,30,39,44,4
-12/18/2024,5,10,35,39,47,5
-12/16/2024,5,17,18,34,50,8
-12/14/2024,2,8,47,51,52,3
-12/11/2024,4,14,30,45,50,4
-12/9/2024,15,24,29,38,51,3
-12/7/2024,7,14,31,44,46,8
-12/4/2024,10,13,32,42,44,9
-12/2/2024,1,20,37,39,47,4
-11/30/2024,4,5,10,15,44,5
-11/27/2024,2,20,23,24,29,9
-11/25/2024,12,14,16,25,33,1
-11/23/2024,2,8,10,14,49,9
-11/20/2024,11,17,25,38,47,9
-11/18/2024,20,36,37,42,43,6
-11/16/2024,4,5,7,24,29,4
-11/13/2024,11,23,29,41,42,10
-11/11/2024,15,38,39,50,52,10
-11/9/2024,14,31,34,41,48,1
-11/6/2024,3,19,42,47,48,7
-11/4/2024,3,9,12,16,52,3
-11/2/2024,7,9,23,32,42,10
-10/30/2024,27,30,37,41,50,7
-10/28/2024,1,10,22,28,41,3
-10/26/2024,2,3,25,42,47,5
-10/23/2024,18,38,42,44,47,3
-10/21/2024,1,4,20,24,26,4
-10/19/2024,3,10,28,34,47,4
-10/16/2024,2,16,21,33,52,4
-10/14/2024,6,25,31,43,51,4
-10/12/2024,11,15,36,37,49,7
-10/9/2024,18,28,32,40,51,4
-10/7/2024,8,26,28,39,45,10
-10/5/2024,8,15,17,32,36,2
-10/2/2024,8,10,17,20,28,4
-9/30/2024,24,28,29,30,51,10
-9/28/2024,12,13,47,48,51,10
-9/25/2024,5,10,13,31,52,8
-9/23/2024,13,15,22,23,35,9
-9/21/2024,1,4,8,37,45,7
-9/18/2024,7,17,29,42,45,5
-9/16/2024,4,16,41,44,52,5
-9/14/2024,6,9,38,42,50,4
-9/11/2024,2,9,10,12,24,7
-9/9/2024,1,10,20,24,40,1
-9/7/2024,1,4,9,33,37,10
-9/4/2024,7,9,28,30,31,3
-9/2/2024,3,6,7,27,39,3
-8/31/2024,17,18,32,42,51,6
-8/28/2024,7,28,41,46,52,4
-8/26/2024,23,38,42,43,44,10
-8/24/2024,3,19,21,28,32,4
-8/21/2024,6,25,41,45,46,1
-8/19/2024,16,21,41,48,49,4
-8/17/2024,4,26,38,42,50,9
-8/14/2024,8,11,15,32,42,6
-8/12/2024,9,24,27,28,52,3
-8/10/2024,6,19,40,41,42,5
-8/7/2024,15,24,42,44,51,4
-8/5/2024,13,21,29,33,38,2
-8/3/2024,5,10,21,42,43,10
-7/31/2024,15,27,28,49,51,1
-7/29/2024,1,26,44,51,52,4
-7/27/2024,9,15,17,42,45,2
-7/24/2024,8,11,31,36,40,6
-7/22/2024,2,12,15,43,52,1
-7/20/2024,6,7,13,16,36,1
-7/17/2024,6,9,15,44,49,3
-7/15/2024,1,7,10,40,41,9
-7/13/2024,8,20,27,34,49,9
-7/10/2024,6,21,25,42,51,4
-7/8/2024,5,21,22,40,46,5
-7/6/2024,11,15,25,38,42,5
-7/3/2024,6,7,37,46,49,10
-7/1/2024,7,18,36,37,43,9
-6/29/2024,10,15,21,22,42,3
-6/26/2024,11,12,27,38,48,6
-6/24/2024,6,18,22,25,35,1
-6/22/2024,1,26,37,39,44,1
-6/19/2024,19,21,24,44,51,8
-6/17/2024,3,12,28,29,35,3
-6/15/2024,26,31,32,36,49,1
-6/12/2024,3,11,16,30,44,8
-6/10/2024,5,11,14,25,26,9
-6/8/2024,5,7,23,37,45,3
-6/5/2024,3,15,17,43,49,7
-6/3/2024,5,6,22,33,38,4
-6/1/2024,13,15,19,29,39,5
-5/29/2024,8,9,11,29,36,3
-5/27/2024,9,25,32,40,51,5
-5/25/2024,12,17,27,29,40,10
-5/22/2024,2,5,15,41,43,5
-5/20/2024,13,15,24,26,27,3
-5/18/2024,7,8,9,12,33,9
-5/15/2024,17,25,27,47,51,10
-5/13/2024,1,15,16,26,47,4
-5/11/2024,15,16,27,50,51,3
-5/8/2024,5,11,18,38,47,5
-5/6/2024,3,6,11,17,30,10
-5/4/2024,5,11,25,37,42,5
-5/1/2024,14,19,24,26,40,7
-4/29/2024,3,14,31,32,50,1
-4/27/2024,9,13,16,39,48,3
-4/24/2024,7,12,17,22,52,3
-4/22/2024,19,28,33,38,52,7
-4/20/2024,6,11,14,15,31,5
-4/17/2024,10,20,24,29,38,1
-4/15/2024,2,12,18,23,52,4
-4/13/2024,7,9,10,29,38,2
-4/10/2024,2,15,21,33,47,7
-4/8/2024,24,28,29,32,38,8
-4/6/2024,2,23,32,35,42,7
-4/3/2024,11,16,20,27,47,4
-4/1/2024,6,16,32,41,44,3
-3/30/2024,9,17,34,48,52,5
-3/27/2024,9,22,30,31,34,5
-3/25/2024,19,32,35,40,43,4
-3/23/2024,5,7,12,41,52,4
-3/20/2024,3,16,29,44,50,7
-3/18/2024,19,23,24,31,44,2
-3/16/2024,11,30,43,47,51,4
-3/13/2024,23,33,34,41,50,7
-3/11/2024,12,15,16,32,46,1
-3/9/2024,3,27,33,37,52,9
-3/6/2024,20,21,24,40,42,4
-3/4/2024,4,5,8,22,47,6
-3/2/2024,9,19,35,38,45,3
-2/28/2024,16,18,25,37,46,7
-2/26/2024,21,30,36,38,49,1
-2/24/2024,10,19,30,33,52,10
-2/21/2024,2,6,26,40,43,1
-2/19/2024,4,14,31,37,41,8
-2/17/2024,6,8,10,14,33,5
-2/14/2024,2,3,15,16,45,10
-2/12/2024,13,14,22,31,52,2
-2/10/2024,1,3,18,21,42,8
-2/7/2024,2,5,17,20,25,9
-2/5/2024,1,15,17,24,29,2
-2/3/2024,10,34,40,47,48,1
-1/31/2024,3,30,38,39,48,8
-1/29/2024,5,9,15,50,51,1
-1/27/2024,13,22,46,47,51,4
-1/24/2024,10,13,15,29,47,7
-1/22/2024,18,22,31,39,50,2
-1/20/2024,7,11,23,24,44,3
-1/17/2024,9,14,16,23,40,5
-1/15/2024,28,29,38,41,52,8
-1/13/2024,6,9,30,38,46,1
-1/10/2024,7,19,27,38,51,5
-1/8/2024,12,21,37,39,45,6
-1/6/2024,14,34,42,46,51,6
-1/3/2024,10,17,31,47,51,4
-1/1/2024,7,9,19,36,45,10
-12/30/2023,9,10,11,30,44,7
-12/27/2023,3,10,36,47,52,10
-12/25/2023,4,10,25,48,52,3
-12/23/2023,16,22,23,24,50,9
-12/20/2023,4,14,15,17,28,7
-12/18/2023,2,3,12,33,40,6
-12/16/2023,13,14,23,25,31,9
-12/13/2023,4,25,34,38,46,6
-12/11/2023,18,39,42,47,52,5
-12/9/2023,3,7,17,36,48,7
-12/6/2023,22,24,27,34,43,8
-12/4/2023,4,16,18,36,47,4
-12/2/2023,3,8,11,38,48,8
-11/29/2023,9,22,24,37,47,10
-11/27/2023,1,8,23,25,50,4
-11/25/2023,3,11,18,38,41,1
-11/22/2023,17,19,37,42,45,7
-11/20/2023,10,14,24,41,51,2
-11/18/2023,9,18,22,26,34,6
-11/15/2023,15,16,26,34,51,1
-11/13/2023,17,18,20,44,51,4
-11/11/2023,5,25,27,38,50,7
-11/8/2023,1,3,23,45,52,2
-11/6/2023,13,15,26,44,46,5
-11/4/2023,8,11,23,47,48,4
-11/1/2023,6,19,21,26,29,1
-10/30/2023,11,28,43,49,50,4
-10/28/2023,12,25,36,39,46,9
-10/25/2023,3,8,27,41,46,3
-10/23/2023,21,27,28,32,51,2
-10/21/2023,11,23,30,36,51,6
-10/18/2023,1,5,14,16,48,9
-10/16/2023,11,30,37,39,47,7
-10/14/2023,6,32,33,36,47,4
-10/11/2023,3,6,9,17,51,2
-10/9/2023,10,13,30,38,40,8
-10/7/2023,5,22,31,35,47,10
-10/4/2023,4,5,8,26,42,8
-10/2/2023,4,5,21,36,51,3
-9/30/2023,4,5,26,27,35,6
-9/27/2023,21,22,25,46,50,1
-9/25/2023,19,23,31,38,52,8
-9/23/2023,15,32,34,39,50,10
-9/20/2023,2,16,27,32,46,3
-9/18/2023,4,24,25,32,51,7
-9/16/2023,23,30,34,40,41,3
-9/13/2023,11,12,25,36,40,4
-9/11/2023,13,34,35,36,49,1
-9/9/2023,5,15,21,22,33,5
-9/6/2023,8,28,39,49,51,2
-9/4/2023,10,17,33,51,52,10
-9/2/2023,3,17,36,37,44,8
-8/30/2023,8,15,30,44,46,8
-8/28/2023,16,33,34,39,46,4
-8/26/2023,8,21,38,43,51,1
-8/23/2023,9,11,29,38,39,4
-8/21/2023,7,10,26,40,50,3
-8/19/2023,4,22,29,32,39,4
-8/16/2023,14,18,31,37,43,2
-8/14/2023,1,26,31,33,50,8
-8/12/2023,3,16,26,29,30,5
-8/9/2023,1,10,12,33,39,5
-8/7/2023,4,8,29,33,52,5
-8/5/2023,1,36,38,41,43,5
-8/2/2023,1,18,33,41,51,10
-7/31/2023,5,11,12,34,40,9
-7/29/2023,8,14,29,50,52,10
-7/26/2023,4,8,25,36,42,8
-7/24/2023,6,13,20,29,51,7
-7/22/2023,1,20,23,36,41,1
-7/19/2023,9,12,16,33,40,4
-7/17/2023,25,28,29,40,51,10
-7/15/2023,5,6,20,42,48,6
-7/12/2023,3,5,18,22,36,3
-7/10/2023,3,26,30,47,51,1
-7/8/2023,29,33,38,43,49,8
-7/5/2023,9,21,38,39,48,8
-7/3/2023,12,27,37,42,43,6
-7/1/2023,13,16,23,43,52,2
-6/28/2023,9,28,33,43,47,1
-6/26/2023,3,31,33,34,38,3
-6/24/2023,11,27,30,37,49,1
-6/21/2023,2,13,20,35,48,7
-6/19/2023,1,14,20,30,33,7
-6/17/2023,4,23,26,35,36,8
-6/14/2023,2,15,26,29,30,4
-6/12/2023,1,29,32,41,46,7
-6/10/2023,4,6,38,46,52,7
-6/7/2023,9,12,21,22,26,9
-6/5/2023,6,15,33,42,43,7
-6/3/2023,9,14,21,22,48,2
-5/31/2023,4,15,27,28,49,5
-5/29/2023,19,34,42,50,52,2
-5/27/2023,2,23,28,40,50,8
-5/24/2023,1,23,24,35,43,4
-5/22/2023,5,8,23,32,43,10
-5/20/2023,4,11,15,18,19,1
-5/17/2023,7,19,32,36,48,4
-5/15/2023,9,16,33,38,41,8
-5/13/2023,7,34,35,39,43,10
-5/10/2023,9,13,14,17,26,2
-5/8/2023,7,18,24,29,44,6
-5/6/2023,13,20,42,43,46,1
-5/3/2023,8,9,31,43,44,1
-5/1/2023,2,17,20,31,45,3
-4/29/2023,2,5,8,36,51,2
-4/26/2023,2,11,12,27,46,9
-4/24/2023,6,8,15,16,31,5
-4/22/2023,5,9,12,24,26,4
-4/19/2023,19,40,41,48,49,5
-4/17/2023,10,13,21,23,30,4
-4/15/2023,10,17,24,30,37,3
-4/12/2023,18,36,45,48,51,5
-4/10/2023,3,10,12,15,37,2
-4/8/2023,1,14,35,37,39,5
-4/5/2023,23,28,38,39,41,2
-4/3/2023,6,27,30,40,52,1
-4/1/2023,2,38,43,46,51,7
-3/29/2023,19,24,38,45,46,4
-3/27/2023,20,37,46,49,52,10
-3/25/2023,3,17,29,41,52,10
-3/22/2023,14,18,21,50,51,3
-3/20/2023,13,14,22,30,37,3
-3/18/2023,35,37,44,45,46,1
-3/15/2023,31,36,43,45,52,2
-3/13/2023,20,23,28,33,51,3
-3/11/2023,33,39,41,45,48,8
-3/8/2023,3,7,29,31,49,10
-3/6/2023,2,17,25,35,50,6
-3/4/2023,2,5,24,32,52,4
-3/1/2023,8,14,17,38,41,7
-2/27/2023,12,17,41,43,51,5
-2/25/2023,14,22,34,39,50,8
-2/22/2023,6,24,25,31,38,7
-2/20/2023,4,10,19,27,39,10
-2/18/2023,5,17,25,48,52,1
-2/15/2023,3,11,32,37,43,1
-2/13/2023,2,17,21,22,26,10
-2/11/2023,2,3,24,28,46,9
-2/8/2023,4,5,29,36,37,7
-2/6/2023,3,4,20,32,35,6
-2/4/2023,8,17,18,21,52,5
-2/1/2023,10,16,33,34,45,4
-1/30/2023,2,16,28,32,38,8
-1/28/2023,1,24,34,37,52,9
-1/25/2023,9,15,28,47,49,7
-1/23/2023,6,8,16,43,47,9
-1/21/2023,25,27,29,35,50,6
-1/18/2023,12,18,24,27,45,1
-1/16/2023,7,20,21,27,52,4
-1/14/2023,25,35,37,38,48,5
-1/11/2023,5,23,45,46,51,3
-1/9/2023,27,32,34,39,43,7
-1/7/2023,26,28,32,36,49,8
-1/4/2023,2,12,30,37,46,1
-1/2/2023,10,12,13,27,50,7
-12/31/2022,9,29,30,35,42,8
-12/28/2022,2,10,21,44,45,7
-12/26/2022,4,11,26,49,51,10
-12/24/2022,7,12,40,44,48,1
-12/21/2022,12,14,23,38,45,2
-12/19/2022,4,10,25,34,50,5
-12/17/2022,7,12,16,40,49,1
-12/14/2022,18,21,22,30,32,3
-12/12/2022,3,23,31,33,51,7
-12/10/2022,2,17,29,31,43,10
-12/7/2022,2,19,22,47,48,5
-12/5/2022,4,13,17,24,34,1
-12/3/2022,30,32,36,42,43,10
-11/30/2022,12,21,35,42,45,6
-11/28/2022,5,6,29,34,49,4
-11/26/2022,1,27,31,46,52,7
-11/23/2022,12,21,29,35,42,3
-11/21/2022,3,12,14,29,32,4
-11/19/2022,9,16,19,32,48,5
-11/16/2022,3,19,26,43,50,2
-11/14/2022,9,23,29,40,49,10
-11/12/2022,8,20,21,26,38,10
-11/9/2022,1,5,7,15,52,4
-11/7/2022,5,13,15,17,20,9
-11/5/2022,5,20,25,40,46,1
-11/2/2022,12,19,37,50,52,9
-10/31/2022,4,23,26,48,51,4
-10/29/2022,14,16,27,38,49,4
-10/26/2022,1,10,26,35,39,6
-10/24/2022,17,19,22,31,52,4
-10/22/2022,5,19,44,49,52,2
-10/19/2022,8,30,35,44,52,7
-10/17/2022,19,20,24,30,39,7
-10/15/2022,3,16,24,26,50,1
-10/12/2022,2,14,20,40,48,2
-10/10/2022,4,8,14,32,44,4
-10/8/2022,1,4,9,14,49,3
-10/5/2022,14,21,37,38,47,5
-10/3/2022,6,7,9,28,39,2
-10/1/2022,5,7,13,16,38,10
-9/28/2022,13,38,39,44,45,6
-9/26/2022,21,22,24,46,51,6
-9/24/2022,3,20,33,34,42,6

