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

61
scripts/ml/ml_functions/MultClfs.py
View file

@ -74,6 +74,7 @@ from sklearn.impute import KNNImputer as KNN
import json
import argparse
import re
from sklearn.decomposition import PCA
#%% GLOBALS
rs = {'random_state': 42}
njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
@ -232,33 +233,33 @@ def MultModelsCl(input_df, target
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
#, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
# , ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
# , n_estimators = 1000
# , bootstrap = True
# , oob_score = True
# , **njobs
# , **rs
# , max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False, **njobs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
#, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
# , ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
# , n_estimators = 1000
# , bootstrap = True
# , oob_score = True
# , **njobs
# , **rs
# , max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False, **njobs) )
]
mm_skf_scoresD = {}
@ -281,6 +282,12 @@ def MultModelsCl(input_df, target
('prep' , col_transform)
, ('model' , model_fn)])
# model_pipeline = Pipeline([
# ('prep' , col_transform)
# , ('pca' , PCA(n_components = 2))
# , ('model' , model_fn)])
print('\nRunning model pipeline:', model_pipeline)
skf_cv_modD = cross_validate(model_pipeline
, 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
, resampling_type = 'none' # default
, var_type = ['mixed']
, scale_numeric = ['min_max_neg']
, scale_numeric = ['min_max']
, return_formatted_output = False
)