Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,16 @@
+# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy all files from the current directory to the container's working directory
+# Copy all files from the current directory on the host to the container's /app 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
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -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:forecast_predictor_api"]
+# 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"]
+
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -1,70 +1,85 @@
-# 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
+import streamlit as st
+import pandas as pd
+import requests
 
-# Initialize the Flask application
-forecast_predictor_api = Flask("Forecast Predictor")
+# Set the title of the Streamlit app
+st.title("Sales Prediction")
 
-# Load the trained machine learning model
-model = joblib.load("SuperKartbest_xgb.joblib")
+# Section for online prediction
+st.subheader("Online Prediction")
 
-@forecast_predictor_api.get('/')
-def home():
-    return "Welcome to the Sales Prediction API!"
+# Collect user input for product and store features
+Product_Weight = st.number_input("Product Weight", min_value=0.0, value=15.0)
+Product_Allocated_Area = st.number_input("Product Allocated Area", min_value=0.0, value=200.0)
+Product_MRP = st.number_input("Product MRP", min_value=0.0, value=100.0)
+Store_Establishment_Year = st.number_input("Store Establishment Year", min_value=1900, max_value=2024, value=2000)
+Product_Sugar_Content_No_Sugar = st.selectbox("Product Sugar Content No Sugar", [0, 1])
+Product_Sugar_Content_Regular = st.selectbox("Product Sugar Content Regular", [0, 1])
+Product_Sugar_Content_reg = st.selectbox("Product Sugar Content reg", [0, 1])
+Product_Type_Breads = st.selectbox("Product Type Breads", [0, 1])
+Product_Type_Breakfast = st.selectbox("Product Type Breakfast", [0, 1])
+Product_Type_Canned = st.selectbox("Product Type Canned", [0, 1])
+Product_Type_Dairy = st.selectbox("Product Type Dairy", [0, 1])
+Product_Type_Frozen_Foods = st.selectbox("Product Type Frozen Foods", [0, 1])
+Product_Type_Fruits_and_Vegetables = st.selectbox("Product Type Fruits and Vegetables", [0, 1])
+Product_Type_Hard_Drinks = st.selectbox("Product Type Hard Drinks", [0, 1])
+Product_Type_Health_and_Hygiene = st.selectbox("Product Type Health and Hygiene", [0, 1])
+Product_Type_Household = st.selectbox("Product Type Household", [0, 1])
+Product_Type_Meat = st.selectbox("Product Type Meat", [0, 1])
+Product_Type_Others = st.selectbox("Product Type Others", [0, 1])
+Product_Type_Seafood = st.selectbox("Product Type Seafood", [0, 1])
+Product_Type_Snack_Foods = st.selectbox("Product Type Snack Foods", [0, 1])
+Product_Type_Soft_Drinks = st.selectbox("Product Type Soft Drinks", [0, 1])
+Product_Type_Starchy_Foods = st.selectbox("Product Type Starchy Foods", [0, 1])
+Store_Size_Medium = st.selectbox("Store Size Medium", [0, 1])
+Store_Size_Small = st.selectbox("Store Size Small", [0, 1])
+Store_Location_City_Type_Tier_2 = st.selectbox("Store Location City Type Tier 2", [0, 1])
+Store_Location_City_Type_Tier_3 = st.selectbox("Store Location City Type Tier 3", [0, 1])
+Store_Type_Food_Mart = st.selectbox("Store Type Food Mart", [0, 1])
+Store_Type_Supermarket_Type1 = st.selectbox("Store Type Supermarket Type1", [0, 1])
+Store_Type_Supermarket_Type2 = st.selectbox("Store Type Supermarket Type2", [0, 1])
 
