modifying output dict for printing in UQ_FS_eg.py
This commit is contained in:
parent
3c7d8690ee
commit
6db5046302
1 changed files with 62 additions and 34 deletions
96
UQ_FS_eg.py
96
UQ_FS_eg.py
|
|
@ -60,43 +60,51 @@ fs_bmod = clf2.best_estimator_
|
|||
print('\nbest model with feature selection:', fs_bmod)
|
||||
|
||||
#########################################################
|
||||
#cv = rskf_cv
|
||||
cv = skf_cv
|
||||
|
||||
# my data: Feature Selelction + GridSearch CV + Pipeline
|
||||
pipe = Pipeline([
|
||||
('pre', MinMaxScaler())
|
||||
, ('fs', RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
|
||||
# , ('fs', RFECV(LogisticRegression(**rs), cv = cv, scoring = 'matthews_corrcoef'))
|
||||
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
|
||||
|
||||
, ('clf', LogisticRegression(**rs))])
|
||||
|
||||
search_space = [{'fs__min_features_to_select': [1,2]
|
||||
# ,'fs__cv': [rskf_cv]
|
||||
},
|
||||
{
|
||||
#'clf': [LogisticRegression()],
|
||||
#'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__C': [1],
|
||||
'clf__max_iter': [100],
|
||||
'clf__penalty': ['l1', 'l2'],
|
||||
'clf__solver': ['saga']
|
||||
},
|
||||
search_space = [
|
||||
{ 'fs__estimator': [LogisticRegression(**rs)]
|
||||
, 'fs__min_features_to_select': [0,1]
|
||||
,'fs__cv': [rskf_cv]
|
||||
},
|
||||
{
|
||||
#'clf': [LogisticRegression()],
|
||||
#'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__C': [1],
|
||||
'clf__max_iter': [100],
|
||||
'clf__penalty': ['l1', 'l2'],
|
||||
'clf__solver': ['saga']
|
||||
},
|
||||
|
||||
{
|
||||
#'clf': [LogisticRegression()],
|
||||
#'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__C': [2, 2.5],
|
||||
'clf__max_iter': [100],
|
||||
'clf__penalty': ['l1', 'l2'],
|
||||
'clf__solver': ['saga']
|
||||
},
|
||||
#{'clf': [RandomForestclf(n_estimators=100)],
|
||||
# 'clf__max_depth': [5, 10, None]},
|
||||
#{'clf': [KNeighborsclf()],
|
||||
# 'clf__n_neighbors': [3, 7, 11],
|
||||
# 'clf__weights': ['uniform', 'distance']
|
||||
#}
|
||||
{
|
||||
#'clf': [LogisticRegression()],
|
||||
#'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__C': [2, 2.5],
|
||||
'clf__max_iter': [100],
|
||||
'clf__penalty': ['l1', 'l2'],
|
||||
'clf__solver': ['saga']
|
||||
},
|
||||
|
||||
#{'clf': [RandomForestclf(n_estimators=100)],
|
||||
# 'clf__max_depth': [5, 10, None]},
|
||||
#{'clf': [KNeighborsclf()],
|
||||
# 'clf__n_neighbors': [3, 7, 11],
|
||||
# 'clf__weights': ['uniform', 'distance']
|
||||
#}
|
||||
]
|
||||
|
||||
gscv_fs = GridSearchCV(pipe
|
||||
, search_space
|
||||
, cv = rskf_cv
|
||||
, cv = cv
|
||||
, scoring = mcc_score_fn
|
||||
, refit = 'mcc'
|
||||
, verbose = 1
|
||||
|
|
@ -111,14 +119,21 @@ gscv_fs.best_score_
|
|||
# Training best score corresponds to the max of the mean_test<score>
|
||||
train_bscore = round(gscv_fs.best_score_, 2); train_bscore
|
||||
print('\nTraining best score (MCC):', train_bscore)
|
||||
gscv_fs.cv_results_['mean_test_mcc']
|
||||
round(gscv_fs.cv_results_['mean_test_mcc'].max(),2)
|
||||
