added Mult_clfs_logo and Mult_clsf.py with consistency
This commit is contained in:
parent
06f2ce97b6
commit
de5c1270be
5 changed files with 201 additions and 115 deletions
|
|
@ -74,10 +74,13 @@ from sklearn.impute import KNNImputer as KNN
|
|||
import json
|
||||
import argparse
|
||||
import re
|
||||
import itertools
|
||||
from sklearn.model_selection import LeaveOneGroupOut
|
||||
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
|
||||
#rs = {'random_state': 42}
|
||||
#njobs = {'n_jobs': os.cpu_count() } # the number of jobs should equal the number of CPU cores
|
||||
|
||||
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
|
|
@ -88,13 +91,13 @@ scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
|||
, 'jcc' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
#skf_cv = StratifiedKFold(n_splits = 10
|
||||
# #, shuffle = False, random_state= None)
|
||||
# , shuffle = True,**rs)
|
||||
|
||||
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
||||
, n_repeats = 3
|
||||
, **rs)
|
||||
#rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
||||
# , n_repeats = 3
|
||||
# , **rs)
|
||||
|
||||
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
||||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
|
|
@ -137,6 +140,7 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
|
|||
, 'bts_jcc' : 'JCC'
|
||||
}
|
||||
|
||||
#gene_group = 'gene_name'
|
||||
#%%############################################################################
|
||||
############################
|
||||
# MultModelsCl()
|
||||
|
|
@ -145,17 +149,23 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
|
|||
# Multiple Classification - Model Pipeline
|
||||
def MultModelsCl(input_df, target
|
||||
, sel_cv
|
||||
, blind_test_df
|
||||
, blind_test_target
|
||||
, tts_split_type
|
||||
|
||||
, resampling_type = 'none' # default
|
||||
, 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']
|
||||
, var_type = ['numerical', 'categorical','mixed']
|
||||
, scale_numeric = ['min_max', 'std', 'min_max_neg', 'none']
|
||||
|
||||
, run_blind_test = True
|
||||
, return_formatted_output = 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
|
||||
):
|
||||
|
||||
'''
|
||||
@ param input_df: input features
|
||||
|
|
@ -173,7 +183,25 @@ def MultModelsCl(input_df, target
|
|||
returns
|
||||
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
|
||||
'''
|
||||
|
||||
#%% 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:
|
||||
# sel_cv = skf_cv
|
||||
# else:
|
||||
# sel_cv = logo
|
||||
#======================================================
|
||||
# Determine categorical and numerical features
|
||||
#======================================================
|
||||
|
|
@ -196,8 +224,9 @@ def MultModelsCl(input_df, target
|
|||
# # t = [('num', MinMaxScaler(), numerical_ix)
|
||||
# # , ('cat', OneHotEncoder(), categorical_ix) ]
|
||||
|
||||
# if var_type == 'mixed':
|
||||
# t = [('cat', OneHotEncoder(), categorical_ix) ]
|
||||
# col_transform = ColumnTransformer(transformers = t
|
||||
# , remainder='passthrough')
|
||||
|
||||
if type(var_type) == list:
|
||||
var_type = str(var_type[0])
|
||||
else:
|
||||
|
|
@ -229,37 +258,37 @@ def MultModelsCl(input_df, target
|
|||
#======================================================
|
||||
# Specify multiple Classification Models
|
||||
#======================================================
|
||||
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) )
|
||||
#
|
||||
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) )
|
||||
|
||||
]
|
||||
|
||||
mm_skf_scoresD = {}
|
||||
|
|
@ -289,10 +318,11 @@ def MultModelsCl(input_df, target
|
|||
|
||||
|
||||
