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

moved logo_skf function to del as using the MultClfs for combined data

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-28 12:24:24 +01:00
parent a6532ddfa3
commit 2c50124b1b
8 changed files with 71 additions and 1735 deletions
Download patch file Download diff file Expand all files Collapse all files

81
scripts/ml/ml_functions/MultClfs_logo_skf.py
View file

@ -77,9 +77,11 @@ import re
import itertools
from sklearn.model_selection import LeaveOneGroupOut
from sklearn.decomposition import PCA
from sklearn.naive_bayes import ComplementNB
from sklearn.dummy import DummyClassifier
#%% GLOBALS
#rs = {'random_state': 42}
#rs = {'random_state': 42} # INSIDE FUNCTION CALL NOW
#njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
@ -90,8 +92,7 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
# for sel_cv
# for sel_cv INSIDE FUNCTION CALL NOW
#skf_cv = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None)
# , shuffle = True, **rs)
@ -149,25 +150,25 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
############################
# Multiple Classification - Model Pipeline
def MultModelsCl_logo_skf(input_df
, target
, sel_cv
, tts_split_type
, resampling_type
#, group = None
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, scale_numeric = ['min_max', 'std', 'min_max_neg', 'none']
, target
, sel_cv
, tts_split_type
, resampling_type
#, group = None
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, scale_numeric = ['min_max', 'std', 'min_max_neg', 'none']
, run_blind_test = True
, blind_test_df = pd.DataFrame()
, blind_test_target = pd.Series(dtype = int)
, return_formatted_output = True
, run_blind_test = True
, blind_test_df = pd.DataFrame()
, blind_test_target = pd.Series(dtype = int)
, return_formatted_output = True
, random_state = 42
, n_jobs = os.cpu_count() # the number of jobs should equal the number of CPU cores
):
, random_state = 42
, n_jobs = os.cpu_count() # the number of jobs should equal the number of CPU cores
):
'''
@ param input_df: input features
@ -189,7 +190,15 @@ def MultModelsCl_logo_skf(input_df
#%% Func globals
rs = {'random_state': random_state}
njobs = {'n_jobs': n_jobs}
skf_cv = StratifiedKFold(n_splits = 10
#, shuffle = False, random_state= None)
, shuffle = True,**rs)
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
, n_repeats = 3
, **rs)
logo = LeaveOneGroupOut()
# select CV type:
# if group == None:
@ -252,8 +261,10 @@ def MultModelsCl_logo_skf(input_df
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
#, ('Bernoulli NB' , BernoulliNB() ) # pks Naive Bayes, CAUTION
, ('Complement NB' , ComplementNB() )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
@ -265,23 +276,23 @@ def MultModelsCl_logo_skf(input_df
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Multinomial NB' , MultinomialNB() )
, ('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) )
, 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) )
, ('Dummy Classifier' , DummyClassifier(strategy = 'most_frequent') )
]
mm_skf_scoresD = {}