Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,22 @@
-FROM python:3.13.5-slim
+# Use a lightweight Python image as the base image
+FROM python:3.9-slim
 
+# Set the working directory in the container
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Copy the requirements.txt file into the container
+COPY requirements.txt .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Install the dependencies
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
+# Copy the application files (app.py and the saved model) into the container
+COPY app.py .
+COPY best_random_forest_pipeline.joblib .
+# If you have other necessary files, copy them here as well
 
+# Expose the port that Streamlit runs on
 EXPOSE 8501
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Command to run the Streamlit application
+CMD ["streamlit", "run", "app.py"]

app.py

@@ -0,0 +1,98 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+
+# Load the trained model pipeline
+model_pipeline = joblib.load('best_random_forest_pipeline.joblib')
+
+# Define the Streamlit app title and description
+st.title('SuperKart Sales Forecasting App')
+st.write('Enter the product and store details to get a sales forecast.')
+
+# Define input fields for the features
+# You need to create input fields for all the features used by your model
+# Based on your preprocessing, the features are:
+# Numerical: Product_Weight, Product_Allocated_Area, Product_MRP, Store_Establishment_Year
+# Categorical: Product_Sugar_Content, Product_Type, Store_Id, Store_Size, Store_Location_City_Type, Store_Type
+
+st.sidebar.header('Product and Store Details')
+
+# Numerical Inputs
+product_weight = st.sidebar.number_input('Product Weight', min_value=0.0, value=10.0)
+product_allocated_area = st.sidebar.number_input('Product Allocated Area', min_value=0.0, value=0.05)
+product_mrp = st.sidebar.number_input('Product MRP', min_value=0.0, value=100.0)
+store_establishment_year = st.sidebar.number_input('Store Establishment Year', min_value=1900, max_value=2024, value=2000)
+
+# Categorical Inputs (using unique values from your data)
+# Replace the options with the actual unique categories from your dataset
+sugar_content_options = ['Low Sugar', 'Regular', 'No Sugar'] # Update with actual unique values
+product_type_options = ['Frozen Foods', 'Dairy', 'Canned', 'Baking Goods', 'Health and Hygiene', 'Snack Foods', 'Household', 'Meat', 'Soft Drinks', 'Breads', 'Hard Drinks', 'Others', 'Starchy Foods', 'Breakfast', 'Seafood', 'Fruits and Vegetables'] # Update with actual unique values
+store_id_options = ['OUT004', 'OUT003', 'OUT001', 'OUT002'] # Update with actual unique values
+store_size_options = ['Medium', 'High', 'Small'] # Update with actual unique values
+store_location_options = ['Tier 2', 'Tier 1', 'Tier 3'] # Update with actual unique values
+store_type_options = ['Supermarket Type2', 'Departmental Store', 'Supermarket Type1', 'Food Mart'] # Update with actual unique values
+
+product_sugar_content = st.sidebar.selectbox('Product Sugar Content', sugar_content_options)
+product_type = st.sidebar.selectbox('Product Type', product_type_options)
+store_id = st.sidebar.selectbox('Store ID', store_id_options)
+store_size = st.sidebar.selectbox('Store Size', store_size_options)
+store_location_city_type = st.sidebar.selectbox('Store Location City Type', store_location_options)
+store_type = st.sidebar.selectbox('Store Type', store_type_options)
+
+
+# Create a dictionary from the input values
+input_data = {
+    'Product_Weight': product_weight,
+    'Product_Allocated_Area': product_allocated_area,
+    'Product_MRP': product_mrp,
+    'Store_Establishment_Year': store_establishment_year,
+    'Product_Sugar_Content': product_sugar_content,
+    'Product_Type': product_type,
+    'Store_Id': store_id,
+    'Store_Size': store_size,
+    'Store_Location_City_Type': store_location_city_type,
+    'Store_Type': store_type
+}
+
+# Convert the dictionary to a pandas DataFrame
+input_df = pd.DataFrame([input_data])
+
+# Display the input data
+st.subheader('Input Details:')
+st.write(input_df)
+
+
+# Make prediction when the button is clicked
+if st.button('Predict Sales'):
+    # Ensure column order matches the training data features expected by the pipeline
+    # This is crucial because the pipeline expects features in a specific order,
+    # especially after one-hot encoding.
+    # The easiest way to handle this is to ensure the input DataFrame has the same
+    # columns and order as the training data features (X_train) before passing
+    # it to the pipeline's predict method.
+
+    # Recreate a dummy DataFrame with the same columns and order as X_train
+    # and then populate it with the input values. This ensures the one-hot encoding
+    # within the pipeline works correctly.
+
+    # Get the column names from X_train (assuming X_train is available or you have saved its column names)
+    # For this script, we'll assume the columns are in a specific order.
+    # In a real deployment, you would save the column order or a sample of X_train
+    # along with the model pipeline.
+
+    # A safer approach is to pass the raw input_df to the pipeline,
+    # as the preprocessor within the pipeline should handle the column transformations
+    # based on how it was fitted on the training data.
+    # However, the order of columns in the input DataFrame should ideally match the
+    # order of columns in the original DataFrame before splitting/preprocessing.
+    # Let's assume the order of columns in input_df matches the original data columns
+    # that were used to create X_train.
+
+    try:
+        prediction = model_pipeline.predict(input_df)
+        st.subheader('Predicted Product Store Sales Total:')
+        st.write(f'{prediction[0]:,.2f}')
+    except Exception as e:
+        st.error(f"An error occurred during prediction: {e}")
+        st.write("Please ensure the input features are correct and match the expected format.")

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+streamlit==1.36.0
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+joblib==1.4.2
+xgboost==2.1.4
+# Add any other libraries you used in your notebook if not already listed