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 --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:revenue_predictor_api"]

Predictive_Maintenance_XGB_Tuned_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437d5fd38664410edd7b466678b492057351a252e789b174a1f17256b0595e71
+size 759980

app.py

@@ -0,0 +1,86 @@
+# 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
+import os # For accessing environment variables if needed
+
+# Initialize the Flask application
+predictive_maintenance_api = Flask("Predictive Maintenance API")
+
+# Define the model path
+# Use the correct path as defined in the notebook
+MODEL_PATH = "backend_files/Predictive_Maintenance_XGB_Tuned_model_v1_0.joblib"
+
+# Load the trained machine learning model
+try:
+    model = joblib.load(MODEL_PATH)
+    print(f"Model loaded successfully from {MODEL_PATH}")
+except Exception as e:
+    print(f"Error loading model: {e}")
+    model = None # Set model to None if loading fails
+
+# Define a route for the home page (GET request)
+@predictive_maintenance_api.get('/')
+def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message.
+    """
+    return "Welcome to the Predictive Maintenance API for Engine Health!"
+
+# Define an endpoint for engine condition prediction (POST request)
+@predictive_maintenance_api.post('/v1/engine_condition_prediction')
+def predict_engine_condition():
+    """
+    This function handles POST requests to the '/v1/engine_condition_prediction' endpoint.
+    It expects a JSON payload containing engine sensor data and returns
+    the predicted engine condition (0 for Normal, 1 for Faulty) as a JSON response.
+    """
+    if model is None:
+        return jsonify({"error": "Model not loaded. Please check server logs."}), 500
+
+    # Get the JSON data from the request body
+    engine_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    # Features: 'Engine_RPM', 'Lub_Oil_Pressure', 'Fuel_Pressure', 'Coolant_Pressure', 'Lub_Oil_Temperature', 'Coolant_Temperature'
+    try:
+        sample_data = {
+            'Engine_RPM': [engine_data['Engine_RPM']],
+            'Lub_Oil_Pressure': [engine_data['Lub_Oil_Pressure']],
+            'Fuel_Pressure': [engine_data['Fuel_Pressure']],
+            'Coolant_Pressure': [engine_data['Coolant_Pressure']],
+            'Lub_Oil_Temperature': [engine_data['Lub_Oil_Temperature']],
+            'Coolant_Temperature': [engine_data['Coolant_Temperature']]
+        }
+    except KeyError as e:
+        return jsonify({"error": f"Missing data for feature: {e}. Please provide all required sensor readings."}), 400
+
+    # Convert the extracted data into a Pandas DataFrame
+    # Ensure the order of columns matches the training data
+    input_df = pd.DataFrame(sample_data)
+
+    # Make prediction
+    # model.predict_proba will give probabilities for both classes [prob_class_0, prob_class_1]
+    # model.predict will give the predicted class (0 or 1)
+    prediction_proba = model.predict_proba(input_df)
+    predicted_class = model.predict(input_df)[0]
+
+    # Map the predicted class to a readable string
+    condition_map = {0: "Normal", 1: "Faulty"}
+    predicted_condition_str = condition_map.get(predicted_class, "Unknown")
+
+    # Return the prediction as a JSON response
+    return jsonify({
+        "predicted_engine_condition_class": int(predicted_class), # Ensure it's a standard Python int
+        "predicted_engine_condition_label": predicted_condition_str,
+        "probability_normal": round(float(prediction_proba[0][0]), 4),
+        "probability_faulty": round(float(prediction_proba[0][1]), 4)
+    })
+
+# To run the Flask app (for local testing)
+if __name__ == '__main__':
+    # You might want to get the port from an environment variable for deployment
+    port = int(os.environ.get('PORT', 5000))
+    predictive_maintenance_api.run(host='0.0.0.0', port=port, 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