Create app.py

app.py

@@ -1,128 +1,131 @@
-import gradio as gr
-import pandas as pd
 import numpy as np
-import pickle
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
-import sklearn
-import os
-
-print(f"Prediction environment scikit-learn version: {sklearn.__version__}")
-
-def decode_file(file_path):
-    with open(file_path, 'rb') as file:
-        obj = pickle.load(file)
-    return obj
-
-# Load the model without try/except
-model = decode_file('./model.pkl')
-
-def preprocess_input(data_dict):
-    """Preprocess input data to match the training format"""
-    # First create DataFrame with original columns
-    df = pd.DataFrame([data_dict])
-    
-    # Store original features before transformation
-    original_df = df.copy()
-    
-    # Numeric features
-    numeric_features = ['age', 'avg_glucose_level', 'bmi']
-    
-    # Scale numeric features and add prefix
-    scaler = StandardScaler()
-    scaled_features = scaler.fit_transform(df[numeric_features])
-    for i, feat in enumerate(numeric_features):
-        df[f'num__{feat}'] = scaled_features[:, i]
-    
-    # Create categorical features
-    # Gender
-    df['cat__gender_Male'] = (df['gender'] == 'Male').astype(float)
-    df['cat__gender_Other'] = 0.0
-    
-    # Hypertension
-    df['cat__hypertension_1'] = df['hypertension'].astype(float)
-    
-    # Heart Disease
-    df['cat__heart_disease_1'] = df['heart_disease'].astype(float)
-    
-    # Ever Married
-    df['cat__ever_married_Yes'] = (df['ever_married'] == 'Yes').astype(float)
-    
-    # Work Type
-    df['cat__work_type_Never_worked'] = (df['work_type'] == 'Never_worked').astype(float)
-    df['cat__work_type_Private'] = (df['work_type'] == 'Private').astype(float)
-    df['cat__work_type_Self-employed'] = (df['work_type'] == 'Self-employed').astype(float)
-    df['cat__work_type_children'] = (df['work_type'] == 'children').astype(float)
-    
-    # Residence Type
-    df['cat__Residence_type_Urban'] = (df['Residence_type'] == 'Urban').astype(float)
-    
-    # Smoking Status
-    df['cat__smoking_status_formerly smoked'] = (df['smoking_status'] == 'formerly smoked').astype(float)
-    df['cat__smoking_status_never smoked'] = (df['smoking_status'] == 'never smoked').astype(float)
-    df['cat__smoking_status_smokes'] = (df['smoking_status'] == 'smokes').astype(float)
-    
-    # Select only the transformed columns in the correct order
-    feature_columns = [
-        'num__age', 'num__avg_glucose_level', 'num__bmi',
-        'cat__gender_Male', 'cat__gender_Other', 'cat__hypertension_1',
-        'cat__heart_disease_1', 'cat__ever_married_Yes',
-        'cat__work_type_Never_worked', 'cat__work_type_Private',
-        'cat__work_type_Self-employed', 'cat__work_type_children',
-        'cat__Residence_type_Urban', 'cat__smoking_status_formerly smoked',
-        'cat__smoking_status_never smoked', 'cat__smoking_status_smokes'
-    ]
-    
-    return df[feature_columns]
-
-def predict(gender, age, hypertension, ever_married, work_type, heart_disease, 
-           avg_glucose_level, bmi, smoking_status, Residence_type):
-    """Make prediction using the loaded model"""
-    if model is None:
-        return "Error: Model not loaded"
-        
-    # Create input dictionary
-    input_data = {
-        'gender': gender,
-        'age': float(age),  # Ensure numeric
-        'hypertension': 1 if hypertension == 'Yes' else 0,
-        'heart_disease': 1 if heart_disease == 'Yes' else 0,
-        'ever_married': ever_married,
-        'work_type': work_type,
-        'Residence_type': Residence_type,
-        'avg_glucose_level': float(avg_glucose_level),  # Ensure numeric
-        'bmi': float(bmi),  # Ensure numeric
