Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +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:churn_predictor_api"]
+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:superkart_revenue_predictor_api"]

app.py

@@ -1,70 +1,98 @@
-import joblib
-import pandas as pd
-from flask import Flask, request, jsonify
-
-# Initialize Flask app with a name
-churn_predictor_api = Flask("Customer Churn Predictor")
-
-# Load the trained churn prediction model
-model = joblib.load("churn_prediction_model_v1_0.joblib")
-
-# Define a route for the home page
-@churn_predictor_api.get('/')
-def home():
-    return "Welcome to the Customer Churn Prediction API!"
-
-# Define an endpoint to predict churn for a single customer
-@churn_predictor_api.post('/v1/customer')
-def predict_churn():
-    # Get JSON data from the request
-    customer_data = request.get_json()
-
-    # Extract relevant customer features from the input data
-    sample = {
-        'CreditScore': customer_data['CreditScore'],
-        'Geography': customer_data['Geography'],
-        'Age': customer_data['Age'],
-        'Tenure': customer_data['Tenure'],
-        'Balance': customer_data['Balance'],
-        'NumOfProducts': customer_data['NumOfProducts'],
-        'HasCrCard': customer_data['HasCrCard'],
-        'IsActiveMember': customer_data['IsActiveMember'],
-        'EstimatedSalary': customer_data['EstimatedSalary']
-    }
-
-    # Convert the extracted data into a DataFrame
-    input_data = pd.DataFrame([sample])
-
-    # Make a churn prediction using the trained model
-    prediction = model.predict(input_data).tolist()[0]
-
-    # Map prediction result to a human-readable label
-    prediction_label = "churn" if prediction == 1 else "not churn"
-
-    # Return the prediction as a JSON response
-    return jsonify({'Prediction': prediction_label})
-
-# Define an endpoint to predict churn for a batch of customers
-@churn_predictor_api.post('/v1/customerbatch')
-def predict_churn_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)
-
-    # Make predictions for the batch data and convert raw predictions into a readable format
-    predictions = [
-        'Churn' if x == 1
-        else "Not Churn"
-        for x in model.predict(input_data.drop("CustomerId",axis=1)).tolist()
-    ]
-
-    cust_id_list = input_data.CustomerId.values.tolist()
-    output_dict = dict(zip(cust_id_list, predictions))
-
-    return output_dict
-
-# Run the Flask app in debug mode
-if __name__ == '__main__':
-    app.run(debug=True)
+# 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
+
+# Initialize the Flask application
+superkart_revenue_predictor_api = Flask("Predict Product Store Sales based on product and store attributes")
+
+# Load the trained machine learning model
+model = joblib.load("superkart_revenue_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superkart_revenue_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 Sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@superkart_revenue_predictor_api.post('/v1/sales')
+def predict_sales_price():
+    """
+    This function handles POST requests to the '/v1/sales' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted sales price as a JSON response.
+    """
+    # Get the JSON data from the request body
+    product_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    json_extract = {
+        '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_Id': product_data['Store_Id'],
+        'Store_Size': product_data['Store_Size'],
+        'Store_Location_City_Type': product_data['Store_Location_City_Type'],
+        'Store_Type': product_data['Store_Type'],
+        'Product_Category': product_data['Product_Category'],
+        'Perishable': product_data['Perishable'],
+        'Store_Age': product_data['Store_Age']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([json_extract])
+
+    # Change MRP to Log as this is done before pipeline (feature engineering)
+    input_data['MRP_log'] = np.log(input_data['Product_MRP'])
+    input_data['Price_Per_Display'] = input_data['Product_MRP'] * input_data['Product_Allocated_Area']
+
+    # Make prediction 
+    predicted_price = model.predict(input_data)[0]
+
+    # Return the actual price
+    return jsonify({'Predicted Sales': predicted_price})
+
+
+# Define an endpoint for batch prediction (POST request)
+@superkart_revenue_predictor_api.post('/v1/salesbatch')
+def predict_salesprice_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 sales 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)
+
+    # Change MRP to Log as this is done before pipeline (feature engineering)
+    input_data['MRP_log'] = np.log(input_data['Product_MRP'])
+    input_data['Price_Per_Display'] = input_data['Product_MRP'] * input_data['Product_Allocated_Area']
+    
+    # Save ID
+    product_ids = input_data['Product_Id']
+
+    # Drop ID
+    input_data = input_data.drop('Product_Id', axis=1)
+
+    # Make predictions for all properties in the DataFrame (get log_prices)
+    predicted_prices = model.predict(input_data).tolist()
+
+    # Create a dictionary of predictions with property IDs as keys
+    output_dict = dict(zip(product_ids, predicted_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__':
+    superkart_revenue_predictor_api.run(debug=True)

requirements.txt

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

superkart_revenue_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf760b47429c697e85c868c40ad96c064497d03c5d0916b8bf5fac2d9a726ef
+size 899187