Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-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:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "2", "-b", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,101 @@
+
+import os, 
+import numpy as np,
+import pandas as pd,
+import joblib
+
+from flask import Flask, request, jsonify  # For creating the Flask API
+
+# Initialize the Flask application
+sales_predictor_api = Flask("Superkart Sales Predictor")
+app = sales_predictor_api
+
+# Load the trained machine learning model
+model = joblib.load("sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@sales_predictor_api.get('/')
+def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message.
+    """
+    return "Welcome to the Superkart Total Sales Prediction API!"
+
+# Define an endpoint for single product prediction (POST request)
+@sales_predictor_api.post('/v1/storesales')
+def predict_store_sales():
+    """
+    This function handles POST requests to the '/v1/storesales' endpoint.
+    It expects a JSON payload containing product details and returns
+    the predicted total sales as a JSON response.
+    """
+    # Get the JSON data from the request body
+    product_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Sugar_Content': product_data['Product_Sugar_Content'],
+        'Product_Weights': product_data['Product_Weights'],
+        'Product_Allocated_Area': product_data['Product_Allocated_Area'],
+        'Product_MRP': product_data['Product_MRP'],
+        'Product_Type': product_data['Product_Type'],
+        'Store_Establishment_Year': product_data['Store_Establishment_Year'],
+        '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 Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction 
+    pred = model.predict(input_data)[0]
+
+    # Calculate actual sales
+    #predictions_actual_product_store_sales_total = np.exp(pred)
+
+    # Convert predicted_actual_sales to Python float
+    predicted_sales = round(float(np.exp(pred)), 2)
+    # The conversion above is needed as we convert the model prediction (total sales) to actual sales using np.exp, which returns predictions as NumPy float32 values.
+    # When we send this value directly within a JSON response, Flask's jsonify function encounters a datatype error
+
+    # Return the actual price
+    return jsonify({'Predicted sales': predicted_sales})
+
+
+# Define an endpoint for batch prediction (POST request)
+@sales_predictor_api.post('/v1/storesalesbatch')
+def predict_store_sales_batch():
+    """
+    This function handles POST requests to the '/v1/storesalesbatch' endpoint.
+    It expects a CSV file containing product details for multiple properties
+    and returns the predicted product sales as a dictionary in the JSON response.
+    """
+    # Get the uploaded CSV file from the request
+    file = request.files['file']
+
+    # Read the CSV file into a Pandas DataFrame
+    input_data = pd.read_csv(file)
+
+    # Make predictions for all properties in the DataFrame (get store totalsales)
+    predictions_product_store_sales_total = model.predict(input_data).tolist()
+
+    # Calculate actual sales
+    predictions_actual_product_store_sales_total = [round(float(np.exp(log_price)), 2) for log_price in predictions_product_store_sales_total]
+
+    # Create a dictionary of predictions with product IDs as keys
+    if "Product_ID" in input_data.columns:
+      product_ids = input_data["Product_ID"].tolist()
+    else:
+      product_ids = list(range(len(input_data)))
+    
+    output_dict = dict(zip(product_ids, predictions_actual_product_store_sales_total))  
+
+    # Return the predictions dictionary as a JSON response
+    return jsonify(output_dict)
+
+# Run the Flask application in debug mode 
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 7860))
+    sales_predictor_api.run(host="0.0.0.0", port=port, debug=False)

requirements.txt

@@ -0,0 +1,8 @@
+flask==2.2.2
+Werkzeug==2.2.2
+gunicorn==20.1.0
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2