lucky_for_life.csv

@@ -1,1692 +0,0 @@
-Draw Date,1,2,3,4,5,Lucky Ball
-8/21/2017,5,29,38,42,45,1
-8/24/2017,1,3,27,40,43,9
-8/28/2017,1,5,6,47,48,17
-8/31/2017,19,20,36,42,47,12
-9/4/2017,1,4,9,15,33,3
-9/7/2017,19,27,28,29,33,16
-9/11/2017,11,23,27,30,48,18
-9/14/2017,4,9,14,17,23,17
-9/18/2017,4,14,19,30,46,9
-9/21/2017,7,13,19,24,30,12
-9/25/2017,14,17,19,30,48,4
-9/28/2017,9,10,12,16,32,14
-10/2/2017,24,25,28,37,47,5
-10/5/2017,12,13,21,26,36,6
-10/9/2017,19,21,23,27,43,2
-10/12/2017,5,19,27,35,43,10
-10/16/2017,1,2,12,17,27,7
-10/19/2017,9,24,27,32,44,15
-10/23/2017,4,7,9,10,31,15
-10/26/2017,2,6,12,39,43,2
-10/30/2017,2,12,22,40,46,10
-11/2/2017,2,4,8,38,47,16
-11/6/2017,22,24,28,44,46,18
-11/9/2017,10,36,40,41,42,9
-11/13/2017,20,21,37,39,42,17
-11/16/2017,14,20,21,22,25,13
-11/20/2017,7,16,20,24,28,11
-11/23/2017,10,15,19,43,44,8
-11/27/2017,12,13,20,37,46,1
-11/30/2017,2,3,27,44,48,16
-12/4/2017,1,2,7,31,37,8
-12/7/2017,7,18,21,41,46,2
-12/11/2017,16,37,46,47,48,9
-12/14/2017,17,21,25,30,48,10
-12/18/2017,13,16,21,29,32,17
-12/21/2017,10,14,15,18,24,16
-12/25/2017,8,37,43,44,45,16
-12/28/2017,4,21,29,44,48,7
-1/1/2018,15,18,25,31,35,2
-1/4/2018,11,12,19,28,46,4
-1/8/2018,1,3,15,22,28,15
-1/11/2018,8,12,15,16,41,9
-1/15/2018,11,15,32,33,40,18
-1/18/2018,5,15,21,28,36,14
-1/22/2018,5,13,26,30,35,5
-1/25/2018,8,9,31,43,45,6
-1/29/2018,1,4,6,30,33,2
-2/1/2018,3,13,21,24,47,10
-2/5/2018,1,2,5,32,48,17
-2/8/2018,4,10,13,32,40,12
-2/12/2018,7,11,33,37,47,10
-2/15/2018,1,11,36,38,46,10
-2/19/2018,2,14,41,44,47,16
-2/22/2018,6,23,32,35,42,8
-2/26/2018,6,11,16,28,37,11
-3/1/2018,7,10,26,44,46,14
-3/5/2018,5,17,23,35,42,12
-3/8/2018,20,24,26,34,39,18
-3/12/2018,1,8,20,44,45,15
-3/15/2018,10,16,17,40,47,5
-3/19/2018,17,26,31,32,45,14
-3/22/2018,9,17,27,29,31,16
-3/26/2018,3,4,15,23,40,6
-3/29/2018,16,19,31,44,48,7
-4/2/2018,2,6,11,32,33,4
-4/5/2018,2,10,12,46,48,12
-4/9/2018,9,13,20,39,44,18
-4/12/2018,5,20,33,39,48,18
-4/16/2018,9,11,26,33,38,7
-4/19/2018,16,19,35,43,48,9
-4/23/2018,7,12,20,27,48,13
-4/26/2018,20,21,27,29,30,17
-4/30/2018,1,10,13,16,21,17
-5/3/2018,5,22,26,29,47,8
-5/7/2018,2,5,6,15,40,16
-5/10/2018,17,35,46,47,48,11
-5/14/2018,11,26,33,36,42,14
-5/17/2018,6,7,14,21,46,8
-5/21/2018,4,12,31,45,48,7
-5/24/2018,18,32,38,39,48,12
-5/28/2018,4,6,13,16,32,7
-5/31/2018,16,34,41,42,48,3
-6/4/2018,1,5,20,33,36,5
-6/7/2018,2,9,27,38,43,13
-6/11/2018,4,5,25,36,46,9
-6/14/2018,7,13,33,37,41,18
-6/18/2018,1,22,27,31,34,6
-6/21/2018,3,6,25,39,44,1
-6/25/2018,3,31,42,45,48,17
-6/28/2018,3,23,27,47,48,3
-7/2/2018,13,18,27,39,43,8
-7/5/2018,12,16,31,32,46,17
-7/9/2018,18,24,43,46,48,6
-7/12/2018,4,8,14,20,26,6
-7/16/2018,14,17,18,21,48,12
-7/19/2018,14,27,29,36,40,4
-7/23/2018,1,5,11,28,48,7
-7/26/2018,9,10,14,20,44,16
-7/30/2018,8,15,34,36,37,2
-8/2/2018,9,16,17,20,23,3
-8/6/2018,5,7,13,15,29,5
-8/9/2018,13,25,30,33,37,5
-8/13/2018,1,15,22,27,41,7
-8/16/2018,8,39,42,43,48,11
-8/20/2018,4,16,36,44,48,11
-8/23/2018,6,10,28,34,45,7
-8/27/2018,6,8,12,19,32,17
-8/30/2018,16,20,32,40,46,10
-9/3/2018,27,40,43,44,47,3
-9/6/2018,14,27,29,36,39,6
-9/10/2018,1,11,13,23,42,3
-9/13/2018,6,12,23,29,43,4
-9/17/2018,3,5,6,19,47,15
-9/20/2018,8,10,17,36,40,16
-9/24/2018,9,16,21,27,45,17
-9/27/2018,5,9,29,30,34,14
-10/1/2018,8,10,13,16,40,1
-10/4/2018,1,10,15,28,34,11
-10/8/2018,5,34,35,36,48,15
-10/11/2018,10,18,33,38,42,7
-10/15/2018,1,30,39,41,42,12
-10/18/2018,4,21,24,30,31,16
-10/22/2018,7,36,37,41,46,16
-10/25/2018,12,20,22,27,30,16
-10/29/2018,14,16,26,29,43,13
-11/1/2018,4,13,31,37,47,5
-11/5/2018,8,18,28,34,37,9
-11/8/2018,10,16,38,39,40,13
-11/12/2018,2,4,9,15,37,15
-11/15/2018,14,28,29,38,42,2
-11/19/2018,1,14,15,43,44,15
-11/22/2018,8,18,38,40,48,2
-11/26/2018,10,23,29,37,43,14
-11/29/2018,1,4,11,36,41,8
-12/3/2018,7,8,28,37,43,11
-12/6/2018,5,14,26,28,31,5
-12/10/2018,16,20,26,28,47,16
-12/13/2018,15,31,38,39,40,1
-12/17/2018,4,8,31,32,44,9
-12/20/2018,8,21,26,40,41,13
-12/24/2018,2,9,14,27,47,7
-12/27/2018,9,16,32,39,41,9
-12/31/2018,4,10,15,19,43,8
-1/3/2019,2,4,17,30,31,15
-1/7/2019,18,31,34,35,37,14
-1/10/2019,9,13,21,34,43,9
-1/14/2019,11,13,18,29,42,3
-1/17/2019,9,22,27,38,46,5
-1/21/2019,2,16,40,43,47,12
-1/24/2019,21,29,30,32,45,10
-1/28/2019,6,12,30,32,37,18
-1/31/2019,4,6,10,29,45,10
-2/4/2019,14,24,30,37,38,12
-2/7/2019,18,23,29,34,43,3
-2/11/2019,3,5,10,32,41,10
-2/14/2019,24,26,32,38,42,18
-2/18/2019,1,8,15,29,31,2
-2/21/2019,15,21,23,27,37,14
-2/25/2019,24,26,31,45,48,17
-2/28/2019,4,7,10,29,37,1
-3/4/2019,4,12,28,35,45,13
-3/7/2019,5,8,29,44,47,8
-3/11/2019,19,24,30,44,46,1
-3/14/2019,11,12,23,24,25,9
-3/18/2019,3,11,24,27,39,14
-3/21/2019,9,24,26,27,38,11
-3/25/2019,7,9,14,29,31,8
-3/28/2019,21,31,34,40,44,10
-4/1/2019,9,19,22,33,41,4
-4/4/2019,3,4,8,16,27,3
-4/8/2019,17,23,34,44,46,14
-4/11/2019,13,17,30,35,39,7
-4/15/2019,4,10,20,24,30,3
-4/18/2019,2,10,27,28,47,18
-4/22/2019,1,11,20,30,46,1
-4/25/2019,8,18,21,44,47,13
-4/29/2019,7,22,28,39,48,5
-5/2/2019,5,7,9,25,33,16
-5/6/2019,13,14,26,36,39,9
-5/9/2019,5,7,39,44,46,15
-5/13/2019,6,11,13,28,38,18
-5/16/2019,9,18,26,28,32,2
-5/20/2019,26,27,29,36,46,2
-5/23/2019,12,23,29,35,38,18
-5/27/2019,15,37,43,46,47,10
-5/30/2019,7,17,18,19,39,9
-6/3/2019,3,19,24,30,44,4
-6/6/2019,4,22,28,29,42,5
-6/10/2019,26,34,39,40,43,11
-6/13/2019,4,5,8,10,46,5
-6/17/2019,3,25,29,40,47,8
-6/20/2019,13,30,33,39,43,4
-6/24/2019,3,17,21,23,44,2
-6/27/2019,14,16,19,23,27,14
-7/1/2019,11,17,22,27,32,16
-7/4/2019,2,7,31,43,48,6
-7/8/2019,11,16,18,23,37,7
-7/11/2019,5,19,23,26,42,13
-7/15/2019,3,14,18,19,32,4
-7/18/2019,8,13,32,34,48,2
-7/22/2019,5,31,33,41,47,17
-7/25/2019,26,29,35,37,48,3
-7/29/2019,5,6,16,19,27,9
-8/1/2019,1,19,22,27,34,15
-8/5/2019,20,30,37,42,47,10
-8/8/2019,25,28,34,45,46,18
-8/12/2019,2,5,14,27,39,3
-8/15/2019,2,11,13,19,27,8
-8/19/2019,8,17,26,28,40,10
-8/22/2019,7,9,14,22,42,14
-8/26/2019,9,25,30,37,48,14
-8/29/2019,11,24,28,33,43,10
-9/2/2019,6,7,22,25,46,14
-9/5/2019,5,20,32,38,47,15
-9/9/2019,8,9,17,22,33,18
-9/12/2019,2,16,29,43,46,3
-9/16/2019,11,12,22,31,37,7
-9/19/2019,13,21,27,28,39,5
-9/23/2019,4,23,25,43,48,9
-9/26/2019,4,11,33,43,47,17
-9/30/2019,3,14,45,47,48,3
-10/3/2019,1,13,42,43,44,18
-10/7/2019,13,18,31,38,43,16
-10/10/2019,27,30,31,34,45,16
-10/14/2019,12,17,19,35,41,9
-10/17/2019,8,9,25,27,33,17
-10/21/2019,9,14,15,35,40,10
-10/24/2019,5,13,24,38,48,6
-10/28/2019,11,15,18,23,34,10
-10/31/2019,2,31,33,41,46,18
-11/4/2019,28,34,42,44,48,15
-11/7/2019,1,10,15,18,40,15
-11/11/2019,3,5,22,23,36,12
-11/14/2019,9,11,21,22,30,14
-11/18/2019,15,22,28,35,37,17
-11/21/2019,15,17,20,23,37,7
-11/25/2019,1,2,3,31,40,5
-11/28/2019,3,9,22,24,41,3
-12/2/2019,10,31,43,44,46,13
-12/5/2019,3,11,16,19,32,3
-12/9/2019,1,16,27,39,45,10
-12/12/2019,16,17,21,28,38,8
-12/16/2019,11,20,21,38,45,17
-12/19/2019,6,27,28,40,44,9
-12/23/2019,1,6,16,21,46,13
-12/26/2019,16,25,29,30,35,17
-12/30/2019,4,15,34,40,47,16
-1/2/2020,1,3,18,22,33,7
-1/6/2020,5,8,15,33,48,2
-1/9/2020,1,14,21,28,37,12
-1/13/2020,7,16,30,32,39,17
-1/16/2020,10,13,15,30,33,8
-1/20/2020,4,7,8,18,27,5
-1/23/2020,11,25,28,33,42,18
-1/27/2020,1,7,17,22,29,15
-1/30/2020,4,6,8,18,39,15
-2/3/2020,2,9,34,36,48,13
-2/6/2020,18,30,31,33,34,16
-2/10/2020,3,7,21,25,26,4
-2/13/2020,5,14,31,40,46,2
-2/17/2020,4,27,29,34,45,14
-2/20/2020,24,27,36,41,47,2
-2/24/2020,23,27,33,44,48,11
-2/27/2020,19,20,32,36,48,4
-3/2/2020,6,13,24,32,40,13
-3/5/2020,6,8,9,36,47,7
-3/9/2020,3,13,16,45,48,13
-3/12/2020,1,13,23,47,48,11
-3/16/2020,3,7,24,26,42,18
-3/19/2020,13,19,24,38,42,14
-3/23/2020,1,30,31,46,48,8
-3/26/2020,7,8,10,30,41,13
-3/30/2020,2,22,29,36,40,18
-4/2/2020,2,4,23,31,48,5
-4/6/2020,2,25,26,30,37,8
-4/9/2020,6,16,23,27,48,10
-4/13/2020,1,37,39,43,45,17
-4/16/2020,6,8,20,28,43,15
-4/20/2020,1,3,6,34,45,12
-4/23/2020,5,31,38,41,45,1
-4/27/2020,1,5,9,28,35,9
-4/30/2020,3,4,11,23,35,17
-5/4/2020,15,20,22,37,48,11
-5/7/2020,3,8,22,23,45,15
-5/11/2020,1,24,28,36,45,7
-5/14/2020,20,26,29,34,41,15
-5/18/2020,10,27,32,43,47,10
-5/21/2020,8,11,24,30,33,12
-5/25/2020,4,28,31,32,41,2
-5/28/2020,1,13,36,41,44,1
-6/1/2020,5,15,30,40,45,16
-6/4/2020,9,18,24,26,29,8
-6/8/2020,26,29,31,34,40,1
-6/11/2020,9,24,25,29,42,6
-6/15/2020,25,28,32,47,48,14
-6/18/2020,1,6,16,27,34,2
-6/22/2020,13,33,34,43,44,1
-6/25/2020,1,8,18,27,46,16
-6/29/2020,6,12,16,19,22,2
-7/2/2020,2,10,15,36,47,18
-7/6/2020,2,10,40,47,48,15
-7/9/2020,10,24,28,33,39,12
-7/13/2020,9,13,34,36,46,10
-7/16/2020,5,7,20,43,48,1
-7/20/2020,11,15,37,40,46,6
-7/23/2020,5,6,23,33,45,3
-7/27/2020,6,10,13,17,31,9
-7/30/2020,14,15,16,39,42,10
-8/3/2020,4,10,20,32,46,15
-8/6/2020,14,18,30,43,45,9
-8/10/2020,4,5,16,19,37,1
-8/13/2020,9,33,34,36,40,14
-8/17/2020,5,9,11,17,27,2
-8/20/2020,9,11,18,39,40,9
-8/24/2020,18,22,25,31,46,18
-8/27/2020,7,8,12,21,36,4
-8/31/2020,3,9,14,18,25,11
-9/3/2020,1,4,13,26,37,13
-9/7/2020,4,7,25,30,36,9
-9/10/2020,4,13,25,28,33,15
-9/14/2020,2,5,25,45,46,10
-9/17/2020,5,28,34,41,44,5
-9/21/2020,7,28,39,41,47,3
-9/24/2020,17,21,30,40,46,4
-9/28/2020,9,14,45,46,47,8
-10/1/2020,5,8,9,25,29,1
-10/5/2020,7,17,29,35,45,17
-10/8/2020,28,30,31,42,43,13
-10/12/2020,2,11,21,39,42,4
-10/15/2020,4,14,27,44,47,11
-10/19/2020,11,17,23,34,41,7
-10/22/2020,11,24,35,37,39,8
-10/26/2020,9,12,20,30,38,6
-10/29/2020,2,11,32,44,47,10
-11/2/2020,7,24,26,33,42,11
-11/5/2020,2,4,8,17,31,2
-11/9/2020,22,24,33,42,45,5
-11/12/2020,14,17,24,33,46,2
-11/16/2020,3,8,16,38,44,15
-11/19/2020,5,16,27,35,36,4
-11/23/2020,13,23,31,37,39,11
-11/26/2020,11,25,31,41,43,9
-11/30/2020,11,18,21,36,38,9
-12/3/2020,11,17,22,25,37,4
-12/7/2020,3,18,22,26,35,14
-12/10/2020,1,5,10,11,31,15
-12/14/2020,7,25,34,37,43,9
-12/17/2020,1,20,28,38,45,8
-12/21/2020,3,32,35,38,40,3
-12/24/2020,2,15,40,44,47,12
-12/28/2020,6,9,11,15,29,14
-12/31/2020,11,28,30,39,43,14
-1/4/2021,2,12,21,26,46,7
-1/7/2021,3,20,25,28,30,18
-1/11/2021,1,8,20,37,39,8
-1/14/2021,3,16,20,21,47,10
-1/18/2021,2,13,14,19,31,7
-1/21/2021,11,15,26,34,47,15
-1/25/2021,1,24,28,34,41,2
-1/28/2021,2,19,24,26,31,1
-2/1/2021,15,17,27,30,39,2
-2/4/2021,3,9,13,24,40,16
-2/8/2021,2,12,22,24,26,11
-2/11/2021,7,9,15,31,39,1
-2/15/2021,1,21,22,34,45,11
-2/18/2021,10,11,17,27,32,15
-2/22/2021,2,10,12,43,45,1
-2/25/2021,16,34,35,38,45,1
-3/1/2021,5,11,17,26,47,3
-3/4/2021,2,5,32,35,37,2
-3/8/2021,3,9,40,41,44,6
-3/11/2021,15,19,28,30,48,5
-3/15/2021,5,14,15,27,37,7
-3/18/2021,2,5,21,28,45,15
-3/22/2021,3,5,24,31,45,1
-3/25/2021,3,24,25,37,44,5
-3/29/2021,9,29,32,42,45,4
-4/1/2021,5,27,36,42,47,9
-4/5/2021,2,5,16,26,39,10
-4/8/2021,17,25,30,37,39,10
-4/12/2021,1,12,16,26,36,4
-4/15/2021,3,4,18,31,43,4
-4/19/2021,13,21,31,32,33,15
-4/22/2021,20,28,29,35,37,15
-4/26/2021,8,22,33,37,38,10
-4/29/2021,1,9,10,18,34,13
-5/3/2021,7,11,12,18,21,10
-5/6/2021,5,13,26,32,47,8
-5/10/2021,4,31,32,42,44,7
-5/13/2021,3,7,25,31,36,8
-5/17/2021,18,29,32,40,44,16
-5/20/2021,7,13,38,43,44,11
-5/24/2021,3,6,7,36,48,3
-5/27/2021,5,6,8,40,43,17
-5/31/2021,2,19,28,31,47,9
-6/3/2021,11,19,22,29,48,6
-6/7/2021,5,7,18,24,34,18
-6/10/2021,6,8,10,24,43,15
-6/14/2021,3,17,19,21,37,12
-6/17/2021,7,10,24,29,45,1
-6/21/2021,22,28,33,38,43,17
-6/24/2021,23,26,31,35,46,12
-6/28/2021,5,7,23,25,48,8
-7/1/2021,15,22,30,33,43,2
-7/5/2021,2,5,6,20,36,11
-7/8/2021,2,17,18,35,44,18
-7/12/2021,11,12,22,24,46,13
-7/15/2021,5,10,14,15,19,8
-7/19/2021,11,38,42,46,48,1
-7/20/2021,6,8,16,31,46,13
-7/21/2021,5,30,36,42,44,5
-7/22/2021,20,28,29,33,34,4
-7/23/2021,5,15,17,24,29,14
-7/24/2021,12,13,26,33,42,9
-7/25/2021,6,12,27,43,46,15
-7/26/2021,8,26,39,42,46,7
-7/27/2021,7,31,33,47,48,17
-7/28/2021,17,20,26,44,48,5
-7/29/2021,2,4,9,10,39,7
-7/30/2021,6,41,44,46,48,13
-7/31/2021,7,26,29,36,42,6
-8/1/2021,7,30,32,46,48,13
-8/2/2021,4,5,24,36,38,2
-8/3/2021,10,15,18,41,45,10
-8/4/2021,1,25,30,36,37,2
-8/5/2021,5,15,36,44,46,17
-8/6/2021,1,4,6,25,26,1
-8/7/2021,2,35,41,43,44,16
-8/8/2021,1,14,23,29,31,6
-8/9/2021,2,4,19,35,48,9
-8/10/2021,15,22,34,44,48,9
-8/11/2021,1,17,21,24,27,14
-8/12/2021,1,9,19,20,31,9
-8/13/2021,6,10,16,26,31,18
-8/14/2021,28,34,39,42,45,4
-8/15/2021,16,23,26,29,46,11
-8/16/2021,3,13,39,40,44,15
-8/17/2021,2,10,25,29,48,6
-8/18/2021,18,21,22,31,33,6
-8/19/2021,11,12,16,38,48,11
-8/20/2021,8,24,36,39,45,6
-8/21/2021,1,10,23,27,33,4
-8/22/2021,5,8,15,23,39,14
-8/23/2021,4,6,24,32,45,12
-8/24/2021,4,10,13,24,44,12
-8/25/2021,9,24,33,40,48,11
-8/26/2021,9,12,31,36,45,14
-8/27/2021,4,8,17,35,39,4
-8/28/2021,2,6,8,11,38,2
-8/29/2021,4,19,30,42,48,16
-8/30/2021,13,22,28,30,44,11
-8/31/2021,6,15,27,36,37,4
-9/1/2021,7,21,23,26,36,3
-9/2/2021,6,21,22,27,41,13
-9/3/2021,7,16,28,36,44,12
-9/4/2021,20,22,23,33,40,16
-9/5/2021,4,21,23,36,42,3
-9/6/2021,3,6,18,38,44,8
-9/7/2021,8,14,16,32,38,15
-9/8/2021,2,5,15,35,44,14
-9/9/2021,1,2,4,34,39,2
-9/10/2021,1,6,19,21,28,2
-9/11/2021,4,5,22,29,39,14
-9/12/2021,1,3,11,13,34,1
-9/13/2021,5,7,22,28,30,5
-9/14/2021,17,22,24,37,48,18
-9/15/2021,21,22,32,45,48,14
-9/16/2021,1,18,19,34,39,15
-9/17/2021,8,12,35,36,45,2
-9/18/2021,4,10,26,30,47,6
-9/19/2021,3,4,31,37,43,6
-9/20/2021,22,35,38,40,41,1
-9/21/2021,1,5,37,44,48,6
-9/22/2021,11,34,38,43,46,6
-9/23/2021,13,27,32,39,41,2
-9/24/2021,7,18,20,31,40,12
-9/25/2021,6,16,24,33,34,5
-9/26/2021,7,23,28,30,39,5
-9/27/2021,1,13,17,40,45,12
-9/28/2021,2,17,23,38,42,14
-9/29/2021,9,26,40,41,45,6
-9/30/2021,12,23,32,38,47,11
-10/1/2021,2,15,38,43,47,10
-10/2/2021,1,12,24,25,37,2
-10/3/2021,15,35,36,39,46,9
-10/4/2021,2,3,29,37,39,17
-10/5/2021,18,20,33,44,46,10
-10/6/2021,8,14,23,44,45,17
-10/7/2021,2,7,21,34,41,5
-10/8/2021,6,22,24,29,46,1
-10/9/2021,12,27,28,30,33,9
-10/10/2021,7,23,27,33,43,15
-10/11/2021,4,17,20,22,40,9
-10/12/2021,1,6,8,25,31,17
-10/13/2021,13,16,18,23,33,17
-10/14/2021,20,28,32,38,45,5
-10/15/2021,5,15,21,32,45,6
-10/16/2021,20,33,38,39,40,6
-10/17/2021,5,11,24,42,43,3
-10/18/2021,9,17,18,25,47,16
-10/19/2021,1,8,22,28,44,7
-10/20/2021,6,20,21,31,42,3
-10/21/2021,6,13,17,25,28,2
-10/22/2021,1,3,14,21,28,10
-10/23/2021,5,12,19,33,44,6
-10/24/2021,3,20,21,32,38,6
-10/25/2021,13,25,27,35,39,9
-10/26/2021,9,11,15,25,37,7
-10/27/2021,14,23,39,42,44,17
-10/28/2021,21,23,24,44,46,13
-10/29/2021,1,14,24,42,45,9
-10/30/2021,5,19,22,36,37,10
-10/31/2021,5,7,11,21,29,15
-11/1/2021,4,27,28,29,47,8
-11/2/2021,8,19,26,38,39,6
-11/3/2021,7,19,25,32,45,3
-11/4/2021,6,9,12,23,41,8
-11/5/2021,1,2,11,35,40,1
-11/6/2021,23,24,27,32,33,10
-11/7/2021,15,18,24,30,42,10
-11/8/2021,23,24,33,40,43,14
-11/9/2021,5,9,10,12,34,15
-11/10/2021,7,8,20,35,47,1
-11/11/2021,21,27,34,36,47,15
-11/12/2021,7,15,21,22,35,12
-11/13/2021,1,29,33,36,38,5
-11/14/2021,1,8,21,22,27,11
-11/15/2021,5,12,14,28,34,3
-11/16/2021,1,12,23,30,47,2
-11/17/2021,7,11,24,28,29,9
-11/18/2021,10,32,36,42,46,16
-11/19/2021,3,4,9,19,40,11
-11/20/2021,12,22,24,26,30,11
-11/21/2021,3,11,17,20,28,5
-11/22/2021,5,7,8,14,35,8
-11/23/2021,6,11,14,16,41,14
-11/24/2021,5,6,9,29,30,4
-11/25/2021,10,12,14,36,41,11
-11/26/2021,1,13,20,34,48,9
-11/27/2021,2,6,7,11,19,1
-11/28/2021,9,14,24,29,30,7
-11/29/2021,16,17,22,25,29,13
-11/30/2021,9,25,29,40,42,14
-12/1/2021,4,6,32,36,40,8
-12/2/2021,8,23,29,34,48,1
-12/3/2021,3,12,14,25,44,7
-12/4/2021,9,18,23,30,47,16
-12/5/2021,7,14,18,19,41,7
-12/6/2021,1,8,11,26,39,10
-12/7/2021,24,31,41,43,44,15
-12/8/2021,5,20,24,40,43,16
-12/9/2021,8,21,23,25,41,16
-12/10/2021,23,29,35,36,39,8
-12/11/2021,8,9,16,31,44,17
-12/12/2021,7,21,35,41,44,17
-12/13/2021,3,9,20,24,43,16
-12/14/2021,10,23,24,28,45,18
-12/15/2021,10,23,26,30,39,7
-12/16/2021,8,10,17,38,48,4
-12/17/2021,6,7,25,28,45,16
-12/18/2021,4,7,27,43,44,6
-12/19/2021,9,16,42,44,48,14
-12/20/2021,17,21,31,35,45,6
-12/21/2021,2,10,18,26,31,14
-12/22/2021,4,29,32,35,46,17
-12/23/2021,18,20,22,24,35,13
-12/24/2021,2,9,22,38,42,8
-12/25/2021,2,5,7,29,44,8
-12/26/2021,4,16,27,28,46,9
-12/27/2021,12,14,28,37,47,8
-12/28/2021,4,6,14,33,41,9
-12/29/2021,9,19,21,33,48,8
-12/30/2021,7,15,19,26,32,9
-12/31/2021,19,36,37,39,41,8
-1/1/2022,10,13,19,36,48,12
-1/2/2022,3,5,12,36,40,1
-1/3/2022,7,12,19,22,30,1
-1/4/2022,7,8,13,29,40,3
-1/5/2022,5,8,22,37,43,8
-1/6/2022,8,10,12,17,23,10
-1/7/2022,5,9,22,28,44,2
-1/8/2022,10,32,44,45,47,16
-1/9/2022,3,10,28,38,46,16
-1/10/2022,7,14,32,43,48,2
-1/11/2022,2,5,8,18,43,16
-1/12/2022,3,27,29,33,48,7
-1/13/2022,3,10,24,27,37,17
-1/14/2022,2,12,14,36,40,3
-1/15/2022,2,9,25,28,36,15
-1/16/2022,5,10,18,28,48,13
-1/17/2022,9,29,33,38,45,2
-1/18/2022,4,31,36,37,43,16
-1/19/2022,17,20,24,40,42,9
-1/20/2022,4,25,27,33,43,5
-1/21/2022,4,23,25,28,35,16
-1/22/2022,9,15,17,21,48,5
-1/23/2022,7,20,34,37,43,10
-1/24/2022,9,22,25,29,31,1
-1/25/2022,19,30,32,36,41,12
-1/26/2022,10,11,15,18,22,3
-1/27/2022,16,23,27,34,40,7
-1/28/2022,11,21,27,32,48,7
-1/29/2022,3,28,31,35,46,6
-1/30/2022,4,11,23,24,31,11
-1/31/2022,3,27,28,35,41,7
-2/1/2022,4,10,20,25,36,17
-2/2/2022,3,5,11,32,40,16
-2/3/2022,6,14,16,25,36,4
-2/4/2022,19,20,22,28,41,11
-2/5/2022,4,18,25,43,45,12
-2/6/2022,24,25,33,37,40,8
-2/7/2022,6,28,36,39,41,16
-2/8/2022,3,10,14,16,29,6
-2/9/2022,8,16,22,23,40,15
-2/10/2022,8,16,25,28,48,9
-2/11/2022,5,7,16,19,43,3
-2/12/2022,13,25,27,39,45,16
-2/13/2022,4,14,18,19,37,4
-2/14/2022,3,10,20,27,41,7
-2/15/2022,25,27,28,31,38,9
-2/16/2022,1,2,7,32,40,16
-2/17/2022,9,29,33,38,41,1
-2/18/2022,1,3,23,42,45,6
-2/19/2022,5,6,14,37,41,17
-2/20/2022,12,15,24,35,48,3
-2/21/2022,10,19,35,43,45,11
-2/22/2022,7,23,24,28,48,15
-2/23/2022,1,21,22,28,32,1
-2/24/2022,1,2,5,10,34,6
-2/25/2022,9,23,25,32,38,14
-2/26/2022,30,40,44,47,48,15
-2/27/2022,7,8,33,39,47,1
-2/28/2022,3,26,29,30,35,15
-3/1/2022,15,21,30,31,35,18
-3/2/2022,12,20,30,32,46,16
-3/3/2022,5,14,18,20,29,9
-3/4/2022,5,8,30,33,39,5
-3/5/2022,7,10,24,35,46,12
-3/6/2022,15,29,34,44,46,8
-3/7/2022,8,13,19,21,34,11
-3/8/2022,1,8,17,26,41,11
-3/9/2022,6,12,25,38,47,11
-3/10/2022,1,7,18,41,42,3
-3/11/2022,9,22,29,30,47,10
-3/12/2022,3,4,6,21,23,16
-3/13/2022,4,7,9,15,28,11
-3/14/2022,3,10,12,22,47,14
-3/15/2022,25,33,34,35,46,2
-3/16/2022,2,3,6,33,46,12
-3/17/2022,10,26,28,42,45,6
-3/18/2022,1,3,22,29,37,3
-3/19/2022,6,13,16,37,41,18
-3/20/2022,7,8,26,31,39,1
-3/21/2022,8,11,40,43,46,10
-3/22/2022,9,11,26,34,36,6
-3/23/2022,1,3,28,34,42,6
-3/24/2022,11,12,19,26,46,12
-3/25/2022,28,30,32,33,39,2
-3/26/2022,13,23,28,34,39,4
-3/27/2022,1,5,11,25,42,7
-3/28/2022,13,31,34,35,37,3
-3/29/2022,6,15,16,22,47,6
-3/30/2022,5,37,38,46,48,9
-3/31/2022,8,20,36,41,45,17
-4/1/2022,6,16,25,40,47,9
-4/2/2022,19,23,32,34,39,16
-4/3/2022,10,20,21,32,36,11
-4/4/2022,16,18,29,32,33,3
-4/5/2022,1,15,28,29,41,9
-4/6/2022,3,5,10,18,23,4
-4/7/2022,8,24,27,30,33,14
-4/8/2022,6,16,20,36,39,7
-4/9/2022,1,4,10,26,42,11
-4/10/2022,7,8,10,17,32,16
-4/11/2022,1,8,38,41,43,6
-4/12/2022,1,14,15,31,32,18
-4/13/2022,10,26,38,39,40,18
-4/14/2022,5,13,15,30,37,10
-4/15/2022,1,21,22,46,48,9
-4/16/2022,6,27,28,35,44,3
-4/17/2022,4,7,10,16,23,12
-4/18/2022,2,14,28,41,48,11
-4/19/2022,1,26,38,41,42,11
-4/20/2022,11,17,28,32,42,2
-4/21/2022,6,11,12,30,31,3
-4/22/2022,2,5,20,41,47,8
-4/23/2022,2,29,30,37,42,14
-4/24/2022,11,13,28,30,37,4
-4/25/2022,8,18,32,36,43,4
-4/26/2022,2,22,35,38,39,2
-4/27/2022,4,6,13,24,41,16
-4/28/2022,17,19,20,26,45,17
-4/29/2022,8,15,20,32,39,15
-4/30/2022,3,5,7,33,45,17
-5/1/2022,7,8,19,36,38,10
-5/2/2022,2,12,32,35,43,14
-5/3/2022,5,8,11,33,34,14
-5/4/2022,14,20,21,34,44,14
-5/5/2022,10,12,21,33,34,4
-5/6/2022,7,17,23,35,46,14
-5/7/2022,10,23,24,38,41,8
-5/8/2022,18,19,24,29,47,10
-5/9/2022,12,19,30,34,39,15
-5/10/2022,1,13,18,22,45,7
-5/11/2022,2,20,30,31,39,15
-5/12/2022,15,21,23,32,45,12
-5/13/2022,6,9,13,28,38,18
-5/14/2022,4,9,13,33,44,3
-5/15/2022,4,7,13,25,40,13
-5/16/2022,2,10,11,18,22,17
-5/17/2022,5,16,29,31,32,14
-5/18/2022,13,28,36,37,42,8
-5/19/2022,15,16,18,23,25,14
-5/20/2022,3,19,43,44,48,2
-5/21/2022,13,17,31,41,47,13
-5/22/2022,7,11,25,31,46,18
-5/23/2022,1,2,6,30,46,12
-5/24/2022,1,3,26,39,46,10
-5/25/2022,11,12,28,30,37,1
-5/26/2022,24,26,27,39,46,15
-5/27/2022,2,3,17,38,47,1
-5/28/2022,3,21,31,37,40,5
-5/29/2022,6,15,29,35,38,9
-5/30/2022,7,24,32,34,36,5
-5/31/2022,1,6,11,35,46,18
-6/1/2022,11,15,26,35,44,4
-6/2/2022,3,28,32,38,39,18
-6/3/2022,2,30,32,40,46,16
-6/4/2022,3,6,12,34,45,9
-6/5/2022,11,19,21,39,46,14
-6/6/2022,9,21,24,29,36,15
-6/7/2022,4,10,15,23,47,9
-6/8/2022,5,14,16,25,26,10
-6/9/2022,2,12,16,33,35,10
-6/10/2022,12,18,26,37,39,8
-6/11/2022,11,16,31,37,41,2
-6/12/2022,1,16,26,27,44,3
-6/13/2022,9,16,17,24,27,4
-6/14/2022,18,24,25,29,37,9
-6/15/2022,13,17,19,32,37,13
-6/16/2022,6,14,23,36,40,6
-6/17/2022,6,13,21,31,40,1
-6/18/2022,12,15,16,25,47,10
-6/19/2022,2,16,23,38,47,9
-6/20/2022,8,22,27,32,38,12
-6/21/2022,2,19,22,27,36,6
-6/22/2022,20,24,31,34,47,4
-6/23/2022,10,12,20,22,47,14
-6/24/2022,15,18,28,41,44,17
-6/25/2022,9,11,30,45,46,17
-6/26/2022,6,21,24,35,48,3
-6/27/2022,2,12,16,29,40,13
-6/28/2022,1,14,38,45,48,5
-6/29/2022,16,17,20,31,42,4
-6/30/2022,4,16,19,24,46,1
-7/1/2022,13,28,30,36,37,18
-7/2/2022,3,13,16,18,27,9
-7/3/2022,20,23,29,41,48,13
-7/4/2022,5,7,8,15,30,10
-7/5/2022,8,15,23,33,48,7
-7/6/2022,1,6,15,35,42,18
-7/7/2022,2,28,33,34,43,16
-7/8/2022,2,20,25,34,43,12
-7/9/2022,14,21,31,35,41,7
-7/10/2022,1,17,24,35,40,7
-7/11/2022,13,14,20,27,34,8
-7/12/2022,8,14,23,47,48,9
-7/13/2022,2,23,28,33,34,11
-7/14/2022,4,14,16,34,39,3
-7/15/2022,4,5,10,22,36,14
-7/16/2022,13,14,34,37,43,18
-7/17/2022,2,4,18,22,41,1
-7/18/2022,4,9,16,36,43,9
-7/19/2022,2,8,19,25,43,17
-7/20/2022,6,36,38,46,47,10
-7/21/2022,19,24,25,29,31,8
-7/22/2022,3,20,33,37,39,11
-7/23/2022,2,12,16,32,44,9
-7/24/2022,11,27,37,38,48,16
-7/25/2022,3,27,33,35,45,2
-7/26/2022,5,7,16,38,44,9
-7/27/2022,4,16,29,34,39,10
-7/28/2022,5,15,20,37,46,9
-7/29/2022,3,11,15,16,45,1
-7/30/2022,8,24,33,44,46,6
-7/31/2022,1,7,8,18,38,1
-8/1/2022,1,5,14,22,41,15
-8/2/2022,5,20,24,26,33,17
-8/3/2022,1,17,25,27,42,10
-8/4/2022,16,21,26,43,45,13
-8/5/2022,19,27,36,39,42,17
-8/6/2022,10,16,32,45,47,10
-8/7/2022,7,12,31,37,44,1
-8/8/2022,4,21,34,37,48,11
-8/9/2022,21,37,42,46,47,12
-8/10/2022,6,19,21,44,45,3
-8/11/2022,3,8,15,43,46,6
-8/12/2022,15,26,28,38,42,5
-8/13/2022,13,26,34,37,48,2
-8/14/2022,1,3,15,17,37,13
-8/15/2022,1,22,26,28,47,13
-8/16/2022,26,33,41,45,46,10
-8/17/2022,4,7,27,37,42,15
-8/18/2022,7,13,17,22,25,4
-8/19/2022,25,30,40,43,44,3
-8/20/2022,3,38,43,44,48,18
-8/21/2022,17,19,22,31,35,8
-8/22/2022,6,7,15,41,43,2
-8/23/2022,4,5,21,27,48,4
-8/24/2022,23,26,30,38,40,12
-8/25/2022,5,6,9,27,30,8
-8/26/2022,2,8,16,30,45,1
-8/27/2022,1,5,10,33,38,9
-8/28/2022,4,5,35,37,48,2
-8/29/2022,2,6,24,32,39,11
-8/30/2022,8,15,19,46,47,18
-8/31/2022,5,23,26,29,36,10
-9/1/2022,1,10,24,26,30,9
-9/2/2022,1,12,17,28,44,14
-9/3/2022,6,8,14,25,42,6
-9/4/2022,10,11,29,45,48,4
-9/5/2022,5,10,21,37,39,12
-9/6/2022,3,8,39,44,47,3
-9/7/2022,2,27,37,40,42,5
-9/8/2022,4,11,17,25,26,3
-9/9/2022,8,16,23,34,42,17
-9/10/2022,20,23,29,30,34,15
-9/11/2022,3,5,28,33,43,18
-9/12/2022,4,6,16,41,46,11
-9/13/2022,12,15,28,29,48,4
-9/14/2022,4,12,25,39,43,7
-9/15/2022,2,18,27,41,45,9
-9/16/2022,23,33,34,35,42,14
-9/17/2022,11,12,23,31,45,3
-9/18/2022,4,5,8,16,19,9
-9/19/2022,4,6,11,15,42,10
-9/20/2022,5,26,28,37,42,10
-9/21/2022,8,19,25,28,35,10
-9/22/2022,4,10,28,31,41,6
-9/23/2022,10,14,17,42,43,11
-9/24/2022,10,18,23,31,46,3
-9/25/2022,4,5,17,39,41,15
-9/26/2022,5,12,18,21,27,11
-9/27/2022,2,10,38,42,47,4
-9/28/2022,2,4,25,44,46,13
-9/29/2022,3,10,11,27,30,5
-9/30/2022,5,14,23,27,48,10
