Upload frontend app files

Dockerfile

@@ -4,17 +4,13 @@ FROM python:3.9-slim
 # Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy the requirements.txt file into the working directory
-COPY requirements.txt .
-
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the rest of the application files into the working directory
+# Copy all files from the current directory on the host to the container's /app directory
 COPY . .
 
-# Expose port 5000
-EXPOSE 5000
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -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"]
 
-# Define the command to run the Flask application
-CMD ["flask", "run", "--host=0.0.0.0"]
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -1,54 +1,51 @@
-from flask import Flask, request, jsonify
-import joblib
+import streamlit as st
+import requests
+import json
 import pandas as pd
 
-app = Flask(__name__)
-
-# Load the serialized full pipeline
-try:
-    full_pipeline = joblib.load('deployment_files/SuperKart_model_v1_0.joblib')
-    # Get the list of columns from the training data used by the pipeline
-    # Adjusting to correctly get column names after one-hot encoding and scaling
-    # This part might need refinement based on the exact structure of your pipeline's preprocessor
-    # A safer approach is to save the column names of X_train during preprocessing
-    # For now, let's assume the order is numerical followed by one-hot encoded categorical
-    # We need to get the feature names from the OneHotEncoder and combine with numerical names
-    categorical_feature_names = full_pipeline.named_steps['preprocessor'].transformers_[0][1].get_feature_names_out(
-        full_pipeline.named_steps['preprocessor'].transformers_[0][2]
-    )
-    numerical_feature_names = full_pipeline.named_steps['scaler'].feature_names_in_
-
-    # Combine numerical and categorical feature names in the correct order
-    pipeline_columns = list(numerical_feature_names) + list(categorical_feature_names)
-
-except Exception as e:
-    full_pipeline = None
-    print(f"Error loading pipeline: {e}")
-
-@app.route('/predict', methods=['POST'])
-def predict():
-    if full_pipeline is None:
-        return jsonify({'error': 'Model not loaded'}), 500
-
+# Define the backend API endpoint URL
+# Replace with the actual URL of your deployed backend API
+BACKEND_API_URL = "YOUR_BACKEND_API_URL"
+
+st.title("SuperKart Sales Forecast")
+
+st.write("Enter the product and store details to get a sales forecast.")
+
+# Create input fields for features
+product_weight = st.number_input("Product Weight", min_value=0.0)
+product_sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar", "reg"])
+product_allocated_area = st.number_input("Product Allocated Area", min_value=0.0)
+product_type = st.selectbox("Product Type", ["Frozen Foods", "Dairy", "Canned", "Baking Goods", "Health and Hygiene", "Meat", "Snack Foods", "Hard Drinks", "Breakfast", "Household", "Breads", "Starchy Foods", "Fruits and Vegetables", "Seafood", "Others", "Soft Drinks"])
+product_mrp = st.number_input("Product MRP", min_value=0.0)
+store_size = st.selectbox("Store Size", ["Medium", "High", "Small"])
+store_location_city_type = st.selectbox("Store Location City Type", ["Tier 2", "Tier 1", "Tier 3"])
+store_type = st.selectbox("Store Type", ["Supermarket Type2", "Departmental Store", "Supermarket Type1", "Food Mart"])
+store_establishment_year = st.number_input("Store Establishment Year", min_value=1985, max_value=2025, step=1)
+
+# Create a button to trigger the prediction
+if st.button("Get Sales Forecast"):
+    # Prepare the input data as a 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_Size": store_size,
+        "Store_Location_City_Type": store_location_city_type,
+        "Store_Type": store_type,
+        "Store_Establishment_Year": store_establishment_year # Include original year for 'Store_Age' calculation in backend
+    }
+
+    # Send the input data to the backend API for prediction
     try:
-        data = request.get_json(force=True)
-
-        # Convert input data to DataFrame, ensuring column order matches training data
-        input_df = pd.DataFrame([data])
-
-        # Reorder columns to match the order expected by the pipeline
-        # This assumes all expected columns are present in the input data
-        input_df = input_df[pipeline_columns]
-
-
-        # Make prediction
-        prediction = full_pipeline.predict(input_df)
-
-        # Return prediction as JSON
-        return jsonify({'prediction': prediction.tolist()})
+        response = requests.post(f"{BACKEND_API_URL}/predict", json=input_data)
+        response.raise_for_status() # Raise an exception for bad status codes
 
-    except Exception as e:
-        return jsonify({'error': str(e)}), 400
+        prediction = response.json()["prediction"][0]
+        st.success(f"The estimated sales total is: ${prediction:.2f}")
 
-if __name__ == '__main__':
-    app.run(debug=True, host='0.0.0.0', port=5000)
+    except requests.exceptions.RequestException as e:
+        st.error(f"Error communicating with the backend API: {e}")
+    except KeyError:
+        st.error("Invalid response from the backend API.")

requirements.txt

@@ -1,5 +1,3 @@
-Flask==3.0.3
-joblib==1.4.2
+streamlit==1.36.0
+requests==2.32.3
 pandas==2.2.2
-scikit-learn==1.6.1
-numpy==2.0.2