Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from deployment_files into the container
+COPY deployment_files/ ./
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Run the Flask app with Gunicorn
+# Here: app.py is in deployment_files, Flask instance = store_sales_api
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:store_sales_api"]

app.py

@@ -0,0 +1,87 @@
+# 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
+
+# Initialize the Flask application
+store_sales_api = Flask("SuperKart Store Sales Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("store_sales_prediction_model_v1_0.joblib")
+
+# Define a route for the home page (GET request)
+@store_sales_api.get('/')
+def home():
+    """
+    Root endpoint to check if the API is running.
+    """
+    return "Welcome to the SuperKart Store Sales Prediction API!"
+
+# Define an endpoint for single store sales prediction (POST request)
+@store_sales_api.post('/v1/sale')
+def predict_store_sales():
+    """
+    Handles POST requests for predicting sales of a single store.
+    Expects JSON input with store details.
+    """
+    # Get JSON input
+    store_data = request.get_json()
+
+    # Extract relevant features (update according to your dataset)
+    sample = {
+        'Store_Type': store_data['Store_Type'],
+        'Location_Type': store_data['Location_Type'],
+        'Region_Code': store_data['Region_Code'],
+        'Holiday': store_data['Holiday'],
+        'Discount': store_data['Discount']
+        # Add any other features you used during training
+    }
+
+    # Convert into DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (direct Store_Sales prediction)
+    predicted_sales = model.predict(input_data)[0]
+
+    # Convert to Python float and round
+    predicted_sales = round(float(predicted_sales), 2)
+
+    # Return JSON response
+    return jsonify({'Predicted Store Sales': predicted_sales})
+
+# Define an endpoint for batch prediction (POST request)
+@store_sales_api.post('/v1/salebatch')
+def predict_store_sales_batch():
+    """
+    Handles batch predictions for multiple stores.
+    Expects a CSV file with store details.
+    """
+    # Get uploaded CSV file
+    file = request.files['file']
+
+    # Read CSV into DataFrame
+    input_data = pd.read_csv(file)
+
+    # Make predictions
+    predicted_sales = model.predict(input_data).tolist()
+
+    # Convert to float and round
+    predicted_sales = [round(float(sale), 2) for sale in predicted_sales]
+
+    # Use Store IDs if available
+    if 'Store_ID' in input_data.columns:
+        store_ids = input_data['Store_ID'].tolist()
+    else:
+        store_ids = list(range(1, len(predicted_sales)+1))  # Fallback index
+
+    # Create dictionary of predictions
+    output_dict = dict(zip(store_ids, predicted_sales))
+
+    # Return JSON
+    return jsonify(output_dict)
+
+# Run Flask app
+if __name__ == '__main__':
+    store_sales_api.run(debug=True)
+

requirements.txt

@@ -0,0 +1,11 @@
+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

superkart_sales_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56473693f512415425d9cc2eed86e49774a1a7cd8a83a664397058963daefdc
+size 63812691