-10/1/2022,11,24,29,32,38,6
-10/2/2022,1,3,10,12,13,2
-10/3/2022,2,9,27,33,40,1
-10/4/2022,21,25,32,37,40,17
-10/5/2022,1,14,32,45,46,1
-10/6/2022,8,13,17,21,45,15
-10/7/2022,7,9,13,16,18,1
-10/8/2022,6,18,33,38,39,17
-10/9/2022,18,24,25,27,29,17
-10/10/2022,15,16,20,28,40,9
-10/11/2022,11,14,20,23,26,2
-10/12/2022,10,14,15,17,30,2
-10/13/2022,9,17,27,42,48,14
-10/14/2022,8,13,26,33,37,4
-10/15/2022,8,15,25,34,43,13
-10/16/2022,6,14,15,20,33,1
-10/17/2022,12,19,24,27,38,11
-10/18/2022,2,18,28,29,43,4
-10/19/2022,1,6,26,28,31,8
-10/20/2022,3,27,33,40,41,12
-10/21/2022,14,20,27,47,48,3
-10/22/2022,1,10,32,37,41,8
-10/23/2022,33,42,44,47,48,15
-10/24/2022,1,5,9,31,38,3
-10/25/2022,17,30,40,41,45,1
-10/26/2022,18,21,22,35,38,18
-10/27/2022,15,28,29,37,43,6
-10/28/2022,14,18,22,37,43,13
-10/29/2022,11,12,39,41,44,11
-10/30/2022,25,27,28,34,44,7
-10/31/2022,3,13,16,19,28,3
-11/1/2022,1,6,10,35,45,1
-11/2/2022,6,10,16,26,42,9
-11/3/2022,14,19,26,32,36,6
-11/4/2022,7,14,15,36,43,2
-11/5/2022,8,18,20,45,47,15
-11/6/2022,1,7,17,32,36,4
-11/7/2022,11,12,15,34,43,15
-11/8/2022,15,17,33,37,40,6
-11/9/2022,3,5,9,36,41,1
-11/10/2022,12,30,34,36,43,16
-11/11/2022,2,23,29,42,46,1
-11/12/2022,2,12,26,29,35,18
-11/13/2022,20,21,24,33,45,2
-11/14/2022,4,15,19,36,43,17
-11/15/2022,17,28,33,34,36,11
-11/16/2022,1,16,21,32,44,8
-11/17/2022,13,14,22,23,30,3
-11/18/2022,20,24,26,33,41,18
-11/19/2022,1,21,34,39,44,10
-11/20/2022,19,24,35,43,47,5
-11/21/2022,1,2,5,33,38,12
-11/22/2022,8,11,13,20,28,4
-11/23/2022,20,21,24,34,37,14
-11/24/2022,12,15,22,25,43,10
-11/25/2022,1,6,23,36,42,1
-11/26/2022,5,12,18,19,31,4
-11/27/2022,2,25,27,30,39,12
-11/28/2022,17,21,35,36,42,9
-11/29/2022,17,18,26,27,48,13
-11/30/2022,5,6,11,15,30,9
-12/1/2022,4,10,27,42,48,1
-12/2/2022,4,8,20,25,34,16
-12/3/2022,1,7,13,30,40,3
-12/4/2022,4,8,22,38,43,12
-12/5/2022,15,19,20,38,48,15
-12/6/2022,11,16,22,31,42,18
-12/7/2022,2,23,32,44,48,2
-12/8/2022,2,4,14,29,40,8
-12/9/2022,4,23,31,44,46,5
-12/10/2022,2,16,30,39,41,9
-12/11/2022,4,15,28,32,45,18
-12/12/2022,13,15,29,36,44,8
-12/13/2022,4,5,10,20,34,6
-12/14/2022,2,4,6,17,20,5
-12/15/2022,2,10,19,35,46,15
-12/16/2022,1,22,30,32,34,18
-12/17/2022,8,12,36,39,47,14
-12/18/2022,11,19,20,25,34,18
-12/19/2022,10,12,23,32,45,11
-12/20/2022,22,23,26,34,39,17
-12/21/2022,1,5,21,27,38,3
-12/22/2022,8,16,24,27,38,1
-12/23/2022,5,12,30,37,41,17
-12/24/2022,4,7,15,25,36,7
-12/25/2022,9,25,34,41,48,18
-12/26/2022,17,18,22,37,43,16
-12/27/2022,9,19,35,42,43,6
-12/28/2022,7,10,14,15,41,8
-12/29/2022,7,9,11,23,32,12
-12/30/2022,8,13,35,42,47,1
-12/31/2022,2,5,37,39,40,14
-1/1/2023,1,4,7,14,36,11
-1/2/2023,4,12,15,25,44,1
-1/3/2023,14,24,34,45,47,1
-1/4/2023,2,5,11,13,40,15
-1/5/2023,7,15,23,32,40,2
-1/6/2023,7,18,24,33,43,6
-1/7/2023,4,5,13,22,44,8
-1/8/2023,6,18,32,42,47,9
-1/9/2023,3,5,24,26,31,5
-1/10/2023,7,15,29,41,43,5
-1/11/2023,24,39,41,42,45,6
-1/12/2023,3,12,17,42,45,6
-1/13/2023,3,17,21,24,44,10
-1/14/2023,4,7,16,22,40,8
-1/15/2023,5,8,13,41,44,10
-1/16/2023,11,17,25,31,38,17
-1/17/2023,3,4,25,35,48,18
-1/18/2023,12,27,35,42,44,6
-1/19/2023,6,8,12,21,42,6
-1/20/2023,2,10,28,30,44,13
-1/21/2023,6,10,11,29,35,7
-1/22/2023,7,9,13,24,44,5
-1/23/2023,1,2,26,36,38,1
-1/24/2023,1,25,28,39,47,10
-1/25/2023,19,22,29,41,43,13
-1/26/2023,15,17,26,29,35,9
-1/27/2023,4,5,7,39,42,10
-1/28/2023,2,5,35,38,45,9
-1/29/2023,15,16,21,23,46,6
-1/30/2023,9,16,34,46,47,13
-1/31/2023,2,3,10,15,22,12
-2/1/2023,11,19,31,33,46,10
-2/2/2023,10,17,22,42,46,13
-2/3/2023,2,20,31,34,48,3
-2/4/2023,14,24,30,44,47,18
-2/5/2023,2,16,23,43,47,3
-2/6/2023,1,5,15,39,46,16
-2/7/2023,3,7,18,31,32,4
-2/8/2023,2,10,32,37,40,5
-2/9/2023,17,33,35,38,48,3
-2/10/2023,10,11,12,18,27,18
-2/11/2023,1,12,13,36,48,6
-2/12/2023,8,9,21,22,32,18
-2/13/2023,1,8,15,39,48,7
-2/14/2023,7,21,27,41,44,13
-2/15/2023,9,16,28,35,44,1
-2/16/2023,6,11,40,42,45,10
-2/17/2023,24,33,36,42,47,14
-2/18/2023,9,10,22,24,34,10
-2/19/2023,8,16,31,39,47,7
-2/20/2023,8,12,41,42,47,1
-2/21/2023,19,22,35,41,48,7
-2/22/2023,7,26,37,39,47,6
-2/23/2023,1,7,20,21,38,15
-2/24/2023,17,22,24,30,44,5
-2/25/2023,26,28,38,42,46,1
-2/26/2023,5,9,18,35,38,9
-2/27/2023,2,3,17,38,40,8
-2/28/2023,1,20,32,41,44,14
-3/1/2023,6,11,19,35,46,7
-3/2/2023,10,13,33,40,47,15
-3/3/2023,9,12,35,37,44,15
-3/4/2023,4,7,15,17,30,5
-3/5/2023,1,7,10,25,43,11
-3/6/2023,3,7,24,25,28,4
-3/7/2023,10,28,30,37,38,1
-3/8/2023,1,16,31,36,44,5
-3/9/2023,28,39,43,44,47,18
-3/10/2023,11,14,24,29,43,6
-3/11/2023,3,7,10,28,35,17
-3/12/2023,9,27,32,37,43,1
-3/13/2023,3,9,20,27,37,15
-3/14/2023,2,3,14,18,47,4
-3/15/2023,16,20,21,39,40,15
-3/16/2023,5,22,28,34,45,7
-3/17/2023,26,29,35,39,48,5
-3/18/2023,8,18,19,29,41,4
-3/19/2023,23,27,30,37,47,3
-3/20/2023,1,6,12,31,38,7
-3/21/2023,7,25,36,38,43,3
-3/22/2023,7,19,30,33,44,18
-3/23/2023,3,7,24,26,48,12
-3/24/2023,1,8,30,31,43,17
-3/25/2023,9,11,20,22,48,14
-3/26/2023,20,30,33,40,47,13
-3/27/2023,13,24,26,36,47,5
-3/28/2023,7,9,16,28,30,5
-3/29/2023,17,22,29,30,47,15
-3/30/2023,10,27,34,36,48,13
-3/31/2023,16,19,28,31,34,4
-4/1/2023,1,12,25,39,45,3
-4/2/2023,3,6,18,22,40,5
-4/3/2023,2,13,21,45,46,16
-4/4/2023,10,13,20,22,25,8
-4/5/2023,6,13,17,25,33,15
-4/6/2023,3,10,17,33,36,6
-4/7/2023,21,25,31,42,48,11
-4/8/2023,1,16,18,20,41,5
-4/9/2023,12,15,28,35,37,7
-4/10/2023,3,5,6,17,21,18
-4/11/2023,1,5,9,33,47,16
-4/12/2023,12,17,21,31,46,1
-4/13/2023,4,11,19,28,37,12
-4/14/2023,3,15,38,40,44,3
-4/15/2023,6,10,22,23,33,16
-4/16/2023,6,21,29,34,47,18
-4/17/2023,3,6,12,38,46,12
-4/18/2023,15,19,22,23,34,10
-4/19/2023,2,3,18,23,31,10
-4/20/2023,1,5,18,33,48,9
-4/21/2023,4,7,8,25,29,2
-4/22/2023,5,18,38,41,45,13
-4/23/2023,16,21,31,33,36,12
-4/24/2023,17,18,21,25,42,13
-4/25/2023,17,28,33,40,42,15
-4/26/2023,20,26,28,38,43,12
-4/27/2023,6,11,12,34,42,9
-4/28/2023,9,31,32,34,47,15
-4/29/2023,17,19,34,36,37,8
-4/30/2023,8,11,30,37,47,13
-5/1/2023,7,10,14,16,26,2
-5/2/2023,29,30,34,46,48,12
-5/3/2023,4,8,12,36,46,13
-5/4/2023,8,9,13,19,43,17
-5/5/2023,6,9,28,37,39,3
-5/6/2023,24,32,35,38,42,2
-5/7/2023,3,6,7,19,42,2
-5/8/2023,3,15,31,33,44,14
-5/9/2023,6,12,15,41,46,8
-5/10/2023,8,9,35,37,40,14
-5/11/2023,10,16,34,40,47,5
-5/12/2023,1,2,13,24,35,14
-5/13/2023,10,12,16,23,32,2
-5/14/2023,5,10,28,45,48,8
-5/15/2023,1,13,17,34,41,11
-5/16/2023,1,14,18,23,34,6
-5/17/2023,15,22,28,29,41,6
-5/18/2023,10,16,23,36,38,1
-5/19/2023,1,10,28,30,40,16
-5/20/2023,13,23,30,34,39,13
-5/21/2023,9,11,18,22,27,9
-5/22/2023,17,25,37,40,41,1
-5/23/2023,16,22,24,26,27,8
-5/24/2023,1,25,26,46,47,18
-5/25/2023,10,20,30,45,48,3
-5/26/2023,2,12,27,32,38,14
-5/27/2023,1,3,12,35,45,5
-5/28/2023,2,10,21,36,44,9
-5/29/2023,14,17,32,33,44,14
-5/30/2023,25,28,35,43,46,2
-5/31/2023,10,19,43,45,47,11
-6/1/2023,2,15,17,22,28,11
-6/2/2023,17,22,26,31,48,18
-6/3/2023,16,19,20,42,46,12
-6/4/2023,13,15,20,35,41,2
-6/5/2023,15,20,23,33,46,17
-6/6/2023,3,35,38,43,47,15
-6/7/2023,1,5,18,43,47,13
-6/8/2023,12,32,38,42,46,6
-6/9/2023,3,15,17,21,35,15
-6/10/2023,2,17,19,29,34,10
-6/11/2023,14,23,24,36,47,5
-6/12/2023,9,26,27,35,41,17
-6/13/2023,3,10,11,14,21,2
-6/14/2023,6,16,28,34,45,18
-6/15/2023,6,7,26,44,47,6
-6/16/2023,2,6,34,38,46,2
-6/17/2023,14,29,30,40,44,18
-6/18/2023,6,12,14,17,41,15
-6/19/2023,15,17,22,43,45,10
-6/20/2023,10,17,26,28,30,10
-6/21/2023,2,5,28,30,37,12
-6/22/2023,11,13,34,35,42,16
-6/23/2023,15,23,27,38,48,3
-6/24/2023,2,23,29,32,37,9
-6/25/2023,16,17,18,35,47,11
-6/26/2023,1,8,24,29,36,1
-6/27/2023,1,15,20,31,44,18
-6/28/2023,14,27,38,40,45,13
-6/29/2023,5,24,28,38,46,8
-6/30/2023,1,34,42,45,48,4
-7/1/2023,3,26,27,29,48,11
-7/2/2023,1,16,17,31,46,11
-7/3/2023,12,14,25,29,43,3
-7/4/2023,3,6,21,41,42,10
-7/5/2023,8,16,26,30,38,2
-7/6/2023,5,7,11,12,40,5
-7/7/2023,2,3,15,16,34,13
-7/8/2023,17,30,33,36,44,9
-7/9/2023,6,8,18,19,48,11
-7/10/2023,6,15,32,34,39,1
-7/11/2023,3,21,24,28,35,14
-7/12/2023,15,16,18,20,45,17
-7/13/2023,19,20,21,22,25,12
-7/14/2023,6,8,16,19,45,18
-7/15/2023,6,9,20,21,27,4
-7/16/2023,3,9,44,46,48,9
-7/17/2023,2,4,17,30,45,12
-7/18/2023,4,20,21,47,48,2
-7/19/2023,12,16,28,32,45,1
-7/20/2023,12,27,31,39,46,5
-7/21/2023,1,13,28,30,41,7
-7/22/2023,15,22,23,30,44,5
-7/23/2023,8,12,17,19,31,12
-7/24/2023,3,17,31,35,42,12
-7/25/2023,2,3,6,7,33,10
-7/26/2023,4,15,32,34,38,15
-7/27/2023,19,25,32,36,40,12
-7/28/2023,2,3,7,21,42,1
-7/29/2023,9,14,23,30,34,4
-7/30/2023,5,9,19,44,46,15
-7/31/2023,8,26,28,30,35,1
-8/1/2023,13,33,40,42,47,8
-8/2/2023,4,15,31,39,46,14
-8/3/2023,5,18,19,25,48,4
-8/4/2023,3,16,18,42,47,7
-8/5/2023,18,24,27,43,44,7
-8/6/2023,4,6,22,25,48,8
-8/7/2023,4,8,12,37,38,11
-8/8/2023,9,11,19,36,45,13
-8/9/2023,13,19,26,27,43,9
-8/10/2023,8,15,23,38,42,15
-8/11/2023,5,8,26,32,40,11
-8/12/2023,11,25,29,30,42,5
-8/13/2023,3,6,12,37,44,3
-8/14/2023,6,25,37,39,47,7
-8/15/2023,1,21,23,28,30,7
-8/16/2023,13,19,25,33,48,15
-8/17/2023,5,14,17,24,34,7
-8/18/2023,7,8,25,36,46,14
-8/19/2023,7,16,34,35,42,13
-8/20/2023,2,18,34,41,47,5
-8/21/2023,2,12,15,28,43,10
-8/22/2023,5,14,15,33,43,17
-8/23/2023,5,21,29,33,37,17
-8/24/2023,5,30,35,40,41,7
-8/25/2023,4,6,26,41,44,6
-8/26/2023,10,13,24,30,40,7
-8/27/2023,38,41,42,45,46,12
-8/28/2023,5,19,26,40,48,13
-8/29/2023,9,24,32,42,43,16
-8/30/2023,6,8,14,39,40,13
-8/31/2023,1,27,30,39,41,6
-9/1/2023,18,22,34,39,47,14
-9/2/2023,14,19,37,46,47,16
-9/3/2023,9,22,26,35,41,17
-9/4/2023,2,4,8,16,22,15
-9/5/2023,3,23,24,31,48,9
-9/6/2023,6,8,9,31,48,4
-9/7/2023,12,34,38,46,48,7
-9/8/2023,1,3,13,35,43,6
-9/9/2023,11,16,27,38,42,18
-9/10/2023,9,16,19,20,48,3
-9/11/2023,7,16,22,34,45,11
-9/12/2023,3,11,13,26,45,13
-9/13/2023,2,8,30,32,37,10
-9/14/2023,9,19,23,26,47,18
-9/15/2023,2,3,24,36,47,13
-9/16/2023,8,20,32,38,43,18
-9/17/2023,11,15,17,24,48,13
-9/18/2023,2,22,28,31,38,6
-9/19/2023,1,3,10,23,34,3
-9/20/2023,8,9,20,31,47,11
-9/21/2023,8,12,29,32,34,18
-9/22/2023,8,30,31,40,46,14
-9/23/2023,15,18,30,44,46,6
-9/24/2023,6,25,26,28,31,17
-9/25/2023,2,7,9,11,18,7
-9/26/2023,12,14,16,32,33,4
-9/27/2023,15,26,31,33,38,10
-9/28/2023,16,19,25,30,47,11
-9/29/2023,12,20,21,33,38,11
-9/30/2023,23,26,38,43,45,12
-10/1/2023,11,13,24,29,47,3
-10/2/2023,9,10,21,38,46,12
-10/3/2023,3,11,16,18,33,1
-10/4/2023,11,25,28,43,45,10
-10/5/2023,15,23,30,40,41,9
-10/6/2023,7,28,33,37,38,10
-10/7/2023,10,18,21,29,40,17
-10/8/2023,1,3,4,11,48,10
-10/9/2023,9,13,17,30,38,10
-10/10/2023,3,6,19,35,44,18
-10/11/2023,23,25,26,37,38,15
-10/12/2023,11,15,22,28,29,18
-10/13/2023,8,14,19,21,30,13
-10/14/2023,19,22,23,27,48,3
-10/15/2023,4,10,14,38,42,1
-10/16/2023,9,15,17,18,48,5
-10/17/2023,2,14,15,21,35,6
-10/18/2023,14,24,28,39,47,17
-10/19/2023,12,30,31,35,47,2
-10/20/2023,2,8,37,39,40,1
-10/21/2023,2,6,24,27,38,2
-10/22/2023,24,30,41,46,47,6
-10/23/2023,11,13,15,22,44,2
-10/24/2023,2,16,21,29,35,7
-10/25/2023,1,19,31,32,38,5
-10/26/2023,9,24,34,39,45,18
-10/27/2023,8,13,15,29,48,9
-10/28/2023,2,13,19,44,46,6
-10/29/2023,17,25,35,40,47,12
-10/30/2023,3,6,12,14,17,18
-10/31/2023,28,31,33,40,47,16
-11/1/2023,16,18,32,36,47,14
-11/2/2023,10,14,17,27,48,10
-11/3/2023,11,16,30,34,40,3
-11/4/2023,10,12,20,28,48,11
-11/5/2023,1,13,32,45,48,14
-11/6/2023,9,11,12,20,32,10
-11/7/2023,1,12,20,37,45,4
-11/8/2023,11,25,27,42,45,12
-11/9/2023,2,15,22,35,39,2
-11/10/2023,6,18,28,31,42,17
-11/11/2023,10,24,27,31,37,11
-11/12/2023,2,13,27,28,34,18
-11/13/2023,8,10,30,45,47,14
-11/14/2023,20,35,36,44,48,1
-11/15/2023,5,6,15,20,48,5
-11/16/2023,11,22,25,29,34,10
-11/17/2023,5,8,27,33,39,17
-11/18/2023,1,2,3,27,30,5
-11/19/2023,11,14,29,42,43,3
-11/20/2023,5,12,16,31,40,9
-11/21/2023,23,30,36,37,47,15
-11/22/2023,7,31,35,39,43,4
-11/23/2023,7,25,33,43,44,9
-11/24/2023,3,12,15,38,44,9
-11/25/2023,3,6,9,21,26,4
-11/26/2023,5,30,31,33,40,7
-11/27/2023,6,20,22,26,38,17
-11/28/2023,9,15,18,31,40,16
-11/29/2023,16,33,38,39,47,10
-11/30/2023,7,12,28,37,41,2
-12/1/2023,15,33,34,41,43,17
-12/2/2023,3,6,17,45,46,15
-12/3/2023,11,15,28,36,40,11
-12/4/2023,1,16,22,39,40,5
-12/5/2023,11,12,21,22,35,1
-12/6/2023,4,9,15,25,40,11
-12/7/2023,3,11,17,18,38,2
-12/8/2023,26,28,31,33,37,18
-12/9/2023,1,6,19,28,48,2
-12/10/2023,11,19,20,37,44,9
-12/11/2023,13,14,19,31,34,4
-12/12/2023,28,30,31,34,45,17
-12/13/2023,8,35,37,39,46,7
-12/14/2023,11,18,41,46,48,8
-12/15/2023,5,16,20,23,30,15
-12/16/2023,12,17,27,36,44,10
-12/17/2023,6,14,21,37,43,5
-12/18/2023,9,11,17,32,33,6
-12/19/2023,7,10,23,31,32,14
-12/20/2023,1,11,19,34,40,11
-12/21/2023,8,10,20,21,47,3
-12/22/2023,12,13,22,31,46,2
-12/23/2023,3,9,11,14,48,5
-12/24/2023,2,18,22,39,41,2
-12/25/2023,4,15,27,29,30,2
-12/26/2023,8,26,27,29,33,9
-12/27/2023,8,12,36,38,45,1
-12/28/2023,12,18,31,36,46,11
-12/29/2023,11,17,21,40,46,3
-12/30/2023,6,13,17,37,44,17
-12/31/2023,3,10,31,39,47,15
-1/1/2024,6,7,15,31,43,8
-1/2/2024,10,24,40,44,48,11
-1/3/2024,3,17,21,25,43,12
-1/4/2024,10,15,30,45,46,15
-1/5/2024,15,21,29,35,41,18
-1/6/2024,8,15,20,38,39,14
-1/7/2024,6,9,19,39,47,15
-1/8/2024,9,19,25,33,43,6
-1/9/2024,5,29,30,39,40,17
-1/10/2024,2,3,15,22,30,14
-1/11/2024,9,10,21,24,28,7
-1/12/2024,4,6,14,33,39,4
-1/13/2024,3,25,32,36,48,6
-1/14/2024,20,28,33,38,42,10
-1/15/2024,3,12,14,25,39,9
-1/16/2024,8,13,21,22,42,7
-1/17/2024,3,13,16,29,36,14
-1/18/2024,20,23,24,34,47,3
-1/19/2024,17,30,33,36,41,8
-1/20/2024,9,10,18,23,40,16
-1/21/2024,11,14,16,32,42,11
-1/22/2024,7,26,30,31,38,3
-1/23/2024,5,8,11,38,40,1
-1/24/2024,2,3,13,19,34,8
-1/25/2024,2,14,35,37,38,11
-1/26/2024,2,4,13,30,37,7
-1/27/2024,9,34,36,39,45,13
-1/28/2024,4,11,23,25,27,8
-1/29/2024,14,16,28,30,43,13
-1/30/2024,1,10,23,36,38,2
-1/31/2024,2,28,38,43,46,1
-2/1/2024,16,21,23,26,45,2
-2/2/2024,1,12,24,37,47,6
-2/3/2024,8,9,18,31,38,9
-2/4/2024,10,16,27,33,44,13
-2/5/2024,7,26,39,43,46,12
-2/6/2024,16,32,34,36,47,3
-2/7/2024,14,23,45,47,48,9
-2/8/2024,7,29,31,38,46,17
-2/9/2024,8,12,18,27,48,17
-2/10/2024,13,15,27,31,40,12
-2/11/2024,1,2,11,24,36,16
-2/12/2024,3,12,18,39,44,7
-2/13/2024,5,11,35,41,44,12
-2/14/2024,4,7,39,42,46,4
-2/15/2024,17,41,42,45,46,16
-2/16/2024,4,12,15,36,46,17
-2/17/2024,21,31,36,37,44,7
-2/18/2024,18,31,42,46,47,14
-2/19/2024,7,19,31,34,47,11
-2/20/2024,5,7,13,37,39,14
-2/21/2024,20,21,29,43,45,13
-2/22/2024,2,4,6,34,47,8
-2/23/2024,7,11,30,35,36,5
-2/24/2024,14,21,28,33,35,18
-2/25/2024,3,13,14,17,26,12
-2/26/2024,1,7,17,38,46,12
-2/27/2024,10,16,28,45,46,5
-2/28/2024,2,9,19,28,34,12
-2/29/2024,15,21,37,41,44,2
-3/1/2024,1,7,29,36,44,4
-3/2/2024,1,4,19,26,37,2
-3/3/2024,3,18,20,42,45,8
-3/4/2024,3,9,17,30,42,15
-3/5/2024,7,17,22,25,43,11
-3/6/2024,13,24,28,36,38,1
-3/7/2024,14,17,28,31,39,3
-3/8/2024,24,32,36,40,48,6
-3/9/2024,12,19,22,42,46,17
-3/10/2024,1,6,26,36,47,4
-3/11/2024,24,26,31,38,42,17
-3/12/2024,3,13,24,36,44,11
-3/13/2024,27,43,44,45,47,18
-3/14/2024,7,24,27,29,43,10
-3/15/2024,13,16,18,19,34,5
-3/16/2024,1,6,19,27,45,14
-3/17/2024,1,15,20,43,44,4
-3/18/2024,8,20,35,36,38,16
-3/19/2024,2,5,19,26,38,6
-3/20/2024,23,30,33,37,45,1
-3/21/2024,10,11,32,40,41,15
-3/22/2024,18,27,34,35,43,16
-3/23/2024,1,3,8,13,29,11
-3/24/2024,5,19,30,37,45,13
-3/25/2024,1,4,31,39,47,5
-3/26/2024,18,25,34,39,48,12
-3/27/2024,3,10,16,37,44,4
-3/28/2024,9,15,29,38,39,16
-3/29/2024,8,13,14,42,44,2
-3/30/2024,17,29,36,38,47,16
-3/31/2024,1,4,13,26,27,1
-4/1/2024,2,11,29,43,45,5
-4/2/2024,6,8,17,22,31,13
-4/3/2024,30,36,41,42,45,15
-4/4/2024,5,24,26,27,43,1
-4/5/2024,3,7,17,30,47,15
-4/6/2024,4,13,19,24,43,15
-4/7/2024,2,6,11,39,45,11
-4/8/2024,4,7,33,34,46,13
-4/9/2024,1,11,12,19,45,3
-4/10/2024,2,4,7,12,39,14
-4/11/2024,4,10,27,33,40,8
-4/12/2024,1,19,20,34,44,4
-4/13/2024,15,20,34,36,43,9
-4/14/2024,6,20,30,37,44,18
-4/15/2024,11,24,25,44,46,4
-4/16/2024,20,22,28,41,45,18
-4/17/2024,6,9,19,27,42,2
-4/18/2024,4,10,16,44,45,14
-4/19/2024,5,8,24,28,34,5
-4/20/2024,17,23,28,33,37,10
-4/21/2024,23,24,31,33,40,10
-4/22/2024,33,36,39,40,47,15
-4/23/2024,11,31,32,36,44,8
-4/24/2024,4,40,41,45,46,6
-4/25/2024,3,9,21,31,41,8
-4/26/2024,11,15,27,28,46,7
-4/27/2024,16,22,26,31,34,12
-4/28/2024,4,25,32,35,40,9
-4/29/2024,12,14,16,25,46,16
-4/30/2024,7,8,19,36,41,1
-5/1/2024,2,9,19,21,46,13
-5/2/2024,7,14,16,37,41,17
-5/3/2024,15,19,32,34,36,7
-5/4/2024,1,4,5,6,33,1
-5/5/2024,1,6,10,16,27,8
-5/6/2024,10,32,35,43,47,6
-5/7/2024,9,21,22,33,48,18
-5/8/2024,17,30,31,33,44,16
-5/9/2024,3,6,7,22,41,4
-5/10/2024,24,30,32,35,41,11
-5/11/2024,3,9,20,23,37,2
-5/12/2024,8,14,26,29,47,15
-5/13/2024,13,16,20,39,43,11
-5/14/2024,9,27,43,44,48,9
-5/15/2024,12,18,24,38,40,5
-5/16/2024,12,19,34,39,45,14
-5/17/2024,2,22,31,34,37,9
-5/18/2024,18,21,34,37,40,13
-5/19/2024,6,16,32,34,41,12
-5/20/2024,12,15,19,20,47,16
-5/21/2024,5,13,24,41,48,15
-5/22/2024,5,8,15,17,37,4
-5/23/2024,4,8,9,28,29,11
-5/24/2024,13,17,24,29,33,7
-5/25/2024,2,4,21,26,42,18
-5/26/2024,2,17,25,26,43,2
-5/27/2024,2,9,17,19,46,4
-5/28/2024,9,18,21,37,46,1
-5/29/2024,9,12,15,41,46,4
-5/30/2024,9,11,12,14,24,5
-5/31/2024,10,31,34,42,46,17
-6/1/2024,22,29,33,36,40,15
-6/2/2024,8,16,19,20,25,6
-6/3/2024,8,21,23,39,40,8
-6/4/2024,8,13,39,42,48,11
-6/5/2024,1,2,12,30,33,6
-6/6/2024,21,28,30,31,37,12
-6/7/2024,3,12,15,25,32,2
-6/8/2024,3,17,29,31,33,11
-6/9/2024,2,3,33,39,41,7
-6/10/2024,7,9,14,23,47,17
-6/11/2024,12,23,31,44,48,8
-6/12/2024,3,12,15,19,34,6
-6/13/2024,1,12,18,23,38,1
-6/14/2024,6,21,25,33,45,6
-6/15/2024,2,7,8,12,21,16
-6/16/2024,1,12,20,38,43,10
-6/17/2024,15,26,32,38,46,3
-6/18/2024,5,14,18,37,48,5
-6/19/2024,10,16,18,19,31,10
-6/20/2024,22,24,25,28,35,4
-6/21/2024,4,7,13,29,46,1
-6/22/2024,12,14,22,38,46,4
-6/23/2024,3,5,23,43,46,8
-6/24/2024,20,26,27,29,33,14
-6/25/2024,15,20,23,33,45,5
-6/26/2024,5,12,36,39,40,6
-6/27/2024,5,14,34,46,48,8
-6/28/2024,10,21,41,43,48,4
-6/29/2024,10,11,22,25,44,9
-6/30/2024,6,9,12,24,32,14
-7/1/2024,13,22,31,47,48,5
-7/2/2024,9,15,18,28,34,3
-7/3/2024,10,11,23,35,42,16
-7/4/2024,3,4,22,33,48,4
-7/5/2024,7,15,23,41,48,17
-7/6/2024,3,13,21,29,37,6
-7/7/2024,7,13,15,30,34,4
-7/8/2024,2,9,27,37,48,1
-7/9/2024,25,31,40,41,44,4
-7/10/2024,2,14,19,22,36,9
-7/11/2024,3,4,9,17,37,10
-7/12/2024,1,2,27,34,44,14
-7/13/2024,8,16,27,33,34,10
-7/14/2024,9,13,16,20,23,11
-7/15/2024,1,2,3,20,24,18
-7/16/2024,21,26,31,34,40,15
-7/17/2024,7,18,20,39,46,10
-7/18/2024,9,22,25,35,45,10
-7/19/2024,4,7,20,26,34,8
-7/20/2024,14,19,20,35,46,11
-7/21/2024,2,5,20,36,39,7
-7/22/2024,17,19,20,28,29,11
-7/23/2024,1,4,15,25,31,17
-7/24/2024,15,18,21,25,36,16
-7/25/2024,2,11,33,46,47,8
-7/26/2024,1,4,21,37,41,13
-7/27/2024,9,32,37,40,43,15
-7/28/2024,2,4,10,26,29,3
-7/29/2024,18,28,30,32,33,11
-7/30/2024,19,22,34,41,45,12
-7/31/2024,10,16,20,31,44,12
-8/1/2024,3,25,36,41,42,14
-8/2/2024,11,13,16,27,33,16
-8/3/2024,8,10,15,17,21,18
-8/4/2024,10,17,19,29,46,10
-8/5/2024,20,26,28,33,44,9
-8/6/2024,4,15,21,22,35,3
-8/7/2024,3,9,30,45,46,1
-8/8/2024,3,4,9,33,44,12
-8/9/2024,19,26,36,42,43,17
-8/10/2024,3,26,30,37,43,2
-8/11/2024,3,5,10,12,32,16
-8/12/2024,3,6,17,24,35,2
-8/13/2024,6,30,37,42,47,3
-8/14/2024,7,19,29,30,39,4
-8/15/2024,3,7,19,24,38,11
-8/16/2024,5,12,17,21,45,8
-8/17/2024,22,24,27,42,47,4
-8/18/2024,2,4,11,32,39,18
-8/19/2024,15,17,35,40,45,6
-8/20/2024,8,12,24,39,40,6
-8/21/2024,9,16,26,42,45,11
-8/22/2024,2,5,21,45,47,18
-8/23/2024,17,24,28,34,39,2
-8/24/2024,13,19,26,33,38,15
-8/25/2024,8,17,19,29,31,12
-8/26/2024,12,18,24,40,44,9
-8/27/2024,1,3,18,23,42,16
-8/28/2024,4,7,8,17,34,6
-8/29/2024,7,13,18,23,42,12
-8/30/2024,3,24,25,30,43,11
-8/31/2024,2,15,37,45,46,18
-9/1/2024,17,22,27,35,42,17
-9/2/2024,3,4,8,28,29,5
-9/3/2024,25,36,38,39,48,8
-9/4/2024,4,12,14,40,47,11
-9/5/2024,2,3,18,23,25,12
-9/6/2024,3,23,24,25,30,5
-9/7/2024,3,20,29,34,39,13
-9/8/2024,9,17,27,42,45,12
-9/9/2024,16,26,30,35,46,6
-9/10/2024,30,39,42,45,48,6
-9/11/2024,12,19,37,43,48,1
-9/12/2024,23,32,38,41,44,18
-9/13/2024,14,15,18,33,40,9
-9/14/2024,5,13,27,28,44,6
-9/15/2024,1,2,10,22,27,11
-9/16/2024,1,2,15,17,39,14
-9/17/2024,10,16,23,29,35,18
-9/18/2024,10,13,28,43,47,9
-9/19/2024,11,20,28,35,43,13
-9/20/2024,2,9,17,18,27,2
-9/21/2024,7,21,31,41,44,5
-9/22/2024,5,13,27,35,48,14
-9/23/2024,1,21,24,27,48,18
-9/24/2024,6,9,18,36,38,4
-9/25/2024,4,7,15,21,31,13
-9/26/2024,4,8,27,37,40,8
-9/27/2024,4,7,9,24,36,1
-9/28/2024,7,20,23,38,48,11
-9/29/2024,7,15,27,31,38,14
-9/30/2024,21,28,29,40,42,18
-10/1/2024,5,13,22,31,48,18
-10/2/2024,6,30,33,42,44,13
-10/3/2024,2,5,29,42,48,18
-10/4/2024,1,4,34,39,42,6
-10/5/2024,3,17,31,32,35,18
-10/6/2024,1,8,10,26,34,10
-10/7/2024,8,21,22,28,47,16
-10/8/2024,5,17,22,26,32,11
-10/9/2024,11,15,31,36,45,2
-10/10/2024,7,8,26,27,47,13
-10/11/2024,3,18,29,33,36,12
-10/12/2024,6,17,20,22,46,13
-10/13/2024,2,6,14,25,45,9
-10/14/2024,1,12,25,32,35,7
-10/15/2024,15,20,21,24,38,5
-10/16/2024,5,29,32,45,46,7
-10/17/2024,23,26,29,36,47,14
-10/18/2024,10,31,32,36,38,6
-10/19/2024,10,14,24,45,46,9
-10/20/2024,3,15,21,37,38,15
-10/21/2024,3,14,23,37,38,2
-10/22/2024,7,12,22,37,48,9
-10/23/2024,9,12,22,25,44,9
-10/24/2024,2,4,9,29,32,8
-10/25/2024,1,3,15,33,36,5
-10/26/2024,6,12,32,35,41,13
-10/27/2024,1,4,8,27,42,1
-10/28/2024,3,17,21,35,39,8
-10/29/2024,4,8,9,25,48,10
-10/30/2024,14,17,27,28,43,13
-10/31/2024,29,30,31,33,36,4
-11/1/2024,15,37,39,45,47,16
-11/2/2024,21,25,30,34,35,9
-11/3/2024,5,13,18,21,42,8
-11/4/2024,8,18,28,36,43,6
-11/5/2024,1,9,14,38,45,12
-11/6/2024,4,7,12,14,43,5
-11/7/2024,5,10,30,37,40,5
-11/8/2024,2,7,19,42,47,4
-11/9/2024,4,7,19,36,39,1
-11/10/2024,11,18,32,38,40,3
-11/11/2024,5,11,17,19,30,11
-11/12/2024,11,21,22,24,48,8
-11/13/2024,18,24,27,43,45,8
-11/14/2024,5,22,30,33,44,3
-11/15/2024,5,28,34,38,44,13
-11/16/2024,6,11,18,20,29,4
-11/17/2024,10,20,26,28,42,2
-11/18/2024,4,9,10,28,29,1
-11/19/2024,7,10,17,24,26,13
-11/20/2024,3,29,30,39,45,13
-11/21/2024,4,11,13,45,47,18
-11/22/2024,17,31,33,38,46,17
-11/23/2024,11,20,21,26,31,7
-11/24/2024,7,11,14,26,48,15
-11/25/2024,7,10,14,33,36,1
-11/26/2024,27,29,32,33,47,2
-11/27/2024,5,16,22,25,45,15
-11/28/2024,18,33,42,44,45,2
-11/29/2024,19,21,31,38,39,5
-11/30/2024,21,22,32,36,48,5
-12/1/2024,1,7,25,33,46,7
-12/2/2024,5,13,14,31,42,15
-12/3/2024,6,11,28,30,37,9
-12/4/2024,1,13,25,33,46,6
-12/5/2024,4,13,25,44,47,18
-12/6/2024,1,3,33,36,39,1
-12/7/2024,1,17,34,41,45,14
-12/8/2024,1,2,39,40,42,4
-12/9/2024,1,13,19,22,28,11
-12/10/2024,6,12,30,39,46,10
-12/11/2024,10,19,32,44,46,1
-12/12/2024,5,7,17,19,32,12
-12/13/2024,3,15,32,34,37,18
-12/14/2024,10,16,35,40,42,16
-12/15/2024,9,12,22,36,45,3
-12/16/2024,3,16,29,31,33,9
-12/17/2024,4,18,29,36,37,18
-12/18/2024,19,26,30,31,41,16
-12/19/2024,2,5,13,18,29,16
-12/20/2024,9,20,21,35,36,3
-12/21/2024,2,9,10,41,42,9
-12/22/2024,4,7,37,43,47,8
-12/23/2024,10,20,22,23,43,1
-12/24/2024,16,22,24,43,47,11
-12/25/2024,4,10,35,42,45,2
-12/26/2024,9,10,12,30,47,9
-11/27/2025,8,12,13,16,45,13
-11/28/2025,19,28,32,41,47,16
-11/29/2025,4,8,9,34,39,13
-11/30/2025,3,8,13,17,18,17
-12/1/2025,10,16,18,30,43,18
-12/2/2025,1,15,17,24,29,2
-12/3/2025,20,21,22,41,43,17
-12/4/2025,1,10,21,35,47,4
-12/5/2025,4,35,38,40,41,3
-12/6/2025,11,12,14,34,48,13
-12/7/2025,5,8,11,12,34,4
-12/8/2025,11,14,28,30,41,11
-12/9/2025,19,24,33,39,40,6
-12/10/2025,5,7,14,16,45,11
-12/11/2025,7,20,24,30,39,18
-12/12/2025,6,20,23,30,36,11
-12/13/2025,12,18,19,24,35,17
-12/14/2025,8,23,32,33,34,15
-12/15/2025,12,16,27,34,41,12
-12/16/2025,3,4,19,24,39,11
-12/17/2025,11,13,20,40,41,7
-12/18/2025,2,9,24,25,44,15
-12/19/2025,8,13,19,34,48,14
-12/20/2025,8,21,30,41,47,15
-12/21/2025,11,24,27,38,46,15
-12/22/2025,9,16,23,34,46,7

