app.py

import gradio as gr
import numpy as np
import joblib
from sklearn.preprocessing import LabelEncoder, MinMaxScaler

def rf_predict(gn, mrg, dpnd, edu, slf_emp, app_inc, coapp_inc, l_am, l_am_tm, cr_hist, prp_area):
  rf = joblib.load('RandomForest.pkl')
  encoder = LabelEncoder()
  scaler = MinMaxScaler()
  ftr = np.array([gn, mrg, dpnd, edu, slf_emp, app_inc, coapp_inc, l_am, l_am_tm, cr_hist, prp_area]).reshape(1, -1)

  for i in [0, 1, 2, 3, 4, 9, 10]:
    ftr[:, i] = encoder.fit_transform(ftr[:, i].reshape(1,-1))
  for j in [5, 6, 7, 8]:
    ftr[:, j] = scaler.fit_transform(ftr[:, j].reshape(1,-1))
  if rf.predict(ftr)==1:
    return 'Yes'
  elif rf.predict(ftr)==0:
    return 'No'
  
rf_interface = gr.Interface(
    fn=rf_predict,
    inputs = [gr.Radio(['Male','Female'],label="Gender:"),
              gr.Radio(['Yes','No'],label="Marital Status:"),
              gr.Dropdown([0,1,2,'3+'],label="Dependents:"),
              gr.Radio(['Graduate','Not Graduate'],label="Education Level:"),
              gr.Radio(['Yes','No'],label="Self-Employed:"),
              gr.Number(label="Applicant Income:"),
              gr.Number(label="Copplicant Income:"),
              gr.Number(label="Loan Amount:"),
              gr.Number(label="Loan Amount Term:"),
              gr.Radio(['Yes','No'],label="Credit History:"),
              gr.Dropdown(['Urban','Semiurban','Rural'],label='Property Area:')],
    outputs = gr.Textbox(label="Loan Approval", lines=1),
    title="Random Forest Classifier [Manual]",
    description="This interface uses Random Forest Classifier for the prediction of approval of Loans")
rf_interface.launch()