Update project for Hugging Face Spaces

.gitignore

@@ -0,0 +1,34 @@
+# Python virtual environment
+venv/
+env/
+ENV/
+
+# Python bytecode
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# Environment variables
+.env
+.env.local
+
+# Streamlit specific
+.streamlit/
+
+# OS specific
+.DS_Store
+Thumbs.db 

.huggingfaceignore

@@ -0,0 +1,8 @@
+.git/
+.gitignore
+.huggingfaceignore
+__pycache__/
+*.pyc
+venv/
+.env
+.DS_Store 

Dockerfile

@@ -0,0 +1,28 @@
+# Use Python 3.10 slim image
+FROM python:3.10-slim
+
+# Create a non-root user
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements first to leverage Docker cache
+COPY --chown=user ./requirements.txt requirements.txt
+
+# Install dependencies
+RUN pip install --no-cache-dir --user -r requirements.txt
+
+# Download NLTK data
+RUN python -c "import nltk; nltk.download('punkt')"
+
+# Copy the rest of the application
+COPY --chown=user . /app
+
+# Expose the port Hugging Face Spaces uses
+EXPOSE 7860
+
+# Command to run the application
+CMD ["streamlit", "run", "app.py", "--server.address", "0.0.0.0", "--server.port", "7860"]

README.md

@@ -1 +1,91 @@
-# sf_tools
+# Bayesian Token Co-occurrence Simulator
+
+A Streamlit application that simulates and visualizes token co-occurrence patterns using Bayesian methods.
+
+## Local Development Setup
+
+1. Create and activate a virtual environment:
+```bash
+# Create virtual environment
+python -m venv venv
+
+# Activate virtual environment
+# On macOS/Linux:
+source venv/bin/activate
+# On Windows:
+.\venv\Scripts\activate
+```
+
+2. Install dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+3. Run the application:
+```bash
+streamlit run app.py
+```
+
+The application will be available at http://localhost:8501
+
+## Docker Setup
+
+1. Build the Docker image:
+```bash
+docker build -t bayesian-token-simulator .
+```
+
+2. Run the Docker container:
+```bash
+docker run -p 8501:8501 bayesian-token-simulator
+```
+
+The application will be available at http://localhost:8501
+
+## Hugging Face Spaces Deployment
+
+1. Clone your Hugging Face Space repository:
+```bash
+git clone https://huggingface.co/spaces/afscomercial/stf_model
+```
+
+2. Copy your project files to the cloned repository:
+```bash
+cp -r app.py requirements.txt Dockerfile .huggingfaceignore stf_model/
+```
+
+3. Push the changes to Hugging Face:
+```bash
+cd stf_model
+git add .
+git commit -m "Add Bayesian Token Co-occurrence Simulator"
+git push
+```
+
+Your application will be automatically deployed to https://huggingface.co/spaces/afscomercial/stf_model
+
+## Project Structure
+
+- `app.py`: Main Streamlit application
+- `requirements.txt`: Python dependencies
+- `Dockerfile`: Docker configuration
+- `.gitignore`: Git ignore rules
+- `.huggingfaceignore`: Hugging Face ignore rules
+
+## Features
+
+- Interactive text input for training sentences
+- Bayesian smoothing parameter adjustment
+- Co-occurrence matrix visualization
+- Next token prediction
+- Real-time updates
+
+## Requirements
+
+- Python 3.8+
+- Streamlit
+- NumPy
+- Pandas
+- Matplotlib
+- Seaborn
+- NLTK

app.py

@@ -0,0 +1,54 @@
+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==1.32.0
+numpy==1.26.4
+pandas==2.2.1
+matplotlib==3.8.3
+seaborn==0.13.2
+nltk==3.8.1