mb_predictor.py

@@ -1,84 +0,0 @@
-# import json
-# from pathlib import Path
-# from lotto_predictor import predict_for_game, NumpyEncoder
-
-# def main():
-#     csv_path = Path("mb_results.csv")
-#     try:
-#         # Run prediction
-#         print("Generating prediction...")
-#         res = predict_for_game(csv_path, "mb", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=False)
-#         print("Prediction:")
-#         print(json.dumps(res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Prediction failed: {str(e)}")
-    
-#     try:
-#         # Run backtest
-#         print("Starting backtest...")
-#         backtest_res = predict_for_game(csv_path, "mb", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=True)
-#         print("Backtest Results:")
-#         print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Backtest failed: {str(e)}")
-
-# if __name__ == "__main__":
-#     main()
-
-
-import json
-from pathlib import Path
-from lotto_predictor import predict_for_game_v3, NumpyEncoder
-
-def main():
-    csv_path = Path("mb_results.csv")
-    
-    try:
-        # Run prediction
-        print("Generating prediction...")
-        res = predict_for_game_v3(csv_path, "mb", run_backtest=False)
-        print("Prediction:")
-        print(json.dumps(res, indent=2, cls=NumpyEncoder))
-        print(f"\nPredicted Numbers: {res['numbers']}")
-        if res.get('star'):
-            print(f"Star Ball: {res['star']}")
-        
-        # Print model info
-        model_info = res.get('model_info', {})
-        print(f"\nModel built for {model_info.get('numbers_modeled', 0)} out of {model_info.get('total_possible', 0)} numbers")
-        
-    except Exception as e:
-        print(f"Prediction failed: {str(e)}")
-        import traceback
-        traceback.print_exc()
-    
-    # try:
-    #     # Run backtest
-    #     print("\n" + "="*50)
-    #     print("Starting backtest...")
-    #     backtest_res = predict_for_game_v3(csv_path, "mb", run_backtest=True)
-    #     print("\nBacktest Results:")
-    #     print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-        
-    #     # Print summary
-    #     if 'error' not in backtest_res:
-    #         print(f"\nBacktest Summary:")
-    #         print(f"Model 3+ matches: {backtest_res.get('model_3plus_rate', 0)}%")
-    #         print(f"Random 3+ matches: {backtest_res.get('random_3plus_rate', 0)}%")
-    #         print(f"Average sum error: {backtest_res.get('avg_sum_error', 0)}")
-    #         print(f"Even count accuracy: {backtest_res.get('even_count_accuracy', 0)}%")
-            
-    #         # Show hit rates comparison
-    #         print("\nHit Rate Comparison:")
-    #         for i in range(6):
-    #             model_rate = backtest_res.get(f'model_hit_{i}_rate', 0)
-    #             random_rate = backtest_res.get(f'random_hit_{i}_rate', 0)
-    #             print(f"{i} matches: Model {model_rate}% vs Random {random_rate}%")
-        
-    # except Exception as e:
-    #     print(f"Backtest failed: {str(e)}")
-    #     import traceback
-    #     traceback.print_exc()
-
-if __name__ == "__main__":
-    main()