-        'smoking_status': smoking_status
-    }
-    
-    # Preprocess the input
-    processed_input = preprocess_input(input_data)
-    
-    # Use the loaded model
-    try:
-        prediction = model.predict_proba(processed_input)[0][1]
-        return f"The probability of stroke is {prediction:.2%}"
-    except Exception as e:
-        return f"Error making prediction: {str(e)}, model is not valid" # updated here
-
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=predict,
-    inputs=[
-        gr.Radio(choices=['Female', 'Male'], label="Gender"),
-        gr.Slider(minimum=0, maximum=100, label="Age"),
-        gr.Radio(choices=['Yes', 'No'], label="Hypertension"),
-        gr.Radio(choices=['Yes', 'No'], label="Ever Married"),
-        gr.Radio(choices=['Private', 'Self-employed', 'Govt_job', 'children', 'Never_worked'], label="Work Type"),
-        gr.Radio(choices=['Yes', 'No'], label="Heart Disease"),
-        gr.Number(label="Average Glucose Level"),
-        gr.Slider(minimum=10, maximum=50, label="BMI"),
-        gr.Radio(choices=['formerly smoked', 'never smoked', 'smokes', 'Unknown'], label="Smoking Status"),
-        gr.Radio(choices=['Urban', 'Rural'], label="Residence Type")
-    ],
-    outputs='text',
-    title='Stroke Probability Predictor',
-    description='Predicts the probability of having a stroke based on input features.'
-)
+from sklearn.linear_model import LogisticRegression
+import gradio as gr
+
+# ---------------------------------------------------------
+# 1. Core Logic & Data Processing (Identical to raw code)
+# ---------------------------------------------------------
+np.random.seed(42)
+num_patients = 1000
+
+data = {
+    'age': np.random.randint(18, 70, size=num_patients),
+    'hypertension': np.random.choice([0, 1], size=num_patients, p=[0.75, 0.25]),
+    'heart_disease': np.random.choice([0, 1], size=num_patients, p=[0.85, 0.15]),
+    'avg_glucose_level': np.round(np.random.uniform(55.0, 280.0, size=num_patients), 1),
+    'bmi': np.round(np.random.uniform(18.0, 48.0, size=num_patients), 1),
+    'stroke': np.random.choice([0, 1], size=num_patients, p=[0.90, 0.10])
+}
+
+df = pd.DataFrame(data)
+
+X = df.drop(columns=['stroke'])
+y = df['stroke']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+model = LogisticRegression()
+model.fit(X_train_scaled, y_train)
+
+# Generate Feature Importance Plot
+def get_feature_importance_plot():
+    importance = model.coef_.flatten()
+    feature_names = ['Age', 'Hypertension', 'Heart Disease', 'Avg Glucose Level', 'BMI']
+    feature_importance = pd.DataFrame({
+        'Clinical Feature': feature_names,
+        'Statistical Weight': importance
+    })
+    feature_importance['Absolute Weight'] = feature_importance['Statistical Weight'].abs()
+    feature_importance = feature_importance.sort_values(by='Absolute Weight', ascending=True)
+
+    fig, ax = plt.subplots(figsize=(8, 4))
+    ax.barh(feature_importance['Clinical Feature'], feature_importance['Statistical Weight'], color='#1f77b4')
+    ax.axvline(0, color='black', linestyle='--', linewidth=1)
+    ax.set_title('Neuro-Vascular Feature Importance (Model Weighting)', fontsize=12, fontweight='bold')
+    ax.set_xlabel('Predictive Influence (Coefficient Value)', fontsize=10)
+    ax.set_ylabel('Clinical Metrics', fontsize=10)
+    ax.grid(axis='x', linestyle=':', alpha=0.6)
+    plt.tight_layout()
+    return fig
+
+# ---------------------------------------------------------
+# 2. Evaluation / Prediction Handler
+# ---------------------------------------------------------
+def analyze_patient(patient_age, hypertension, heart_disease, blood_glucose, patient_bmi):
+    has_hypertension = 1 if hypertension == "Yes" else 0
