Upload backend app files

Dockerfile

@@ -1,20 +1,20 @@
-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 the requirements.txt file into the working directory
+COPY requirements.txt .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
+# Copy the rest of the application files into the working directory
+COPY . .
 
-EXPOSE 8501
+# Expose port 5000
+EXPOSE 5000
 
-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 Flask application
+CMD ["flask", "run", "--host=0.0.0.0"]

app.py

@@ -0,0 +1,51 @@
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
+
+app = Flask(__name__)
+
+# Load the serialized full pipeline
+try:
+    full_pipeline = joblib.load('deployment_files/SuperKart_model_v1_0.joblib')
+    # Get the list of columns from the training data used by the pipeline
+    pipeline_columns = full_pipeline.named_steps['preprocessor'].transformers_[0][1].get_feature_names_out(
+        full_pipeline.named_steps['preprocessor'].transformers_[0][2]
+    ).tolist()
+    # Add numerical columns to the pipeline columns list
+    numerical_cols_in_pipeline = [col for col in full_pipeline.named_steps['scaler'].feature_names_in_]
+    pipeline_columns = numerical_cols_in_pipeline + [col for col in pipeline_columns if col not in numerical_cols_in_pipeline]
+
+except Exception as e:
+    full_pipeline = None
+    print(f"Error loading pipeline: {e}")
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if full_pipeline is None:
+        return jsonify({'error': 'Model not loaded'}), 500
+
+    try:
+        data = request.get_json(force=True)
+
+        # Convert input data to DataFrame, ensuring column order matches training data
+        input_df = pd.DataFrame([data])
+
+        # Reorder columns to match the order expected by the pipeline
+        # This assumes all expected columns are present in the input data
+        input_df = input_df[pipeline_columns]
+
+
+        # Make prediction
+        prediction = full_pipeline.predict(input_df)
+
+        # Return prediction as JSON
+        return jsonify({'prediction': prediction.tolist()})
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
+
+if __name__ == '__main__':
+    # Create the backend_app directory if it doesn't exist
+    import os
+    os.makedirs('backend_app', exist_ok=True)
+    app.run(debug=True, host='0.0.0.0', port=5000)

requirements.txt

@@ -1,3 +1,5 @@
-altair
-pandas
-streamlit
+Flask==3.0.3
+joblib==1.4.2
+pandas==2.2.2
+scikit-learn==1.6.1
+numpy==2.0.2