mb_results.csv

@@ -1,576 +0,0 @@
-date,b1,b2,b3,b4,b5,megaball
-1/28/2026,8,11,23,28,37,4
-1/26/2026,10,12,26,30,37,2
-1/24/2026,6,13,24,31,37,5
-1/21/2026,12,13,39,40,41,6
-1/19/2026,18,21,36,37,38,1
-1/17/2026,2,10,23,26,28,3
-1/14/2026,5,8,21,28,37,6
-1/12/2026,2,19,23,32,33,4
-1/10/2026,7,8,9,14,31,3
-1/7/2026,3,8,13,33,40,4
-1/5/2026,1,9,17,21,28,4
-1/3/2026,1,22,24,26,30,6
-12/31/2025,5,18,25,36,41,6
-12/29/2025,3,13,24,33,39,2
-12/27/2025,5,9,11,26,39,6
-12/24/2025,6,14,23,27,37,6
-12/22/2025,19,20,29,34,40,2
-12/20/2025,5,8,11,13,40,6
-12/17/2025,17,26,29,39,40,2
-12/15/2025,1,5,8,10,41,3
-12/13/2025,1,20,21,24,32,4
-12/10/2025,2,25,26,27,41,5
-12/8/2025,1,10,12,19,23,1
-12/6/2025,8,19,25,27,41,1
-12/3/2025,3,7,23,24,34,2
-12/1/2025,6,13,14,29,33,2
-11/29/2025,7,14,30,33,40,1
-11/26/2025,1,15,21,26,37,4
-11/24/2025,19,20,24,28,40,1
-11/22/2025,2,4,5,9,19,1
-11/19/2025,4,14,16,39,40,2
-11/17/2025,5,19,26,27,33,1
-11/15/2025,4,11,28,34,38,4
-11/12/2025,11,14,17,19,31,5
-11/10/2025,1,15,17,21,28,3
-11/8/2025,5,7,10,33,39,6
-11/5/2025,9,19,22,30,38,6
-11/3/2025,2,9,18,19,25,3
-11/1/2025,8,13,19,24,36,2
-10/29/2025,5,6,17,22,41,6
-10/27/2025,5,7,34,35,39,2
-10/25/2025,7,20,23,37,39,4
-10/22/2025,3,20,23,29,33,3
-10/20/2025,1,10,14,21,33,6
-10/18/2025,14,20,23,24,25,1
-10/15/2025,11,19,29,30,37,3
-10/13/2025,1,2,10,13,21,3
-10/11/2025,23,27,29,30,31,3
-10/8/2025,3,10,17,31,35,3
-10/6/2025,9,15,28,34,35,2
-10/4/2025,4,7,13,19,23,3
-10/1/2025,2,8,24,25,32,4
-9/29/2025,14,21,29,32,35,6
-9/27/2025,14,15,18,26,34,5
-9/24/2025,4,6,15,22,36,4
-9/21/2025,2,14,15,32,33,1
-9/20/2025,4,8,16,26,28,3
-9/17/2025,6,10,21,31,34,3
-9/15/2025,7,10,18,19,41,5
-9/13/2025,4,7,15,30,34,2
-9/10/2025,12,22,29,30,41,5
-9/8/2025,1,3,20,26,41,6
-9/6/2025,3,4,23,26,39,2
-9/3/2025,2,3,16,25,33,5
-9/1/2025,8,14,16,24,34,3
-8/30/2025,1,8,9,16,38,4
-8/27/2025,3,5,11,15,25,1
-8/25/2025,2,13,19,20,38,5
-8/23/2025,10,17,29,36,38,3
-8/20/2025,2,3,11,14,38,6
-8/18/2025,14,15,18,25,30,1
-8/16/2025,5,11,25,31,41,1
-8/13/2025,1,2,7,9,21,4
-8/11/2025,9,10,31,38,39,3
-8/9/2025,12,23,26,37,41,6
-8/6/2025,9,12,16,17,36,4
-8/4/2025,5,16,29,39,41,1
-8/2/2025,1,4,5,9,20,4
-7/30/2025,1,2,11,15,27,3
-7/28/2025,3,4,5,17,34,1
-7/26/2025,15,16,21,24,33,5
-7/23/2025,3,4,16,25,31,6
-7/21/2025,6,18,20,22,24,5
-7/19/2025,5,9,25,34,38,4
-7/16/2025,5,17,22,26,37,4
-7/14/2025,2,4,34,35,40,3
-7/12/2025,13,16,21,22,36,3
-7/9/2025,20,23,27,31,32,2
-7/7/2025,4,26,29,33,39,3
-7/5/2025,4,16,33,40,41,5
-7/2/2025,8,10,13,15,17,3
-6/30/2025,4,6,26,34,39,2
-6/28/2025,5,6,19,20,34,1
-6/25/2025,20,25,29,40,41,1
-6/23/2025,8,23,24,26,32,5
-6/21/2025,11,17,21,29,41,5
-6/18/2025,15,19,21,27,35,3
-6/16/2025,8,14,25,36,38,1
-6/14/2025,19,21,36,38,39,2
-6/11/2025,2,4,18,32,33,5
-6/9/2025,20,24,27,38,41,6
-6/7/2025,5,13,24,34,39,2
-6/4/2025,6,8,15,34,37,4
-6/2/2025,1,8,10,19,20,1
-5/31/2025,6,7,32,39,41,3
-5/28/2025,3,19,27,30,36,2
-5/26/2025,2,14,16,29,34,1
-5/24/2025,4,7,19,38,40,4
-5/21/2025,2,20,21,22,26,6
-5/19/2025,12,21,22,27,28,4
-5/17/2025,9,22,24,27,31,6
-5/14/2025,1,7,16,22,38,2
-5/12/2025,1,6,15,30,38,1
-5/10/2025,3,5,11,18,31,5
-5/7/2025,6,29,31,32,41,6
-5/5/2025,15,20,24,34,35,4
-5/3/2025,1,9,24,29,33,6
-4/30/2025,4,9,14,21,29,1
-4/28/2025,2,15,17,28,30,3
-4/26/2025,9,10,12,16,35,6
-4/23/2025,6,19,27,28,41,3
-4/21/2025,4,6,18,28,41,4
-4/19/2025,9,17,25,36,37,6
-4/16/2025,9,11,21,31,38,5
-4/14/2025,15,17,20,27,38,2
-4/12/2025,16,19,26,27,30,5
-4/9/2025,4,14,21,30,37,2
-4/7/2025,7,24,26,38,39,6
-4/5/2025,6,11,15,22,37,1
-4/2/2025,4,13,22,23,36,1
-3/31/2025,1,13,14,21,29,2
-3/29/2025,4,18,36,37,39,2
-3/26/2025,9,11,15,23,40,6
-3/24/2025,2,3,4,8,19,6
-3/22/2025,2,4,21,22,34,6
-3/19/2025,15,24,27,31,36,6
-3/17/2025,7,18,21,25,35,3
-3/15/2025,12,21,26,30,31,1
-3/12/2025,10,12,13,21,30,6
-3/10/2025,3,16,24,35,41,2
-3/8/2025,10,12,17,19,40,6
-3/5/2025,1,3,18,30,40,6
-3/3/2025,9,10,29,32,40,4
-3/1/2025,7,26,30,31,38,2
-2/26/2025,2,12,27,32,34,6
-2/24/2025,13,23,33,35,39,6
-2/22/2025,19,25,33,38,40,2
-2/19/2025,22,30,34,36,41,6
-2/17/2025,7,8,26,33,37,5
-2/15/2025,19,29,32,33,36,6
-2/12/2025,10,29,32,34,36,4
-2/10/2025,5,10,25,26,36,3
-2/8/2025,3,16,24,25,31,2
-2/5/2025,4,11,20,33,34,5
-2/3/2025,8,16,26,29,39,5
-2/1/2025,1,9,14,19,33,5
-1/29/2025,2,6,17,27,41,5
-1/27/2025,3,30,31,34,39,4
-1/25/2025,1,15,20,25,27,1
-1/22/2025,26,27,31,40,41,5
-1/20/2025,5,9,14,25,37,5
-1/18/2025,2,4,16,21,32,1
-1/15/2025,8,20,29,34,36,6
-1/13/2025,2,6,20,23,24,2
-1/11/2025,9,16,21,24,36,5
-1/8/2025,18,24,25,27,31,3
-1/6/2025,7,8,29,33,35,4
-1/4/2025,10,14,22,30,34,4
-1/1/2025,1,19,21,24,27,1
-12/30/2024,6,9,14,28,39,3
-12/28/2024,1,27,28,29,32,4
-12/25/2024,10,20,24,25,37,3
-12/23/2024,16,18,21,24,37,5
-12/21/2024,2,4,6,7,20,4
-12/18/2024,2,9,29,36,37,2
-12/16/2024,2,19,26,35,36,3
-12/14/2024,3,7,14,26,37,4
-12/11/2024,5,9,18,20,28,3
-12/9/2024,6,7,16,26,29,5
-12/7/2024,2,19,21,24,28,6
-12/4/2024,3,5,21,28,37,1
-12/2/2024,12,31,37,38,41,1
-11/30/2024,18,22,24,33,38,3
-11/27/2024,11,17,20,24,35,6
-11/25/2024,1,10,18,20,40,1
-11/23/2024,19,21,30,32,37,2
-11/20/2024,6,23,28,34,35,5
-11/18/2024,3,12,16,24,25,4
-11/16/2024,3,10,17,23,25,6
-11/13/2024,4,5,23,35,39,3
-11/11/2024,1,2,9,30,38,6
-11/9/2024,3,11,15,28,29,3
-11/6/2024,3,8,11,13,31,6
-11/4/2024,2,13,14,32,39,4
-11/2/2024,15,24,27,28,38,6
-10/30/2024,1,12,30,34,38,1
-10/28/2024,7,28,35,38,40,1
-10/26/2024,5,11,16,19,37,1
-10/23/2024,10,15,17,26,38,3
-10/21/2024,2,4,23,25,36,4
-10/19/2024,6,17,19,39,41,5
-10/16/2024,2,5,7,14,21,2
-10/14/2024,14,15,22,33,40,4
-10/12/2024,18,21,31,33,39,1
-10/9/2024,10,15,21,26,32,3
-10/7/2024,7,17,20,22,25,4
-10/5/2024,1,2,6,28,30,4
-10/2/2024,4,6,13,19,35,1
-9/30/2024,10,11,35,36,38,1
-9/28/2024,16,20,23,37,39,3
-9/25/2024,2,8,18,19,27,5
-9/23/2024,1,18,25,26,39,1
-9/21/2024,3,26,31,33,39,4
-9/18/2024,1,3,6,18,23,6
-9/16/2024,11,14,19,29,41,2
-9/14/2024,1,13,22,25,34,1
-9/11/2024,12,13,14,15,22,4
-9/9/2024,5,9,19,23,36,6
-9/7/2024,10,14,20,25,37,4
-9/4/2024,6,18,21,24,38,1
-9/2/2024,5,20,25,37,41,3
-8/31/2024,9,10,15,26,29,3
-8/28/2024,15,23,24,33,41,3
-8/26/2024,4,10,14,30,38,4
-8/24/2024,7,13,28,31,39,5
-8/21/2024,11,20,25,29,33,2
-8/19/2024,2,14,34,36,40,6
-8/17/2024,2,4,17,19,33,2
-8/14/2024,7,13,18,36,41,2
-8/12/2024,18,22,29,34,39,1
-8/10/2024,9,15,21,22,40,5
-8/7/2024,12,21,24,27,31,5
-8/5/2024,1,14,23,27,29,3
-8/3/2024,7,14,19,26,33,3
-7/31/2024,1,10,14,16,22,1
-7/29/2024,10,19,22,34,35,5
-7/27/2024,3,24,26,29,30,6
-7/24/2024,5,7,10,18,26,5
-7/22/2024,2,3,15,17,22,2
-7/20/2024,3,6,7,30,37,2
-7/17/2024,4,5,11,12,35,2
-7/15/2024,2,8,37,38,41,4
-7/13/2024,6,12,15,31,41,5
-7/10/2024,6,8,12,14,34,2
-7/8/2024,9,20,27,33,36,3
-7/6/2024,8,12,21,35,38,5
-7/3/2024,6,16,19,29,34,6
-7/1/2024,2,17,26,33,37,1
-6/29/2024,6,10,22,26,39,3
-6/26/2024,7,21,31,35,36,3
-6/24/2024,8,11,21,25,34,6
-6/22/2024,12,15,19,22,31,5
-6/19/2024,2,4,9,10,12,4
-6/17/2024,10,16,20,23,28,4
-6/15/2024,7,14,18,21,24,6
-6/12/2024,12,17,21,28,31,1
-6/10/2024,9,10,11,13,15,5
-6/8/2024,20,22,25,27,38,5
-6/5/2024,3,8,10,13,27,3
-6/3/2024,8,13,19,33,40,2
-6/1/2024,2,7,11,19,22,6
-5/29/2024,13,19,21,36,40,6
-5/27/2024,14,15,27,28,35,3
-5/25/2024,11,14,23,34,35,5
-5/22/2024,17,19,24,25,33,2
-5/20/2024,11,14,20,32,35,3
-5/18/2024,1,15,33,35,40,1
-5/15/2024,13,14,23,32,38,2
-5/13/2024,4,5,19,21,34,3
-5/11/2024,3,7,15,27,37,5
-5/8/2024,4,6,17,25,27,4
-5/6/2024,5,20,24,29,35,2
-5/4/2024,8,15,30,32,38,6
-5/1/2024,11,18,20,34,38,6
-4/29/2024,6,10,22,31,36,4
-4/27/2024,3,8,13,29,37,5
-4/24/2024,4,17,24,25,36,3
-4/22/2024,24,25,26,35,40,1
-4/20/2024,3,9,17,18,27,5
-4/17/2024,13,14,18,21,41,6
-4/15/2024,3,11,28,35,39,6
-4/13/2024,28,35,36,38,40,2
-4/10/2024,1,9,25,29,32,2
-4/8/2024,3,5,6,11,37,5
-4/6/2024,8,19,21,27,41,3
-4/3/2024,13,16,27,34,37,6
-4/1/2024,2,11,24,26,28,4
-3/30/2024,10,13,15,21,27,2
-3/27/2024,3,13,14,28,39,5
-3/25/2024,4,16,18,19,30,5
-3/23/2024,4,5,8,15,23,3
-3/20/2024,5,19,30,33,37,4
-3/18/2024,2,12,15,19,33,5
-3/16/2024,4,17,28,33,37,5
-3/13/2024,3,5,11,18,29,6
-3/11/2024,14,18,25,30,38,4
-3/9/2024,5,6,8,19,24,2
-3/6/2024,13,14,25,33,39,4
-3/4/2024,2,10,23,28,32,1
-3/2/2024,17,30,33,38,40,1
-2/28/2024,21,22,24,25,30,6
-2/26/2024,4,15,23,28,31,5
-2/24/2024,2,7,23,25,38,6
-2/21/2024,1,11,22,26,32,6
-2/19/2024,11,17,20,25,29,6
-2/17/2024,3,8,26,31,40,1
-2/14/2024,2,3,7,9,17,1
-2/12/2024,7,13,14,22,31,4
-2/10/2024,1,5,6,14,32,5
-2/7/2024,8,17,24,31,41,4
-2/5/2024,8,26,31,38,40,2
-2/3/2024,8,12,15,21,25,3
-1/31/2024,1,12,27,37,41,4
-1/29/2024,4,5,15,23,35,2
-1/27/2024,1,3,4,22,24,5
-1/24/2024,2,4,21,24,26,6
-1/22/2024,3,9,21,24,37,3
-1/20/2024,12,13,19,22,35,6
-1/17/2024,1,2,10,16,22,6
-1/15/2024,11,21,23,30,37,4
-1/13/2024,14,17,23,26,37,5
-1/10/2024,10,14,26,31,34,4
-1/8/2024,10,14,25,29,30,6
-1/6/2024,12,17,25,36,38,3
-1/3/2024,2,12,14,15,20,4
-1/1/2024,4,16,22,25,40,3
-12/30/2023,6,11,13,21,26,6
-12/27/2023,7,20,21,31,36,3
-12/25/2023,5,6,12,31,40,4
-12/23/2023,2,5,6,12,26,2
-12/20/2023,1,15,16,25,37,3
-12/18/2023,14,15,22,24,37,4
-12/16/2023,12,13,15,20,23,2
-12/13/2023,3,4,12,17,28,2
-12/11/2023,3,7,17,20,21,2
-12/9/2023,2,11,13,16,28,6
-12/6/2023,1,4,21,26,40,1
-12/4/2023,4,17,18,19,24,3
-12/2/2023,16,27,33,39,41,4
-11/29/2023,23,25,27,35,36,3
-11/27/2023,9,16,21,22,29,4
-11/25/2023,10,13,16,22,39,2
-11/22/2023,12,24,28,29,40,3
-11/20/2023,5,13,17,21,39,1
-11/18/2023,12,18,25,33,35,5
-11/15/2023,19,20,21,24,33,1
-11/13/2023,4,8,9,12,41,4
-11/11/2023,6,14,25,28,35,1
-11/8/2023,2,16,22,23,27,6
-11/6/2023,4,5,6,12,24,5
-11/4/2023,7,12,18,21,32,5
-11/1/2023,5,20,32,37,38,6
-10/30/2023,15,21,27,36,41,5
-10/28/2023,1,13,21,26,29,4
-10/25/2023,4,30,32,33,35,6
-10/23/2023,1,20,27,32,38,3
-10/21/2023,2,14,21,22,34,3
-10/18/2023,2,5,13,20,32,4
-10/16/2023,10,11,18,34,35,3
-10/14/2023,5,22,25,30,35,2
-10/11/2023,3,4,12,20,34,3
-10/9/2023,17,21,27,35,41,6
-10/7/2023,1,8,14,26,28,6
-10/4/2023,1,21,33,34,41,4
-10/2/2023,13,17,28,37,38,5
-9/30/2023,3,9,28,35,38,4
-9/27/2023,2,3,7,14,32,3
-9/25/2023,6,21,31,38,39,2
-9/23/2023,2,17,24,37,39,2
-9/20/2023,1,2,3,26,28,3
-9/18/2023,1,14,20,25,37,3
-9/16/2023,5,15,17,30,31,2
-9/13/2023,1,6,15,23,31,5
-9/9/2023,8,14,17,23,25,3
-9/6/2023,2,27,29,30,35,3
-9/2/2023,2,8,16,18,24,2
-8/30/2023,2,4,6,14,29,2
-8/26/2023,8,13,20,28,31,2
-8/23/2023,6,8,19,34,40,1
-8/19/2023,15,18,23,27,33,1
-8/16/2023,4,8,13,17,32,4
-8/12/2023,1,16,26,36,41,3
-8/9/2023,5,13,17,23,33,1
-8/5/2023,13,21,27,32,40,1
-8/2/2023,11,13,31,39,41,3
-7/29/2023,10,13,28,34,39,3
-7/26/2023,15,18,19,20,41,1
-7/22/2023,11,13,16,21,35,1
-7/19/2023,6,11,15,35,40,4
-7/15/2023,7,19,21,34,35,4
-7/12/2023,1,16,23,26,38,4
-7/8/2023,7,19,25,28,31,5
-7/5/2023,1,12,23,28,33,6
-7/1/2023,6,9,13,23,39,5
-6/28/2023,1,8,10,20,37,6
-6/24/2023,12,20,31,36,39,4
-6/21/2023,3,9,16,18,25,3
-6/17/2023,1,13,15,23,35,3
-6/14/2023,3,4,13,16,35,5
-6/10/2023,2,11,13,29,36,4
-6/7/2023,3,5,9,20,31,1
-6/3/2023,2,8,26,27,38,6
-5/31/2023,4,14,27,29,40,2
-5/27/2023,11,13,15,30,38,2
-5/24/2023,2,3,4,12,25,3
-5/20/2023,2,19,21,29,39,3
-5/17/2023,15,18,27,34,35,2
-5/13/2023,3,5,15,31,38,4
-5/10/2023,12,19,20,23,37,2
-5/6/2023,2,5,22,26,32,6
-5/3/2023,3,9,24,30,38,2
-4/29/2023,7,12,29,36,37,6
-4/26/2023,13,16,19,31,37,3
-4/22/2023,20,27,28,34,35,2
-4/19/2023,13,19,24,32,41,6
-4/15/2023,3,14,16,18,36,4
-4/12/2023,1,5,19,31,36,1
-4/8/2023,2,12,18,19,30,1
-4/5/2023,4,10,26,28,38,5
-4/1/2023,1,7,22,23,34,1
-3/29/2023,21,25,26,35,37,5
-3/25/2023,20,22,26,30,37,4
-3/22/2023,10,25,33,36,39,2
-3/18/2023,2,14,21,24,32,6
-3/15/2023,9,14,28,30,35,2
-3/11/2023,22,23,28,30,40,3
-3/8/2023,1,11,28,31,38,1
-3/4/2023,11,34,36,39,41,1
-3/1/2023,10,22,24,25,38,5
-2/25/2023,2,6,11,23,26,1
-2/22/2023,2,6,8,16,40,4
-2/18/2023,6,24,27,36,40,6
-2/15/2023,4,13,14,15,25,3
-2/11/2023,20,21,27,32,35,5
-2/8/2023,2,8,12,22,38,5
-2/4/2023,2,6,13,20,21,1
-2/1/2023,13,19,20,24,37,5
-1/28/2023,2,11,26,32,37,1
-1/25/2023,3,12,20,29,36,3
-1/21/2023,2,4,14,23,31,6
-1/18/2023,4,20,27,38,39,4
-1/14/2023,21,25,29,37,39,2
-1/11/2023,1,17,27,30,38,4
-1/7/2023,5,10,17,35,40,1
-1/4/2023,2,3,9,26,31,1
-12/31/2022,1,9,13,14,18,1
-12/28/2022,1,5,16,18,35,6
-12/24/2022,8,14,15,19,37,6
-12/21/2022,6,15,16,34,40,4
-12/17/2022,7,8,19,35,36,4
-12/14/2022,3,6,15,16,20,3
-12/10/2022,8,9,12,14,28,2
-12/7/2022,1,8,14,17,27,3
-12/3/2022,3,15,28,31,33,1
-11/30/2022,13,28,32,34,40,2
-11/26/2022,16,19,22,27,36,5
-11/23/2022,1,8,14,18,29,4
-11/19/2022,4,5,9,32,39,5
-11/16/2022,3,27,30,32,33,3
-11/12/2022,3,10,32,39,41,3
-11/9/2022,1,4,20,32,33,5
-11/5/2022,13,17,20,24,40,5
-11/2/2022,13,18,29,32,37,1
-10/29/2022,6,13,24,26,31,1
-10/26/2022,3,9,18,31,39,6
-10/22/2022,16,17,18,20,24,6
-10/19/2022,3,7,22,31,40,1
-10/15/2022,3,9,13,21,27,4
-10/12/2022,8,21,22,23,37,4
-10/8/2022,2,19,20,24,36,4
-10/5/2022,9,23,33,39,40,2
-10/1/2022,24,26,28,30,41,2
-9/28/2022,5,21,22,23,36,5
-9/24/2022,11,32,34,36,37,4
-9/21/2022,11,14,21,22,23,1
-9/17/2022,5,13,26,27,31,2
-9/14/2022,7,9,14,27,35,5
-9/10/2022,2,9,10,30,40,3
-9/7/2022,18,19,21,26,40,4
-9/3/2022,10,22,24,30,31,6
-8/31/2022,17,18,24,32,39,5
-8/27/2022,6,17,22,26,31,3
-8/24/2022,6,13,21,39,40,5
-8/20/2022,1,8,26,31,38,2
-8/17/2022,5,13,32,36,41,4
-8/13/2022,6,20,26,32,39,1
-8/10/2022,2,11,17,23,31,2
-8/6/2022,1,3,16,30,38,3
-8/3/2022,3,4,7,25,35,1
-7/30/2022,1,3,4,30,38,3
-7/27/2022,1,6,9,24,35,4
-7/23/2022,6,16,32,34,39,2
-7/20/2022,16,17,22,34,40,6
-7/16/2022,12,14,22,31,36,4
-7/13/2022,1,16,18,33,41,5
-7/9/2022,14,16,22,36,41,1
-7/6/2022,14,20,25,29,38,4
-7/2/2022,4,8,12,18,21,6
-6/29/2022,1,19,20,24,40,2
-6/25/2022,20,22,23,33,39,1
-6/22/2022,2,22,31,34,41,2
-6/18/2022,7,8,12,25,35,5
-6/15/2022,4,27,33,34,36,6
-6/11/2022,12,13,19,33,35,5
-6/8/2022,11,15,25,38,39,4
-6/4/2022,1,15,25,33,34,1
-6/1/2022,9,11,18,24,31,2
-5/28/2022,8,16,20,25,26,5
-5/25/2022,16,24,26,27,28,2
-5/21/2022,11,20,25,28,31,1
-5/18/2022,9,11,15,23,33,5
-5/14/2022,5,11,12,26,35,2
-5/11/2022,22,29,34,37,40,6
-5/7/2022,11,14,20,27,39,6
-5/4/2022,1,2,7,22,34,6
-4/30/2022,1,17,27,33,41,3
-4/27/2022,3,16,19,21,38,2
-4/23/2022,6,14,21,35,41,2
-4/20/2022,2,12,22,31,40,4
-4/16/2022,2,7,26,38,41,5
-4/13/2022,9,14,15,23,33,3
-4/9/2022,9,21,24,26,37,4
-4/6/2022,1,8,14,28,38,5
-4/2/2022,7,17,32,37,38,5
-3/30/2022,8,10,11,19,38,2
-3/26/2022,5,7,19,22,33,4
-3/23/2022,4,7,8,9,30,1
-3/19/2022,8,10,18,30,33,5
-3/16/2022,7,18,20,29,33,1
-3/12/2022,3,8,13,33,38,2
-3/9/2022,4,15,29,31,36,2
-3/5/2022,4,19,22,25,40,6
-3/2/2022,4,8,18,23,38,5
-2/26/2022,9,15,19,37,39,2
-2/23/2022,6,19,30,34,38,5
-2/19/2022,22,27,28,30,39,3
-2/16/2022,7,8,19,24,41,4
-2/12/2022,6,18,29,34,35,4
-2/9/2022,9,10,31,37,39,2
-2/5/2022,16,21,24,27,34,2
-2/2/2022,2,5,13,19,31,5
-1/29/2022,15,19,32,35,37,4
-1/26/2022,5,15,27,36,39,6
-1/22/2022,2,4,11,24,32,1
-1/19/2022,1,16,18,35,40,5
-1/15/2022,3,10,11,12,26,2
-1/12/2022,3,18,26,36,41,1
-1/8/2022,11,20,31,32,37,3
-1/5/2022,8,10,25,28,37,5
-1/1/2022,1,16,21,26,31,5
-12/29/2021,7,20,24,30,39,4
-12/25/2021,4,8,13,17,36,2
-12/22/2021,1,9,12,14,18,2
-12/18/2021,6,13,17,29,35,5
-12/15/2021,4,6,20,31,32,1
-12/11/2021,12,15,20,22,34,4
-12/8/2021,3,9,11,21,33,5
-12/4/2021,3,7,18,19,33,5
-12/1/2021,5,24,25,30,33,4
-11/27/2021,2,8,17,25,38,1
-11/24/2021,4,16,33,38,41,6
-11/20/2021,3,8,11,20,38,6
-11/17/2021,5,6,16,19,31,4
-11/13/2021,8,12,19,31,35,6
-11/10/2021,10,22,28,31,41,4
-11/6/2021,7,9,14,24,31,4
-11/3/2021,14,16,18,25,37,4
-10/30/2021,2,24,26,31,39,6
-10/27/2021,21,29,32,35,36,6
-10/23/2021,11,17,24,38,39,1
-10/20/2021,1,14,19,23,28,6
-10/16/2021,3,14,19,21,41,5
-10/13/2021,8,9,22,26,33,3
-10/9/2021,1,9,12,13,40,1
-10/6/2021,5,10,16,22,31,4

mm_predictor.py

@@ -1,85 +0,0 @@
-# import json
-# from pathlib import Path
-# from lotto_predictor import predict_for_game, NumpyEncoder
-
-# def main():
-#     csv_path = Path("mm_results.csv")
-#     try:
-#         # Run prediction
-#         print("Generating prediction...")
-#         res = predict_for_game(csv_path, "mm", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=False)
-#         print("Prediction:")
-#         print(json.dumps(res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Prediction failed: {str(e)}")
-    
-#     try:
-#         # Run backtest
-#         print("Starting backtest...")
-#         backtest_res = predict_for_game(csv_path, "mm", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=True)
-#         print("Backtest Results:")
-#         print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Backtest failed: {str(e)}")
-
-# if __name__ == "__main__":
-#     main()
-
-
-
-import json
-from pathlib import Path
-from lotto_predictor import predict_for_game_v3, NumpyEncoder
-
-def main():
-    csv_path = Path("mm_results.csv")
-    
-    try:
-        # Run prediction
-        print("Generating prediction...")
-        res = predict_for_game_v3(csv_path, "mm", run_backtest=False)
-        print("Prediction:")
-        print(json.dumps(res, indent=2, cls=NumpyEncoder))
-        print(f"\nPredicted Numbers: {res['numbers']}")
-        if res.get('star'):
-            print(f"Star Ball: {res['star']}")
-        
-        # Print model info
-        model_info = res.get('model_info', {})
-        print(f"\nModel built for {model_info.get('numbers_modeled', 0)} out of {model_info.get('total_possible', 0)} numbers")
-        
-    except Exception as e:
-        print(f"Prediction failed: {str(e)}")
-        import traceback
-        traceback.print_exc()
-    
-    # try:
-    #     # Run backtest
-    #     print("\n" + "="*50)
-    #     print("Starting backtest...")
-    #     backtest_res = predict_for_game_v3(csv_path, "mm", run_backtest=True)
-    #     print("\nBacktest Results:")
-    #     print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-        
-    #     # Print summary
-    #     if 'error' not in backtest_res:
-    #         print(f"\nBacktest Summary:")
-    #         print(f"Model 3+ matches: {backtest_res.get('model_3plus_rate', 0)}%")
-    #         print(f"Random 3+ matches: {backtest_res.get('random_3plus_rate', 0)}%")
-    #         print(f"Average sum error: {backtest_res.get('avg_sum_error', 0)}")
-    #         print(f"Even count accuracy: {backtest_res.get('even_count_accuracy', 0)}%")
-            
-    #         # Show hit rates comparison
-    #         print("\nHit Rate Comparison:")
-    #         for i in range(6):
-    #             model_rate = backtest_res.get(f'model_hit_{i}_rate', 0)
-    #             random_rate = backtest_res.get(f'random_hit_{i}_rate', 0)
-    #             print(f"{i} matches: Model {model_rate}% vs Random {random_rate}%")
-        
-    # except Exception as e:
-    #     print(f"Backtest failed: {str(e)}")
-    #     import traceback
-    #     traceback.print_exc()
-
-if __name__ == "__main__":
-    main()

