Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,86 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize Flask app
+app = Flask(__name__)
+
+# Load the trained sales forecasting model pipeline
+model = joblib.load("final_sales_forecasting_model.joblib") #
+
+# Define a route for the home page
+@app.route('/')
+def home():
+    return "Welcome to the SuperKart Sales Forecasting API"
+
+# Define an endpoint to predict sales for a single product-store combination
+@app.route('/predict_single', methods=['POST'])
+def predict_single():
+    # Get JSON data from the request
+    data = request.get_json()
+
+    # Extract relevant features from the input data, ensuring correct order and names
+    # The keys in the dictionary should match the column names in your original training data X
+    try:
+        sample = {
+            'Product_Id': data['Product_Id'],
+            'Product_Weight': data['Product_Weight'],
+            'Product_Sugar_Content': data['Product_Sugar_Content'],
+            'Product_Allocated_Area': data['Product_Allocated_Area'],
+            'Product_Type': data['Product_Type'],
+            'Product_MRP': data['Product_MRP'],
+            'Store_Id': data['Store_Id'],
+            'Store_Establishment_Year': data['Store_Establishment_Year'],
+            'Store_Size': data['Store_Size'],
+            'Store_Location_City_Type': data['Store_Location_City_Type'],
+            'Store_Type': data['Store_Type']
+        }
+
+        # Convert the extracted data into a DataFrame
+        input_data = pd.DataFrame([sample])
+
+        # Make a sales prediction using the trained model pipeline
+        prediction = model.predict(input_data).tolist()[0]
+
+        # Return the prediction as a JSON response
+        return jsonify({'predicted_sales': prediction})
+
+    except KeyError as e:
+        return jsonify({'error': f'Missing data for key: {e}'}), 400
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+
+# Define an endpoint to predict sales for a batch of product-store combinations from a CSV file
+@app.route('/predict_batch', methods=['POST'])
+def predict_batch():
+    # Get the uploaded file from the request
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file part in the request'}), 400
+
+    file = request.files['file']
+
+    # If the user does not select a file, the browser submits an empty file without a filename.
+    if file.filename == '':
+        return jsonify({'error': 'No selected file'}), 400
+
+    if file:
+        try:
+            # Read the file into a DataFrame
+            input_data = pd.read_csv(file)
+
+            # Make sales predictions using the trained model pipeline
+            predictions = model.predict(input_data).tolist()
+
+            # Return the predictions as a JSON response
+            return jsonify({'predicted_sales': predictions})
+
+        except Exception as e:
+            return jsonify({'error': str(e)}), 500
+    else:
+        return jsonify({'error': 'Something went wrong with file upload'}), 500
+
+
+# Run the Flask app in debug mode
+if __name__ == '__main__':
+    app.run(debug=True)

final_sales_forecasting_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3de540996696fa424339c00294222bc600489164d994d93c7e5a3483dccd6e6
+size 65134690

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]