Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,14 @@
-FROM python:3.13.5-slim
+# Use a minimal base image with Python 3.9 installed
+FROM python:3.9-slim
 
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Define the command to run the Streamlit app on port 8501 and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

app.py

@@ -0,0 +1,52 @@
+import streamlit as st
+import pandas as pd
+import joblib
+
+# Load the trained regression model
+def load_model():
+    return joblib.load("boston_housing_model_v1_0.joblib")
+
+model = load_model()
+
+# Streamlit UI for Boston Housing Price Prediction
+st.title("Boston Housing Price Prediction App")
+st.write("This app predicts the median value of owner-occupied homes (`MEDV`) in $1000s based on Boston housing dataset features.")
+st.write("Move the sliders below to adjust values and get a prediction.")
+
+# Collect user input using sliders
+CRIM = st.slider("Per capita crime rate by town (CRIM)", 0.0, 100.0, 0.2, 0.1)
+ZN = st.slider("Proportion of residential land zoned for lots over 25,000 sq.ft. (ZN)", 0.0, 100.0, 12.0, 1.0)
+INDUS = st.slider("Proportion of non-retail business acres per town (INDUS)", 0.0, 30.0, 11.0, 0.5)
+NX = st.slider("Nitric oxides concentration (NX)", 0.0, 1.0, 0.55, 0.01)
+RM = st.slider("Average number of rooms per dwelling (RM)", 3.0, 9.0, 6.3, 0.1)
+AGE = st.slider("Proportion of owner-occupied units built prior to 1940 (AGE)", 0.0, 100.0, 65.0, 1.0)
+DIS = st.slider("Weighted distances to employment centers (DIS)", 1.0, 12.0, 4.0, 0.1)
+RAD = st.slider("Index of accessibility to radial highways (RAD)", 1, 24, 4, 1)
+TAX = st.slider("Full-value property tax rate per $10,000 (TAX)", 100, 700, 300, 1)
+PTRATIO = st.slider("Pupil-teacher ratio by town (PTRATIO)", 10.0, 25.0, 19.0, 0.1)
+LSTAT = st.slider("% lower status of the population (LSTAT)", 0.0, 40.0, 12.0, 0.1)
+
+# Categorical feature
+CHAS = st.selectbox("Charles River dummy variable (CHAS)", ["0 (No)", "1 (Yes)"])
+CHAS_value = 1 if CHAS.startswith("1") else 0
+
+# Create input DataFrame
+input_data = pd.DataFrame([{
+    'CRIM': CRIM,
+    'ZN': ZN,
+    'INDUS': INDUS,
+    'NX': NX,
+    'RM': RM,
+    'AGE': AGE,
+    'DIS': DIS,
+    'RAD': RAD,
+    'TAX': TAX,
+    'PTRATIO': PTRATIO,
+    'LSTAT': LSTAT,
+    'CHAS': CHAS_value
+}])
+
+# Predict button
+if st.button("Predict MEDV"):
+    predicted_price = model.predict(input_data)[0]
+    st.success(f"💰 Estimated Median Value of Home (MEDV): ${predicted_price*1000:,.2f}")

boston_housing_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49f57a85f57e4ffd4861e9d01a904c6508563fc8a6e869038ffe7a9d393521f
+size 233799

requirements.txt

@@ -1,3 +1,6 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+streamlit==1.43.2