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: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:product_sales_predictor_api"]

app.py

@@ -0,0 +1,98 @@
+# Import necessary libraries
+import numpy as np
+import joblib  # For loading the serialized model
+import pandas as pd  # For data manipulation
+from flask import Flask, request, jsonify  # For creating the Flask API
+from datetime import datetime  # For handling date and time operations
+# Initialize the Flask application
+product_sales_predictor_api = Flask("SuperKart Product Sales Predictor")
+
+
+# Load the trained machine learning model
+model = joblib.load("superkart_model.joblib")
+
+# Define a route for the home page (GET request)
+@product_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 Product Sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@product_sales_predictor_api.post('/v1/sales')
+def predict_product_sales():
+    """
+    This function handles POST requests to the '/v1/sales' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted rental price as a JSON response.
+    """
+    # Get the JSON data from the request body
+    property_data = request.get_json()
+    current_year = datetime.now().year
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Id': property_data['Product_Id'],
+        'Product_Weight': property_data['Product_Weight'],
+        'Product_Sugar_Content': property_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': property_data['Product_Allocated_Area'],
+        'Product_Type': property_data['Product_Type'],
+        'Product_MRP': property_data['Product_MRP'],
+        'Store_Id': property_data['Store_Id'],
+        'Store_Establishment_Year': property_data['Store_Establishment_Year'],
+        'Store_Size': property_data['Store_Size'],
+        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
+        'Store_Type': property_data['Store_Type'],
+        'Store_Age': current_year - property_data['Store_Establishment_Year']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_sales)
+    predicted_sales = model.predict(input_data)[0]
+
+    # Calculate actual price
+    #predicted_sales = np.exp(predicted_log_sales)
+
+    # Convert predicted_price to Python float
+    predicted_sales = round(float(predicted_sales), 2)
+    # The conversion above is needed as we convert the model prediction (log price) to actual price 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 (in dollars)': predicted_sales})
+
+
+# Define an endpoint for batch prediction (POST request)
+@product_sales_predictor_api.post('/v1/salesbatch')
+def predict_product_sales_batch():
+    """
+    This function handles POST requests to the '/v1/salesbatch' endpoint.
+    It expects a CSV file containing property details for multiple properties
+    and returns the predicted rental prices 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 log_prices)
+    predicted_list_sales = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_sales = [round(float(list_sales), 2) for list_sales in predicted_list_sales]
+
+    # Create a dictionary of predictions with property IDs as keys
+    product_ids = input_data['Product_Id'].tolist()  # Assuming 'id' is the property ID column
+    output_dict = dict(zip(product_ids, predicted_sales))  # Use actual prices
+
+    # Return the predictions dictionary as a JSON response
+    return output_dict
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    product_sales_predictor_api.run(debug=True)

batch_superkart_predict.csv

@@ -0,0 +1,20 @@
+Product_Id,Product_Weight,Product_Sugar_Content,Product_Allocated_Area,Product_Type,Product_MRP,Store_Id,Store_Establishment_Year,Store_Size,Store_Location_City_Type,Store_Type,Store_Age
+FD6114,12.66,Low Sugar,0.027,Frozen Foods,117.08,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD7839,16.54,Low Sugar,0.144,Dairy,171.43,OUT003,1999,Medium,Tier 1,Departmental Store,26
+FD5075,14.28,Regular,0.031,Canned,162.08,OUT001,1987,High,Tier 2,Supermarket Type1,38
+FD8233,12.1,Low Sugar,0.112,Baking Goods,186.31,OUT001,1987,High,Tier 2,Supermarket Type1,38
+NC1180,9.57,No Sugar,0.01,Health and Hygiene,123.67,OUT002,1998,Small,Tier 3,Food Mart,27
+FD5680,12.03,Low Sugar,0.053,Snack Foods,113.64,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD5484,16.35,Low Sugar,0.112,Meat,185.71,OUT003,1999,Medium,Tier 1,Departmental Store,26
+NC5885,12.94,No Sugar,0.286,Household,194.75,OUT003,1999,Medium,Tier 1,Departmental Store,26
+FD1961,9.45,Low Sugar,0.047,Snack Foods,95.95,OUT002,1998,Small,Tier 3,Food Mart,27
+NC6657,8.94,No Sugar,0.045,Health and Hygiene,143.01,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+DR2699,10.64,Low Sugar,0.02,Hard Drinks,165.99,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD6027,13.92,Low Sugar,0.099,Fruits and Vegetables,116.89,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD8553,10.97,Low Sugar,0.156,Fruits and Vegetables,175.71,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD5276,12.25,Low Sugar,0.04,Canned,160.42,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD1231,11.31,Regular,0.049,Baking Goods,168.4,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD1387,13.26,Low Sugar,0.024,Breads,156.17,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+NC1071,10.74,No Sugar,0.173,Household,138.19,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD2625,12.45,Low Sugar,0.045,Frozen Foods,143.25,OUT004,2009,Medium,Tier 2,Supermarket Type2,16
+FD4982,13.17,Low Sugar,0.075,Fruits and Vegetables,185.03,OUT003,1999,Medium,Tier 1,Departmental Store,26

requirements.txt

@@ -0,0 +1,11 @@
+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]
+streamlit==1.43.2

superkart_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dfd819393497b85d7b01c6f39d9d61960fc48719e7bcbf9c3fa13b5b0ca791
+size 260929