+    has_heart_disease = 1 if heart_disease == "Yes" else 0
+
+    custom_patient = np.array([[patient_age, has_hypertension, has_heart_disease, blood_glucose, patient_bmi]])
+    custom_patient_scaled = scaler.transform(custom_patient)
+
+    prob = model.predict_proba(custom_patient_scaled)[0][1] * 100
+
+    report = []
+    report.append("==========================================================")
+    report.append("             DYNAMIC CLINICAL ANALYSIS REPORT             ")
+    report.append("==========================================================")
+    report.append("📋 PATIENT BIOMETRICS PROFILE:")
+    report.append(f"   • Age: {patient_age} years old")
+    report.append(f"   • Hypertension History: {hypertension}")
+    report.append(f"   • Cardiovascular Disease: {heart_disease}")
+    report.append(f"   • Avg Blood Glucose: {blood_glucose} mg/dL")
+    report.append(f"   • Body Mass Index (BMI): {patient_bmi} kg/m²")
+    report.append("----------------------------------------------------------")
+    report.append(f"🎯 CALCULATED CEREBROVASCULAR STROKE RISK: {prob:.2f}%")
+    report.append("----------------------------------------------------------")
+
+    if prob >= 15.0:
+        report.append("🚨 WARNING: ELEVATED VASCULAR RISK CATEGORY")
+        report.append("👉 DPT Action: Check baseline BP/HR. Avoid prolonged dependent positions or maximum manual resistance.")
+        report.append("👉 Objective: Focus on submaximal aerobic training, functional mobility, and reactive balance strategy.")
+    else:
+        report.append("✅ CLEARANCE: BASELINE STABLE RISK PROFILE")
+        report.append("👉 DPT Action: Safe to push metabolic capacity and neuroplasticity boundaries.")
+        report.append("👉 Objective: High-intensity task-specific training and advanced dynamic gait coordination.")
+    report.append("==========================================================")
+
+    fig = get_feature_importance_plot()
+    return "\n".join(report), fig
+
+# ---------------------------------------------------------
+# 3. Gradio Web Interface
+# ---------------------------------------------------------
+with gr.Blocks(title="DPT Neurological Clinical Appraisal") as demo:
+    gr.Markdown("# 🧠 DPT Neurological Clinical Appraisal & Stroke Risk Calculator")
+    gr.Markdown("Adjust patient biometrics below to calculate cerebrovascular risk and generate clinical DPT guidance.")
+
+    with gr.Row():
+        with gr.Column():
+            age_input = gr.Slider(minimum=18, maximum=100, value=67, step=1, label="Patient Age")
+            htn_input = gr.Radio(choices=["No", "Yes"], value="Yes", label="Hypertension History")
+            hd_input = gr.Radio(choices=["No", "Yes"], value="No", label="Heart Disease History")
+            glucose_input = gr.Slider(minimum=50.0, maximum=300.0, value=185.4, step=0.1, label="Avg Blood Glucose Level (mg/dL)")
+            bmi_input = gr.Slider(minimum=15.0, maximum=50.0, value=31.2, step=0.1, label="Patient BMI (kg/m²)")
+            submit_btn = gr.Button("Calculate Risk Profile", variant="primary")
+
+        with gr.Column():
+            output_report = gr.Textbox(label="Clinical Report Output", lines=18, max_lines=25)
+            output_plot = gr.Plot(label="Model Feature Weights")
+
+    submit_btn.click(
+        fn=analyze_patient,
+        inputs=[age_input, htn_input, hd_input, glucose_input, bmi_input],
+        outputs=[output_report, output_plot]
+    )
+
+    demo.load(
+        fn=analyze_patient,
+        inputs=[age_input, htn_input, hd_input, glucose_input, bmi_input],
+        outputs=[output_report, output_plot]
+    )
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()