Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,17 @@
-# 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 fe_requirements.txt
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir -r be_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"]
-CMD ["streamlit", "run", "fe_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
+# 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:app"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "be_app:super_kart_predictor_api"]

app.py

@@ -1,110 +1,132 @@
-# import streamlit as st
+# import numpy as np
+# import joblib
 # import pandas as pd
-# import requests
-
-# # Streamlit UI for Customer Churn Prediction
-# st.title("SuperKart Sales Prediction App")
-# st.subheader("Online Sales Prediction")
-
-# # Collect user input based on dataset columns
-# Product_Id = st.number_input("Product ID", min_value=1, max_value=1000000, value=1)
-# Product_Weight = st.number_input("Product Weight (kg)", min_value=0.1, max_value=100.0, value=1.0, format="%.2f")
-# Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low", "Medium", "High"])  # Adjust options as per your dataset
-# Product_Allocated_Area = st.number_input("Product Allocated Area (sq. units)", min_value=0.0, max_value=10000.0, value=100.0, format="%.2f")
-# Product_Type = st.selectbox("Product Type", ["Type A", "Type B", "Type C"])  # Replace with actual product types
-# Product_MRP = st.number_input("Product MRP", min_value=0.0, max_value=10000.0, value=100.0, format="%.2f")
-
-# Store_Id = st.number_input("Store ID", min_value=1, max_value=1000000, value=1)
-# Store_Establishment_Year = st.number_input("Store Establishment Year", min_value=1900, max_value=2025, value=2000)
-
-# Store_Size = st.selectbox("Store Size", ["Small", "Medium", "Large"])  # Adjust options according to your data
-# Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
-# Store_Type = st.selectbox("Store Type", ["Type 1", "Type 2", "Type 3"])  # Replace with actual store types
-
-# # Product_Store_Sales_Total = st.number_input("Total Product Store Sales", min_value=0.0, value=0.0, format="%.2f")
-
-# # Convert user input to dataframe
-# input_data = {
-#     'Product_Id': Product_Id,
-#     '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
-# }
-
-# # Change as per requirement
-# if st.button("Predict"):
-#     # response = requests.post("https://siaese/superkart-api/v1/sales", json=input_data.to_dict(orient='records')[0])    # enter user name and space name before running the cell
-#     response = requests.post("https://siaese/superkart-api/v1/sales", json=input_data)    # enter user name and space name before running the cell
-#     if response.status_code == 200:
-#         prediction = response.json()['Predicted Sales for SuperKart']
-#         st.success(f'Predicted Sales: {prediction}')
-#     else:
-#         st.error("Error making sales prediction")
-
-# # Sales Prediction
-# st.subheader("Sales Prediction")
-import streamlit as st
+# from flask import Flask, request, jsonify
+
+# # Initialize the Flask app with a custom name
+# super_kart_predictor_api = Flask("Super Kart Sales Predictor")
+
+# # Load the trained model from the specified path
+# # Make sure model_path variable is defined or replace with the actual path string
+# model = joblib.load(model_path)
+
+# # Define a route for the home page (GET request)
+# @super_kart_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 Predictor API!"
+
+# # Define a route for predictions (POST request)
+# @super_kart_predictor_api.post("/v1/sales")
+# def predict_sales():
+#   """
+#   This function handles POST requests to the /v1/sales endpoint.
+#   It expects a JSON payload containing commodity sales details and returns
+#   the predicted sales as a JSON response
+#   """
+#   # Get JSON data from the POST request
+#   superkart_data = request.get_json
+#   print(superkart_data)
+
+#   # Extract relevant features from the JSON payload into a dictionary
+#   sample = {
+#       'Product_Weight': superkart_data['Product_Weight'],
+#       'Product_Allocated_Area': superkart_data['Product_Allocated_Area'],
+#       'Product_MRP': superkart_data['Product_MRP'],
+#       'Store_Tenure': superkart_data['Store_Tenure'],
+#       'Product_Category': superkart_data['Product_Category'],
+#       'Product_Sugar_Content': superkart_data['Product_Sugar_Content'],
+#       'Product_Type': superkart_data['Product_Type'],
+#       'Store_Id': superkart_data['Store_Id'],
+#       'Store_Size': superkart_data['Store_Size'],
+#       'Store_Location_City_Type': superkart_data['Store_Location_City_Type'],
+#       'Store_Type': superkart_data['Store_Type'],
+#       'Perishability': superkart_data['Perishability']
+#   }
+
+#   # Create a DataFrame from the input dictionary for model compatibility
+#   input_data = pd.DataFrame([sample])
+
+#   # Predict sales price using the loaded model
+#   predicted_sales_price = model.predict(input_data)[0]
+
+#   # Convert predicted sales price back from log scale using exponential
+#   predicted_sales = np.exp(predicted_sales_price)
+
+#   # Convert the prediction to a float type with rounding to 2 decimal places
+#   predicted_sales = float(predicted_sales, 2)
+
+#   # Return the prediction as a JSON response
+#   return jsonify({"predicted_sales_price": predicted_sales})
+import numpy as np
+import joblib
 import pandas as pd
-import requests
-
-# Streamlit UI for Customer Churn Prediction
-st.title("SuperKart Sales Prediction App")