mm_results.csv

@@ -1,469 +0,0 @@
-date,b1,b2,b3,b4,b5,megaball
-1/27/2026,4,20,38,56,66,5
-1/23/2026,30,42,49,53,66,4
-1/20/2026,8,47,50,56,70,12
-1/16/2026,2,22,33,42,67,1
-1/13/2026,16,40,56,64,66,4
-1/9/2026,12,30,36,42,47,16
-1/6/2026,9,39,47,58,68,24
-1/2/2026,6,13,34,43,52,4
-12/30/2025,18,43,49,63,69,6
-12/26/2025,9,19,31,63,64,7
-12/23/2025,15,37,38,41,64,21
-12/19/2025,1,11,27,39,59,18
-12/16/2025,20,24,46,59,65,7
-12/12/2025,10,50,55,58,59,5
-12/9/2025,19,32,41,49,66,6
-12/5/2025,34,38,42,44,69,8
-12/2/2025,17,25,26,53,60,16
-11/28/2025,6,7,13,39,48,4
-11/24/2025,11,15,31,32,59,18
-11/21/2025,3,4,19,31,63,9
-11/18/2025,5,10,23,27,30,10
-11/14/2025,1,8,11,12,57,7
-11/11/2025,10,13,40,42,46,1
-11/4/2025,11,14,17,50,57,6
-10/31/2025,2,24,52,66,68,9
-10/28/2025,2,19,33,53,61,4
-10/21/2025,2,18,27,34,59,18
-10/17/2025,9,21,27,48,56,10
-10/14/2025,12,22,49,57,58,19
-10/10/2025,3,18,23,37,56,8
-10/7/2025,17,26,33,45,65,19
-10/3/2025,18,19,38,54,57,19
-9/30/2025,4,8,27,37,63,14
-9/26/2025,4,21,27,33,49,21
-9/23/2025,13,24,41,42,70,18
-9/19/2025,2,22,27,42,58,8
-9/16/2025,10,14,34,40,43,5
-9/12/2025,17,18,21,42,64,7
-9/9/2025,6,43,52,64,65,22
-9/5/2025,6,14,36,58,62,24
-9/2/2025,7,17,35,40,64,23
-8/29/2025,13,31,32,44,45,21
-8/26/2025,7,12,30,40,69,17
-8/22/2025,18,30,44,48,50,12
-8/19/2025,10,19,24,49,68,10
-8/12/2025,1,8,31,56,67,23
-8/8/2025,2,6,8,14,49,12
-8/5/2025,12,27,42,59,65,2
-8/1/2025,18,27,29,33,70,22
-7/29/2025,17,30,34,63,67,11
-7/25/2025,14,21,25,29,52,7
-7/22/2025,22,41,42,59,69,17
-7/18/2025,11,43,54,55,63,3
-7/15/2025,6,10,24,35,43,1
-7/11/2025,12,23,24,31,56,1
-7/8/2025,4,6,38,44,62,24
-7/4/2025,17,20,24,41,42,24
-7/1/2025,19,28,31,39,54,5
-6/27/2025,18,21,29,42,50,2
-6/24/2025,10,11,18,24,60,20
-6/20/2025,26,49,58,61,63,9
-6/17/2025,16,23,39,46,55,12
-6/13/2025,8,10,22,40,47,1
-6/10/2025,10,11,14,38,45,24
-6/6/2025,16,40,54,56,57,3
-6/3/2025,16,24,29,36,45,13
-5/30/2025,2,28,37,38,58,13
-5/27/2025,6,28,34,48,62,9
-5/23/2025,7,18,40,55,68,18
-5/20/2025,18,30,33,55,64,11
-5/16/2025,2,22,42,62,66,14
-5/13/2025,6,29,33,47,68,20
-5/9/2025,9,10,12,48,60,16
-5/6/2025,16,17,43,46,58,16
-5/2/2025,14,37,40,41,68,2
-4/29/2025,16,33,40,51,57,10
-4/25/2025,38,40,60,62,70,9
-4/22/2025,25,39,49,52,65,22
-4/18/2025,5,13,15,17,28,1
-4/15/2025,6,10,13,24,63,2
-4/11/2025,15,37,38,56,58,19
-4/8/2025,10,16,50,60,61,17
-4/4/2025,11,28,35,37,69,25
-4/1/2025,11,12,21,29,49,3
-3/28/2025,2,9,31,60,63,23
-3/25/2025,1,5,17,39,62,8
-3/21/2025,15,22,31,52,57,2
-3/18/2025,27,28,31,32,33,24
-3/14/2025,3,17,39,42,70,1
-3/11/2025,1,19,26,38,69,15
-3/7/2025,8,20,48,58,60,7
-3/4/2025,14,19,47,52,70,6
-2/28/2025,9,19,30,35,66,16
-2/25/2025,4,8,11,32,52,13
-2/21/2025,1,13,28,37,46,10
-2/18/2025,1,20,25,58,61,22
-2/14/2025,11,19,31,49,56,16
-2/11/2025,7,30,39,41,70,13
-2/7/2025,4,24,32,41,55,16
-2/4/2025,14,24,31,53,54,1
-1/31/2025,9,28,48,56,63,2
-1/28/2025,10,19,31,47,56,6
-1/24/2025,8,12,43,52,62,18
-1/21/2025,27,30,56,64,65,22
-1/17/2025,8,10,37,54,69,22
-1/14/2025,4,14,35,49,62,6
-1/10/2025,9,23,39,65,66,22
-1/7/2025,20,24,33,39,48,18
-1/6/2025,9,39,47,58,68,24
-1/3/2025,20,42,46,59,69,19
-12/31/2024,13,22,27,29,35,1
-12/27/2024,3,7,37,49,55,6
-12/24/2024,11,14,38,45,46,3
-12/20/2024,2,20,51,56,67,19
-12/17/2024,56,66,67,68,69,18
-12/13/2024,36,43,52,58,65,16
-12/10/2024,12,14,26,48,52,21
-12/6/2024,16,21,33,39,45,24
-12/3/2024,52,60,61,66,67,23
-11/29/2024,3,29,34,37,38,17
-11/26/2024,5,22,24,39,42,3
-11/22/2024,13,20,26,32,65,2
-11/19/2024,5,35,50,51,59,8
-11/15/2024,5,17,35,55,69,19
-11/12/2024,18,31,33,64,68,17
-11/8/2024,25,28,42,64,69,19
-11/5/2024,2,24,25,52,58,9
-11/1/2024,11,22,42,46,51,4
-10/29/2024,16,22,26,36,56,1
-10/25/2024,23,26,35,41,43,7
-10/22/2024,8,43,48,58,60,4
-10/18/2024,4,9,26,39,58,23
-10/15/2024,22,34,44,54,62,3
-10/11/2024,3,10,29,52,57,20
-10/8/2024,3,19,20,22,66,9
-10/4/2024,21,39,42,43,45,3
-10/1/2024,27,35,47,50,66,25
-9/27/2024,29,46,53,69,70,23
-9/24/2024,1,6,10,23,27,18
-9/20/2024,20,21,40,49,55,11
-9/17/2024,14,31,48,57,64,9
-9/13/2024,21,55,56,57,66,1
-9/10/2024,1,2,16,24,66,6
-9/6/2024,6,23,41,59,63,25
-9/3/2024,12,41,43,52,55,9
-8/30/2024,10,17,20,24,54,8
-8/27/2024,16,18,21,54,65,5
-8/23/2024,28,30,44,66,69,2
-8/20/2024,5,20,26,49,51,24
-8/16/2024,22,38,48,51,61,5
-8/13/2024,34,55,59,65,70,12
-8/9/2024,12,32,38,40,57,21
-8/6/2024,23,29,36,61,70,22
-8/2/2024,6,7,24,44,54,13
-7/30/2024,19,23,30,33,50,25
-7/26/2024,2,14,33,58,65,3
-7/23/2024,3,9,14,26,51,21
-7/19/2024,10,17,23,50,67,3
-7/16/2024,5,35,42,58,66,22
-7/12/2024,15,35,48,53,68,8
-7/9/2024,21,26,54,60,64,3
-7/5/2024,6,15,32,54,67,4
-7/2/2024,4,8,19,31,45,11
-6/28/2024,28,31,33,42,66,24
-6/25/2024,3,16,27,47,62,8
-6/21/2024,3,18,27,40,44,19
-6/18/2024,21,22,50,55,67,20
-6/14/2024,1,25,26,31,65,2
-6/11/2024,1,5,7,22,24,8
-6/7/2024,3,5,12,22,66,7
-6/4/2024,19,37,40,63,69,17
-5/31/2024,4,11,23,33,49,23
-5/28/2024,12,18,48,57,62,4
-5/24/2024,46,54,56,67,70,16
-5/21/2024,2,5,8,28,69,14
-5/17/2024,8,17,40,60,70,3
-5/14/2024,13,19,43,62,64,6
-5/10/2024,13,22,26,32,65,18
-5/7/2024,26,28,36,63,66,15
-5/3/2024,6,13,15,53,56,11
-4/30/2024,10,18,27,37,61,5
-4/26/2024,15,23,53,57,61,9
-4/23/2024,11,17,33,39,43,14
-4/19/2024,19,30,34,46,58,3
-4/16/2024,21,26,36,44,59,2
-4/12/2024,1,12,14,18,66,16
-4/9/2024,34,43,51,52,69,25
-4/5/2024,20,30,54,63,65,14
-4/2/2024,10,50,56,60,66,19
-3/29/2024,11,30,33,38,60,16
-3/26/2024,7,11,22,29,38,4
-3/22/2024,3,8,31,35,44,16
-3/19/2024,24,46,49,62,66,7
-3/15/2024,13,25,50,51,66,6
-3/12/2024,2,16,31,57,64,24
-3/8/2024,19,20,22,47,58,1
-3/5/2024,2,49,50,61,70,14
-3/1/2024,15,33,37,55,61,24
-2/27/2024,6,18,26,27,49,4
-2/23/2024,4,6,40,41,60,11
-2/20/2024,5,45,55,58,68,7
-2/16/2024,19,23,39,42,67,18
-2/13/2024,1,3,19,25,58,20
-2/9/2024,17,22,29,46,69,1
-2/6/2024,2,10,31,44,57,10
-2/2/2024,11,22,42,64,69,18
-1/30/2024,3,5,16,58,59,11
-1/26/2024,14,31,34,50,61,13
-1/23/2024,21,28,58,69,70,20
-1/19/2024,1,9,16,17,30,17
-1/16/2024,2,10,42,49,54,13
-1/12/2024,19,34,35,45,67,7
-1/9/2024,12,15,32,33,53,24
-1/5/2024,5,23,26,38,44,25
-1/2/2024,3,18,27,29,64,1
-12/29/2023,11,27,30,62,70,10
-12/26/2023,8,10,22,58,64,21
-12/22/2023,10,26,36,54,69,4
-12/19/2023,17,26,50,58,61,11
-12/15/2023,10,20,28,40,54,12
-12/12/2023,8,23,44,45,53,3
-12/8/2023,21,26,53,66,70,13
-12/5/2023,18,35,40,64,67,18
-12/1/2023,12,47,49,52,65,12
-11/28/2023,27,37,42,59,61,11
-11/24/2023,6,15,45,59,68,1
-11/21/2023,17,22,25,30,38,24
-11/17/2023,6,12,31,33,69,17
-11/14/2023,29,35,59,61,69,22
-11/10/2023,13,33,59,68,70,8
-11/7/2023,3,11,33,42,52,20
-11/3/2023,15,32,38,47,65,12
-10/31/2023,14,35,37,55,70,15
-10/27/2023,11,32,43,57,70,6
-10/24/2023,16,20,30,54,59,7
-10/20/2023,7,29,36,49,61,22
-10/17/2023,5,6,29,32,61,20
-10/13/2023,6,18,44,46,68,18
-10/10/2023,3,8,17,46,63,7
-10/6/2023,12,24,46,57,66,22
-10/3/2023,3,19,32,39,59,24
-9/29/2023,18,40,47,55,64,11
-9/26/2023,15,30,35,42,60,16
-9/22/2023,10,13,14,57,66,3
-9/19/2023,6,9,13,29,66,24
-9/15/2023,5,13,29,50,53,25
-9/12/2023,2,14,21,42,67,18
-9/8/2023,3,12,17,51,62,1
-9/5/2023,3,43,50,51,65,13
-9/1/2023,10,31,42,43,55,8
-8/29/2023,9,39,52,61,63,25
-8/25/2023,12,23,26,31,38,2
-8/22/2023,1,12,26,36,50,7
-8/18/2023,10,20,29,44,66,11
-8/15/2023,18,39,42,57,63,7
-8/11/2023,8,9,18,35,41,18
-8/8/2023,13,19,20,32,33,14
-8/4/2023,11,30,45,52,56,20
-8/1/2023,8,24,30,45,61,12
-7/28/2023,5,10,28,52,63,18
-7/25/2023,3,5,6,44,61,25
-7/21/2023,29,40,47,50,57,25
-7/18/2023,19,22,31,37,54,18
-7/14/2023,10,24,48,51,66,15
-7/11/2023,10,17,33,51,64,5
-7/7/2023,8,10,17,55,66,3
-7/4/2023,21,33,54,61,67,12
-6/30/2023,13,22,47,51,55,9
-6/27/2023,8,34,35,41,52,12
-6/23/2023,13,62,65,67,69,14
-6/20/2023,6,37,39,45,46,21
-6/16/2023,4,24,34,45,57,19
-6/13/2023,8,10,19,44,47,4
-6/9/2023,3,19,53,60,68,13
-6/6/2023,6,12,23,29,57,4
-6/2/2023,3,16,19,36,60,25
-5/30/2023,13,16,40,64,68,21
-5/26/2023,12,20,37,41,64,1
-5/23/2023,3,10,22,65,66,19
-5/19/2023,5,11,41,44,55,14
-5/16/2023,15,34,36,69,70,17
-5/12/2023,1,2,23,40,45,15
-5/9/2023,4,37,46,48,51,19
-5/5/2023,16,18,28,42,43,11
-5/2/2023,3,15,16,32,41,9
-4/28/2023,18,38,53,62,64,20
-4/25/2023,8,29,46,47,48,12
-4/21/2023,3,21,29,46,63,9
-4/18/2023,7,9,15,19,25,4
-4/14/2023,23,27,41,48,51,22
-4/11/2023,31,35,53,54,55,24
-4/7/2023,12,32,49,51,66,21
-4/4/2023,1,37,45,62,64,4
-3/31/2023,16,26,27,42,61,23
-3/28/2023,2,3,18,32,68,24
-3/24/2023,14,17,33,42,66,15
-3/21/2023,1,21,25,27,40,11
-3/17/2023,26,28,29,39,49,25
-3/14/2023,1,7,23,38,55,2
-3/10/2023,9,20,59,60,63,5
-3/7/2023,15,22,25,28,69,21
-3/3/2023,8,25,36,39,67,11
-2/28/2023,14,16,40,52,59,13
-2/24/2023,2,22,49,65,67,7
-2/21/2023,2,15,30,36,63,24
-2/17/2023,2,33,38,57,70,13
-2/14/2023,23,24,35,40,43,1
-2/10/2023,20,29,30,52,58,19
-2/7/2023,9,15,46,55,57,4
-2/3/2023,1,4,50,54,59,17
-1/31/2023,7,9,18,29,39,13
-1/27/2023,4,43,46,47,61,22
-1/24/2023,33,41,47,50,62,20
-1/20/2023,20,29,31,64,66,17
-1/17/2023,2,12,18,24,39,18
-1/13/2023,30,43,45,46,61,14
-1/10/2023,7,13,14,15,18,9
-1/6/2023,3,20,46,59,63,13
-1/3/2023,25,29,33,41,44,18
-12/30/2022,1,3,6,44,51,7
-12/27/2022,9,13,36,59,61,11
-12/23/2022,15,21,32,38,62,8
-12/20/2022,3,4,33,36,52,17
-12/16/2022,8,35,40,53,56,11
-12/13/2022,14,22,48,58,68,6
-12/9/2022,8,19,53,61,69,19
-12/6/2022,15,16,19,28,47,13
-12/2/2022,1,21,36,46,52,16
-11/29/2022,20,23,37,46,52,6
-11/25/2022,29,31,46,54,67,18
-11/22/2022,13,23,24,25,43,2
-11/18/2022,2,14,16,38,66,9
-11/15/2022,6,19,28,46,61,18
-11/11/2022,1,5,17,37,70,22
-11/8/2022,5,13,29,38,59,23
-11/4/2022,2,20,47,55,59,19
-11/1/2022,5,9,15,16,17,25
-10/28/2022,4,18,31,53,69,7
-10/25/2022,21,30,35,45,66,21
-10/21/2022,34,36,43,45,68,22
-10/18/2022,1,15,20,44,67,23
-10/14/2022,9,22,26,41,44,19
-10/11/2022,3,7,11,13,38,1
-10/7/2022,6,11,29,36,55,21
-10/4/2022,15,18,25,33,38,25
-9/30/2022,16,26,37,40,51,6
-9/27/2022,8,14,24,43,51,9
-9/23/2022,5,50,53,58,64,22
-9/20/2022,9,21,28,30,52,10
-9/16/2022,15,30,35,38,66,12
-9/13/2022,14,25,38,59,64,21
-9/9/2022,16,21,54,55,69,22
-9/6/2022,6,17,46,59,68,2
-9/2/2022,39,40,52,60,67,20
-8/30/2022,2,38,55,57,65,17
-8/26/2022,6,27,30,38,64,23
-8/23/2022,3,5,47,48,67,7
-8/19/2022,12,18,24,46,65,3
-8/16/2022,33,35,41,45,51,1
-8/12/2022,23,24,50,54,64,3
-8/9/2022,1,8,10,25,32,13
-8/5/2022,2,5,29,64,69,18
-8/2/2022,10,14,25,37,63,14
-7/29/2022,13,36,45,57,67,14
-7/26/2022,7,29,60,63,66,15
-7/22/2022,14,40,60,64,66,16
-7/19/2022,2,31,32,37,70,25
-7/15/2022,8,20,26,53,64,15
-7/12/2022,4,7,10,45,64,12
-7/8/2022,20,36,61,62,69,20
-7/5/2022,27,31,50,51,61,21
-7/1/2022,1,27,29,38,62,12
-6/28/2022,7,12,21,43,55,11
-6/24/2022,1,7,11,25,56,14
-6/21/2022,8,13,18,32,42,20
-6/17/2022,20,36,53,56,69,16
-6/14/2022,30,37,38,42,58,22
-6/10/2022,3,12,14,18,32,4
-6/7/2022,4,34,40,41,53,3
-6/3/2022,11,16,22,48,59,11
-5/31/2022,6,15,41,63,64,24
-5/27/2022,3,14,40,53,54,8
-5/24/2022,3,5,6,63,68,25
-5/20/2022,33,40,59,60,69,22
-5/17/2022,7,21,24,41,65,24
-5/13/2022,11,41,43,44,65,13
-5/10/2022,15,19,20,61,70,9
-5/6/2022,16,21,33,52,70,10
-5/3/2022,15,19,27,35,57,17
-4/29/2022,9,11,34,49,66,15
-4/26/2022,5,7,19,46,69,2
-4/22/2022,7,28,29,58,59,10
-4/19/2022,2,9,33,47,53,24
-4/15/2022,4,17,20,46,64,23
-4/12/2022,2,8,14,20,31,17
-4/8/2022,8,11,29,32,40,2
-4/5/2022,22,43,60,63,64,18
-4/1/2022,26,42,47,48,63,21
-3/29/2022,7,22,36,45,47,12
-3/25/2022,3,13,42,51,58,17
-3/22/2022,8,15,21,27,61,8
-3/18/2022,2,6,25,40,45,5
-3/15/2022,9,14,28,59,60,24
-3/11/2022,24,28,39,44,66,25
-3/8/2022,7,18,38,58,64,24
-3/4/2022,11,19,28,46,47,5
-3/1/2022,18,22,38,39,50,18
-2/25/2022,15,31,40,56,66,4
-2/22/2022,6,17,22,57,62,3
-2/18/2022,6,11,50,63,68,17
-2/15/2022,2,4,15,21,63,19
-2/11/2022,11,16,23,24,30,24
-2/8/2022,1,17,20,52,54,2
-2/4/2022,7,16,34,44,61,24
-2/1/2022,11,24,38,62,66,1
-1/28/2022,3,16,25,44,55,13
-1/25/2022,3,12,38,53,58,13
-1/21/2022,38,45,46,55,67,18
-1/18/2022,4,19,39,42,52,9
-1/14/2022,5,8,13,22,48,25
-1/11/2022,2,3,19,52,58,16
-1/7/2022,7,29,43,56,57,6
-1/4/2022,4,6,16,21,22,1
-12/31/2021,2,5,30,46,61,8
-12/28/2021,3,5,8,31,38,4
-12/24/2021,16,17,25,36,37,16
-12/21/2021,25,31,58,64,67,24
-12/17/2021,21,32,38,48,62,10
-12/14/2021,33,35,44,55,69,20
-12/10/2021,23,25,40,42,60,8
-12/7/2021,1,7,40,43,68,1
-12/3/2021,22,45,48,58,61,13
-11/30/2021,7,8,26,30,39,17
-11/26/2021,7,27,37,42,59,2
-11/23/2021,7,24,54,57,58,6
-11/19/2021,5,23,52,53,59,18
-11/16/2021,6,22,44,53,65,3
-11/12/2021,30,32,42,46,48,15
-11/9/2021,9,14,16,26,49,14
-11/5/2021,10,15,20,66,68,18
-11/2/2021,5,10,26,58,65,9
-10/29/2021,15,26,28,35,45,4
-10/26/2021,6,14,19,56,62,9
-10/22/2021,9,14,26,29,66,22
-10/19/2021,3,12,13,19,52,1
-10/15/2021,3,20,31,34,65,18
-10/12/2021,21,26,56,61,65,4
-10/8/2021,21,24,36,40,70,22
-10/5/2021,7,11,18,30,36,4
-10/1/2021,21,25,36,62,63,6
-9/28/2021,18,30,43,68,69,22
-9/24/2021,17,21,27,43,56,15
-9/21/2021,36,41,45,51,56,13
-9/17/2021,17,32,40,59,61,18
-9/14/2021,4,13,19,63,64,16
-9/10/2021,20,32,35,47,64,18
-9/7/2021,15,17,25,32,53,12
-9/3/2021,7,10,12,61,65,3
-8/31/2021,8,14,31,58,68,15
-8/27/2021,1,10,44,47,56,23
-8/24/2021,17,18,26,52,67,19
-8/20/2021,41,43,51,57,70,1
-8/17/2021,3,6,16,38,56,24
-8/13/2021,17,21,35,40,53,11
-8/10/2021,29,45,50,59,62,12
-8/6/2021,9,18,40,46,69,9
-8/3/2021,1,9,17,27,34,24
-7/30/2021,19,26,31,52,68,10

pb_predictor.py

@@ -1,84 +0,0 @@
-# import json
-# from pathlib import Path
-# from lotto_predictor import predict_for_game, NumpyEncoder
-
-# def main():
-#     csv_path = Path("pb_results.csv")
-#     try:
-#         # Run prediction
-#         print("Generating prediction...")
-#         res = predict_for_game(csv_path, "pb", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=False)
-#         print("Prediction:")
-#         print(json.dumps(res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Prediction failed: {str(e)}")
-    
-#     try:
-#         # Run backtest
-#         print("Starting backtest...")
-#         backtest_res = predict_for_game(csv_path, "pb", allow_sequences=True, include_wheel=False, wheel_template_path=Path("wheel.txt"), run_backtest=True)
-#         print("Backtest Results:")
-#         print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-#     except Exception as e:
-#         print(f"Backtest failed: {str(e)}")
-
-# if __name__ == "__main__":
-#     main()
-
-
-import json
-from pathlib import Path
-from lotto_predictor import predict_for_game_v3, NumpyEncoder
-
-def main():
-    csv_path = Path("pb_results.csv")
-    
-    try:
-        # Run prediction
-        print("Generating prediction...")
-        res = predict_for_game_v3(csv_path, "pb", run_backtest=False)
-        print("Prediction:")
-        print(json.dumps(res, indent=2, cls=NumpyEncoder))
-        print(f"\nPredicted Numbers: {res['numbers']}")
-        if res.get('star'):
-            print(f"Star Ball: {res['star']}")
-        
-        # Print model info
-        model_info = res.get('model_info', {})
-        print(f"\nModel built for {model_info.get('numbers_modeled', 0)} out of {model_info.get('total_possible', 0)} numbers")
-        
-    except Exception as e:
-        print(f"Prediction failed: {str(e)}")
-        import traceback
-        traceback.print_exc()
-    
-    # try:
-    #     # Run backtest
-    #     print("\n" + "="*50)
-    #     print("Starting backtest...")
-    #     backtest_res = predict_for_game_v3(csv_path, "pb", run_backtest=True)
-    #     print("\nBacktest Results:")
-    #     print(json.dumps(backtest_res, indent=2, cls=NumpyEncoder))
-        
-    #     # Print summary
-    #     if 'error' not in backtest_res:
-    #         print(f"\nBacktest Summary:")
-    #         print(f"Model 3+ matches: {backtest_res.get('model_3plus_rate', 0)}%")
-    #         print(f"Random 3+ matches: {backtest_res.get('random_3plus_rate', 0)}%")
-    #         print(f"Average sum error: {backtest_res.get('avg_sum_error', 0)}")
-    #         print(f"Even count accuracy: {backtest_res.get('even_count_accuracy', 0)}%")
-            
-    #         # Show hit rates comparison
-    #         print("\nHit Rate Comparison:")
-    #         for i in range(6):
-    #             model_rate = backtest_res.get(f'model_hit_{i}_rate', 0)
-    #             random_rate = backtest_res.get(f'random_hit_{i}_rate', 0)
-    #             print(f"{i} matches: Model {model_rate}% vs Random {random_rate}%")
-        
-    # except Exception as e:
-    #     print(f"Backtest failed: {str(e)}")
-    #     import traceback
-    #     traceback.print_exc()
-
-if __name__ == "__main__":
-    main()

