app

app.py

@@ -1,50 +1,27 @@
 
+"""
+Webapp Front End
+"""
+
 import gradio as gr
 import joblib
-import numpy as np
 import pandas as pd
 
-# Load the trained model
-model_path = "trained_model.pkl"
+MODEL_PATH = "Random_Foresttest_model.pkl"
 
-def load_model(path):
-    try:
-        return joblib.load(path)
-    except Exception as e:
-        raise ValueError(f"Error loading model: {e}")
+try:
+    rf_model = joblib.load(MODEL_PATH)
+except FileNotFoundError as e:
+    raise FileNotFoundError(
+        f"Model file not found at {MODEL_PATH}. Please check the path."
+    ) from e
 
 # Define the prediction function
-def predict_heart_disease(
-    PhysicalHealthDays: float,
-    MentalHealthDays: float,
-    SleepHours: float,
-    BMI: float,
-    PhysicalActivities: str,
-    AlcoholDrinkers: str,
-    HIVTesting: str,
-    RemovedTeeth: str,
-    HighRiskLastYear: str,
-    CovidPos: str,
-):
+def predict_with_model(State: float, Sex: float, GeneralHealth: float, PhysicalHealthDays: float, MentalHealthDays: float, LastCheckupTime: float, PhysicalActivities: float, SleepHours: float, HadStroke: float, HadArthritis: float, HadDiabetes: float, SmokerStatus: float, ECigaretteUsage: float, RaceEthnicityCategory: float, AgeCategory: float, HeightInMeters: float, WeightInKilograms: float, BMI: float, AlcoholDrinkers: float, HighRiskLastYear: float):
     try:
-        model = load_model(model_path)
-        # Encode categorical inputs as integers
-        physical_activities = 1 if PhysicalActivities.lower() == "yes" else 0
-        alcohol_drinkers = 1 if AlcoholDrinkers.lower() == "yes" else 0
-        hiv_testing = 1 if HIVTesting.lower() == "yes" else 0
-        removed_teeth = 1 if RemovedTeeth.lower() == "yes" else 0
-        high_risk_last_year = 1 if HighRiskLastYear.lower() == "yes" else 0
-        covid_pos = 1 if CovidPos.lower() == "yes" else 0
-
-        # Combine inputs into a numpy array for prediction
-        features = np.array([
-            PhysicalHealthDays, MentalHealthDays, SleepHours, BMI,
-            physical_activities, alcohol_drinkers, hiv_testing,
-            removed_teeth, high_risk_last_year, covid_pos
-        ]).reshape(1, -1)
-
-        # Predict with the model
-        prediction = model.predict(features)
+        # Prepare input as a DataFrame
+        input_data = pd.DataFrame([[State, Sex, GeneralHealth, PhysicalHealthDays, MentalHealthDays, LastCheckupTime, PhysicalActivities, SleepHours, HadStroke, HadArthritis, HadDiabetes, SmokerStatus, ECigaretteUsage, RaceEthnicityCategory, AgeCategory, HeightInMeters, WeightInKilograms, BMI, AlcoholDrinkers, HighRiskLastYear]], columns=['State', 'Sex', 'GeneralHealth', 'PhysicalHealthDays', 'MentalHealthDays', 'LastCheckupTime', 'PhysicalActivities', 'SleepHours', 'HadStroke', 'HadArthritis', 'HadDiabetes', 'SmokerStatus', 'ECigaretteUsage', 'RaceEthnicityCategory', 'AgeCategory', 'HeightInMeters', 'WeightInKilograms', 'BMI', 'AlcoholDrinkers', 'HighRiskLastYear'])
+        prediction = rf_model.predict(input_data)
         return "Heart Disease Risk" if prediction[0] == 1 else "No Risk"
     except Exception as e:
         return f"Error during prediction: {e}"
@@ -52,33 +29,19 @@ def predict_heart_disease(
 # Define the Gradio interface
 with gr.Blocks() as app:
     gr.Markdown("# Heart Disease Prediction App")
-    gr.Markdown("### Provide input values and receive a prediction.")
-    
-    with gr.Row():
-        PhysicalHealthDays = gr.Slider(0, 30, label="Physical Health Days")
-        MentalHealthDays = gr.Slider(0, 30, label="Mental Health Days")
-        SleepHours = gr.Slider(0, 24, label="Average Sleep Hours")
-        BMI = gr.Slider(10, 50, label="Body Mass Index (BMI)")
-    
-    with gr.Row():
-        PhysicalActivities = gr.Radio(["Yes", "No"], label="Engaged in Physical Activities?")
-        AlcoholDrinkers = gr.Radio(["Yes", "No"], label="Consumes Alcohol?")
-        HIVTesting = gr.Radio(["Yes", "No"], label="Tested for HIV?")
-        RemovedTeeth = gr.Radio(["Yes", "No"], label="Has Removed Teeth?")
-        HighRiskLastYear = gr.Radio(["Yes", "No"], label="High Risk Last Year?")
-        CovidPos = gr.Radio(["Yes", "No"], label="Tested Positive for COVID-19?")
+    gr.Markdown("### Provide input values for the features below and get a prediction.")
+
+    input_components = []
+    for feature in ['State', 'Sex', 'GeneralHealth', 'PhysicalHealthDays', 'MentalHealthDays', 'LastCheckupTime', 'PhysicalActivities', 'SleepHours', 'HadStroke', 'HadArthritis', 'HadDiabetes', 'SmokerStatus', 'ECigaretteUsage', 'RaceEthnicityCategory', 'AgeCategory', 'HeightInMeters', 'WeightInKilograms', 'BMI', 'AlcoholDrinkers', 'HighRiskLastYear']:
+        input_components.append(gr.Slider(0, 100, step=1, label=feature))
 
     predict_button = gr.Button("Predict")
     output = gr.Textbox(label="Prediction Result")
 
     # Connect prediction logic
     predict_button.click(
-        fn=predict_heart_disease,
-        inputs=[
-            PhysicalHealthDays, MentalHealthDays, SleepHours, BMI,
-            PhysicalActivities, AlcoholDrinkers, HIVTesting,
-            RemovedTeeth, HighRiskLastYear, CovidPos
-        ],
+        fn=predict_with_model,
+        inputs=input_components,
         outputs=output,
     )