Initial commit of Bayesian Simulator

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.9-slim
+WORKDIR /app
+# Install system dependencies
+RUN apt-get update && apt-get install -y build-essential
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+# Copy app files
+COPY . .
+# Expose default Streamlit port
+EXPOSE 8501
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from nltk.tokenize import word_tokenize
+import nltk
+
+nltk.download('punkt')
+
+st.title("📊 Bayesian Token Co-occurrence Simulator")
+
+# User input
+user_input = st.text_area("✍️ Enter your training sentences (one per line):", 
+""" 
+fido loves the red ball
+timmy and fido go to the park
+fido and timmy love to play
+the red ball is timmy's favorite toy
+""")
+
+sentences = user_input.strip().split('\n')
+tokenized = [word_tokenize(s.lower()) for s in sentences if s.strip()]
+vocab = sorted(set(word for sentence in tokenized for word in sentence))
+token2idx = {word: i for i, word in enumerate(vocab)}
+idx2token = {i: word for word, i in token2idx.items()}
+
+# Co-occurrence matrix
+window_size = 2
+matrix = np.zeros((len(vocab), len(vocab)))
+
+for sentence in tokenized:
+    for i, word in enumerate(sentence):
+        for j in range(max(0, i - window_size), min(len(sentence), i + window_size + 1)):
+            if i != j:
+                matrix[token2idx[word]][token2idx[sentence[j]]] += 1
+
+alpha = st.slider("🔧 Set Bayesian Prior (α smoothing)", 0.0, 2.0, 0.1)
+posterior = matrix + alpha
+
+df = pd.DataFrame(posterior, index=vocab, columns=vocab)
+st.subheader("📈 Co-occurrence Heatmap")
+fig, ax = plt.subplots(figsize=(10, 8))
+sns.heatmap(df, annot=True, cmap="Blues", fmt=".1f", ax=ax)
+st.pyplot(fig)
+
+# Next-token prediction
+selected_word = st.selectbox("🔮 Predict next token after:", vocab)
+row = posterior[token2idx[selected_word]]
+probs = row / row.sum()
+prediction = np.random.choice(vocab, p=probs)
+
+st.markdown(f"**Predicted next token:** `{prediction}`")
+
+

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+nltk
+numpy
+pandas
+matplotlib
+seaborn