pb_results.csv

@@ -1,426 +0,0 @@
-date,b1,b2,b3,b4,b5,powerball
-1/28/2026,21,35,40,46,68,11
-1/26/2026,21,31,51,60,63,18
-1/24/2026,2,16,35,61,63,5
-1/21/2026,11,26,27,53,55,12
-1/19/2026,5,28,34,37,55,17
-1/17/2026,5,8,27,49,57,14
-1/14/2026,6,24,39,42,51,2
-1/12/2026,5,27,45,56,59,4
-1/10/2026,5,19,21,28,64,14
-1/7/2026,15,28,57,58,62,23
-1/5/2026,4,18,24,51,56,14
-1/3/2026,18,21,40,53,60,23
-12/31/2025,11,18,21,24,38,26
-12/29/2025,11,19,34,48,53,21
-12/27/2025,5,10,34,39,62,1
-12/24/2025,4,25,31,52,59,19
-12/22/2025,3,18,36,41,54,7
-12/20/2025,4,5,28,52,69,20
-12/17/2025,25,33,53,62,66,17
-12/15/2025,23,35,59,63,68,2
-12/13/2025,1,28,31,5,58,16
-12/10/2025,10,16,29,33,69,22
-12/8/2025,8,32,52,56,65,23
-12/6/2025,13,14,26,28,44,7
-12/3/2025,1,14,20,46,51,26
-12/1/2025,5,18,26,47,59,1
-11/29/2025,19,22,30,32,59,1
-11/26/2025,7,8,15,19,28,3
-11/24/2025,8,16,26,30,58,14
-11/22/2025,28,32,36,51,69,2
-11/19/2025,10,31,49,51,68,19
-11/17/2025,7,33,50,57,66,23
-11/15/2025,6,7,12,47,53,21
-11/12/2025,29,39,43,51,65,23
-11/10/2025,6,28,44,48,58,23
-11/8/2025,3,53,60,62,68,11
-11/5/2025,9,17,29,61,66,26
-11/3/2025,3,32,40,43,57,18
-11/1/2025,2,26,43,44,62,22
-10/29/2025,4,24,49,60,65,1
-10/27/2025,17,39,43,51,66,20
-10/25/2025,2,12,22,39,67,15
-10/22/2025,18,37,52,54,60,12
-10/20/2025,32,38,66,67,69,19
-10/18/2025,3,11,27,40,58,10
-10/15/2025,10,13,28,34,47,15
-10/13/2025,13,14,32,52,64,12
-10/11/2025,13,16,18,20,27,10
-10/8/2025,8,10,44,48,54,14
-10/6/2025,28,29,32,66,67,3
-10/4/2025,3,7,47,67,68,2
-10/1/2025,8,17,22,28,55,14
-9/29/2025,1,3,27,60,65,16
-9/27/2025,10,16,32,61,66,4
-9/24/2025,15,31,45,49,53,19
-9/22/2025,3,29,42,46,59,15
-9/20/2025,15,29,64,66,67,4
-9/17/2025,7,30,50,54,62,20
-9/15/2025,14,15,32,42,49,1
-9/13/2025,28,37,42,50,53,19
-9/10/2025,2,24,45,53,64,5
-9/8/2025,26,28,41,53,64,9
-9/6/2025,11,23,44,61,62,17
-9/3/2025,3,16,29,61,69,22
-9/1/2025,8,23,25,40,53,5
-8/30/2025,3,18,22,27,33,17
-8/27/2025,9,12,22,41,61,25
-8/25/2025,16,19,34,37,64,22
-8/23/2025,11,14,34,47,51,18
-8/20/2025,31,59,62,65,68,5
-8/18/2025,15,46,61,63,64,1
-8/16/2025,23,40,49,65,69,23
-8/13/2025,4,11,40,44,50,4
-8/11/2025,6,16,33,40,62,2
-8/9/2025,7,14,23,24,60,14
-8/6/2025,15,27,43,45,53,9
-8/4/2025,8,9,19,31,38,21
-8/2/2025,6,18,34,35,36,2
-7/30/2025,4,15,35,50,64,8
-7/28/2025,7,35,36,43,62,3
-7/26/2025,8,31,57,65,67,23
-7/23/2025,2,18,19,25,35,25
-7/21/2025,8,11,28,33,42,2
-7/19/2025,28,48,51,61,69,20
-7/16/2025,4,21,43,48,49,22
-7/14/2025,8,12,45,46,63,24
-7/12/2025,8,16,24,33,54,18
-7/9/2025,5,9,25,28,69,5
-7/7/2025,33,35,58,61,69,25
-7/5/2025,1,28,34,50,58,8
-7/2/2025,7,19,21,54,63,21
-6/30/2025,13,28,44,52,55,6
-6/28/2025,4,35,43,52,62,12
-6/25/2025,2,12,37,51,61,22
-6/23/2025,5,25,42,44,65,20
-6/21/2025,3,16,32,52,62,24
-6/18/2025,23,29,50,64,67,11
-6/16/2025,17,21,23,27,52,19
-6/14/2025,4,6,9,23,59,25
-6/11/2025,13,25,29,37,53,3
-6/9/2025,30,33,40,43,52,25
-6/7/2025,31,36,43,48,62,25
-6/4/2025,5,17,23,35,45,24
-6/2/2025,1,7,44,57,61,21
-5/31/2025,1,29,37,56,68,13
-5/28/2025,23,27,32,35,59,11
-5/26/2025,13,47,52,64,67,25
-5/24/2025,12,18,28,48,52,5
-5/21/2025,9,29,31,34,43,2
-5/19/2025,13,14,37,50,60,11
-5/17/2025,7,34,40,42,52,15
-5/14/2025,4,10,24,29,53,4
-5/12/2025,15,16,41,48,60,21
-5/10/2025,5,20,28,39,42,13
-5/7/2025,14,15,30,40,59,20
-5/5/2025,16,34,40,45,66,19
-5/3/2025,10,21,23,35,65,24
-4/30/2025,1,2,3,57,59,9
-4/28/2025,26,43,51,56,60,24
-4/26/2025,1,12,14,18,69,2
-4/23/2025,15,44,63,66,69,20
-4/21/2025,4,33,45,46,51,25
-4/19/2025,7,25,37,39,63,1
-4/16/2025,20,24,42,43,49,19
-4/14/2025,3,20,30,52,62,1
-4/12/2025,16,22,44,45,53,19
-4/9/2025,4,29,37,55,67,10
-4/7/2025,20,23,48,59,66,4
-4/5/2025,4,23,30,46,62,2
-4/2/2025,5,17,41,64,69,1
-3/31/2025,12,41,44,52,64,25
-3/29/2025,7,11,21,53,61,2
-3/26/2025,5,20,29,39,53,6
-3/24/2025,6,23,35,36,47,12
-3/22/2025,6,7,25,46,57,12
-3/19/2025,8,11,21,49,59,15
-3/17/2025,11,18,23,38,60,9
-3/15/2025,12,28,33,36,54,5
-3/12/2025,11,13,28,51,58,1
-3/10/2025,17,40,47,50,55,6
-3/8/2025,2,4,16,23,63,13
-3/5/2025,24,28,40,63,65,20
-3/3/2025,18,20,50,52,56,20
-3/1/2025,2,23,36,44,49,25
-2/26/2025,28,48,55,60,62,20
-2/24/2025,10,11,34,59,68,14
-2/22/2025,7,18,22,50,65,15
-2/19/2025,6,21,28,49,60,20
-2/17/2025,4,44,47,52,57,9
-2/15/2025,3,16,45,54,56,12
-2/12/2025,21,32,36,45,49,18
-2/10/2025,2,17,18,29,43,3
-2/8/2025,23,44,57,60,62,9
-2/5/2025,19,27,30,50,62,14
-2/3/2025,12,37,47,54,60,17
-2/1/2025,23,29,32,49,61,8
-1/29/2025,8,12,31,33,38,18
-1/27/2025,2,40,47,53,55,20
-1/25/2025,8,15,17,53,66,14
-1/22/2025,5,6,27,40,49,5
-1/20/2025,15,16,32,47,54,6
-1/18/2025,14,31,35,64,69,23
-1/15/2025,8,41,52,53,58,7
-1/13/2025,4,6,16,39,66,9
-1/11/2025,3,6,32,37,65,4
-1/8/2025,1,20,36,38,43,24
-1/6/2025,17,34,46,66,67,14
-1/4/2025,26,32,43,54,56,24
-1/1/2025,6,12,28,35,66,26
-12/30/2024,9,19,33,38,39,1
-12/28/2024,6,31,51,54,55,12
-12/25/2024,15,26,27,30,35,3
-12/23/2024,22,42,44,57,64,18
-12/21/2024,1,12,17,21,58,1
-12/18/2024,6,15,18,33,49,7
-12/16/2024,9,30,33,57,61,17
-12/14/2024,12,17,23,52,67,1
-12/11/2024,13,44,50,52,54,20
-12/9/2024,35,37,40,45,51,24
-12/7/2024,1,31,43,55,57,22
-12/4/2024,1,23,25,28,61,13
-12/2/2024,3,9,26,61,67,13
-11/30/2024,4,24,29,39,63,25
-11/27/2024,1,6,7,13,40,5
-11/25/2024,5,35,45,60,63,12
-11/23/2024,12,13,34,44,67,8
-11/20/2024,16,30,60,62,64,25
-11/18/2024,27,31,41,52,69,26
-11/16/2024,21,22,25,32,38,16
-11/13/2024,9,20,26,43,58,9
-11/11/2024,3,21,24,34,46,9
-11/9/2024,11,24,50,56,66,16
-11/6/2024,12,17,37,58,62,4
-11/4/2024,6,18,33,48,53,21
-11/2/2024,10,45,48,58,61,2
-10/30/2024,13,22,29,43,58,22
-10/28/2024,21,27,32,48,67,17
-10/26/2024,8,12,40,45,51,15
-10/23/2024,2,15,27,29,39,20
-10/21/2024,1,25,57,62,64,15
-10/19/2024,7,16,19,45,64,25
-10/16/2024,4,30,39,44,60,11
-10/14/2024,14,18,33,64,67,14
-10/12/2024,5,14,20,41,57,6
-10/9/2024,25,32,43,53,66,10
-10/7/2024,18,30,31,52,63,22
-10/5/2024,2,12,46,52,65,3
-10/2/2024,1,2,21,37,43,21
-9/30/2024,9,11,30,43,69,20
-9/28/2024,3,11,13,24,39,22
-9/25/2024,2,26,45,46,52,21
-9/23/2024,15,21,25,37,45,19
-9/21/2024,17,19,21,37,45,14
-9/18/2024,1,11,22,47,68,7
-9/16/2024,8,9,11,27,31,17
-9/14/2024,29,34,38,48,56,16
-9/11/2024,10,12,55,65,67,3
-9/9/2024,1,16,21,47,60,5
-9/7/2024,14,34,37,55,63,20
-9/4/2024,7,10,21,33,59,20
-9/2/2024,8,42,46,48,53,22
-8/31/2024,4,34,35,38,69,19
-8/28/2024,5,33,47,50,64,20
-8/26/2024,2,4,23,68,69,15
-8/24/2024,5,15,21,24,43,17
-8/21/2024,27,31,33,38,67,3
-8/19/2024,1,2,15,23,28,10
-8/17/2024,12,31,43,45,46,22
-8/14/2024,8,9,23,29,62,13
-8/12/2024,9,22,57,67,68,14
-8/10/2024,9,24,33,64,69,9
-8/7/2024,6,19,35,47,57,9
-8/5/2024,29,42,44,51,54,12
-8/3/2024,13,33,40,60,61,20
-7/31/2024,23,34,37,50,58,7
-7/29/2024,11,27,30,33,44,16
-7/27/2024,3,31,37,40,64,17
-7/24/2024,16,42,59,63,68,13
-7/22/2024,31,36,56,58,69,20
-7/20/2024,18,25,31,40,57,4
-7/17/2024,24,27,32,47,66,26
-7/15/2024,9,31,39,40,45,23
-7/13/2024,9,55,59,66,69,21
-7/10/2024,7,11,12,27,46,26
-7/8/2024,20,22,31,33,45,1
-7/6/2024,5,32,35,39,49,21
-7/3/2024,2,26,33,55,57,22
-7/1/2024,5,9,32,39,55,9
-6/29/2024,26,51,54,61,69,25
-6/26/2024,4,9,36,47,56,7
-6/24/2024,5,6,36,53,69,8
-6/22/2024,4,5,15,32,62,21
-6/19/2024,4,27,44,50,64,7
-6/17/2024,30,48,53,58,66,9
-6/15/2024,4,36,48,54,56,2
-6/12/2024,19,30,31,61,62,21
-6/10/2024,3,10,33,58,59,9
-6/8/2024,8,38,52,54,64,15
-6/5/2024,8,44,45,51,69,12
-6/3/2024,19,29,35,36,45,16
-6/1/2024,28,38,52,54,68,8
-5/29/2024,17,34,56,60,61,9
-5/27/2024,9,30,39,49,59,21
-5/25/2024,6,33,35,36,64,24
-5/22/2024,5,16,18,26,67,4
-5/20/2024,1,7,48,64,68,5
-5/18/2024,19,36,37,42,59,19
-5/15/2024,19,42,45,55,69,6
-5/13/2024,5,14,29,38,66,1
-5/11/2024,3,6,39,49,67,21
-5/8/2024,7,41,43,44,51,5
-5/6/2024,7,23,24,56,60,25
-5/4/2024,14,20,23,53,69,4
-5/1/2024,1,11,19,21,68,15
-4/29/2024,11,38,47,67,69,14
-4/27/2024,9,30,53,55,62,23
-4/24/2024,2,20,22,26,47,21
-4/22/2024,12,16,33,39,52,1
-4/20/2024,4,35,41,44,58,25
-4/17/2024,24,29,44,47,54,2
-4/15/2024,7,16,41,56,61,23
-4/13/2024,7,33,40,43,69,10
-4/10/2024,6,7,12,24,36,15
-4/8/2024,6,21,23,39,54,23
-4/6/2024,22,27,44,52,69,9
-4/3/2024,11,38,41,62,65,15
-4/1/2024,19,24,40,42,56,23
-3/30/2024,12,13,33,50,52,23
-3/27/2024,37,46,57,60,66,8
-3/25/2024,7,11,19,53,68,23
-3/23/2024,6,23,25,34,51,3
-3/20/2024,13,22,27,54,66,9
-3/18/2024,10,17,20,39,44,16
-3/16/2024,12,23,44,57,61,5
-3/13/2024,21,29,54,59,62,4
-3/11/2024,1,3,7,16,66,5
-3/9/2024,30,36,49,52,63,16
-3/6/2024,6,19,28,44,60,10
-3/4/2024,36,42,50,52,67,26
-3/2/2024,3,18,27,36,53,12
-2/28/2024,16,26,29,38,50,6
-2/26/2024,24,29,42,51,54,16
-2/24/2024,3,8,40,53,58,3
-2/21/2024,4,27,33,41,42,14
-2/19/2024,4,23,45,50,53,17
-2/17/2024,6,28,59,62,69,21
-2/14/2024,1,4,45,47,67,18
-2/12/2024,17,36,43,53,67,14
-2/10/2024,27,28,34,37,44,8
-2/7/2024,12,21,62,67,69,17
-2/5/2024,1,2,27,30,67,9
-2/3/2024,9,11,27,59,66,19
-1/31/2024,15,18,19,41,43,14
-1/29/2024,39,41,43,49,64,4
-1/27/2024,7,38,65,66,68,21
-1/24/2024,1,5,32,50,64,8
-1/22/2024,24,25,43,52,63,21
-1/20/2024,16,31,34,47,65,10
-1/17/2024,18,22,43,61,65,2
-1/15/2024,13,30,35,49,59,4
-1/13/2024,13,31,33,51,58,15
-1/10/2024,25,40,43,48,50,11
-1/8/2024,7,17,28,40,45,2
-1/6/2024,4,31,34,38,61,13
-1/3/2024,30,31,38,48,68,8
-1/1/2024,12,21,42,44,49,1
-12/30/2023,10,11,26,27,34,7
-12/27/2023,4,11,38,51,68,5
-12/25/2023,5,12,20,24,29,4
-12/23/2023,9,14,17,18,53,6
-12/20/2023,27,35,41,56,60,16
-12/18/2023,5,8,19,34,39,26
-12/16/2023,3,9,10,20,62,25
-12/13/2023,3,8,41,56,64,18
-12/11/2023,1,24,27,31,62,20
-12/9/2023,5,25,26,40,60,1
-12/6/2023,2,12,37,56,65,21
-12/4/2023,18,19,27,28,45,9
-12/2/2023,28,35,41,47,60,3
-11/29/2023,6,47,50,61,68,4
-11/27/2023,2,21,38,61,66,12
-11/25/2023,27,33,63,66,68,9
-11/22/2023,20,24,33,39,42,21
-11/20/2023,19,26,30,39,63,13
-11/18/2023,34,50,51,61,67,20
-11/15/2023,3,4,51,53,60,6
-11/13/2023,24,33,35,37,42,21
-11/11/2023,1,12,14,24,57,7
-11/8/2023,14,21,33,39,62,20
-11/6/2023,12,25,40,59,61,26
-11/4/2023,1,28,30,34,52,6
-11/1/2023,22,26,39,47,63,12
-10/30/2023,19,22,34,66,69,5
-10/28/2023,14,24,50,59,64,2
-10/25/2023,25,27,41,53,68,2
-10/23/2023,18,21,25,46,64,21
-10/21/2023,6,15,24,67,68,11
-10/18/2023,1,4,13,35,58,24
-10/16/2023,2,27,31,44,64,18
-10/14/2023,14,16,42,48,64,14
-10/11/2023,22,24,40,52,64,10
-10/9/2023,16,34,46,55,67,14
-10/7/2023,47,54,57,60,65,19
-10/4/2023,9,35,54,63,64,1
-10/2/2023,12,26,27,43,47,5
-9/30/2023,19,30,37,44,46,22
-9/27/2023,1,7,46,47,63,7
-9/25/2023,10,12,22,36,50,4
-9/23/2023,1,12,20,33,66,21
-9/20/2023,16,27,59,62,63,23
-9/18/2023,2,21,26,40,42,9
-9/16/2023,8,11,19,24,46,5
-9/13/2023,22,30,37,44,45,18
-9/11/2023,9,25,27,53,66,5
-9/9/2023,11,19,29,63,68,25
-9/6/2023,9,14,20,23,63,1
-9/4/2023,1,26,32,46,51,13
-9/2/2023,25,38,42,66,67,19
-8/30/2023,4,13,35,61,69,4
-8/28/2023,4,6,25,55,68,26
-8/26/2023,20,22,26,28,63,5
-8/23/2023,25,30,32,33,55,20
-8/21/2023,3,4,12,22,28,16
-8/19/2023,1,25,27,38,62,13
-8/16/2023,9,11,17,19,55,1
-8/14/2023,32,34,37,39,47,3
-8/12/2023,19,21,37,50,65,26
-8/9/2023,10,15,21,67,69,3
-8/7/2023,6,13,20,35,54,22
-8/5/2023,18,42,44,62,65,23
-8/2/2023,23,24,33,51,64,5
-7/31/2023,2,11,48,58,65,13
-7/29/2023,10,25,27,34,38,2
-7/26/2023,3,16,40,48,60,14
-7/24/2023,3,4,12,28,49,25
-7/22/2023,25,27,36,37,63,7
-7/19/2023,7,10,11,13,24,24
-7/17/2023,5,8,9,17,41,21
-7/15/2023,2,9,43,55,57,18
-7/12/2023,23,35,45,66,67,20
-7/10/2023,2,24,34,53,58,13
-7/8/2023,7,23,24,32,43,18
-7/5/2023,17,24,48,62,68,23
-7/3/2023,15,26,31,38,61,3
-7/1/2023,4,17,35,49,61,8
-6/28/2023,19,25,34,57,68,4
-6/26/2023,6,28,39,43,54,12
-6/24/2023,2,38,44,50,62,19
-6/21/2023,5,11,33,35,63,14
-6/19/2023,36,39,52,57,69,1
-6/17/2023,2,12,45,61,64,26
-6/14/2023,3,20,36,42,64,4
-6/12/2023,2,3,16,23,68,7
-6/10/2023,21,32,42,46,50,4
-6/7/2023,16,21,29,53,66,2
-6/5/2023,2,31,45,46,49,20
-6/3/2023,15,45,64,67,68,18
-5/31/2023,2,4,54,61,62,14
-5/29/2023,21,33,35,62,64,24
-5/27/2023,24,38,39,48,56,4
-5/24/2023,12,21,44,50,58,26
-5/22/2023,9,38,48,52,68,25
-5/20/2023,17,23,32,38,63,23
-5/17/2023,18,34,37,45,51,14
-5/15/2023,1,26,28,55,58,25

pick3_ultra_predictor.py

@@ -1,193 +0,0 @@
-#!/usr/bin/env python3
-"""
-Pick 3 Ultra Predictor (stable + reproducible)
-
-- Trains fast ML models per digit-position (0-9 classification)
-- Deterministic outputs across machines when the same CSV is used
-- Designed to be called from Streamlit (HuggingFace) or CLI
-
-CSV format expected (like Pick3eve.csv):
-  DrawDate, 1, 2, 3   (digits as ints 0-9)
-"""
-
-from __future__ import annotations
-
-import argparse
-from dataclasses import dataclass
-from typing import List, Tuple
-
-import numpy as np
-import pandas as pd
-from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
-from sklearn.neural_network import MLPClassifier
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
-
-
-SEED = 42
-
-
-@dataclass
-class TrainReport:
-    pos: int
-    n_rows: int
-    rf_acc: float
-    gb_acc: float
-    mlp_acc: float
-
-
-class Pick3UltraPredictor:
-    def __init__(self, csv_path: str, seed: int = SEED):
-        self.csv_path = csv_path
-        self.seed = int(seed)
-        self.df: pd.DataFrame = pd.DataFrame()
-        self.models = {}  # pos -> (rf, gb, mlp)
-        self.reports: List[TrainReport] = []
-
-    def load(self) -> pd.DataFrame:
-        df = pd.read_csv(self.csv_path)
-        if "DrawDate" not in df.columns:
-            raise ValueError("Pick3 CSV must include a 'DrawDate' column.")
-        for c in ("1", "2", "3"):
-            if c not in df.columns:
-                raise ValueError("Pick3 CSV must include digit columns '1','2','3'.")
-        df = df.copy()
-        df["DrawDate"] = pd.to_datetime(df["DrawDate"], errors="coerce")
-        df = df.dropna(subset=["DrawDate"]).sort_values("DrawDate").reset_index(drop=True)
-
-        # basic time features
-        df["dow"] = df["DrawDate"].dt.dayofweek.astype(int)
-        df["month"] = df["DrawDate"].dt.month.astype(int)
-        df["day"] = df["DrawDate"].dt.day.astype(int)
-
-        # rolling digit frequencies (global) as features
-        for d in range(10):
-            mask = ((df[["1", "2", "3"]] == d).any(axis=1)).astype(int)
-            df[f"hit_{d}"] = mask
-            df[f"roll20_{d}"] = df[f"hit_{d}"].rolling(20, min_periods=5).mean().fillna(0.0)
-            df[f"roll80_{d}"] = df[f"hit_{d}"].rolling(80, min_periods=10).mean().fillna(0.0)
-
-        # previous draw digits as features (lag-1)
-        for c in ("1", "2", "3"):
-            df[f"prev_{c}"] = df[c].shift(1).fillna(method="bfill").astype(int)
-
-        self.df = df
-        return df
-
-    def _feature_cols(self) -> List[str]:
-        cols = ["dow", "month", "day", "prev_1", "prev_2", "prev_3"]
-        cols += [f"roll20_{d}" for d in range(10)]
-        cols += [f"roll80_{d}" for d in range(10)]
-        return cols
-
-    def train_models(self) -> List[TrainReport]:
-        if self.df.empty:
-            self.load()
-
-        X = self.df[self._feature_cols()].values
-        reports: List[TrainReport] = []
-
-        rng = np.random.default_rng(self.seed)
-
-        for pos, col in enumerate(("1", "2", "3"), start=1):
-            y = self.df[col].astype(int).values
-            X_train, X_test, y_train, y_test = train_test_split(
-                X, y, test_size=0.20, random_state=self.seed, stratify=y
-            )
-
-            rf = RandomForestClassifier(
-                n_estimators=400,
-                max_depth=10,
-                random_state=self.seed,
-                n_jobs=-1,
-            )
-            gb = GradientBoostingClassifier(random_state=self.seed)
-            mlp = MLPClassifier(
-                hidden_layer_sizes=(64, 32),
-                max_iter=600,
-                random_state=self.seed,
-                alpha=0.0005,
-            )
-
-            rf.fit(X_train, y_train)
-            gb.fit(X_train, y_train)
-            mlp.fit(X_train, y_train)
-
-            rf_acc = float(accuracy_score(y_test, rf.predict(X_test)))
-            gb_acc = float(accuracy_score(y_test, gb.predict(X_test)))
-            mlp_acc = float(accuracy_score(y_test, mlp.predict(X_test)))
-
-            self.models[pos] = (rf, gb, mlp)
-
-            reports.append(TrainReport(pos=pos, n_rows=len(self.df), rf_acc=rf_acc, gb_acc=gb_acc, mlp_acc=mlp_acc))
-
-        self.reports = reports
-        return reports
-
-    def _latest_feature_row(self) -> np.ndarray:
-        row = self.df.iloc[[-1]][self._feature_cols()].values
-        return row
-
-    def predict_top_k(self, top_k: int = 20, per_pos_top: int = 6) -> List[Tuple[str, float]]:
-        if not self.models:
-            self.train_models()
-
-        x = self._latest_feature_row()
-
-        # per-position digit probabilities (ensemble average)
-        pos_probs = {}
-        for pos in (1, 2, 3):
-            rf, gb, mlp = self.models[pos]
-            probs = []
-            for mdl in (rf, gb, mlp):
-                p = mdl.predict_proba(x)[0]
-                probs.append(p)
-            p_mean = np.mean(np.vstack(probs), axis=0)
-            p_mean = np.clip(p_mean, 1e-9, 1.0)
-            p_mean = p_mean / p_mean.sum()
-            pos_probs[pos] = p_mean
-
-        # Take top digits per position, then brute-force combine
-        top_digits = {}
-        for pos in (1, 2, 3):
-            p = pos_probs[pos]
-            idx = np.argsort(-p)[:per_pos_top]
-            top_digits[pos] = [(int(d), float(p[d])) for d in idx]
-
-        combos: List[Tuple[str, float]] = []
-        for d1, p1 in top_digits[1]:
-            for d2, p2 in top_digits[2]:
-                for d3, p3 in top_digits[3]:
-                    score = p1 * p2 * p3
-
-                    # mild pattern bias: avoid all-same digits (still possible, just downweighted)
-                    if d1 == d2 == d3:
-                        score *= 0.65
-
-                    combos.append((f"{d1}-{d2}-{d3}", float(score)))
-
-        combos.sort(key=lambda x: x[1], reverse=True)
-        return combos[:max(1, int(top_k))]
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--csv", default="Pick3eve.csv")
-    ap.add_argument("--top-k", type=int, default=20)
-    ap.add_argument("--seed", type=int, default=SEED)
-    args = ap.parse_args()
-
-    p = Pick3UltraPredictor(args.csv, seed=args.seed)
-    rep = p.train_models()
-
-    print("PICK 3 TRAINING REPORT")
-    for r in rep:
-        print(f"Pos {r.pos}: rows={r.n_rows} | RF acc={r.rf_acc:.3f} | GB acc={r.gb_acc:.3f} | MLP acc={r.mlp_acc:.3f}")
-
-    print("\nTOP PICKS")
-    for i, (combo, score) in enumerate(p.predict_top_k(top_k=args.top_k), start=1):
-        print(f"{i:2d}) {combo}  (score={score:.6f})")
-
-
-if __name__ == "__main__":
-    main()

pick4_catboost_ultra.py

@@ -1,187 +0,0 @@
-#!/usr/bin/env python3
-"""
-Pick 4 Ultra Predictor (stable + reproducible)
-
-- Trains fast ML models per digit-position (0-9 classification)
-- Deterministic outputs across machines when the same CSV is used
-- Designed to be called from Streamlit (HuggingFace) or CLI
-
-CSV format expected (like Pick4eve.csv):
-  DrawDate, 1, 2, 3, 4   (digits as ints 0-9)
-"""
-
-from __future__ import annotations
-
-import argparse
-from dataclasses import dataclass
-from typing import List, Tuple
-
-import numpy as np
-import pandas as pd
-from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
-from sklearn.neural_network import MLPClassifier
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
-
-
-SEED = 42
-
-
-@dataclass
-class TrainReport:
-    pos: int
-    n_rows: int
-    rf_acc: float
-    gb_acc: float
-    mlp_acc: float
-
-
-class Pick4UltraPredictor:
-    def __init__(self, csv_path: str, seed: int = SEED):
-        self.csv_path = csv_path
-        self.seed = int(seed)
-        self.df: pd.DataFrame = pd.DataFrame()
-        self.models = {}  # pos -> (rf, gb, mlp)
-        self.reports: List[TrainReport] = []
-
-    def load(self) -> pd.DataFrame:
-        df = pd.read_csv(self.csv_path)
-        if "DrawDate" not in df.columns:
-            raise ValueError("Pick4 CSV must include a 'DrawDate' column.")
-        for c in ("1", "2", "3", "4"):
-            if c not in df.columns:
-                raise ValueError("Pick4 CSV must include digit columns '1','2','3','4'.")
-        df = df.copy()
-        df["DrawDate"] = pd.to_datetime(df["DrawDate"], errors="coerce")
-        df = df.dropna(subset=["DrawDate"]).sort_values("DrawDate").reset_index(drop=True)
-
-        df["dow"] = df["DrawDate"].dt.dayofweek.astype(int)
-        df["month"] = df["DrawDate"].dt.month.astype(int)
-        df["day"] = df["DrawDate"].dt.day.astype(int)
-
-        for d in range(10):
-            mask = ((df[["1", "2", "3", "4"]] == d).any(axis=1)).astype(int)
-            df[f"hit_{d}"] = mask
-            df[f"roll20_{d}"] = df[f"hit_{d}"].rolling(20, min_periods=5).mean().fillna(0.0)
-            df[f"roll80_{d}"] = df[f"hit_{d}"].rolling(80, min_periods=10).mean().fillna(0.0)
-
-        for c in ("1", "2", "3", "4"):
-            df[f"prev_{c}"] = df[c].shift(1).fillna(method="bfill").astype(int)
-
-        self.df = df
-        return df
-
-    def _feature_cols(self) -> List[str]:
-        cols = ["dow", "month", "day", "prev_1", "prev_2", "prev_3", "prev_4"]
-        cols += [f"roll20_{d}" for d in range(10)]
-        cols += [f"roll80_{d}" for d in range(10)]
-        return cols
-
-    def train_models(self) -> List[TrainReport]:
-        if self.df.empty:
-            self.load()
-
-        X = self.df[self._feature_cols()].values
-        reports: List[TrainReport] = []
-
-        for pos, col in enumerate(("1", "2", "3", "4"), start=1):
-            y = self.df[col].astype(int).values
-            X_train, X_test, y_train, y_test = train_test_split(
-                X, y, test_size=0.20, random_state=self.seed, stratify=y
-            )
-
-            rf = RandomForestClassifier(
-                n_estimators=450,
-                max_depth=11,
-                random_state=self.seed,
-                n_jobs=-1,
-            )
-            gb = GradientBoostingClassifier(random_state=self.seed)
-            mlp = MLPClassifier(
-                hidden_layer_sizes=(72, 36),
-                max_iter=650,
-                random_state=self.seed,
-                alpha=0.0005,
-            )
-
-            rf.fit(X_train, y_train)
-            gb.fit(X_train, y_train)
-            mlp.fit(X_train, y_train)
-
-            rf_acc = float(accuracy_score(y_test, rf.predict(X_test)))
-            gb_acc = float(accuracy_score(y_test, gb.predict(X_test)))
-            mlp_acc = float(accuracy_score(y_test, mlp.predict(X_test)))
-
-            self.models[pos] = (rf, gb, mlp)
-            reports.append(TrainReport(pos=pos, n_rows=len(self.df), rf_acc=rf_acc, gb_acc=gb_acc, mlp_acc=mlp_acc))
-
-        self.reports = reports
-        return reports
-
-    def _latest_feature_row(self) -> np.ndarray:
-        return self.df.iloc[[-1]][self._feature_cols()].values
-
-    def predict_top_k(self, top_k: int = 30, per_pos_top: int = 5) -> List[Tuple[str, float]]:
-        if not self.models:
-            self.train_models()
-
-        x = self._latest_feature_row()
-
-        pos_probs = {}
-        for pos in (1, 2, 3, 4):
-            rf, gb, mlp = self.models[pos]
-            probs = []
-            for mdl in (rf, gb, mlp):
-                p = mdl.predict_proba(x)[0]
-                probs.append(p)
-            p_mean = np.mean(np.vstack(probs), axis=0)
-            p_mean = np.clip(p_mean, 1e-9, 1.0)
-            p_mean = p_mean / p_mean.sum()
-            pos_probs[pos] = p_mean
-
-        top_digits = {}
-        for pos in (1, 2, 3, 4):
-            p = pos_probs[pos]
-            idx = np.argsort(-p)[:per_pos_top]
-            top_digits[pos] = [(int(d), float(p[d])) for d in idx]
-
-        combos: List[Tuple[str, float]] = []
-        for d1, p1 in top_digits[1]:
-            for d2, p2 in top_digits[2]:
-                for d3, p3 in top_digits[3]:
-                    for d4, p4 in top_digits[4]:
-                        score = p1 * p2 * p3 * p4
-
-                        # mild pattern bias: penalize very "flat" patterns
-                        if d1 == d2 == d3 == d4:
-                            score *= 0.55
-                        if len({d1, d2, d3, d4}) <= 2:
-                            score *= 0.85
-
-                        combos.append((f"{d1}-{d2}-{d3}-{d4}", float(score)))
-
-        combos.sort(key=lambda x: x[1], reverse=True)
-        return combos[:max(1, int(top_k))]
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--csv", default="Pick4eve.csv")
-    ap.add_argument("--top-k", type=int, default=30)
-    ap.add_argument("--seed", type=int, default=SEED)
-    args = ap.parse_args()
-
-    p = Pick4UltraPredictor(args.csv, seed=args.seed)
-    rep = p.train_models()
-
-    print("PICK 4 TRAINING REPORT")
-    for r in rep:
-        print(f"Pos {r.pos}: rows={r.n_rows} | RF acc={r.rf_acc:.3f} | GB acc={r.gb_acc:.3f} | MLP acc={r.mlp_acc:.3f}")
-
-    print("\nTOP PICKS")
-    for i, (combo, score) in enumerate(p.predict_top_k(top_k=args.top_k), start=1):
-        print(f"{i:2d}) {combo}  (score={score:.8f})")
-
-
-if __name__ == "__main__":
-    main()

