Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Expose API port
+EXPOSE 7860
+
+# Start Flask API with Gunicorn (4 workers, bind to 7860)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860","app:sales_prediction_api"]

app.py

@@ -0,0 +1,97 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# -------------------------------
+# Initialize Flask App
+# -------------------------------
+sales_prediction_api = Flask('Superkart Sales Prediction')
+
+# -------------------------------
+# Load the trained Gradient Boosting model
+# -------------------------------
+model = joblib.load("gradient_tuned.joblib")
+
+# -------------------------------
+# Root endpoint (Health check)
+# -------------------------------
+@sales_prediction_api.get("/")
+def home():
+    """Simple health check endpoint"""
+    return 'Welcome to the SuperKart Sales Prediction API'
+
+# -------------------------------
+# Single Prediction Endpoint
+# -------------------------------
+@sales_prediction_api.post("/v1/salesdata")
+def predict_sales():
+    """Predict sales for a single product/store record"""
+    try:
+        # Parse incoming JSON
+        sales_data = request.get_json()
+
+        # Prepare input dictionary with only the features used by the model
+        sample = {
+            'Product_Weight': sales_data['Product_Weight'],
+            'Product_Allocated_Area': sales_data['Product_Allocated_Area'],
+            'Product_MRP': sales_data['Product_MRP'],
+            'Product_Sugar_Content': sales_data['Product_Sugar_Content'],
+            'Product_Type': sales_data['Product_Type'],
+            'Store_Id': sales_data['Store_Id'],
+            'Store_Size': sales_data['Store_Size'],
+            'Store_Location_City_Type': sales_data['Store_Location_City_Type'],
+        }
+
+        # Convert to DataFrame
+        input_df = pd.DataFrame([sample])
+
+        # Predict sales
+        predicted_sales = model.predict(input_df)[0]
+        predicted_sales = round(float(predicted_sales), 2)
+
+        # Return JSON response
+        return jsonify({"predicted_sales": predicted_sales})
+
+    except Exception as e:
+        return jsonify({"error": str(e)})
+
+# -------------------------------
+# Batch Prediction Endpoint
+# -------------------------------
+@sales_prediction_api.post("/v1/salesdatabatch")
+def predict_sales_batch():
+    """Predict sales for multiple product/store records from a CSV file"""
+    try:
+        # Get uploaded CSV file
+        file = request.files['file']
+        input_df = pd.read_csv(file)
+
+        # Keep only the features used by the model
+        features = [
+            'Product_Weight', 'Product_Allocated_Area', 'Product_MRP',
+            'Product_Sugar_Content', 'Product_Type', 'Store_Id',
+            'Store_Size', 'Store_Location_City_Type'
+        ]
+        input_features = input_df[features]
+
+        # Predict sales
+        predicted_sales = model.predict(input_features)
+        predicted_sales = [round(float(sale), 2) for sale in predicted_sales]
+
+        # Attach predictions to Product IDs if available
+        if 'Product_Id' in input_df.columns:
+            product_ids = input_df['Product_Id'].tolist()
+            output_dict = dict(zip(product_ids, predicted_sales))
+        else:
+            output_dict = {"predicted_sales": predicted_sales}
+
+        return jsonify(output_dict)
+
+    except Exception as e:
+        return jsonify({"error": str(e)})
+
+# -------------------------------
+# Run Flask App
+# -------------------------------
+if __name__ == '__main__':
+    sales_prediction_api.run(debug=True)

gradient_tuned.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b4d70fdf4fd9609e15aec0d5d8426f4a6b1d04b8d958f98de8c2227cfd097a
+size 1650258

requirements.txt

@@ -0,0 +1,10 @@
+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==2.32.3
+uvicorn[standard]==0.32.0