Upload 4 files

Dockerfile

@@ -0,0 +1,24 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the requirements file into the container at /app (corrected path)
+COPY requirements.txt .
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the Flask application file into the container at /app (corrected path)
+COPY app.py .
+
+# Copy the trained model file into the container at /app (corrected path)
+COPY best_rf_model.joblib .
+
+# Expose the port that the app will run on
+EXPOSE 8000
+
+# Run Gunicorn to serve the Flask application
+# The 'app:app' refers to the 'app' object in the 'app.py' file
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]

app.py

@@ -0,0 +1,76 @@
+import flask
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
+import numpy as np
+import sys # Import sys for stdout redirection
+
+print('Starting Superkart Sales Predictor Flask app...', file=sys.stdout)
+
+# Instantiate Flask app
+app = Flask("Superkart Sales Predictor")
+print('Flask app instantiated.', file=sys.stdout)
+
+# Load the pre-trained model
+print('Attempting to load model...', file=sys.stdout)
+loaded_model = joblib.load('best_rf_model.joblib')
+print('Model loaded successfully!', file=sys.stdout)
+
+# For demonstration, let's manually define the expected features based on the notebook's X_train structure
+# In a real app, you'd load this from a saved file to ensure consistency
+expected_features_list = ['Product_Weight', 'Product_Sugar_Content', 'Product_Allocated_Area',
+                        'Product_Type', 'Product_MRP', 'Store_Size',
+                        'Store_Location_City_Type', 'Store_Type', 'yr_since_store_estab']
+
+# Define the prediction endpoint
+@app.route('/predict', methods=['POST'])
+def predict():
+    print('Prediction request received.', file=sys.stdout)
+    try:
+        # Get data from POST request
+        print('Attempting to get JSON data from request...', file=sys.stdout)
+        data = request.get_json(force=True)
+        print(f'Received data: {data}', file=sys.stdout)
+
+        # Convert incoming data to DataFrame matching training features structure
+        if isinstance(data, dict):
+            input_df = pd.DataFrame([data])
+        elif isinstance(data, list):
+            input_df = pd.DataFrame(data)
+        else:
+            print('Invalid input data format.', file=sys.stdout)
+            return jsonify({'error': 'Invalid input data format, expected dict or list of dicts'}), 400
+
+        # Reindex the DataFrame to ensure all expected columns are present, filling missing with NaN
+        # The order of columns is crucial for the preprocessor.
+        print('Reindexing input DataFrame and converting dtypes...', file=sys.stdout)
+        input_df = input_df.reindex(columns=expected_features_list, fill_value=np.nan)
+
+        # Ensure categorical columns have 'category' dtype as expected by the preprocessor
+        # Identify categorical columns from the original X_train
+        categorical_cols_expected = ['Product_Sugar_Content', 'Product_Type', 'Store_Size',
+                                     'Store_Location_City_Type', 'Store_Type']
+
+        for col in categorical_cols_expected:
+            if col in input_df.columns:
+                input_df[col] = input_df[col].astype('category')
+            else:
+                # Handle cases where a categorical column might be missing from input_df
+                pass
+        print('Input DataFrame prepared for prediction.', file=sys.stdout)
+
+        # Make prediction using the loaded model pipeline
+        print('Making prediction...', file=sys.stdout)
+        predictions = loaded_model.predict(input_df)
+        print('Prediction successful.', file=sys.stdout)
+
+        # Convert predictions to a list or array for JSON response
+        return jsonify(predictions.tolist())
+
+    except Exception as e:
+        print(f'Error during prediction: {str(e)}', file=sys.stderr) # Log errors to stderr
+        return jsonify({'error': str(e)}), 500
+
+# This part is for local testing and should be commented out or protected for deployment
+# if __name__ == '__main__':
+#     app.run(debug=True, host='0.0.0.0', port=5000)

best_rf_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2326677ef77a20fc5201db9d125fbc24f8c8261079a828a2244ba17b4cc8d953
+size 20544778

requirements.txt

@@ -0,0 +1,10 @@
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.28.1
+uvicorn[standard]