Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +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:churn_predictor_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

@@ -1,68 +1,70 @@
-import joblib
-import pandas as pd
-from flask import Flask, request, jsonify
-# Initialize Flask app with a name
-sale_predictor_api = Flask("Store sale Predictor")
+import streamlit as st
 
 
-# Define a route for the home page
-@sale_predictor_api.get('/')
-def home():
-    return "Welcome to the Sale Prediction API!"
+st.title("Store Sale Prediction")
 
-# Define an endpoint to predict sale for a single store
-@sale_predictor_api.post('/v1/store')
-def predict_sale():
-    # Get JSON data from the request
-    store_data = request.get_json()
+# Batch Prediction
+st.subheader("Online Prediction")
 
-    # Extract relevant customer features from the input data
-    sample = {
-        'Product_Id': store_data['Product_Id'],
-        'Product_Weight': store_data['Product_Weight'],
-        'Product_Sugar_Content': store_data['Product_Sugar_Content'],
-        'Product_Allocated_Area': store_data['Product_Allocated_Area'],
-        'Product_Type': store_data['Product_Type'],
-        'Product_MRP': store_data['Product_MRP'],
-        'Store_Establishment_Year': store_data['Store_Establishment_Year'],
-        'Store_Size': store_data['Store_Size'],
-        'Store_Location_City_Type': store_data['Store_Location_City_Type'],
-        'Store_Type': store_data['Store_Type']
-    }
+# Input fields for Store data
+Product_Id = st.text_input("Product_Id : ")
+Product_Weight = st.number_input("Product_Weight ", min_value=0, max_value=50, value=10)
+Product_Sugar_Content = st.selectbox("Product_Sugar_Content ", ["Low Sugar", "Regular", and "no sugar"])
+Product_Allocated_Area = st.number_input("Product_Allocated_Area", min_value=18, max_value=100, value=30)
+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_MRP = st.number_input("Product_MRP", min_value=0.0, value=1000.0)
+Store_Id = st.selectbox("Store_Id", ["OUT004","OUT001",    "OUT003",    "OUT002"   ])
+Store_Establishment_Year = st.number_input("Store_Establishment_Year", ["Yes", "No"])
+Store_Size = st.selectbox("Store_Size", ["Medium","High","Small"])
+Store_Location_City_Type = st.Store_Location_City_Type("Store_Location_City_Type", ["Tier 2","Tier 1","Tier 3"])
+Store_Type = st.Store_Type("Store_Type", ["Supermarket Type2","Supermarket Type1","Departmental Store","Food Mart"])
 
-    # Convert the extracted data into a DataFrame
-    input_data = pd.DataFrame([sample])
+Store_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
+}
 
-    # Make a sale prediction using the trained model
-    prediction = model.predict(input_data).tolist()[0]
+if st.button("Predict", type='primary'):
+    response = requests.post("https://<user_name>-<space_name>.hf.space/v1/Store", json=Store_data)    # enter user name and space name before running the cell
+    if response.status_code == 200:
+        result = response.json()
+        churn_prediction = result["Prediction"]  # Extract only the value
+        st.write(f"Based on the information provided, the Store with ID {StoreID} is likely to {churn_prediction}.")
+    else:
+        st.error("Error in API request")
 
-    # Map prediction result to a human-readable label
-    prediction_label = "sale" if prediction == 1 else "not sale"
+# Batch Prediction
+st.subheader("Batch Prediction")
 
-    # Return the prediction as a JSON response
-    return jsonify({'Prediction': prediction_label})
-
-# Define an endpoint to predict sale for a batch of customers
-@sale_predictor_api.post('/v1/storebatch')
-def predict_sale_batch():
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
-
-    # Read the file into a DataFrame
-    input_data = pd.read_csv(file)
-
-    # Make predictions for the batch data and convert raw predictions into a readable format
-    predictions = [
-        'sale' if x == 1
-        else "Not sale"
-        for x in model.predict(input_data.drop("CustomerId",axis=1)).tolist()
-    ]
-
-    cust_id_list = input_data.CustomerId.values.tolist()
-    output_dict = dict(zip(cust_id_list, predictions))
-
-    return output_dict
-
-# Run the Flask app in debug mode
-if __name__ == '__main__':
-    app.run(debug=True)
+file = st.file_uploader("Upload CSV file", type=["csv"])
+if file is not None:
+    if st.button("Predict for Batch", type='primary'):
+        response = requests.post("https://<user_name>-<space_name>.hf.space/v1/Storebatch", files={"file": file})    # enter user name and space name before running the cell
+        if response.status_code == 200:
+            result = response.json()
+            st.header("Batch Prediction Results")
+            st.write(result)
+        else:
+            st.error("Error in API request")

requirements.txt

@@ -1,11 +1,3 @@
 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