Upload folder using huggingface_hub

Dockerfile

@@ -1,21 +1,16 @@
-FROM python:3.9-slim
-
-WORKDIR /app
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
-
-RUN pip3 install -r requirements.txt
-
-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"]
+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 --upgrade -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:superkart_api"]

app.py

@@ -0,0 +1,57 @@
+import numpy as np
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize the Flask app
+superkart_api = Flask("SuperKart Sales Prediction API")
+
+# Load the trained model (assumed to include preprocessing pipeline)
+model = joblib.load("deployment_files/best_random_forest_model.joblib")
+
+@superkart_api.get('/')
+def home():
+    return "Welcome to the SuperKart Sales Prediction API!"
+
+@superkart_api.post('/v1/sales')
+def predict_sales():
+    """
+    Handle POST request with a JSON payload for single prediction.
+    """
+    try:
+        input_data = request.get_json()
+
+        # Wrap in list to convert to DataFrame
+        df = pd.DataFrame([input_data])
+
+        # Predict using the trained pipeline
+        prediction = model.predict(df)[0]
+
+        return jsonify({'Predicted Quarterly Sales (in INR)': round(float(prediction), 2)})
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
+
+@superkart_api.post('/v1/salesbatch')
+def predict_sales_batch():
+    """
+    Handle POST request with a CSV file for batch predictions.
+    """
+    try:
+        file = request.files['file']
+        input_df = pd.read_csv(file)
+
+        # Predict using the trained pipeline
+        predictions = model.predict(input_df)
+        predictions = [round(float(val), 2) for val in predictions]
+
+        # Add to original DataFrame
+        input_df['Predicted_Quarterly_Sales'] = predictions
+
+        return input_df.to_dict(orient='records')
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
+
+if __name__ == '__main__':
+    superkart_api.run(debug=True)

best_random_forest_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a46f3144128240a6cd8795f05a9034ed47f3d10dd977b06b5b0d454f127719e
+size 45505863

requirements.txt

@@ -1,3 +1,11 @@
-altair
-pandas
-streamlit
+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