137 lines
No EOL
4.9 KiB
Python
137 lines
No EOL
4.9 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed May 18 06:03:24 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#%% RandomForest + hyperparam: BaseEstimator: ClfSwitcher()
|
|
class ClfSwitcher(BaseEstimator):
|
|
def __init__(
|
|
self,
|
|
estimator = SGDClassifier(),
|
|
):
|
|
"""
|
|
A Custom BaseEstimator that can switch between classifiers.
|
|
:param estimator: sklearn object - The classifier
|
|
"""
|
|
self.estimator = estimator
|
|
|
|
def fit(self, X, y=None, **kwargs):
|
|
self.estimator.fit(X, y)
|
|
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 = [
|
|
{
|
|
'clf__estimator': [RandomForestClassifier(**rs
|
|
, **njobs
|
|
, bootstrap = True
|
|
, oob_score = True)],
|
|
'clf__estimator__max_depth': [4, 6, 8, 10, 12, 16, 20, None]
|
|
, 'clf__estimator__class_weight':['balanced','balanced_subsample']
|
|
, 'clf__estimator__n_estimators': [10, 25, 50, 100]
|
|
, 'clf__estimator__criterion': ['gini', 'entropy']#, 'log_loss']
|
|
#, 'clf__estimator__max_features': ['auto', 'sqrt']
|
|
, 'clf__estimator__min_samples_leaf': [1, 2, 3, 4, 5, 10]
|
|
, 'clf__estimator__min_samples_split': [2, 5, 15, 20]
|
|
}
|
|
|
|
# {
|
|
# 'clf__estimator': [RandomForestClassifier(**rs
|
|
# , **njobs
|
|
# , bootstrap = True
|
|
# , oob_score = True)],
|
|
# 'clf__estimator__max_depth': [ 6, 8, 10 ]
|
|
# , 'clf__estimator__class_weight':['balanced_subsample']
|
|
# , 'clf__estimator__n_estimators': [10]
|
|
# , 'clf__estimator__criterion': ['entropy']
|
|
# #, 'clf__estimator__max_features': ['auto', 'sqrt']
|
|
# , 'clf__estimator__min_samples_leaf': [2, 8]
|
|
# , 'clf__estimator__min_samples_split': [20]
|
|
# }
|
|
|
|
]
|
|
|
|
# Create pipeline
|
|
pipeline = Pipeline([
|
|
('pre', MinMaxScaler()),
|
|
('clf', ClfSwitcher()),
|
|
])
|
|
|
|
# Grid search i.e hyperparameter tuning and refitting on mcc
|
|
gscv_rf = GridSearchCV(pipeline
|
|
, parameters
|
|
#, scoring = 'f1', refit = 'f1'
|
|
, scoring = mcc_score_fn, refit = 'mcc'
|
|
, cv = skf_cv
|
|
, **njobs
|
|
, return_train_score = False
|
|
, verbose = 3)
|
|
|
|
# Fit
|
|
gscv_rf_fit_be = gscv_rf.fit(X, y)
|
|
|
|
print('Best model:\n', gscv_rf.best_params_)
|
|
gscv_rf_fit_be.best_params_
|
|
|
|
print('Best models score:\n', gscv_rf_fit_be.best_score_, ':' , round(gscv_rf_fit_be.best_score_, 2))
|
|
|
|
# See how it does on the BLIND test
|
|
#print('\nBlind test score, mcc:', )
|
|
|
|
test_predict = gscv_rf_fit_be.predict(X_bts)
|
|
print(test_predict)
|
|
print(np.array(y_bts))
|
|
y_btsf = np.array(y_bts)
|
|
|
|
#gscv_rf_fit_be.score(test_predict, y_btsf)
|
|
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.metrics import matthews_corrcoef
|
|
print(accuracy_score(y_btsf, test_predict))
|
|
print(matthews_corrcoef(y_btsf, test_predict))
|
|
print(matthews_corrcoef(test_predict, y_btsf))
|
|
print(accuracy_score(test_predict, y_btsf))
|
|
|
|
#check_score = f1_score(y, gscv_rf.predict(X))
|
|
#check_score # should be the same as the best score when the same metric used!
|
|
# mod_pred = gscv_rf.predict(X_test)
|
|
# fscore = f1_score(y_test, mod_pred)
|
|
# fscore
|
|
|
|
gscv_rf_be_mod = gscv_rf.best_params_
|
|
print(gscv_rf_be_mod)
|
|
gscv_rf_fit_be_res = gscv_rf_fit_be.cv_results_
|
|
#print('\nMean test score from fit results:', round(mean(gscv_rf_fit_be_res['mean_test_mcc']),2))
|
|
print('\nMean test score from fit results:', round(np.nanmean(gscv_rf_fit_be_res['mean_test_mcc']),2))
|
|
|
|
|
|
# /home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:427
|
|
# : FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3.
|
|
# To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter
|
|
# as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers.
|
|
# warn(
|
|
|
|
# ALL
|
|
# {'clf__estimator': RandomForestClassifier(class_weight='balanced_subsample', criterion='entropy',
|
|
# max_depth=6, max_features='auto', min_samples_leaf=2,
|
|
# min_samples_split=20, n_estimators=10, n_jobs=10,
|
|
# oob_score=True, random_state=42)
|
|
# , 'clf__estimator__class_weight': 'balanced_subsample'
|
|
# , 'clf__estimator__criterion': 'entropy'
|
|
# , 'clf__estimator__max_depth': 6
|
|
# , 'clf__estimator__max_features': 'auto'
|
|
# , 'clf__estimator__min_samples_leaf': 2
|
|
# , 'clf__estimator__min_samples_split': 20
|
|
# , 'clf__estimator__n_estimators': 10}
|
|
|
|
#%% |