Update app.py

app.py

@@ -1,82 +1,51 @@
 import gradio as gr
 import pandas as pd
 import numpy as np
-import os
-import joblib  # Change to joblib for direct loading
+import pickle
+from sklearn.ensemble import RandomForestClassifier
 
-# Load the model - for Hugging Face deployment
-try:
-    # Load model directly from python_model.pkl
-    model = joblib.load("python_model.pkl")
-    print("Model loaded successfully")
-    print("Model type:", type(model))
-    
-except Exception as e:
-    print(f"Error loading model: {str(e)}")
-    print(f"Current working directory: {os.getcwd()}")
-    print("Files in current directory:", os.listdir())
-    raise
+# Load the trained model
+model = pickle.load(open('stroke_prediction_model.pkl', 'rb'))
 
-def predict_stroke_risk(age, gender, hypertension, heart_disease, ever_married,
-                       work_type, residence_type, avg_glucose_level, bmi, smoking_status):
-    """Make stroke prediction with the trained model"""
-    try:
-        # Create a DataFrame with the input data
-        data = pd.DataFrame({
-            'gender': [gender],
-            'age': [float(age)],
-            'hypertension': [int(hypertension)],
-            'heart_disease': [int(heart_disease)],
-            'ever_married': [ever_married],
-            'work_type': [work_type],
-            'Residence_type': [residence_type],
-            'avg_glucose_level': [float(avg_glucose_level)],
-            'bmi': [float(bmi)],
-            'smoking_status': [smoking_status]
-        })
-        
-        # Make prediction
-        prediction = model.predict(data)
-        probability = model.predict_proba(data)[0][1]
-        
-        # Create result message
-        if prediction[0] == 1:
-            result = f"High Risk of Stroke (Probability: {probability:.2%})"
-        else:
-            result = f"Low Risk of Stroke (Probability: {probability:.2%})"
-        
-        return result
-    except Exception as e:
-        print(f"Error during prediction: {str(e)}")
-        return f"Error making prediction: {str(e)}"
+def predict_stroke(gender, age, hypertension, heart_disease, ever_married, 
+                  work_type, residence_type, avg_glucose_level, bmi, smoking_status):
+    # Create a DataFrame with the input features
+    input_data = pd.DataFrame([[gender, age, hypertension, heart_disease, ever_married, 
+                               work_type, residence_type, avg_glucose_level, bmi, smoking_status]], 
+                             columns=['gender', 'age', 'hypertension', 'heart_disease', 'ever_married',
+                                    'work_type', 'Residence_type', 'avg_glucose_level', 'bmi', 'smoking_status'])
+    
+    # Make prediction
+    prediction = model.predict(input_data)[0]
+    probability = model.predict_proba(input_data)[0][1]
+    
+    return "High Risk" if prediction == 1 else "Low Risk", f"{probability:.2%}"
 
 # Create the Gradio interface
 iface = gr.Interface(
-    fn=predict_stroke_risk,
+    fn=predict_stroke,
     inputs=[
-        gr.Slider(minimum=0, maximum=120, step=1, label="Age"),
         gr.Dropdown(choices=["Male", "Female"], label="Gender"),
+        gr.Slider(minimum=0, maximum=100, label="Age"),
         gr.Checkbox(label="Hypertension"),
         gr.Checkbox(label="Heart Disease"),
         gr.Dropdown(choices=["Yes", "No"], label="Ever Married"),
-        gr.Dropdown(
-            choices=["Private", "Self-employed", "Govt_job", "children", "Never_worked"],
-            label="Work Type"
-        ),
+        gr.Dropdown(choices=["Private", "Self-employed", "Govt_job", "children", "Never_worked"], label="Work Type"),
         gr.Dropdown(choices=["Urban", "Rural"], label="Residence Type"),
-        gr.Slider(minimum=50, maximum=300, step=1, label="Average Glucose Level"),
-        gr.Slider(minimum=10, maximum=70, step=0.1, label="BMI"),
-        gr.Dropdown(
-            choices=["formerly smoked", "never smoked", "smokes", "Unknown"],
-            label="Smoking Status"
-        )
+        gr.Slider(minimum=50, maximum=300, label="Average Glucose Level"),
+        gr.Slider(minimum=10, maximum=100, label="BMI"),
+        gr.Dropdown(choices=["formerly smoked", "never smoked", "smokes", "Unknown"], label="Smoking Status")
+    ],
+    outputs=[
+        gr.Label(label="Stroke Risk"),
+        gr.Label(label="Probability")
     ],
-    outputs=gr.Text(label="Prediction Result"),
     title="Stroke Risk Prediction",
     description="Enter patient information to predict stroke risk.",
     examples=[
-        [67, "Male", True, False, "Yes", "Private", "Urban", 228.69, 36.6, "formerly smoked"],
-        [61, "Female", False, False, "Yes", "Self-employed", "Rural", 202.21, 30.0, "never smoked"]
+        ["Male", 67, True, True, "Yes", "Private", "Urban", 228.69, 36.6, "formerly smoked"],
+        ["Female", 61, False, False, "Yes", "Self-employed", "Rural", 202.21, 30.0, "never smoked"],
+        ["Male", 80, False, True, "Yes", "Private", "Rural", 105.92, 32.5, "never smoked"]
     ]
 )