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

46
scripts/ml/ml_functions/MultClfs.py
View file

@ -92,10 +92,10 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
, 'roc_auc' : make_scorer(roc_auc_score)
, 'jcc' : make_scorer(jaccard_score)
})
# for sel_cv INSIDE FUNCTION CALL NOW
#skf_cv = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None)
# , shuffle = True,**rs)
# , shuffle = True, **rs)
#rskf_cv = RepeatedStratifiedKFold(n_splits = 10
# , n_repeats = 3
@ -149,25 +149,26 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline
def MultModelsCl(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']
def MultModelsCl(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']
, 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
@ -357,10 +358,9 @@ def MultModelsCl(input_df, target
y_pred = cross_val_predict(model_pipeline
, input_df
, target
#, commented out thing,
, cv=sel_cv
, **njobs
)
, cv = sel_cv
#, groups = group
, **njobs)
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()