round(np.nanmax(gscv_fs.cv_results_['mean_test_mcc']),2)
|
||||
|
||||
check_train_score = [round(gscv_fs.cv_results_['mean_test_mcc'].max(),2)
|
||||
, round(np.nanmax(gscv_fs.cv_results_['mean_test_mcc']),2)]
|
||||
|
||||
check_train_score = np.nanmax(check_train_score)
|
||||
|
||||
# Training results
|
||||
gscv_tr_resD = gscv_fs.cv_results_
|
||||
mod_refit_param = gscv_fs.refit
|
||||
|
||||
# sanity check
|
||||
if train_bscore == round(gscv_tr_resD['mean_test_mcc'].max(),2):
|
||||
if train_bscore == check_train_score:
|
||||
print('\nVerified training score (MCC):', train_bscore )
|
||||
else:
|
||||
print('\nTraining score could not be internatlly verified. Please check training results dict')
|
||||
|
|
@ -186,19 +201,27 @@ print('\n========================================'
|
|||
bts_predict = gscv_fs.predict(X_bts)
|
||||
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, bts_predict),2))
|
||||
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, bts_predict),2))
|
||||
bts_mcc_score = round(matthews_corrcoef(y_bts, bts_predict),2)
|
||||
|
||||
# Diff b/w train and bts test scores
|
||||
train_test_diff = train_bscore - bts_mcc
|
||||
print('\nDiff b/w train and blind test score (MCC):', train_test_diff)
|
||||
|
||||
|
||||
# create a dict with all scores
|
||||
lr_btsD = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
||||
'bts_fscore':None
|
||||
, 'bts_mcc':None
|
||||
#'bts_mcc':None
|
||||
'bts_fscore':None
|
||||
, 'bts_precision':None
|
||||
, 'bts_recall':None
|
||||
, 'bts_accuracy':None
|
||||
, 'bts_roc_auc':None
|
||||
, 'bts_jaccard':None }
|
||||
, 'bts_jaccard':None}
|
||||
|
||||
|
||||
lr_btsD
|
||||
#lr_btsD['bts_mcc'] = bts_mcc_score
|
||||
lr_btsD['bts_fscore'] = round(f1_score(y_bts, bts_predict),2)
|
||||
lr_btsD['bts_mcc'] = round(matthews_corrcoef(y_bts, bts_predict),2)
|
||||
lr_btsD['bts_precision'] = round(precision_score(y_bts, bts_predict),2)
|
||||
lr_btsD['bts_recall'] = round(recall_score(y_bts, bts_predict),2)
|
||||
lr_btsD['bts_accuracy'] = round(accuracy_score(y_bts, bts_predict),2)
|
||||
|
|
@ -218,8 +241,7 @@ output_modelD = {'model_name': model_name
|
|||
, 'fs_res_array_rank': gscv_fs.best_estimator_.named_steps['fs'].ranking_
|
||||
, 'all_feature_names': all_features
|
||||
, 'n_sel_features': n_sf
|
||||
, 'sel_features_names': sel_features
|
||||
, 'train_score (MCC)': train_bscore}
|
||||
, 'sel_features_names': sel_features}
|
||||
output_modelD
|
||||
|
||||
#========================================
|
||||
|
|
@ -228,6 +250,12 @@ output_modelD
|
|||
output_modelD.update(lr_btsD)
|
||||
output_modelD
|
||||
|
||||
output_modelD['train_score (MCC)'] = train_bscore
|
||||
output_modelD['bts_mcc'] = bts_mcc_score
|
||||
output_modelD['train_bts_diff'] = train_test_diff
|
||||
output_modelD
|
||||
|
||||
|
||||
#========================================
|
||||
# Write final output file
|
||||
# https://stackoverflow.com/questions/19201290/how-to-save-a-dictionary-to-a-file
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue