mody_2024/train.py

29 lines
1.1 KiB
Python

from load_dataset import load_data, analisis_univariado
#from trainer import BinaryTuner
import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings("ignore")
_, dms2, dms3, _ = load_data()
with pd.ExcelWriter("Univariado2.xlsx", engine='xlsxwriter') as xls:
mody2 = analisis_univariado(dms2.dropna(), target="MODY2_label", continuas=['edad diag', 'IMC', 'glu ayu', 'glu 120','A1c'], discretas=['sexo', 'diabetes_familia'])
mody2.to_excel(xls, sheet_name='MODY2', index=False)
mody3 = analisis_univariado(dms3.dropna(), target="MODY3_label", continuas=['edad diag', 'IMC', 'glu ayu', 'glu 120','A1c'], discretas=['sexo', 'diabetes_familia'])
mody3.to_excel(xls, sheet_name='MODY3', index=False)
# mody2 = BinaryTuner(dms2, 'MODY2_label', seeds=[231964], test_size=0.2)
# mody2.fit()
# mody2.explain_model('GaussianNB', 'fulldataset-oversampled-mice', 231964)
# mody2.wrap_and_save()
#
#
# mody3 = BinaryTuner(dms3, 'MODY3_label', seeds=[536202], test_size=0.2)
# mody3.fit()
# mody3.explain_model('RandomForestClassifier', 'fulldataset-original-mice', 536202)
# mody3.wrap_and_save()