Upload folder using huggingface_hub

app.py

@@ -1,61 +1,94 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-# Set the title of the Streamlit app
-st.title("SuperKart Sale Price Prediction")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-Product_Weight = st.number_input("Product_Weight", min_value=4.0, max_value=20.0, step=0.5)
-Product_Sugar_Content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "Regular", "No Sugar"])
-Product_Allocated_Area = st.number_input("Product_Allocated_Area", min_value=0.004, step=0.001, max_value=0.295)
-Product_Type = st.selectbox("Product_Type", ["Dairy", "Fruits and Vegetables", "Meat", "Bakery", "Baking Goods", "Frozen Foods", "Canned", "Breads", "Breakfast","Hard Drinks","Seafood","Snack Foods","Soft Drinks","Starchy Foods"])
-Product_MRP = st.number_input("Product_MRP", min_value=41, step=5, max_value=250)
-Store_Id = st.selectbox("Store_Id", ["OUT001", "OUT002", "OUT003", "OUT004"])
-Store_Establishment_Year = st.selectbox("Store_Establishment_Year", ["1987", "1998", "1999", "2009"])
-Store_Size = st.selectbox("Store_Size", ["Small", "Medium", "High", "OUT004"])
-Store_Location_City_Type = st.selectbox("Store_Location_City_Type", ["Tier 1", "Tier 2", "Tier 3"])
-Store_Type = st.selectbox("Store_Type", ["Departmental Store", "Food Mart", "Supermarket Type1", "Supermarket Type2"])
-
-# Convert user input into a DataFrame
-input_data = pd.DataFrame([{
-    'Product_Weight': Product_Weight,
-    'Product_Sugar_Content': Product_Sugar_Content,
-    'Product_Allocated_Area': Product_Allocated_Area,
-    'Product_Type': Product_Type,
-    'Product_MRP': Product_MRP,
-    'Store_Id': Store_Id,  # Convert to 't' or 'f'
-    'Store_Establishment_Year': Store_Establishment_Year,
-    'Store_Size': Store_Size,
-    'Store_Location_City_Type': Store_Location_City_Type,
-    'Store_Type' : Store_Type
-}])
-
-# Make prediction when the "Predict" button is clicked
-if st.button("Predict"):
-    response = requests.post("https://SarojRauth-salepriceprediction1.hf.space/v1/sale", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
-    if response.status_code == 200:
-        prediction = response.json()['Predicted Price (in dollars)']
-        st.success(f"Predicted Rental Price (in dollars): {prediction}")
-    else:
-        st.error("Error making prediction.")
-
-# Section for batch prediction
-st.subheader("Batch Prediction")
-
-# Allow users to upload a CSV file for batch prediction
-uploaded_file = st.file_uploader("Upload CSV file for batch prediction", type=["csv"])
-
-# Make batch prediction when the "Predict Batch" button is clicked
-if uploaded_file is not None:
-    if st.button("Predict Batch"):
-        response = requests.post("https://SarojRauth-salepriceprediction1.hf.space/v1/salebatch", files={"file": uploaded_file})  # Send file to Flask API
-        if response.status_code == 200:
-            predictions = response.json()
-            st.success("Batch predictions completed!")
-            st.write(predictions)  # Display the predictions
-        else:
-            st.error("Error making batch prediction.")
+# 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_sale_predictor_api = Flask("SuperKart sale Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("SuperKart_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@superKart_sale_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 Sale Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@superKart_sale_predictor_api.post('/v1/sale')
+def predict_sale_price():
+    """
+    This function handles POST requests to the '/v1/sale' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted sale price as a JSON response.
+    """
+    # Get the JSON data from the request body
+    property_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        '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']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_log_price = model.predict(input_data)[0]
+
+    # Calculate actual price
+    predicted_price = np.exp(predicted_log_price)
+
+    # Convert predicted_price to Python float
+    predicted_price = round(float(predicted_price), 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 Price (in dollars)': predicted_price})
+
+
+# Define an endpoint for batch prediction (POST request)
+@superKart_sale_predictor_api.post('/v1/salebatch')
+def predict_sale_price_batch():
+    """
+    This function handles POST requests to the '/v1/salebatch' 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_log_prices = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_prices = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_prices]
+
+    # Create a dictionary of predictions with property IDs as keys
+    product_id = input_data['id'].tolist()  # Assuming 'id' is the property ID column
+    output_dict = dict(zip(product_id, predicted_prices))  # 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__':
+    superKart_sale_predictor_api.run(debug=True)

requirements.txt

@@ -1,5 +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
-streamlit
-numpy
-flask
+uvicorn[standard]
+streamlit==1.43.2