54 lines
2.8 KiB
Python
54 lines
2.8 KiB
Python
from load_dataset import load_data, univariate_analysis
|
|
#from trainer import BinaryTuner
|
|
import pandas as pd
|
|
import numpy as np
|
|
import warnings
|
|
warnings.filterwarnings("ignore")
|
|
|
|
# Load data from HC.xslc raw original data file and extract mody data into filtered dataframes
|
|
# filtered data is stord as `MODY_data.xlsx` for screening.
|
|
# this returns a tuple (mody1, mody2, mody3, mody5) dataFrames from each sheet in the filtered record
|
|
_, dms2, dms3, _ = load_data()
|
|
|
|
# Univariate analysis of the origin data
|
|
with pd.ExcelWriter("UnivariateODY.xlsx", engine='xlsxwriter') as xls:
|
|
# continous are tested shapiro for normality. metrics for groups are computed, then ttested or mannwhitneyu for difference in groups
|
|
# binary use fisher and frecuency tables
|
|
mody2 = univariate_analysis(dms2.dropna(), target="MODY2_label", continous=['edad diag', 'IMC', 'glu ayu', 'glu 120','A1c'], discrete=['sexo', 'diabetes_familia'])
|
|
mody2.to_excel(xls, sheet_name='MODY2', index=False)
|
|
|
|
mody3 = univariate_analysis(dms3.dropna(), target="MODY3_label", continous=['edad diag', 'IMC', 'glu ayu', 'glu 120','A1c'], discrete=['sexo', 'diabetes_familia'])
|
|
mody3.to_excel(xls, sheet_name='MODY3', index=False)
|
|
|
|
# For reproducibility, seeds from the original research, set to None to get random
|
|
seeds = [231964, 48928, 132268, 113986, 574626, 130068, 226585, 446306, 535997, 685636, 779992, 600946, 231614, 1027776, 747054, 546372, 885843, 536202, 852539, 848580, 997648, 440679, 118304, 49131, 861767]
|
|
# seeds = None
|
|
# or
|
|
# import np
|
|
# seeds = [np.random.randint(1, 2**20) for _ in range(n_seeds)]
|
|
|
|
# The BinaryTuner do a Grid Search for multiple hyperparameter space and
|
|
# save metrics the test split for the best combinations of ML hyperparameters
|
|
# * Hyperparameters GridSearch for each ML Model for up to 60 different combinations
|
|
# * 10 different Machine Learning Models capable of Binary Clasification
|
|
# * Model trained on data with no missing values, and impute MICE and KNN
|
|
# * Different random train and test splits, for given test_size ratio
|
|
# A folder is created with the label name with all the state and run data
|
|
mody2 = BinaryTuner(dms2, 'MODY2_label', seeds=seed, test_size=0.2)
|
|
|
|
# CheckPoint during search all trained models are saved inside the label folder
|
|
# including the scalers required for inference and testing
|
|
mody2.fit()
|
|
|
|
# Generate Chap Explainer for (Model, dataset, seed). See folder structure.
|
|
mody2.explain_model('GaussianNB', 'fulldataset-oversampled-mice', 231964)
|
|
|
|
# Create summary of metrics and zip the folder for easy portabilitys
|
|
mody2.wrap_and_save()
|
|
|
|
# Repeat process for next dataset
|
|
mody3 = BinaryTuner(dms3, 'MODY3_label', seeds=seeds, test_size=0.2)
|
|
mody3.fit()
|
|
mody3.explain_model('RandomForestClassifier', 'fulldataset-original-mice', 536202)
|
|
mody3.wrap_and_save()
|