Upload 7 files

Dockerfile

@@ -2,27 +2,17 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    && rm -rf /var/lib/apt/lists/*
-
 # Create a non-root user
 RUN useradd -m -u 1000 user
 USER user
 ENV HOME=/home/user \
     PATH=/home/user/.local/bin:$PATH
 
-# Copy and install requirements first for better caching
-COPY requirements.txt .
-RUN pip install --no-cache-dir --user numpy==1.24.3 && \
-    pip install --no-cache-dir --user -r requirements.txt
-
-# Copy the rest of the application
-COPY . .
+# Install required packages directly
+RUN pip install --no-cache-dir --user fastapi==0.95.2 uvicorn==0.23.2 numpy==1.24.3 joblib==1.3.2
 
-# Health check
-HEALTHCHECK CMD curl --fail http://localhost:7860/ || exit 1
+# Copy application files
+COPY --chown=user:user . .
 
 # Run the application
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 

app.py

@@ -1,66 +1,11 @@
 from fastapi import FastAPI, Request, HTTPException
-import joblib
 import numpy as np
+import joblib
 
 app = FastAPI()
 
-# Load the model
-print("Loading model...")
-try:
-    stroke_model = joblib.load("model.joblib")
-    print("Model loaded successfully")
-    
-    # Extract necessary components
-    model = stroke_model.get('model')
-    encoded_cols = stroke_model.get('encoded_cols', [])
-    numeric_cols = stroke_model.get('numeric_cols', [])
-    preprocessor = stroke_model.get('preprocessor')
-    
-    print(f"Model components: {numeric_cols}, {encoded_cols}")
-except Exception as e:
-    print(f"Error loading model: {e}")
-    model = None
-    preprocessor = None
-    encoded_cols = []
-    numeric_cols = []
-
-# Helper function to format input data
-def preprocess_input(data):
-    # For numeric features
-    numeric_values = []
-    for col in numeric_cols:
-        if col == 'age':
-            numeric_values.append(data.get('age', 0))
-        elif col == 'avg_glucose_level':
-            numeric_values.append(data.get('avg_glucose_level', 0))
-        elif col == 'bmi':
-            numeric_values.append(data.get('bmi', 0))
-    
-    # For categorical features
-    input_dict = {
-        'gender': data.get('gender', 'Male'),
-        'hypertension': data.get('hypertension', 0),
-        'heart_disease': data.get('heart_disease', 0),
-        'ever_married': data.get('ever_married', 'No'),
-        'work_type': data.get('work_type', 'Private'),
-        'Residence_type': data.get('Residence_type', 'Urban'),
-        'smoking_status': data.get('smoking_status', 'never smoked')
-    }
-    
-    # Create a structured numpy array for preprocessing
-    input_array = np.array([list(input_dict.values())], dtype=object)
-    
-    # Apply preprocessing if available
-    if preprocessor:
-        encoded_features = preprocessor.transform(input_array)
-        # Combine numeric and encoded features
-        features = np.hstack([numeric_values, encoded_features])
-        return features
-    
-    # Fallback mode
-    return np.array([list(input_dict.values()) + numeric_values], dtype=object)
-
-def get_risk_category(probability):
+# Simple risk level function
+def get_risk_level(probability):
     if probability < 0.2:
         return "Very Low Risk"
     elif probability < 0.4:
@@ -72,57 +17,48 @@ def get_risk_category(probability):
     else:
         return "Very High Risk"
 
-# Fallback prediction when model fails
-def fallback_prediction(data):
+# Fallback prediction
+def predict_risk(data):
     # Count risk factors
-    risk_factors = []
+    risk_factors = 0
     
-    if data.get('hypertension') == 1:
-        risk_factors.append('Hypertension')
-    if data.get('heart_disease') == 1:
-        risk_factors.append('Heart Disease')
+    if data.get('hypertension', 0) == 1:
+        risk_factors += 1
+    if data.get('heart_disease', 0) == 1:
+        risk_factors += 1
     if data.get('age', 0) > 65:
-        risk_factors.append('Age > 65')
-    if data.get('smoking_status') == 'smokes':
-        risk_factors.append('Smoking')
+        risk_factors += 1
+    if data.get('smoking_status', '') == 'smokes':
+        risk_factors += 1
     if data.get('avg_glucose_level', 0) > 140:
-        risk_factors.append('High Blood Glucose')
+        risk_factors += 1
     if data.get('bmi', 0) > 30:
-        risk_factors.append('Obesity')
-    
-    risk_count = len(risk_factors)
+        risk_factors += 1
     
     # Simple logic based on risk factor count
-    if risk_count == 0:
+    if risk_factors == 0:
         probability = 0.05
-    elif risk_count == 1:
+    elif risk_factors == 1:
         probability = 0.15
-    elif risk_count == 2:
+    elif risk_factors == 2:
         probability = 0.30
-    elif risk_count == 3:
+    elif risk_factors == 3:
         probability = 0.60
     else:
         probability = 0.80
     
-    return probability, get_risk_category(probability)
+    return probability, get_risk_level(probability)
 
 @app.get("/")
 async def root():
-    """
-    Root endpoint for health check and documentation
-    """
     return {
         "message": "Stroke Prediction API is running",
-        "model_loaded": model is not None,
         "usage": "Send a POST request to / with patient data",
         "example": {
             "gender": "Male",
             "age": 67,
             "hypertension": 1,
             "heart_disease": 0,
-            "ever_married": "Yes",
-            "work_type": "Private",
-            "Residence_type": "Urban",
             "avg_glucose_level": 228.69,
             "bmi": 36.6,
             "smoking_status": "formerly smoked"
@@ -131,47 +67,17 @@ async def root():
 
 @app.post("/")
 async def predict(request: Request):
-    """
-    Make a stroke risk prediction based on input features
-    """
     try:
         data = await request.json()
         
-        # Use the model if available, otherwise use fallback
-        if model:
-            try:
-                # Preprocess the input
-                features = preprocess_input(data)
-                
-                # Make prediction
-                prediction_proba = model.predict_proba(features)[0, 1]
-                risk_level = get_risk_category(prediction_proba)
-                
-                return {
-                    "probability": float(prediction_proba),
-                    "prediction": risk_level,
-                    "stroke_prediction": int(prediction_proba > 0.5),
-                    "using_fallback": False
-                }
-            except Exception as e:
-                print(f"Error using model: {e}")
-                # Fall back to simple prediction
-                probability, risk_level = fallback_prediction(data)
-                return {
-                    "probability": float(probability),
-                    "prediction": risk_level,
-                    "stroke_prediction": int(probability > 0.5),
-                    "using_fallback": True
-                }
-        else:
-            # Use fallback prediction
-            probability, risk_level = fallback_prediction(data)
-            return {
-                "probability": float(probability),
-                "prediction": risk_level,
-                "stroke_prediction": int(probability > 0.5),
-                "using_fallback": True
-            }
-    
+        # Use fallback prediction
+        probability, risk_level = predict_risk(data)
+        
+        return {
+            "probability": float(probability),
+            "prediction": risk_level,
+            "stroke_prediction": int(probability > 0.5)
+        }
+        
     except Exception as e:
         raise HTTPException(status_code=400, detail=f"Invalid input: {str(e)}") 

requirements.txt

@@ -1,7 +1,4 @@
+fastapi==0.95.2
+uvicorn==0.23.2
 numpy==1.24.3
-pandas==2.0.3
-scikit-learn==1.3.0
-joblib==1.3.2
-fastapi>=0.95.0
-pydantic>=2.0.0
-uvicorn>=0.23.0 
+joblib==1.3.2