Upload folder using huggingface_hub

Dockerfile

@@ -1,14 +1,16 @@
-# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container to /app
+# Set the working directory inside the container
 WORKDIR /app
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# 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 run the Streamlit app on port 8501 and make it accessible externally
-CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
+# 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:house_price_api"]

app.py

@@ -1,100 +1,77 @@
-import streamlit as st
+import joblib
 import pandas as pd
-import requests
-
-# Streamlit UI for SuperKart Sales Revenue Forecasting
-st.title("SuperKart Sales Revenue Forecasting App")
-st.write("This app predicts the total sales revenue for product-store combinations based on product and store features.")
-st.write("Adjust the values below to get a sales prediction.")
-
-# Collect user input using sliders and selectboxes
-col1, col2 = st.columns(2)
-
-with col1:
-    st.subheader("Product Features")
-    Product_Weight = st.slider("Product Weight", 5.0, 25.0, 12.5, 0.1)
-    Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
-    Product_Allocated_Area = st.slider("Product Allocated Area (ratio)", 0.0, 0.5, 0.05, 0.01)
-    Product_Type = st.selectbox("Product Type", [
-        "Meat", "Snack Foods", "Hard Drinks", "Dairy", "Canned", "Soft Drinks",
-        "Health and Hygiene", "Baking Goods", "Bread", "Breakfast", "Frozen Foods",
-        "Fruits and Vegetables", "Household", "Seafood", "Starchy Foods", "Others"
-    ])
-    Product_MRP = st.slider("Product MRP (Maximum Retail Price)", 50.0, 300.0, 150.0, 1.0)
-
-with col2:
-    st.subheader("Store Features")
-    Store_Establishment_Year = st.slider("Store Establishment Year", 1985, 2015, 2000, 1)
-    Store_Size = st.selectbox("Store Size", ["Small", "Medium", "High"])
-    Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
-    Store_Type = st.selectbox("Store Type", [
-        "Departmental Store", "Supermarket Type1", "Supermarket Type2", "Food Mart"
-    ])
-
-# Create input data dictionary
-input_data = {
-    '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_Establishment_Year': Store_Establishment_Year,
-    'Store_Size': Store_Size,
-    'Store_Location_City_Type': Store_Location_City_Type,
-    'Store_Type': Store_Type
-}
-
-if st.button("Predict Sales Revenue", type='primary'):
-    # Replace with your Hugging Face backend space URL
-    api_url = "https://<----user-name---->-<---repo name--->.hf.space/v1/sales"  # Enter user name and space name
-    try:
-        response = requests.post(api_url, json=input_data, timeout=30)
-        if response.status_code == 200:
-            result = response.json()
-            predicted_sales = result["Predicted_Sales_Total"]
-            st.success(f"💰 Predicted Sales Revenue: **${predicted_sales:,.2f}**")
-            st.info(f"This prediction is for a {Product_Type} product in a {Store_Size} {Store_Type} located in {Store_Location_City_Type}.")
-        else:
-            st.error(f"Error in API request: Status Code {response.status_code}")
-            st.error(f"Response: {response.text}")
-    except requests.exceptions.RequestException as e:
-        st.error(f"Error connecting to API: {str(e)}")
-        st.info("Please ensure your backend API is deployed and the URL is correct.")
-
-# Batch Prediction
-st.subheader("Batch Prediction")
-st.write("Upload a CSV file with product and store features to get predictions for multiple combinations.")
-
-file = st.file_uploader("Upload CSV file", type=["csv"])
-if file is not None:
-    # Display preview of uploaded file
-    df_preview = pd.read_csv(file)
-    st.write("Preview of uploaded file:")
-    st.dataframe(df_preview.head())
-
-    if st.button("Predict for Batch", type='primary'):
-        # Replace with your Hugging Face backend space URL
-        api_url = "https://<----user-name---->-<---repo name--->.hf.space/v1/salesbatch"  # Enter user name and space name
-        try:
-            files = {"file": (file.name, file, "text/csv")}
-            response = requests.post(api_url, files=files, timeout=60)
-            if response.status_code == 200:
-                result = response.json()
-                result_df = pd.DataFrame(result)
-                st.header("Batch Prediction Results")
-                st.dataframe(result_df)
-
-                # Download button
-                csv = result_df.to_csv(index=False).encode('utf-8')
-                st.download_button(
-                    label="Download Predictions as CSV",
-                    data=csv,
-                    file_name="predictions.csv",
-                    mime="text/csv"
-                )
-            else:
-                st.error(f"Error in API request: Status Code {response.status_code}")
-                st.error(f"Response: {response.text}")
-        except requests.exceptions.RequestException as e:
-            st.error(f"Error connecting to API: {str(e)}")
-            st.info("Please ensure your backend API is deployed and the URL is correct.")
+from flask import Flask, request, jsonify
+import numpy as np
+
+# Initialize Flask app
+sales_forecast_api = Flask("SuperKart Sales Forecast Predictor")
+
+# Load the trained SuperKart sales model
+model = joblib.load("superkart_sales_model_v1_0.joblib")
+
+# Define a route for the home page
+@sales_forecast_api.get('/')
+def home():
+    return "Welcome to the SuperKart Sales Revenue Forecasting API!"
+
+# Define an endpoint to predict sales for a single product-store combination
+@sales_forecast_api.post('/v1/sales')
+def predict_sales():
+    # Get JSON data from the request
+    sales_data = request.get_json()
+
+    # Extract relevant features from the input data
+    # Note: Store_Age will be calculated from Store_Establishment_Year
+    current_year = 2024
+    store_age = current_year - sales_data['Store_Establishment_Year']
+
+    sample = {
+        'Product_Weight': sales_data['Product_Weight'],
+        'Product_Sugar_Content': sales_data['Product_Sugar_Content'],
+        'Product_Allocated_Area': sales_data['Product_Allocated_Area'],
+        'Product_Type': sales_data['Product_Type'],
+        'Product_MRP': sales_data['Product_MRP'],
+        'Store_Establishment_Year': sales_data['Store_Establishment_Year'],
+        'Store_Size': sales_data['Store_Size'],
+        'Store_Location_City_Type': sales_data['Store_Location_City_Type'],
+        'Store_Type': sales_data['Store_Type'],
+        'Store_Age': store_age
+    }
+
+    # Convert the extracted data into a DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make a prediction using the trained model
+    prediction = model.predict(input_data).tolist()[0]
+
+    # Return the prediction as a JSON response
+    return jsonify({'Predicted_Sales_Total': prediction})
+
+# Define an endpoint to predict sales for a batch of product-store combinations
+@sales_forecast_api.post('/v1/salesbatch')
+def predict_sales_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)
+
+    # Calculate Store_Age if not present
+    if 'Store_Age' not in input_data.columns:
+        current_year = 2024
+        input_data['Store_Age'] = current_year - input_data['Store_Establishment_Year']
+
+    # Make predictions for the batch data
+    predictions = model.predict(input_data).tolist()
+
+    # Add predictions to the DataFrame
+    input_data['Predicted_Sales_Total'] = predictions
+
+    # Convert results to dictionary
+    result = input_data.to_dict(orient="records")
+
+    return jsonify(result)
+
+# Run the Flask app in debug mode
+if __name__ == '__main__':
+    sales_forecast_api.run(debug=True)

requirements.txt

@@ -1,3 +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
-streamlit==1.43.2
+uvicorn[standard]

superkart_sales_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200c1855aa4114e035256f3c29e366623272deda030dc23af2613f70315a8f4b
+size 23837399