Update Dockerfile

Dockerfile

@@ -6,6 +6,7 @@ ENV HOME=/app
 ENV XDG_CONFIG_HOME=/app/.streamlit
 ENV NLTK_DATA=/app/nltk_data
 
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
     build-essential \
     curl \
@@ -13,8 +14,10 @@ RUN apt-get update && apt-get install -y \
     git \
     && rm -rf /var/lib/apt/lists/*
 
+# Create necessary directories
 RUN mkdir -p /app/.streamlit /app/nltk_data && chmod -R 777 /app
 
+# Copy project files
 COPY requirements.txt ./
 COPY src/ ./src/
 COPY src/c_d.csv ./src/
@@ -22,11 +25,14 @@ COPY src/logistic_models.pkl ./src/
 COPY src/tfidf.pkl ./src/
 COPY src/multilabels.pkl ./src/
 
+# Install Python dependencies
 RUN pip install --no-cache-dir -r requirements.txt
-RUN python -m nltk.downloader -d /app/nltk_data punkt averaged_perceptron_tagger wordnet stopwords
 
+# Only now that nltk is installed, download NLTK resources
+RUN python -m nltk.downloader -d /app/nltk_data punkt averaged_perceptron_tagger wordnet stopwords
 
-# Expose only for dev
+# Expose port (for dev, can remove if reverse proxying)
 EXPOSE 8501
 
+# Start the Streamlit app
 CMD ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]