tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

tried pca

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-05 23:05:37 +01:00
parent 8d831f3613
commit a15d801c2a
2 changed files with 35 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

7
scripts/ml/ml_functions/MultClfs.py
View file

@ -74,6 +74,7 @@ from sklearn.impute import KNNImputer as KNN
import json import json
import argparse import argparse
import re import re
from sklearn.decomposition import PCA
#%% GLOBALS #%% GLOBALS
rs = {'random_state': 42} rs = {'random_state': 42}
njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
@ -281,6 +282,12 @@ def MultModelsCl(input_df, target
('prep' , col_transform) ('prep' , col_transform)
, ('model' , model_fn)]) , ('model' , model_fn)])
# model_pipeline = Pipeline([
# ('prep' , col_transform)
# , ('pca' , PCA(n_components = 2))
# , ('model' , model_fn)])
print('\nRunning model pipeline:', model_pipeline) print('\nRunning model pipeline:', model_pipeline)
skf_cv_modD = cross_validate(model_pipeline skf_cv_modD = cross_validate(model_pipeline
, input_df , input_df

2
scripts/ml/ml_functions/test_func_singlegene.py
View file

@ -82,7 +82,7 @@ fooD = MultModelsCl(input_df = df2['X']
, tts_split_type = spl_type , tts_split_type = spl_type
, resampling_type = 'none' # default , resampling_type = 'none' # default
, var_type = ['mixed'] , var_type = ['mixed']
, scale_numeric = ['min_max_neg'] , scale_numeric = ['min_max']
, return_formatted_output = False , return_formatted_output = False
) )