predictor.py

@@ -1,528 +0,0 @@
-#!/usr/bin/env python3
-"""
-predictor.py — Universal RandomForest (CSV-only) predictor for lottery-style games.
-
-What it does
-- Reads a game's CSV draw history directly (no dependence on your engine pools).
-- Trains RandomForestClassifier models to estimate the probability each number will appear next draw.
-- Produces:
-    * RF-1: Top-N numbers by probability (most likely)
-    * RF-2: Diversified RF (sampled from top pool; differs from RF-1 by >=2 numbers by default)
-
-Designed to be robust across many CSV formats:
-- Columns like n1..n5 / num1..num5 / ball1..ball5
-- Any 5 numeric columns (fallback)
-- A single column containing a hyphen/space/comma separated list of numbers (fallback heuristic)
-
-Optional bonus support
-- If a bonus column exists (e.g., megaball/powerball/starball), you can pass bonus_max and it will
-  also train a bonus RF and return bonus prediction.
-
-Requirements
-- pandas
-- scikit-learn
-- numpy
-
-If scikit-learn isn't installed, this module returns None predictions (safe failure).
-
-Usage (import)
-    from predictor import UniversalRFPredictor
-    rf = UniversalRFPredictor()
-    out = rf.predict(csv_path, main_max=52, main_n=5, bonus_max=10, bonus_n=1)
-    print(out["rf1_numbers"], out.get("rf1_bonus"))
-    print(out["rf2_numbers"], out.get("rf2_bonus"))
-
-Usage (CLI)
-    python predictor.py --csv "E:\data\la_results.csv" --main-max 52 --main-n 5 --bonus-max 10 --bonus-n 1
-"""
-
-from __future__ import annotations
-
-import argparse
-import hashlib
-import os
-import re
-import random
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Sequence, Tuple
-
-# ----------------------------- helpers -----------------------------
-
-_SPLIT_RE = re.compile(r"[^0-9]+")
-
-def _safe_int(x: Any) -> Optional[int]:
-    try:
-        if x is None:
-            return None
-        if isinstance(x, bool):
-            return None
-        return int(x)
-    except Exception:
-        try:
-            s = str(x).strip()
-            if not s:
-                return None
-            return int(float(s))
-        except Exception:
-            return None
-
-def _dedupe(seq: Sequence[Any]) -> List[int]:
-    out: List[int] = []
-    seen = set()
-    for v in (seq or []):
-        iv = _safe_int(v)
-        if iv is None:
-            continue
-        if iv in seen:
-            continue
-        seen.add(iv)
-        out.append(iv)
-    return out
-
-def _md5_seed(s: str, fallback: int = 1337) -> int:
-    try:
-        return int(hashlib.md5(s.encode("utf-8")).hexdigest()[:8], 16)
-    except Exception:
-        return fallback
-
-def _clip(nums: Sequence[int], lo: int, hi: int) -> List[int]:
-    out = []
-    for n in nums:
-        if lo <= n <= hi:
-            out.append(n)
-    return out
-
-# ----------------------------- CSV parsing -----------------------------
-
-@dataclass
-class ParsedHistory:
-    draws: List[List[int]]            # list of main number lists
-    bonus: List[Optional[int]]        # list of bonus values aligned with draws
-
-class CSVHistoryReader:
-    """Best-effort reader for many draw-history CSV layouts."""
-
-    DEFAULT_MAIN_PATTERNS = [
-        ["n1", "n2", "n3", "n4", "n5"],
-        ["num1", "num2", "num3", "num4", "num5"],
-        ["ball1", "ball2", "ball3", "ball4", "ball5"],
-        ["w1", "w2", "w3", "w4", "w5"],
-    ]
-
-    DEFAULT_BONUS_CANDIDATES = [
-        "mb", "megaball", "mega_ball",
-        "pb", "powerball", "power_ball",
-        "sb", "star", "starball", "star_ball",
-        "bonus", "bonusball", "bonus_ball",
-        "luckyball", "lucky_ball",
-    ]
-
-    def __init__(self, verbose: bool = False):
-        self.verbose = verbose
-
-    def read(self, csv_path: str, main_n: int = 5) -> ParsedHistory:
-        try:
-            import pandas as pd  # type: ignore
-        except Exception:
-            return ParsedHistory(draws=[], bonus=[])
-
-        try:
-            df = pd.read_csv(csv_path)
-        except Exception:
-            return ParsedHistory(draws=[], bonus=[])
-
-        # 1) Find main columns using common patterns
-        main_cols: Optional[List[str]] = None
-        for pat in self.DEFAULT_MAIN_PATTERNS:
-            if all(c in df.columns for c in pat[:main_n]):
-                main_cols = pat[:main_n]
-                break
-
-        # 2) If not found, choose first `main_n` numeric columns
-        if main_cols is None:
-            numeric_cols = []
-            for c in df.columns:
-                try:
-                    kind = getattr(df[c].dtype, "kind", "")
-                except Exception:
-                    kind = ""
-                if kind in ("i", "u", "f"):
-                    numeric_cols.append(c)
-            if len(numeric_cols) >= main_n:
-                main_cols = numeric_cols[:main_n]
-
-        # 3) If still not found, look for a single column that contains a list of numbers
-        list_col: Optional[str] = None
-        if main_cols is None:
-            for c in df.columns:
-                if df[c].dtype == object:
-                    # check if it looks like "1-2-3-4-5" or "1 2 3 4 5"
-                    sample = df[c].dropna().astype(str).head(10).tolist()
-                    hits = 0
-                    for s in sample:
-                        parts = [p for p in _SPLIT_RE.split(s) if p]
-                        if len(parts) >= main_n and all(p.isdigit() for p in parts[:main_n]):
-                            hits += 1
-                    if hits >= max(1, len(sample) // 2):
-                        list_col = c
-                        break
-
-        # Bonus column detection
-        bonus_col: Optional[str] = None
-        lower_cols = {str(c).lower(): c for c in df.columns}
-        for cand in self.DEFAULT_BONUS_CANDIDATES:
-            if cand in lower_cols:
-                bonus_col = lower_cols[cand]
-                break
-
-        draws: List[List[int]] = []
-        bonus: List[Optional[int]] = []
-
-        if main_cols is not None:
-            for _, row in df[main_cols].iterrows():
-                nums = []
-                ok = True
-                for c in main_cols:
-                    iv = _safe_int(row[c])
-                    if iv is None:
-                        ok = False
-                        break
-                    nums.append(iv)
-                if ok and len(nums) == main_n:
-                    draws.append(nums)
-                    bonus.append(_safe_int(row[bonus_col]) if bonus_col else None)
-
-        elif list_col is not None:
-            for _, row in df[[list_col]].iterrows():
-                s = str(row[list_col])
-                parts = [p for p in _SPLIT_RE.split(s) if p]
-                if len(parts) < main_n:
-                    continue
-                nums = []
-                ok = True
-                for p in parts[:main_n]:
-                    iv = _safe_int(p)
-                    if iv is None:
-                        ok = False
-                        break
-                    nums.append(iv)
-                if ok and len(nums) == main_n:
-                    draws.append(nums)
-                    # bonus may also be embedded later; ignore here (None)
-                    bonus.append(None)
-        else:
-            # Could not parse
-            return ParsedHistory(draws=[], bonus=[])
-
-        return ParsedHistory(draws=draws, bonus=bonus)
-
-# ----------------------------- RF core -----------------------------
-
-class UniversalRFPredictor:
-    def __init__(self, verbose: bool = False):
-        self.verbose = verbose
-        self.reader = CSVHistoryReader(verbose=verbose)
-
-    def _build_features(self, draws: List[List[int]], universe_max: int, lookback: int = 12):
-        """Build per-number time-series features and next-step feature vector."""
-        import numpy as np  # type: ignore
-
-        if len(draws) < (lookback + 5):
-            return {}
-
-        appears = {n: [0] * len(draws) for n in range(1, universe_max + 1)}
-        for t, d in enumerate(draws):
-            s = set(d)
-            for n in s:
-                if 1 <= n <= universe_max:
-                    appears[n][t] = 1
-
-        def recent_count(arr, t, w):
-            return int(sum(arr[max(0, t - w):t]))
-
-        def gap_since(arr, t):
-            for k in range(1, t + 1):
-                if arr[t - k] == 1:
-                    return k
-            return t
-
-        feats = {}
-        for n in range(1, universe_max + 1):
-            arr = appears[n]
-            X, y = [], []
-            for t in range(lookback, len(draws)):
-                f = [
-                    recent_count(arr, t, 5),
-                    recent_count(arr, t, 10),
-                    gap_since(arr, t),
-                    arr[t - 1],
-                    arr[t - 2] if t - 2 >= 0 else 0,
-                    arr[t - 3] if t - 3 >= 0 else 0,
-                ]
-                X.append(f)
-                y.append(arr[t])
-
-            t = len(draws)
-            last_f = [
-                recent_count(arr, t, 5),
-                recent_count(arr, t, 10),
-                gap_since(arr, t),
-                arr[t - 1],
-                arr[t - 2] if t - 2 >= 0 else 0,
-                arr[t - 3] if t - 3 >= 0 else 0,
-            ]
-            feats[n] = (np.asarray(X, float), np.asarray(y, int), np.asarray(last_f, float))
-        return feats
-
-    def _rank_numbers(self, draws: List[List[int]], universe_max: int, seed: int) -> List[Tuple[int, float]]:
-        try:
-            from sklearn.ensemble import RandomForestClassifier  # type: ignore
-            import numpy as np  # type: ignore
-        except Exception:
-            return []
-
-        feats = self._build_features(draws, universe_max, lookback=12)
-        if not feats:
-            return []
-
-        probs: List[Tuple[int, float]] = []
-        for n, (X, y, last_f) in feats.items():
-            if int(y.sum()) < 5 or int((1 - y).sum()) < 5:
-                continue
-            try:
-                clf = RandomForestClassifier(
-                    n_estimators=240,
-                    max_depth=9,
-                    random_state=seed,
-                    class_weight="balanced",
-                    n_jobs=-1
-                )
-                clf.fit(X, y)
-                p = float(clf.predict_proba(last_f.reshape(1, -1))[0][1])
-                probs.append((n, p))
-            except Exception:
-                continue
-
-        probs.sort(key=lambda t: t[1], reverse=True)
-        return probs
-
-    def _rank_bonus(self, bonus_series: List[Optional[int]], bonus_max: int, seed: int) -> List[Tuple[int, float]]:
-        """Simple RF for bonus (single categorical per draw)."""
-        try:
-            from sklearn.ensemble import RandomForestClassifier  # type: ignore
-            import numpy as np  # type: ignore
-        except Exception:
-            return []
-
-        # Need enough bonus observations
-        b = [_safe_int(x) for x in bonus_series]
-        if sum(1 for x in b if x is not None) < 40:
-            return []
-
-        # Build appearance series for each bonus value 1..bonus_max
-        T = len(b)
-
-        def recent_count(arr, t, w):
-            return int(sum(arr[max(0, t - w):t]))
-
-        def gap_since(arr, t):
-            for k in range(1, t + 1):
-                if arr[t - k] == 1:
-                    return k
-            return t
-
-        probs: List[Tuple[int, float]] = []
-        for val in range(1, bonus_max + 1):
-            arr = [1 if _safe_int(b[t]) == val else 0 for t in range(T)]
-            X, y = [], []
-            lookback = 10
-            for t in range(lookback, T):
-                f = [
-                    recent_count(arr, t, 5),
-                    recent_count(arr, t, 10),
-                    gap_since(arr, t),
-                    arr[t - 1],
-                    arr[t - 2] if t - 2 >= 0 else 0,
-                    arr[t - 3] if t - 3 >= 0 else 0,
-                ]
-                X.append(f)
-                y.append(arr[t])
-            if len(X) < 30:
-                continue
-            X = np.asarray(X, float)
-            y = np.asarray(y, int)
-            if int(y.sum()) < 3 or int((1 - y).sum()) < 3:
-                continue
-            last_f = np.asarray([
-                recent_count(arr, T, 5),
-                recent_count(arr, T, 10),
-                gap_since(arr, T),
-                arr[T - 1],
-                arr[T - 2] if T - 2 >= 0 else 0,
-                arr[T - 3] if T - 3 >= 0 else 0,
-            ], float).reshape(1, -1)
-
-            try:
-                clf = RandomForestClassifier(
-                    n_estimators=200,
-                    max_depth=8,
-                    random_state=seed,
-                    class_weight="balanced",
-                    n_jobs=-1
-                )
-                clf.fit(X, y)
-                p = float(clf.predict_proba(last_f)[0][1])
-                probs.append((val, p))
-            except Exception:
-                continue
-
-        probs.sort(key=lambda t: t[1], reverse=True)
-        return probs
-
-    def _pick_rf1_rf2(self, probs: List[Tuple[int, float]], main_n: int, min_diff: int = 2) -> Tuple[List[int], Optional[List[int]]]:
-        if not probs or len(probs) < main_n:
-            return [], None
-
-        rf1 = [n for n, _ in probs[:main_n]]
-
-        # diversified sampling from top pool
-        pool = probs[:max(12, main_n * 3)]
-        nums = [n for n, _ in pool]
-        weights = [max(1e-9, p) for _, p in pool]
-
-        seed = _md5_seed(",".join(map(str, rf1)) + "|" + ",".join(map(str, nums[:10])))
-        rng = random.Random(seed)
-
-        def sample_ticket() -> List[int]:
-            chosen = []
-            remaining = list(zip(nums, weights))
-            for _ in range(main_n):
-                total = sum(w for _, w in remaining)
-                if total <= 0:
-                    break
-                r = rng.random() * total
-                cum = 0.0
-                pick_idx = 0
-                for i, (n, w) in enumerate(remaining):
-                    cum += w
-                    if cum >= r:
-                        pick_idx = i
-                        break
-                n_pick, _ = remaining.pop(pick_idx)
-                chosen.append(n_pick)
-            return sorted(_dedupe(chosen))
-
-        rf2: Optional[List[int]] = None
-        for _ in range(60):
-            cand = sample_ticket()
-            if len(cand) != main_n:
-                continue
-            overlap = len(set(cand) & set(rf1))
-            # require at least `min_diff` numbers different
-            if overlap <= (main_n - min_diff):
-                rf2 = cand
-                break
-
-        # fallback: if diversification fails, return None (honest)
-        return sorted(rf1), sorted(rf2) if rf2 else None
-
-    def predict(
-        self,
-        csv_path: str,
-        main_max: int,
-        main_n: int = 5,
-        bonus_max: Optional[int] = None,
-        bonus_n: int = 0,
-        seed_key: str = "",
-        min_diff: int = 2,
-        min_draws: int = 60,
-    ) -> Dict[str, Any]:
-        """Return RF predictions from CSV history."""
-        out: Dict[str, Any] = {
-            "ok": False,
-            "rf1_numbers": [],
-            "rf2_numbers": None,
-            "rf1_bonus": None,
-            "rf2_bonus": None,
-            "reason": "",
-        }
-
-        if not csv_path or not os.path.exists(csv_path):
-            out["reason"] = "csv_missing"
-            return out
-
-        hist = self.reader.read(csv_path, main_n=main_n)
-        draws = hist.draws
-        if len(draws) < min_draws:
-            out["reason"] = f"too_few_draws:{len(draws)}"
-            return out
-
-        # clip to valid range defensively
-        draws = [_clip(_dedupe(d), 1, int(main_max))[:main_n] for d in draws if d]
-        draws = [d for d in draws if len(d) == main_n]
-        if len(draws) < min_draws:
-            out["reason"] = f"too_few_valid_draws:{len(draws)}"
-            return out
-
-        seed = _md5_seed(seed_key or (csv_path + "|" + str(main_max) + "|" + str(main_n)))
-        probs = self._rank_numbers(draws, int(main_max), seed=seed)
-        if not probs:
-            out["reason"] = "rf_rank_empty"
-            return out
-
-        rf1, rf2 = self._pick_rf1_rf2(probs, main_n=int(main_n), min_diff=int(min_diff))
-        if not rf1:
-            out["reason"] = "rf1_empty"
-            return out
-
-        out["rf1_numbers"] = rf1
-        out["rf2_numbers"] = rf2
-        out["ok"] = True
-
-        # Bonus prediction (optional)
-        if bonus_max and bonus_n and bonus_n > 0:
-            bprobs = self._rank_bonus(hist.bonus, int(bonus_max), seed=seed)
-            if bprobs:
-                out["rf1_bonus"] = bprobs[0][0]
-                # For bonus, "diversification" isn't meaningful; if rf2 exists, reuse rf1_bonus
-                out["rf2_bonus"] = out["rf1_bonus"]
-
-        return out
-
-
-# ----------------------------- CLI -----------------------------
-
-def main():
-    p = argparse.ArgumentParser(description="Universal RF predictor (CSV-only).")
-    p.add_argument("--csv", required=True, help="Path to draw-history CSV")
-    p.add_argument("--main-max", required=True, type=int, help="Max main number (e.g., 52)")
-    p.add_argument("--main-n", default=5, type=int, help="Count of main numbers per draw")
-    p.add_argument("--bonus-max", default=None, type=int, help="Max bonus number (optional)")
-    p.add_argument("--bonus-n", default=0, type=int, help="Bonus count (0 or 1)")
-    p.add_argument("--min-draws", default=60, type=int, help="Minimum draws required")
-    p.add_argument("--min-diff", default=2, type=int, help="RF-2 min number-diff vs RF-1")
-    p.add_argument("--seed-key", default="", help="Seed key for reproducibility")
-    p.add_argument("--verbose", action="store_true")
-    args = p.parse_args()
-
-    rf = UniversalRFPredictor(verbose=args.verbose)
-    out = rf.predict(
-        csv_path=args.csv,
-        main_max=args.main_max,
-        main_n=args.main_n,
-        bonus_max=args.bonus_max,
-        bonus_n=args.bonus_n,
-        seed_key=args.seed_key,
-        min_diff=args.min_diff,
-        min_draws=args.min_draws,
-    )
-    print(out)
-
-    if out.get("ok"):
-        print("RF-1:", out["rf1_numbers"], "BONUS:", out.get("rf1_bonus"))
-        print("RF-2:", out.get("rf2_numbers"), "BONUS:", out.get("rf2_bonus"))
-    else:
-        print("Not OK:", out.get("reason"))
-
-if __name__ == "__main__":
-    main()

predictor_common.py

@@ -1,67 +0,0 @@
-#!/usr/bin/env python3
-from __future__ import annotations
-import json, random
-from datetime import datetime
-from pathlib import Path
-from typing import Any, Dict, Optional
-import numpy as np
-
-def set_reproducible_seeds(seed: int = 42) -> None:
-    random.seed(seed)
-    np.random.seed(seed)
-
-def configure_engine_flags(engine_mod, *, deep_low=True, tight_relax=True, mid_carry=True, wildcard=True):
-    flags = {
-        "deep_low_patch": bool(deep_low),
-        "tight_relax_patch": bool(tight_relax),
-        "mid_carry_patch": bool(mid_carry),
-        "wildcard_strike": bool(wildcard),
-    }
-    if hasattr(engine_mod, "PATCH_UI_FLAGS") and isinstance(getattr(engine_mod, "PATCH_UI_FLAGS"), dict):
-        engine_mod.PATCH_UI_FLAGS.update(flags)
-
-def summarize_result(game_key: str, res: Dict[str, Any]) -> str:
-    lines = [f"GAME: {game_key}", f"GENERATED: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ""]
-    nums = res.get("numbers") or []
-    star = res.get("star", None)
-    if nums:
-        lines.append(f"PRIMARY: {'-'.join(map(str, nums))}" + (f" | ⭐ {star}" if star is not None else ""))
-        lines.append("")
-    god_sets = res.get("god_sets") or res.get("godmode_sets") or res.get("god_mode_sets") or []
-    if god_sets:
-        lines.append("GOD MODE SETS:")
-        for s in god_sets:
-            sn = s.get("numbers") or []
-            ss = s.get("star", None)
-            if sn:
-                lines.append(f"- {s.get('style','set')}: {'-'.join(map(str, sn))}" + (f" | ⭐ {ss}" if ss is not None else ""))
-        lines.append("")
-    strike = res.get("strike_tickets") or {}
-    if strike:
-        lines.append("STRIKE TICKETS:")
-        for k, v in strike.items():
-            sn = (v or {}).get("numbers") or []
-            ss = (v or {}).get("star", None)
-            if sn:
-                lines.append(f"- {k}: {'-'.join(map(str, sn))}" + (f" | ⭐ {ss}" if ss is not None else ""))
-        lines.append("")
-    wc = res.get("wildcard")
-    if wc:
-        sn = (wc or {}).get("numbers") or []
-        ss = (wc or {}).get("star", None)
-        if sn:
-            lines.append(f"WILDCARD PROFILE: {'-'.join(map(str, sn))}" + (f" | ⭐ {ss}" if ss is not None else ""))
-    return "\n".join(lines)
-
-def run_prediction(engine_mod, csv_filename: str, game_key: str, *, seed: int,
-                   deep_low=True, tight_relax=True, mid_carry=True, wildcard=True,
-                   out_dir: Optional[str] = None) -> Dict[str, Any]:
-    set_reproducible_seeds(seed)
-    configure_engine_flags(engine_mod, deep_low=deep_low, tight_relax=tight_relax, mid_carry=mid_carry, wildcard=wildcard)
-    res = engine_mod.predict_for_game_v3(Path(csv_filename), game_key, run_backtest=False)
-    outp = Path(out_dir or ".")
-    outp.mkdir(parents=True, exist_ok=True)
-    ts = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
-    base = f"{game_key}_godmode_{ts}"
-    (outp / f"{base}.txt").write_text(summarize_result(game_key, res), encoding="utf-8")
-    return res

requirements.txt

@@ -1,16 +1,4 @@
-streamlit
-pandas
-numpy
-scikit-learn
-xgboost
-lightgbm
-catboost
-streamlit>=1.30.0
-numpy==1.26.4
-pandas==2.2.2
-scikit-learn==1.5.2
-xgboost==2.1.1
-catboost==1.2.7
-
-
-
+pandas
+numpy
+scikit-learn
+streamlit

requirementsold.txt

@@ -1,11 +0,0 @@
-pandas
-numpy
-scikit-learn
-streamlit
-gradio>=4.0.0
-pandas>=2.0.0
-numpy>=1.24.0
-xgboost
-matplotlib
-gradio
-

wheel.txt

@@ -1,81 +0,0 @@
-Pick-5 Balanced Wheel� 53120.076                                          Page 1
-Wheeling 20 numbers in 76 games for a 3/4 Win                             pb0569
-Re: ai wheel 20 numbers                                      Printed: 07/09/2025
-Your Numbers: 01-02-03-04-05-06-07-08-09-10-11-12-13-14-15-16-17-18-19-20
-
- 1-01-02-06-18-19-46
- 2-01-03-13-18-19-54
- 3-01-04-10-18-19-52
- 4-01-05-15-18-19-58
- 5-01-07-12-18-19-57
- 6-01-08-09-18-19-55
- 7-01-11-16-18-19-65
- 8-01-14-18-19-20-72
- 9-02-03-04-05-17-31
-10-02-03-06-11-12-34
-11-02-03-07-10-14-36
-12-02-03-08-13-20-46
-13-02-03-09-15-16-45
-14-02-04-06-13-15-40
-15-02-04-07-08-16-37
-16-02-04-09-11-14-40
-17-02-04-10-12-20-48
-18-02-05-06-10-16-39
-19-02-05-07-11-13-38
-20-02-05-08-09-12-36
-21-02-05-14-15-20-56
-22-02-06-07-09-20-44
-23-02-06-08-14-17-47
-24-02-07-12-15-17-53
-25-02-08-10-11-15-46
-26-02-09-10-13-17-51
-27-02-11-16-17-20-66
-28-02-12-13-14-16-57
-29-03-04-06-14-20-47
-30-03-04-07-09-13-36
-31-03-04-08-12-15-42
-32-03-04-10-11-16-44
-33-03-05-06-07-15-36
-34-03-05-08-14-16-46
-35-03-05-09-11-20-48
-36-03-05-10-12-13-43
-37-03-06-08-09-10-36
-38-03-06-13-16-17-55
-39-03-07-08-11-17-46
-40-03-07-12-16-20-58
-41-03-09-12-14-17-55
-42-03-10-15-17-20-65
-43-03-11-13-14-15-56
-44-04-05-06-08-11-34
-45-04-05-07-12-14-42
-46-04-05-09-10-15-43
-47-04-05-13-16-20-58
-48-04-06-07-10-17-44
-49-04-06-09-12-16-47
-50-04-07-11-15-20-57
-51-04-08-09-17-20-58
-52-04-08-10-13-14-49
-53-04-11-12-13-17-57
-54-04-14-15-16-17-66
-55-05-06-09-13-14-47
-56-05-06-12-17-20-60
-57-05-07-08-10-20-50
-58-05-07-09-16-17-54
-59-05-08-13-15-17-58
-60-05-10-11-14-17-57
-61-05-11-12-15-16-59
-62-06-07-08-12-13-46
-63-06-07-11-14-16-54
-64-06-08-15-16-20-65
-65-06-09-11-15-17-58
-66-06-10-11-13-20-60
-67-06-10-12-14-15-57
-68-07-08-09-14-15-53
-69-07-09-10-11-12-49
-70-07-10-13-15-16-61
-71-07-13-14-17-20-71
-72-08-09-11-13-16-57
-73-08-10-12-16-17-63
-74-08-11-12-14-20-65
-75-09-10-14-16-20-69
-76-09-12-13-15-20-69