Upload folder using huggingface_hub

Dockerfile

@@ -1,17 +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:superkart_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

@@ -1,74 +1,56 @@
-# 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
-from flask_cors import CORS
-
-# Initialize the Flask application
-superkart_api = Flask("SuperKart Revenue Predictor")
-CORS(superkart_api)
-
-#model path needs to be updated to root once this is pushed
-model_path = "deployment_files/SuperKart_Model_V1_0.joblib"
-
-# Load the trained machine learning model
-model = joblib.load("model_path")
-
-# Health check route
-@superkart_api.get('/')
-def home():
-    return "Welcome to SuperKart Sales Prediction"
-
 
-    # Prediction route
-@superkart_api.post('/v1/predict')
-def predict_sales():
-    try:
-        # Parse JSON payload
-        data = request.get_json()
-        print("Raw incoming data:", data)
-
-        # Validate expected fields
-        required_fields = [
-            'Product_Weight',
-            'Product_Sugar_Content',
-            'Product_Allocated_Area',
-            'Product_MRP',
-            'Store_Size',
-            'Store_Location_City_Type',
-            'Store_Type',
-            'Store_Age_Years',
-            'Product_Type_Category'
-        ]
-        missing_fields = [f for f in required_fields if f not in data]
-        if missing_fields:
-            return jsonify({'error': f"Missing fields: {missing_fields}"}), 400
-
-        # Convert and transform input
-        sample = {
-            'Product_Weight': float(data['Product_Weight']),
-            'Product_Sugar_Content': data['Product_Sugar_Content'],
-            'Product_Allocated_Area_Log': np.log1p(float(data['Product_Allocated_Area'])),  # log-transform
-            'Product_MRP': float(data['Product_MRP']),
-            'Store_Size': data['Store_Size'],
-            'Store_Location_City_Type': data['Store_Location_City_Type'],
-            'Store_Type': data['Store_Type'],
-            'Store_Age_Years': int(data['Store_Age_Years']),
-            'Product_Type_Category': data['Product_Type_Category']
-        }
-
-        input_df = pd.DataFrame([sample])
-        print("Transformed input for model:\n", input_df)
-
-        # Make prediction
-        prediction = model.predict(input_df).tolist()[0]
-        return jsonify({'Predicted_Sales': prediction})
-
-    except Exception as e:
-        print("Error during prediction:", str(e))
-        return jsonify({'error': f"Prediction failed: {str(e)}"}), 500
+import streamlit as st
+import pandas as pd
+import joblib
+import numpy as np
 
-# Run the app (for local testing only)
-if __name__ == '__main__':
-    superkart_api.run(debug=True)
+# Load the trained model
+@st.cache_resource
+def load_model():
+    return joblib.load("SuperKart_Model_V1_0.joblib")
+
+model = load_model()
+
+# Streamlit UI for Price Prediction
+st.title("SuperKart Revenue Prediction App")
+st.write("This tool predicts the sales revenue listing based on the given details.")
+
+st.subheader("Enter the listing details:")
+
+# Collect user input
+Product_Type = st.selectbox("Product_Type", ["Fruits and Vegetables ", "Snack Foods", "Frozen Foods","Dairy","Household","Baking Goods","Canned","Health and Hygiene","Meat","Soft Drinks","Breads","Hard Drinks","Others","Starchy Foods ","Breakfast","Seafood"])
+Product_Weight = st.number_input("Product_Weight", min_value=0.0, value=12.66)
+Product_MRP    = st.number_input("Product_MRP",min_value=0.0, value=100.0)
+Product_Allocated_Area  = st.number_input("Product_Allocated_Area", min_value=0.0, value=100.0)
+Product_Sugar_Content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "No Sugar", "Regular", "reg"])
+Store_Type = st.selectbox("Store_Type", ["Supermarket Type2 ", "Supermarket Type1","Departmental Store","Food Mart"])
+Store_Location_City_Type = st.selectbox("Store_Location_City_Type", ["Tier 2", "Tier 1","Tier 3"])
+Store_Id = st.selectbox("Store_Id",["OUT004","OUT003","OUT002","OUT001"])
+Store_Establishment_Year = st.number_input(
+    "Store_Establishment_Year",
+    min_value=1900,
+    max_value=2025,
+    step=1,
+    value=2000,
+    format='%d'
+)
+
+# Convert user input into a DataFrame
+input_data = pd.DataFrame([{
+    'Product_Type': Product_Type,
+    'Product_Weight': Product_Weight,
+    'Product_MRP': Product_MRP,
+    'Product_Allocated_Area': Product_Allocated_Area,
+    'Product_Sugar_Content': Product_Sugar_Content,
+    'Store_Type': Store_Type,
+    'Store_Location_City_Type': Store_Location_City_Type,
+    'Store_Id': Store_Id,
+    'Store_Establishment_Year': Store_Establishment_Year,
+}])
+
+
+# Predict button
+if st.button("Predict"):
+    prediction = model.predict(input_data)
+    #st.write(f"The predicted revnue is ${np.exp(prediction)[0]:.2f}.")
+    st.write(f"The predicted revenue is ${prediction[0]:.2f}.")

