Upload folder using huggingface_hub

Dockerfile

@@ -12,5 +12,3 @@ 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", "--server.enableXsrfProtection=false"]
-
-# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

SuperKart_prediction_model_v1_0.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e916470523930ab73e4d8af7ae5333301dd57cb94fe45e7923716a263abc6116
-size 197068
+oid sha256:3af9691e3fe153ab300bdca3d9c252d7f6093bf233d4fab7302ff16a9b9d999d
+size 325355

app.py

@@ -1,11 +1,18 @@
-import requests
+
 import streamlit as st
 import pandas as pd
+from datetime import datetime
+import joblib
+
+# Load the trained model
+def load_model():
+    return joblib.load("SuperKart_sales_prediction_model_v1_0.joblib")
 
-st.title("SuperKart Sales Prediction")
+model = load_model()
 
-# Single Item Prediction
-st.subheader("Single Item Prediction")
+# Streamlit UI for Customer Churn Prediction
+st.title("Sales Prediction App")
+st.write("This tool predicts customer Sales details. Enter the required information below.")
 
 # Input fields for product and store data based on SuperKart dataset features
 product_weight = st.number_input("Product Weight", min_value=0.0, value=12.66)
@@ -19,43 +26,45 @@ store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
 store_location_city_type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
 store_type = st.selectbox("Store Type", ["Departmental Store", "Supermarket Type1", "Supermarket Type2", "Food Mart"])
 
-item_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_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,
+# Convert categorical inputs to match model training
+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_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],
 }
 
-# Replace with your Hugging Face Space URL for the backend
-backend_url = "https://Amittripipathi-SuperKart.hf.space"
-
-if st.button("Predict Sales", type='primary'):
-    response = requests.post(f"{backend_url}/v1/predict_sale", json=item_data)
-    if response.status_code == 200:
-        result = response.json()
-        predicted_sales = result["Predicted_Sales"]
-        st.write(f"The predicted sales for this item is: {predicted_sales:.2f}")
-    else:
-        st.error(f"Error in API request: {response.status_code} - {response.text}")
-
-# Batch Prediction
-st.subheader("Batch Prediction")
-
-file = st.file_uploader("Upload CSV file for Batch Prediction", type=["csv"])
-if file is not None:
-    if st.button("Predict for Batch", type='primary'):
-        response = requests.post(f"{backend_url}/v1/predict_sale_batch", files={"file": file})
-        if response.status_code == 200:
-            result = response.json()
-            st.header("Batch Prediction Results")
-            # Display batch predictions
-            predictions_df = pd.DataFrame(result['Batch_Predictions'], columns=['Predicted_Sales'])
-            st.dataframe(predictions_df)
-        else:
-            st.error(f"Error in API request: {response.status_code} - {response.text}")
+# Custom transformer to calculate store age
+class StoreAgeCalculator(BaseEstimator, TransformerMixin):
+    def __init__(self):
+        self.current_year = datetime.now().year
+
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        X = X.copy()
+        X['Store_Age'] = self.current_year - X['Store_Establishment_Year']
+        return X.drop(columns=['Store_Establishment_Year'])
+
+# Convert the input data to a DataFrame
+input_df = pd.DataFrame(input_data)
+
+# Convert categorical columns to category type
+input_df['Product_Sugar_Content'] = input_df['Product_Sugar_Content'].astype('category')
+input_df['Product_Type'] = input_df['Product_Type'].astype('category')
+input_df['Store_Id'] = input_df['Store_Id'].astype('category')
+input_df['Store_Size'] = input_df['Store_Size'].astype('category')
+input_df['Store_Location_City_Type'] = input_df['Store_Location_City_Type'].astype('category')
+input_df['Store_Type'] = input_df['Store_Type'].astype('category')
+
+# Make predictions
+if st.button("Predict"):
+    predictions = model.predict(input_df)
+    st.write(f"Prediction: The customer is likely to **{predictions[0]}**.")

requirements.txt

@@ -1,3 +1,13 @@
 pandas==2.2.2
-requests==2.28.1
+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==2.32.3
+uvicorn[standard]
 streamlit==1.43.2
+huggingface_hub==0.30.1
+seaborn==0.13.2