-@forecast_predictor_api.post('/v1/predict')
-def predict_single():
-    # Get the JSON data from the request body
-    product_data = request.get_json()
-    
-    # Extract relevant features from the JSON data
-    sample = {
-        'Product_Weight': product_data['Product_Weight'],
-        'Product_Allocated_Area': product_data['Product_Allocated_Area'],
-        'Product_MRP': product_data['Product_MRP'],
-        'Store_Establishment_Year': product_data['Store_Establishment_Year'],
-        'Product_Sugar_Content_No Sugar': product_data['Product_Sugar_Content_No Sugar'],
-        'Product_Sugar_Content_Regular': product_data['Product_Sugar_Content_Regular'],
-        'Product_Sugar_Content_reg': product_data['Product_Sugar_Content_reg'],
-        'Product_Type_Breads': product_data['Product_Type_Breads'],
-        'Product_Type_Breakfast': product_data['Product_Type_Breakfast'],
-        'Product_Type_Canned': product_data['Product_Type_Canned'],
-        'Product_Type_Dairy': product_data['Product_Type_Dairy'],
-        'Product_Type_Frozen Foods': product_data['Product_Type_Frozen Foods'],
-        'Product_Type_Fruits and Vegetables': product_data['Product_Type_Fruits and Vegetables'],
-        'Product_Type_Hard Drinks': product_data['Product_Type_Hard Drinks'],
-        'Product_Type_Health and Hygiene': product_data['Product_Type_Health and Hygiene'],
-        'Product_Type_Household': product_data['Product_Type_Household'],
-        'Product_Type_Meat': product_data['Product_Type_Meat'],
-        'Product_Type_Others': product_data['Product_Type_Others'],
-        'Product_Type_Seafood': product_data['Product_Type_Seafood'],
-        'Product_Type_Snack Foods': product_data['Product_Type_Snack Foods'],
-        'Product_Type_Soft Drinks': product_data['Product_Type_Soft Drinks'],
-        'Product_Type_Starchy Foods': product_data['Product_Type_Starchy Foods'],
-        'Store_Size_Medium': product_data['Store_Size_Medium'],
-        'Store_Size_Small': product_data['Store_Size_Small'],
-        'Store_Location_City_Type_Tier 2': product_data['Store_Location_City_Type_Tier 2'],
-        'Store_Location_City_Type_Tier 3': product_data['Store_Location_City_Type_Tier 3'],
-        'Store_Type_Food Mart': product_data['Store_Type_Food Mart'],
-        'Store_Type_Supermarket Type1': product_data['Store_Type_Supermarket Type1'],
-        'Store_Type_Supermarket Type2': product_data['Store_Type_Supermarket Type2']
-    }
-    # Convert the extracted data into a Pandas DataFrame
-    input_data = pd.DataFrame([sample])
+# Convert user input into a DataFrame
+input_data = pd.DataFrame([{
+    'Product_Weight': Product_Weight,
+    'Product_Allocated_Area': Product_Allocated_Area,
+    'Product_MRP': Product_MRP,
+    'Store_Establishment_Year': Store_Establishment_Year,
+    'Product_Sugar_Content_No Sugar': Product_Sugar_Content_No_Sugar,
+    'Product_Sugar_Content_Regular': Product_Sugar_Content_Regular,
+    'Product_Sugar_Content_reg': Product_Sugar_Content_reg,
+    'Product_Type_Breads': Product_Type_Breads,
+    'Product_Type_Breakfast': Product_Type_Breakfast,
+    'Product_Type_Canned': Product_Type_Canned,
+    'Product_Type_Dairy': Product_Type_Dairy,
+    'Product_Type_Frozen Foods': Product_Type_Frozen_Foods,
+    'Product_Type_Fruits and Vegetables': Product_Type_Fruits_and_Vegetables,
+    'Product_Type_Hard Drinks': Product_Type_Hard_Drinks,
+    'Product_Type_Health and Hygiene': Product_Type_Health_and_Hygiene,
+    'Product_Type_Household': Product_Type_Household,
+    'Product_Type_Meat': Product_Type_Meat,
+    'Product_Type_Others': Product_Type_Others,
+    'Product_Type_Seafood': Product_Type_Seafood,
+    'Product_Type_Snack Foods': Product_Type_Snack_Foods,
+    'Product_Type_Soft Drinks': Product_Type_Soft_Drinks,
+    'Product_Type_Starchy Foods': Product_Type_Starchy_Foods,
+    'Store_Size_Medium': Store_Size_Medium,
+    'Store_Size_Small': Store_Size_Small,
+    'Store_Location_City_Type_Tier 2': Store_Location_City_Type_Tier_2,
+    'Store_Location_City_Type_Tier 3': Store_Location_City_Type_Tier_3,
+    'Store_Type_Food Mart': Store_Type_Food_Mart,
+    'Store_Type_Supermarket Type1': Store_Type_Supermarket_Type1,
+    'Store_Type_Supermarket Type2': Store_Type_Supermarket_Type2
+}])
 
-    # Make prediction (get log_price)
-    predicted_price = model.predict(input_data)[0]
 
-    # 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
+https://huggingface.co/spaces/nlauchande/ForecastBackend/v1/predict
 
-    # Return the actual price
-    return jsonify({'Predicted Price (in dollars)': predicted_price})
-
-# Run the Flask application in debug mode if this script is executed directly
-if __name__ == '__main__':
-    forecast_predictor_api.run(debug=True)
+# Make prediction when the "Predict" button is clicked
+if st.button("Predict"):
+    response = requests.post("https://nlauchande-nlauchande/ForecastBackend.hf.space/v1/predict", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
+    if response.status_code == 200:
+        prediction = response.json()['Predicted Sales']
+        st.success(f"Predicted Sales: {prediction}")
+    else:
+        st.error("Error making prediction.")

requirements.txt

@@ -1,11 +1,3 @@
 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