print('\nRunning model pipeline:', model_pipeline)
|
||||
skf_cv_modD = cross_validate(model_pipeline
|
||||
cv_modD = cross_validate(model_pipeline
|
||||
, input_df
|
||||
, target
|
||||
, cv = sel_cv
|
||||
#, groups = group
|
||||
, scoring = scoring_fn
|
||||
, return_train_score = True)
|
||||
#==============================
|
||||
|
|
@ -300,7 +330,7 @@ def MultModelsCl(input_df, target
|
|||
#==============================
|
||||
mm_skf_scoresD[model_name] = {}
|
||||
|
||||
for key, value in skf_cv_modD.items():
|
||||
for key, value in cv_modD.items():
|
||||
print('\nkey:', key, '\nvalue:', value)
|
||||
print('\nmean value:', np.mean(value))
|
||||
mm_skf_scoresD[model_name][key] = round(np.mean(value),2)
|
||||
|
|
@ -308,7 +338,7 @@ def MultModelsCl(input_df, target
|
|||
# ADD more info: meta data related to input df
|
||||
mm_skf_scoresD[model_name]['resampling'] = resampling_type
|
||||
mm_skf_scoresD[model_name]['n_training_size'] = len(input_df)
|
||||
#mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(Counter(target)[0]/Counter(target)[1], 2)
|
||||
mm_skf_scoresD[model_name]['n_trainingY_ratio'] = round(Counter(target)[0]/Counter(target)[1], 2)
|
||||
mm_skf_scoresD[model_name]['n_features'] = len(input_df.columns)
|
||||
mm_skf_scoresD[model_name]['tts_split'] = tts_split_type
|
||||
|
||||
|
|
@ -321,7 +351,12 @@ def MultModelsCl(input_df, target
|
|||
cmD = {}
|
||||
|
||||
# Calculate cm
|
||||
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = sel_cv, **njobs)
|
||||
y_pred = cross_val_predict(model_pipeline
|
||||
, input_df
|
||||
, target
|
||||
, 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()
|
||||
|
||||
|
|
@ -357,7 +392,7 @@ def MultModelsCl(input_df, target
|
|||
# Build bts numbers dict
|
||||
btD = {'n_blindY_neg' : Counter(blind_test_target)[0]
|
||||
, 'n_blindY_pos' : Counter(blind_test_target)[1]
|
||||
#, 'n_testY_ratio' : round(Counter(blind_test_target)[0]/Counter(blind_test_target)[1], 2)
|
||||
, 'n_testY_ratio' : round(Counter(blind_test_target)[0]/Counter(blind_test_target)[1], 2)
|
||||
, 'n_test_size' : len(blind_test_df) }
|
||||
|
||||
# Update cmD+tnD dicts with btD
|
||||
|
|
@ -371,9 +406,9 @@ def MultModelsCl(input_df, target
|
|||
bts_predict = model_pipeline.predict(blind_test_df)
|
||||
|
||||
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
|
||||
print('\nMCC on Blind test:' , bts_mcc_score)
|
||||
print('\nMCC on Blind test:' , bts_mcc_score)
|
||||
#print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
|
||||
print('\nMCC on Training:' , mm_skf_scoresD[model_name]['test_mcc'] )
|
||||
print('\nMCC on Training:' , mm_skf_scoresD[model_name]['test_mcc'] )
|
||||
|
||||
mm_skf_scoresD[model_name]['bts_mcc'] = bts_mcc_score
|
||||
mm_skf_scoresD[model_name]['bts_fscore'] = round(f1_score(blind_test_target, bts_predict),2)
|
||||
|
|
@ -384,7 +419,7 @@ def MultModelsCl(input_df, target
|
|||
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
|
||||
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
|
||||
|
||||
|
||||
|
||||
#return(mm_skf_scoresD)
|
||||
#============================
|
||||
# Process the dict to have WF
|
||||
|
|
@ -526,7 +561,8 @@ def ProcessMultModelsCl(inputD = {}, blind_test_data = True):
|
|||
sys.exit('\nFAIL: Could not merge metadata with CV and BT dfs')
|
||||
|
||||
else:
|
||||
print('\nConcatenting dfs not possible [WF],check numbers ')
|
||||
# print('\nConcatenting dfs not possible [WF],check numbers ')
|
||||
print('\nOnly combining CV and metadata')
|
||||
|
||||
#-------------------------------------
|
||||
# Combine WF+Metadata: Final output
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue