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 --upgrade -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:sales_prediction_api`: Runs the Flask app (assuming `app.py` contains the Flask instance named `sales_prediction_api`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:sales_prediction_api"]

app.py

@@ -0,0 +1,64 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize Flask app with a name
+sales_prediction_api = Flask("Customer Churn Predictor")
+
+# Load the trained prediction model
+model = joblib.load("sales_prediction_model_v1_0.joblib")
+pipeline = joblib.load("sales_prediction_pipeline_v1_0.joblib")
+
+# Define a route for the home page
+@sales_prediction_api.get('/')
+def home():
+    return "Welcome to the SuperKart Sales Prediction API!"
+
+# Define an endpoint to predict for a single product
+@sales_prediction_api.post('/v1/product')
+def predict_sales():
+    # Get JSON data from the request
+    product_data = request.get_json()
+
+    # Extract relevant features from the input data
+    sample = {
+        'Product_Id': product_data['Product_Id'],
+        'Product_Weight': product_data['Product_Weight'],
+        'Product_Sugar_Content': product_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': product_data['Product_Allocated_Area'],
+        'Product_Type': product_data['Product_Type'],
+        'Product_MRP': product_data['Product_MRP'],
+        'Store_Size': product_data['Store_Size'],
+        'Store_Location_City_Type': product_data['Store_Location_City_Type'],
+        'Store_Type': product_data['Store_Type']
+    }
+
+    # Convert the extracted data into a DataFrame
+    input_data = pd.DataFrame([sample])
+    input_data = pipeline.transform(input_data)
+    # Make a prediction using the trained model
+    prediction = model.predict(input_data).tolist()[0]
+
+    # Return the prediction as a JSON response
+    return jsonify({'Prediction': {"Product_Id": Product_Id, "Sales": prediction}})
+
+# Define an endpoint to predict sales for a batch of products
+@sales_prediction_api.post('/v1/productbatch')
+def predict_batch():
+    # Get the uploaded CSV file from the request
+    file = request.files['file']
+
+    # Read the file into a DataFrame
+    input_data = pd.read_csv(file)
+    input_data = pipeline.transform(input_data)
+    # Make predictions for the batch data:
+    predictions = model.predict(input_data).tolist()
+
+    id_list = input_data.Product_Id.values.tolist()
+    output_dict = dict(zip(id_list, predictions))
+
+    return output_dict
+
+# Run the Flask app in debug mode
+if __name__ == '__main__':
+    sales_prediction_api.run(debug=True)

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==3.1.3
+flask==3.1.2
+gunicorn==20.1.0
+requests==2.32.3
+uvicorn[standard]