175 lines
4.9 KiB
Python
175 lines
4.9 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Mon May 16 05:59:12 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Tue Mar 15 11:09:50 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#%% Import libraries, data, and scoring func: UQ_pnca_ML.py
|
|
rs = {'random_state': 42}
|
|
njobs = {'n_jobs': 10}
|
|
#%% Logistic Regression + hyperparam: BaseEstimator: ClfSwitcher()
|
|
|
|
class ClfSwitcher(BaseEstimator):
|
|
def __init__(
|
|
self,
|
|
estimator = SGDClassifier(),
|
|
#feature = RFECV(SGDClassifier())
|
|
):
|
|
"""
|
|
A Custom BaseEstimator that can switch between classifiers.
|
|
:param estimator: sklearn object - The classifier
|
|
"""
|
|
self.estimator = estimator
|
|
#self.feature = feature
|
|
|
|
def fit(self, X, y=None, **kwargs):
|
|
self.estimator.fit(X, y)
|
|
#self.feature.fit(X, y)
|
|
return self
|
|
|
|
# def transform(self, X, y=None):
|
|
# #self.estimator.transform(X, y)
|
|
# self.feature.transform(X)
|
|
# return self
|
|
|
|
def predict(self, X, y=None):
|
|
return self.estimator.predict(X)
|
|
|
|
def predict_proba(self, X):
|
|
return self.estimator.predict_proba(X)
|
|
|
|
def score(self, X, y):
|
|
return self.estimator.score(X, y)
|
|
|
|
#%%
|
|
parameters = [
|
|
|
|
# {'fs__feature__min_features_to_select': [1]
|
|
# , 'fs__feature__scoring': ['matthews_corrcoef']
|
|
# , 'fs__feature__cv': [skf_cv]},
|
|
|
|
{'fs__min_features_to_select': [1]
|
|
#, 'fs__scoring': ['matthews_corrcoef']
|
|
, 'fs__cv': [skf_cv]},
|
|
|
|
{
|
|
'clf__estimator': [LogisticRegression(**rs)],
|
|
#'clf__estimator__C': np.logspace(0, 4, 10),
|
|
'clf__estimator__penalty': ['none', 'l1', 'l2', 'elasticnet'],
|
|
'clf__estimator__max_iter': list(range(100,800,100)),
|
|
'clf__estimator__solver': ['saga']
|
|
}#,
|
|
# {
|
|
# 'clf__estimator': [MODEL2(**rs)],
|
|
# 'clf__estimator__C': np.logspace(0, 4, 10),
|
|
# 'clf__estimator__penalty': ['l2', 'none'],
|
|
# 'clf__estimator__max_iter': list(range(100,800,100)),
|
|
# 'clf__estimator__solver': ['newton-cg', 'lbfgs', 'sag']
|
|
# },
|
|
]
|
|
#%% Create pipeline
|
|
pipeline = Pipeline([
|
|
('pre', MinMaxScaler())
|
|
, ('fs', RFECV(LogisticRegression(**rs), scoring = 'matthews_corrcoef'))#cant be my mcc_fn
|
|
# , ('fs', ClfSwitcher())
|
|
, ('clf', ClfSwitcher())
|
|
])
|
|
|
|
#%%
|
|
# Grid search i.e hyperparameter tuning and refitting on mcc
|
|
gscv_lr = GridSearchCV(pipeline
|
|
, parameters
|
|
, scoring = mcc_score_fn, refit = 'mcc'
|
|
, cv = skf_cv
|
|
, **njobs
|
|
, return_train_score = False
|
|
, verbose = 3)
|
|
|
|
# Fit
|
|
gscv_lr.fit(X, y)
|
|
|
|
####
|
|
gscv_lr_fit = gscv_lr.fit(X, y)
|
|
gscv_lr_fit_be_mod = gscv_lr_fit.best_params_
|
|
gscv_lr_fit_be_res = gscv_lr_fit.cv_results_
|
|
|
|
#%% Grid search i.e hyperparameter tuning and refitting on mcc
|
|
|
|
param_grid2 = [
|
|
|
|
{'fs__min_features_to_select': [1]
|
|
, 'fs__cv': [skf_cv]
|
|
},
|
|
|
|
|
|
{
|
|
#'clf__estimator': [LogisticRegression(**rs)],
|
|
'clf__C': np.logspace(0, 4, 10),
|
|
'clf__penalty': ['l2'],
|
|
'clf__max_iter': list(range(100,200,100)),
|
|
#'clf__solver': ['newton-cg', 'lbfgs', 'sag']
|
|
'clf__solver': ['sag']
|
|
|
|
},
|
|
{
|
|
#'clf__estimator': [LogisticRegression(**rs)],
|
|
'clf__C': np.logspace(0, 4, 10),
|
|
'clf__penalty': ['l1', 'l2'],
|
|
'clf__max_iter': list(range(100,200,100)),
|
|
'clf__solver': ['liblinear']
|
|
}
|
|
|
|
]
|
|
# step 4: create pipeline
|
|
pipeline = Pipeline([
|
|
('pre', MinMaxScaler())
|
|
#, ('fs', model_rfecv)
|
|
, ('fs', RFECV(LogisticRegression(**rs), scoring = 'matthews_corrcoef'))
|
|
, ('clf', LogisticRegression(**rs))])
|
|
|
|
# step 5: Perform Gridsearch CV
|
|
gs_final = GridSearchCV(pipeline
|
|
, param_grid2
|
|
, cv = skf_cv
|
|
, scoring = mcc_score_fn, refit = 'mcc'
|
|
, verbose = 1
|
|
, return_train_score = False
|
|
, **njobs)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#%% Fit
|
|
mod_fs_fit = mod_fs.fit(X, y)
|
|
mod_fs_fbm = mod_fs_fit.best_params_
|
|
mod_fs_fbmr = mod_fs_fit.cv_results_
|
|
mod_fs_fbs = mod_fs_fit.best_score_
|
|
print('Best model:\n', mod_fs_fbm)
|
|
print('Best models score:\n', mod_fs_fbs, ':' , round(mod_fs_fbs, 2))
|
|
|
|
#print('\nMean test score from fit results:', round(mean(mod_fs_fbmr['mean_test_mcc']),2))
|
|
print('\nMean test score from fit results:', round(np.nanmean(mod_fs_fbmr['mean_test_mcc']),2))
|
|
|
|
###############################################################################
|
|
#%% Blind test
|
|
######################################
|
|
# Blind test
|
|
######################################
|
|
test_predict = mod_fs_fit.predict(X_bts)
|
|
print(test_predict)
|
|
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, test_predict),2))
|
|
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, test_predict),2))
|