app.py

import gradio as gr
import numpy as np
import pandas as pd
from sklearn.multioutput import MultiOutputRegressor
from sklearn.ensemble import GradientBoostingRegressor
import pickle

def create_gui():
    """
    Creates and launches the Gradio user interface for the biomass adsorption prediction.
    """
    # Define the input and output components of the GUI
    inputs = [
        gr.Dropdown(choices=["Benzocaine", "Ciprofloxacin", "Citalopram", "Diclofenac", "Dimetridazole", 
                             "Floxentine", "Ibuprofen", "Metronidazole", "Nitroimidazole", "Norfloxacin", 
                             "Oxytetracycline", "Salicylic Acid", "Sulfadiazine", "Sulfamethazine", "Sulfamethoxazole", 
                             "Tetracycline", "Triclosan"], 
                    label="Pharmaceutical Type"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="TemP (K)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="Time (min)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="PS (mm)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="BET (m2/g)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="PV (cm3)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="C (%)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="H (%)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="N (%)"),
        gr.components.Slider(minimum=0, maximum=100, step=0.01, label="O (%)"),
    ]

    outputs = [
        gr.components.Textbox(label="Qm (mg/g)"),
    ]
    
    # Define the title and description of the GUI
    title = "GUI for Pharmaceutical Removal via Biochar Adsorption"
    description = "This GUI uses machine learning to predict pharmaceutical removal. The app takes ten features and predicts adsorption capacity."

    gr.Interface(fn=biomass_prediction, inputs=inputs, outputs=outputs, title=title, description=description).launch()

def biomass_prediction(*inputs):
    """
    Predicts properties based on input features of the biomass.
    
    Parameters:
    pharm_type (str): Pharmaceutical type.
    TemP (float): Temperature K of the biomass.
    Time (float): Minutes for x.
    PS (float): Pore space in mm.
    BET (float): Area of powder in m2/g being poured into the solution.
    PV (float): Pore volume in cm3.
    C (float): C (%) content of the biomass.
    H (float): H (%) content of the biomass.
    N (float): N (%) content of the biomass.
    O (float): O (%) content of the biomass.
    
    Returns:
    float: Absorption capacity
    """
    # Concatenate the inputs into a numpy array
    input_data = pd.DataFrame([inputs], columns=['pharm type', 'TemP (K)', 'Time (min)', 'PS (mm)', 'BET (m2/g)', 'PV (cm3)',  'C (%)', 'H (%)', 'N (%)', 'O (%)'])

    # Check if values are zero or negative
    if np.all(input_data <= 0):
        return 0

    # Load the trained model from the pickled file
    with open('trained_model.pkl', 'rb') as file:
        loaded_model = pickle.load(file)

    # Make predictions using the loaded machine learning model
    prediction = loaded_model.predict(input_data)
    prediction = np.round(prediction, 2)

    # Extract prediction value and save it to a separate variable
    output1 = prediction[0][0]
  
    # Return predicted output values
    return output1

if __name__ == '__main__': 
    # Create GUI
    create_gui()