-st.subheader("Online Sales Prediction")
-
-# Collect user input based on dataset columns
-Product_Id = st.number_input("Product ID", min_value=1, max_value=1000000, value=1)
-Product_Weight = st.number_input("Product Weight (kg)", min_value=0.1, max_value=100.0, value=1.0, format="%.2f")
-Product_Sugar_Content = st.selectbox("Product Sugar Content", ["Low", "Medium", "High"])  # Adjust options as per your dataset
-Product_Allocated_Area = st.number_input("Product Allocated Area (sq. units)", min_value=0.0, max_value=10000.0, value=100.0, format="%.2f")
-Product_Type = st.selectbox("Product Type", ["Type A", "Type B", "Type C"])  # Replace with actual product types
-Product_MRP = st.number_input("Product MRP", min_value=0.0, max_value=10000.0, value=100.0, format="%.2f")
-Product_Category = st.selectbox("Product_Category", ["FD" "NC" "DR"])
-
-Store_Id = st.number_input("Store ID", min_value=1, max_value=1000000, value=1)
-Store_Establishment_Year = st.number_input("Store Establishment Year", min_value=1900, max_value=2025, value=2000)
-Store_Tenure = st.number_input("Store_Tenure", min_value=16, max_value=50, value=32)
-Store_Size = st.selectbox("Store Size", ["Small", "Medium", "Large"])  # Adjust options according to your data
-Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
-Store_Type = st.selectbox("Store Type", ["Type 1", "Type 2", "Type 3"])  # Replace with actual store types
-
-Perishability = st.selectbox("Perishability", ["Perishable", "Non-Perishable", "Unknown"])  # Replace with actual store types
-
-# Product_Store_Sales_Total = st.number_input("Total Product Store Sales", min_value=0.0, value=0.0, format="%.2f")
-
-# Convert user input to dataframe
-input_data = {
-    "Product_Id": Product_Id,
-    "Product_Weight": Product_Weight,
-    "Product_Sugar_Content": Product_Sugar_Content,
-    "Product_Allocated_Area": Product_Allocated_Area,
-    "Product_Type": Product_Type,
-    "Product_MRP": Product_MRP,
-    "Product_Category": Product_Category,       
-    "Store_Id": Store_Id,
-    "Store_Tenure": Store_Tenure,    
-    "Store_Establishment_Year": Store_Establishment_Year,
-    "Store_Size": Store_Size,
-    "Store_Location_City_Type": Store_Location_City_Type,
-    "Store_Type": Store_Type,
-    "Perishability": Perishability
-}
-
-# Change as per requirement
-if st.button("Predict"):
-    # response = requests.post("https://siaese/superkart-api/v1/sales", json=input_data.to_dict(orient="records")[0])    # enter user name and space name before running the cell
-    response = requests.post("https://siaese/superkart-api/v1/sales", json=input_data)    # enter user name and space name before running the cell
-    if response.status_code == 200:
-        prediction = response.json()["predicted_sales_price"]
-        st.success(f"Predicted Sales: {prediction}")
-    else:
-        st.error("Error making sales prediction")
-
-# Sales Prediction
-st.subheader("Sales Prediction")
+from flask import Flask, request, jsonify
+
+# Initialize the Flask app with a custom name
+super_kart_predictor_api = Flask("Super Kart Sales Predictor")
+
+# Load the trained model from the specified path
+# Make sure model_path variable is defined or replace with the actual path string
+model_path = "super_kart_prediction_gbr_tuned_model_v1_0.joblib"
+model = joblib.load(model_path)
+
+# Define a route for the home page (GET request)
+@super_kart_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 Predictor API!"
+
+# Define a route for predictions (POST request)
+@super_kart_predictor_api.post("/v1/sales")
+def predict_sales():
+  """
+  This function handles POST requests to the /v1/sales endpoint.
+  It expects a JSON payload containing commodity sales details and returns
+  the predicted sales as a JSON response
+  """
+  # Get JSON data from the POST request
+  superkart_data = request.get_json()
+  print(f"\nIncoming request data: \n{superkart_data}\n")
+
+  # Extract relevant features from the JSON payload into a dictionary
+  sample = {
+      'Product_Weight': superkart_data['Product_Weight'],
+      'Product_Allocated_Area': superkart_data['Product_Allocated_Area'],
+      'Product_MRP': superkart_data['Product_MRP'],
+      'Product_Sugar_Content': superkart_data['Product_Sugar_Content'],
+      'Product_Type': superkart_data['Product_Type'],
+      'Product_Category': superkart_data['Product_Category'],      
+      'Store_Id': superkart_data['Store_Id'],
+      'Store_Establishment_Year': superkart_data['Store_Establishment_Year'],      
+      'Store_Size': superkart_data['Store_Size'],
+      'Store_Location_City_Type': superkart_data['Store_Location_City_Type'],
+      'Store_Type': superkart_data['Store_Type'],
+      'Store_Tenure': superkart_data['Store_Tenure'],
+      'Perishability': superkart_data['Perishability'],
+  }
+
+  # Create a DataFrame from the input dictionary for model compatibility
+  input_data = pd.DataFrame([sample])
+
+  # Predict sales price using the loaded model
+  predicted_sales_price = model.predict(input_data)[0]
+
+  # Convert the prediction to a float type with rounding to 3 decimal places
+  predicted_sales = round(predicted_sales_price, 3)
+
+  print(f"\nPredicted Sales Price: {predicted_sales}\n")
+
+  # Return the prediction as a JSON response
+  return jsonify({"predicted_sales_price": predicted_sales})
+
+
+
+# if __name__ == '__main__':
+#   super_kart_predictor_api.run()

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]