backend/Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working 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
+
+# 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:superkart_api"]
+

backend/SuperKart_Model_V1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06234b86b6bdeea8fa7023e0d50f4e8e378d395609985f79b17a456f7311bc27
+size 211281

backend/app.py

@@ -0,0 +1,74 @@
+# 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
+from flask_cors import CORS
+
+# Initialize the Flask application
+superkart_api = Flask("SuperKart Revenue Predictor")
+CORS(superkart_api)
+
+#model path needs to be updated to root once this is pushed
+model_path = "deployment_files/Backend/SuperKart_Model_V1_0.joblib"
+
+# Load the trained machine learning model
+model = joblib.load("model_path")
+
+# Health check route
+@superkart_api.get('/')
+def home():
+    return "Welcome to SuperKart Sales Prediction"
+
+
+    # Prediction route
+@superkart_api.post('/v1/predict')
+def predict_sales():
+    try:
+        # Parse JSON payload
+        data = request.get_json()
+        print("Raw incoming data:", data)
+
+        # Validate expected fields
+        required_fields = [
+            'Product_Weight',
+            'Product_Sugar_Content',
+            'Product_Allocated_Area',
+            'Product_MRP',
+            'Store_Size',
+            'Store_Location_City_Type',
+            'Store_Type',
+            'Store_Age_Years',
+            'Product_Type_Category'
+        ]
+        missing_fields = [f for f in required_fields if f not in data]
+        if missing_fields:
+            return jsonify({'error': f"Missing fields: {missing_fields}"}), 400
+
+        # Convert and transform input
+        sample = {
+            'Product_Weight': float(data['Product_Weight']),
+            'Product_Sugar_Content': data['Product_Sugar_Content'],
+            'Product_Allocated_Area_Log': np.log1p(float(data['Product_Allocated_Area'])),  # log-transform
+            'Product_MRP': float(data['Product_MRP']),
+            'Store_Size': data['Store_Size'],
+            'Store_Location_City_Type': data['Store_Location_City_Type'],
+            'Store_Type': data['Store_Type'],
+            'Store_Age_Years': int(data['Store_Age_Years']),
+            'Product_Type_Category': data['Product_Type_Category']
+        }
+
+        input_df = pd.DataFrame([sample])
+        print("Transformed input for model:\n", input_df)
+
+        # Make prediction
+        prediction = model.predict(input_df).tolist()[0]
+        return jsonify({'Predicted_Sales': prediction})
+
+    except Exception as e:
+        print("Error during prediction:", str(e))
+        return jsonify({'error': f"Prediction failed: {str(e)}"}), 500
+
+# Run the app (for local testing only)
+if __name__ == '__main__':
+    superkart_api.run(debug=True)

backend/requirements.txt

@@ -0,0 +1,20 @@
+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
+
+# Flask web server
+flask==2.2.2
+flask-cors==3.0.10
+gunicorn==20.1.0
+Werkzeug==2.2.2
+
+# For API testing
+requests==2.32.3

requirements.txt

@@ -3,18 +3,5 @@ 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
 
-# Flask web server
-flask==2.2.2
-flask-cors==3.0.10
-gunicorn==20.1.0
-Werkzeug==2.2.2
-
-# For API testing
-requests==2.32.3