Upload folder using huggingface_hub

app.py

@@ -1,66 +1,95 @@
-import streamlit as st
-import pandas as pd
-import requests
-
-model_root_url = "https://bala-ai-KartSalesPredictionBackend.hf.space/v1/kart"  # Base URL of the deployed Flask API on Hugging Face Spaces
-
-
-# Set the title of the Streamlit app
-st.title("Super Kart Sales Prediction")
-
-# Section for online prediction
-st.subheader("Online Prediction")
-
-# Collect user input for property features
-Product_Sugar_Content = st.selectbox("Room Type", ["Entire home/apt", "Private room", "Shared room"])
-Product_Type = st.number_input("Accommodates (Number of guests)", min_value=1, value=2)
-Store_Establishment_Year = st.number_input("Bathrooms", min_value=1, step=1, value=2)
-Store_Location_City_Type = st.selectbox("Cancellation Policy (kind of cancellation policy)", ["strict", "flexible", "moderate"])
-Store_Id = st.selectbox("Cleaning Fee Charged?", ["True", "False"])
-Product_MRP = st.selectbox("Instantly Bookable?", ["False", "True"])
-Product_Weight = st.number_input("Review Score Rating", min_value=0.1, max_value=100.0, step=1.0, value=90.0)
-Store_Size = st.number_input("Bedrooms", min_value=0, step=1, value=1)
-Product_Allocated_Area = st.number_input("Area", min_value=0.1, step=1, value=1)
-
-# Convert user input into a DataFrame
-input_data = pd.DataFrame([{
-
-  "Product_Sugar_Content": Product_Sugar_Content,
-  "Product_Type": Product_Type,
-  "Store_Establishment_Year": Store_Establishment_Year,
-  "Store_Location_City_Type": Store_Location_City_Type,
-  "Store_Id": Store_Id,
-  "Product_MRP": Product_MRP,
-  "Product_Weight": Product_Weight,
-  "Store_Size": Store_Size,
-  "Store_Type" : Store_Type,
-  "Product_Allocated_Area" : Product_Allocated_Area
-
-
-}])
-
-# Make prediction when the "Predict" button is clicked
-if st.button("Predict"):
-    response = requests.post(model_root_url, 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://<username>-<repo_id>.hf.space/v1/rentalbatch", 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
+super_kart_sales_predictor_api = Flask("Super Kart Sales Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("super_kart_sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@super_kart_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 super kart sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@super_kart_sales_predictor_api.post('/v1/kart')
+def predict_kart_sales():
+    """
+    This function handles POST requests to the '/v1/rental' 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()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Type': property_data['Product_Type'],
+        'Product_Weight': property_data['Product_Weight'],
+        'Product_MRP': property_data['Product_MRP'],
+        'Store_Type': property_data['Store_Type'],
+        'Store_Size': property_data['Store_Size'],
+        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
+        'Product_Sugar_Content': property_data['Product_Sugar_Content'],
+
+        'Store_Id': property_data['Store_Id'],
+
+        'Product_Allocated_Area': property_data['Product_Allocated_Area'],
+        'Store_Establishment_Year': property_data['Store_Establishment_Year']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction 
+    predicted_sales = model.predict(input_data)[0]
+
+
+
+    # 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)
+@super_kart_sales_predictor_api.post('/v1/salesbatch')
+def predict_rental_price_batch():
+    """
+    This function handles POST requests to the '/v1/rentalbatch' 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_sales = model.predict(input_data).tolist()
+
+    # Calculate actual prices
+    predicted_sales = [round(float(np.exp(log_price)), 2) for log_price in predicted_log_sales]
+
+    # Create a dictionary of predictions with property IDs as keys
+    property_ids = input_data['id'].tolist()  # Assuming 'id' is the property ID column
+    output_dict = dict(zip(property_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__':
+    rental_price_predictor_api.run(debug=True)

requirements.txt

@@ -1,2 +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