Upload 3 files

Dockerfile

@@ -0,0 +1,16 @@
+# Use official Python 3.12.4 image
+FROM python:3.12.4-slim
+
+# FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["gunicorn","-b", "0.0.0.0:7860", "main:app"]

app.py

@@ -0,0 +1,133 @@
+from flask import Flask, request, jsonify
+import pandas as pd
+import numpy as np
+from data import StrokeData,HeartData
+from sklearn.preprocessing import LabelEncoder
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+
+import joblib
+import pickle  
+
+
+class HeartData:
+    def __init__(self, age, sex, chest_pain_type, resting_bp, restecg, max_hr, exang, oldpeak, slope, thal):
+        self.features = [age, sex, chest_pain_type, resting_bp, restecg, max_hr, exang, oldpeak, slope, thal]
+
+class StrokeData:
+    def __init__(self, age, hypertension, heart_disease, ever_married, work_type, avg_glucose_level, bmi, smoking_status):
+        self.features = [age, hypertension, heart_disease, ever_married, work_type, avg_glucose_level, bmi, smoking_status]
+
+class HealthPredictor:
+    def __init__(self):
+        self.heart_model_path = 'Heart_Disease/Saved_Model_Status/HeartModelRandomForest'
+        self.heart_scaler_path = 'Heart_Disease/Saved_Model_Status/Standard_scaler.pkl'
+        self.stroke_model_path = 'Stroke_Code/Saved_Model_Status/StrokeModelRandomForest'
+        self.stroke_scaler_path = 'Stroke_Code/Saved_Model_Status/Standard_scaler.pkl'
+        self.encoders_paths = {
+            'ever_married': 'Stroke_Code/Saved_Model_Status/ever_married_encoder.pkl',
+            'work_type': 'Stroke_Code/Saved_Model_Status/work_type_encoder.pkl',
+            'smoking_status': 'Stroke_Code/Saved_Model_Status/smoking_status_encoder.pkl'
+        }
+
+        self.heart_model = self.load_model(self.heart_model_path)
+        self.heart_scaler = self.load_scaler(self.heart_scaler_path)
+        self.stroke_model = self.load_model(self.stroke_model_path)
+        self.stroke_scaler = self.load_scaler(self.stroke_scaler_path)
+
+        self.ever_married_encoder = self.load_encoder(self.encoders_paths['ever_married'])
+        self.work_type_encoder = self.load_encoder(self.encoders_paths['work_type'])
+        self.smoking_status_encoder = self.load_encoder(self.encoders_paths['smoking_status'])
+
+    def load_model(self, path):
+        with open(path, 'rb') as file:
+            return pickle.load(file)
+
+    def load_scaler(self, path):
+        return joblib.load(path)
+
+    def load_encoder(self, path):
+        return joblib.load(path)
+
+    def predict_heart(self, data_point):
+        data_point_scaled = self.heart_scaler.transform(np.array([data_point]))
+        return self.heart_model.predict(data_point_scaled)[0]
+
+    def predict_stroke(self, data_point):
+        data_point[3] = self.ever_married_encoder.transform([data_point[3]])[0]
+        data_point[4] = self.work_type_encoder.transform([data_point[4]])[0]
+        data_point[7] = self.smoking_status_encoder.transform([data_point[7]])[0]
+
+        data_point_scaled = self.stroke_scaler.transform(np.array([data_point]))
+        
+        # Get prediction probability
+        probabilities = self.stroke_model.predict_proba(data_point_scaled)[0]
+
+        # You can return both prediction and probabilities if needed
+        prediction = np.argmax(probabilities)
+        return prediction, probabilities
+        
+        # return self.stroke_model.predict(data_point_scaled)[0]
+
+
+class PersonData:
+    def __init__(self, age, sex, chest_pain_type, resting_bp, restecg, max_hr, exang, oldpeak, slope, thal,
+                hypertension, ever_married, work_type, avg_glucose_level, bmi, smoking_status):
+        self.features = [age, sex, chest_pain_type, resting_bp, restecg, max_hr, exang, oldpeak, slope, thal,
+                hypertension, ever_married, work_type, avg_glucose_level, bmi, smoking_status]
+        self.predictor = HealthPredictor()
+        self.heart_prediction = self.predict_heart()
+        self.stroke_prediction, self.stroke_proba = self.predict_stroke()
+
+    def predict_heart(self):
+        heart_data = HeartData(*self.features[:10])
+        return self.predictor.predict_heart(heart_data.features)
+
+    def predict_stroke(self):
+        self.heart_prediction
+        stroke_data = StrokeData(self.features[0], self.features[10], self.heart_prediction, self.features[11], self.features[12],
+                                 self.features[13], self.features[14], self.features[15])
+        return self.predictor.predict_stroke(stroke_data.features)
+    
+app = Flask(__name__)
+
+@app.route('/', methods=['GET'])
+def home():
+    return "✅ Sahha Health Prediction API is Running", 200
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        data = request.get_json()
+
+        person_data = PersonData(
+            age=data['age'],
+            sex=data['sex'],
+            chest_pain_type=data['chest_pain_type'],
+            resting_bp=data['resting_bp'],
+            restecg=data['restecg'],
+            max_hr=data['max_hr'],
+            exang=data['exang'],
+            oldpeak=data['oldpeak'],
+            slope=data['slope'],
+            thal=data['thal'],
+            hypertension=data['hypertension'],
+            ever_married=data['ever_married'],
+            work_type=data['work_type'],
+            avg_glucose_level=data['avg_glucose_level'],
+            bmi=data['bmi'],
+            smoking_status=data['smoking_status']
+        )
+
+        return jsonify({
+            'heart_prediction': int(person_data.heart_prediction),
+            'stroke_prediction': int(person_data.stroke_prediction),
+            'stroke_probability': round(float(person_data.stroke_proba[person_data.stroke_prediction]), 4)           
+        })
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == "__main__":
+    app.run(host='0.0.0.0', port=8087, debug=True)
+

requirements.txt

@@ -0,0 +1,48 @@
+blinker==1.9.0
+certifi==2025.4.26
+charset-normalizer==3.4.2
+click==8.1.8
+colorama==0.4.6
+contourpy==1.3.2
+cycler==0.12.1
+filelock==3.18.0
+Flask==3.1.0
+fonttools==4.57.0
+fsspec==2025.5.1
+idna==3.10
+imbalanced-learn==0.13.0
+itsdangerous==2.2.0
+Jinja2==3.1.6
+joblib==1.4.2
+kiwisolver==1.4.8
+MarkupSafe==3.0.2
+matplotlib==3.10.1
+mpmath==1.3.0
+narwhals==1.36.0
+networkx==3.5
+numpy==2.2.5
+opencv-python==4.11.0.86
+packaging==25.0
+pandas==2.2.3
+pillow==11.2.1
+plotly==6.0.1
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+pytz==2025.2
+requests==2.32.3
+scikit-learn==1.6.1
+scipy==1.15.2
+seaborn==0.13.2
+setuptools==80.9.0
+six==1.17.0
+sklearn-compat==0.1.3
+sympy==1.14.0
+threadpoolctl==3.6.0
+torch==2.7.0
+torchvision==0.22.0
+typing_extensions==4.13.2
+tzdata==2025.2
+urllib3==2.4.0
+Werkzeug==3.1.3
+xgboost==3.0.0
+gunicorn