Upload folder using huggingface_hub

Dockerfile

@@ -1,19 +1,16 @@
-
-# Use the official Python image
-FROM python:3.9
+FROM python:3.9-slim
 
 # Set the working directory inside the container
 WORKDIR /app
 
-# Copy the requirements file and install dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the app files
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Expose Streamlit's default port
-EXPOSE 8501
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-# Run the Streamlit app
-CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# 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:sales_forecaster_api"]

app.py

@@ -1,61 +1,94 @@
-import streamlit as st
-import requests
-import json
-
-st.title("SuperKart Sales Forecaster")
-st.write("Enter the details of the product and store to get a sales forecast.")
-
-# Create input fields for the user
-product_weight = st.number_input("Product Weight", min_value=0.0, format="%f")
-product_sugar_content = st.selectbox("Product Sugar Content", ['Low Sugar', 'Regular', 'No Sugar'])
-product_allocated_area = st.number_input("Product Allocated Area", min_value=0.0, format="%f")
-product_type = st.selectbox("Product Type", ['Dairy', 'Soft Drinks', 'Meat', 'Fruits and Vegetables', 'Household', 'Baking Goods', 'Snack Foods', 'Frozen Foods', 'Breakfast', 'Health and Hygiene', 'Hard Drinks', 'Canned', 'Bread', 'Starchy Foods', 'Others', 'Seafood'])
-product_mrp = st.number_input("Product MRP", min_value=0.0, format="%f")
-store_id = st.selectbox("Store ID", [f"Store_{i}" for i in range(1, 11)])
-store_establishment_year = st.number_input("Store Establishment Year", min_value=1900, max_value=2024, step=1)
-store_size = st.selectbox("Store Size", ['Medium', 'High', 'Low'])
-store_location_city_type = st.selectbox("Store Location City Type", ['Tier 1', 'Tier 3', 'Tier 2'])
-store_type = st.selectbox("Store Type", ['Supermarket Type 1', 'Supermarket Type 2', 'Departmental Store', 'Food Mart'])
-
-# Prepare the data to be sent to the API
-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_Id': store_id,
-    '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"):
-    # Send the data to the Flask API
-    try:
-        response = requests.post("https://pkulkar-SalesForcasterFrontend.hf.space/v1/sales", json=input_data)
-        if response.status_code == 200:
-            prediction = response.json()
-            st.success(f"Predicted Sales: {prediction['Predicted Price (in dollars)']:.2f}")
-        else:
-            st.error(f"Error predicting sales: {response.status_code} - {response.text}")
-    except requests.exceptions.RequestException as e:
-        st.error(f"Error connecting to the API: {e}")
-
-# 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 Sales Batch"):
-        response = requests.post("https://pkulkar-SalesForcasterFrontend.hf.space/v1/salesbatch", 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
+sales_forecaster_api = Flask("SuperKart Sales Forecast")
+
+# Load the trained machine learning model
+model = joblib.load("/content/drive/MyDrive/Python/Project7/deployment_files/sales_prediction_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@sales_forecaster_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 Forecast API!"
+
+# Define an endpoint for single property prediction (POST request)
+@sales_forecaster_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 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_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_sales_price = model.predict(input_data)[0]
+
+    # Calculate actual price
+    predicted_price = np.exp(predicted_sales_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)
+@sales_forecaster_api.post('/v1/salesbatch')
+def predict_sales_price_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_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
+    property_ids = input_data['id'].tolist()  # Assuming 'id' is the property ID column
+    output_dict = dict(zip(property_ids, 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__':
+    sales_forecaster_api.run(debug=True)

requirements.txt

@@ -3,9 +3,3 @@ 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==2.32.3
-uvicorn[standard]
-streamlit==1.43.2