KNN_UI.py

import os
import gradio as gr
import pandas as pd
from KNN.KNNModel import KNNModel

class KNN_UI:
    def __init__(self):
        self.knn_model = KNNModel()
        try:
            # Load and preprocess data
            self.knn_model.load_and_preprocess_data()
            # Find optimal k and train the model
            X_train, X_test, y_train, y_test = self.knn_model.load_and_preprocess_data()
            self.knn_model.find_optimal_k(X_train, y_train)
            self.knn_model.train_model(X_train, y_train)
        except Exception as e:
            print(f"Error during initialization: {e}")

    def get_interface(self) -> gr.Blocks:
        with gr.Blocks() as interface:
            #self.__get_inputs_ui()
            gr.Markdown("## Fat Percentage Prediction through kNN Regressor" )
            gr.Markdown("")
            gr.Markdown(
                         "Welcome to the **Fat Percentage Prediction** section. Here, you can determine an individual's Fat Percentage based on a set of input parameters."
                            )
           
           
            gr.Markdown(
                        "You are to input details such as workout frequency, session duration, water intake, calories burned, and experience level to make a prediction. "
                        "The Experience Level is grouped into three Levels: 1- Beginner, Professional, and 3- Expert. "
                        
             
               )
            self.__get_inputs_ui()   

        return interface

    def __get_inputs_ui(self):
        def predict(workout_frequency,session_duration, water_intake, calories_burned, experience_level):
            try:
                # Encode categorical features
                if 'Experience_Level' not in self.knn_model.label_encoders:
                    return f"Error: 'Experience_Level' encoder not found. Ensure the column exists in the dataset."

                experience_level_encoded = self.knn_model.label_encoders['Experience_Level'].transform([experience_level])[0]

                # Create input DataFrame
                input_data = pd.DataFrame({
                    'Workout_Frequency (days/week)': [workout_frequency],
                    'Session_Duration (hours)': [session_duration],
                    'Water_Intake (liters)': [water_intake],
                    'Calories_Burned': [calories_burned],
                    'Experience_Level': [experience_level_encoded]
                })

                # Predict fat percentage
                predicted_fat_percentage = self.knn_model.predict(input_data)
                return f"Predicted Fat Percentage: {predicted_fat_percentage:.2f}%"
            except Exception as e:
                return f"Error: {str(e)}"

        with gr.Column() as inputs_ui:
            gr.Markdown("# Input your record")
            workout_frequency = gr.Number(label="Workout Frequency (days/week)", minimum=1, maximum=7, step=1, value=3)
            session_duration = gr.Number(label="Session Duration (hours)", minimum=0.0, maximum=24.0, step=0.1, value=1.25)
            water_intake = gr.Number(label="Water Intake (liters/day)", minimum=0.0, maximum=10.0, step=0.1, value=2.5)
            calories_burned = gr.Number(label="Calories Burned", minimum=0.0, maximum=2000.0, step=0.1, value=905.5)
            experience_level = gr.Dropdown(
                label="Experience Level",
                choices=self.knn_model.label_encoders['Experience_Level'].classes_.tolist()
                
            )

            predict_btn = gr.Button("Calculate")
            gr.Markdown("# Calculated Fat Percentage")
            res = gr.Markdown("")

            predict_btn.click(predict, inputs=[calories_burned, session_duration, workout_frequency, water_intake, experience_level], outputs=res)

        return inputs_ui

# Initialize the UI and launch the Gradio interface
if __name__ == "__main__":
    knn_ui = KNN_UI()
    interface = knn_ui.get_interface()
    interface.launch()