trying Stratified Kfold split on running multiple pipelines

This commit is contained in:
Tanushree Tunstall 2022-03-09 18:35:54 +00:00
parent bb8f6f70ba
commit 1bfb35c30c
7 changed files with 287 additions and 72 deletions

View file

@ -21,12 +21,15 @@ from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.compose import make_column_transformer
from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, roc_auc_score, roc_curve, f1_score
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef
from sklearn.metrics import make_scorer
from sklearn.metrics import classification_report
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.pipeline import Pipeline
from sklearn.pipeline import make_pipeline
@ -39,13 +42,15 @@ import matplotlib.pyplot as plt
import numpy as np
print(np.__version__)
print(pd.__version__)
from statistics import mean, stdev
from statistics import mean, stdev, median, mode
#%%
homedir = os.path.expanduser("~")
os.chdir(homedir + "/git/ML_AI_training/")
# my function
from MultClassPipe import MultClassPipeline
from MultClassPipe import MultClassPipeline
from MultClassPipe2 import MultClassPipeline2
from MultClassPipe3 import MultClassPipeSKF
gene = 'pncA'
drug = 'pyrazinamide'