Upload app_flask.py with huggingface_hub

app_flask.py

@@ -0,0 +1,77 @@
+import flask
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
+import numpy as np
+
+# Initialize the Flask application
+app = Flask(__name__)
+
+# Load the trained model pipeline
+# Ensure the path to your joblib file is correct
+try:
+    model_pipeline = joblib.load('best_random_forest_pipeline.joblib')
+except FileNotFoundError:
+    print("Error: Model file not found. Make sure 'best_random_forest_pipeline.joblib' is in the same directory.")
+    exit() # Exit if the model file is not found
+
+@app.route('/')
+def home():
+    return "Flask app is running. Use the /predict endpoint to get predictions."
+
+# Define an endpoint for a single prediction
+@app.route('/predict', methods=['POST'])
+def predict():
+    if request.method == 'POST':
+        try:
+            # Get the data from the POST request
+            # This endpoint expects a single JSON object representing one data point
+            data = request.get_json()
+
+            # Convert the incoming JSON data to a pandas DataFrame
+            # Ensure the column names and order match the training data
+            # It's crucial that the keys in the incoming JSON match the original feature names
+            # expected by your preprocessor and model.
+
+            # Example: Assuming the incoming JSON has keys matching the original column names
+            # before one-hot encoding and dropping the target/log_sales.
+            # You might need to add validation here to ensure all required keys are present.
+
+            input_df = pd.DataFrame([data])
+
+            # Ensure categorical columns in input_df are of 'category' dtype
+            # This is important because the preprocessor expects this dtype for categorical columns
+            categorical_cols = ['Product_Sugar_Content', 'Product_Type', 'Store_Id', 'Store_Size', 'Store_Location_City_Type', 'Store_Type'] # List your actual categorical columns
+            for col in categorical_cols:
+                 if col in input_df.columns:
+                     input_df[col] = input_df[col].astype('category')
+                     # If your original data had specific categories, you might need to set them here
+                     # input_df[col] = input_df[col].cat.set_categories(your_original_data[col].cat.categories)
+
+
+            # Make a prediction using the loaded model pipeline
+            # The pipeline handles preprocessing internally
+            prediction = model_pipeline.predict(input_df)
+
+            # Return the prediction as a JSON response
+            # Since this is a single prediction, return the first (and only) element
+            return jsonify({'prediction': prediction[0]})
+
+        except Exception as e:
+            return jsonify({'error': str(e)})
+
+if __name__ == '__main__':
+    # To run this locally for testing:
+    # 1. Save this code as app_flask.py
+    # 2. Make sure your 'best_random_forest_pipeline.joblib' is in the same directory
+    # 3. Run 'python app_flask.py' in your terminal
+
+    # For Colab, you might need a tool like ngrok to expose the local server to the internet
+    # Or you can adapt this to run directly within Colab if needed, but a separate file is standard for deployment.
+    # Running directly in Colab:
+    # from flask_ngrok2 import run_with_ngrok
+    # run_with_ngrok(app)
+    # app.run()
+
+    # Standard way to run Flask app
+    app.run(debug=True)