added feature selection on all models but lets see if it works, only worked until DT
This commit is contained in:
parent
a420822a93
commit
3c7d8690ee
17 changed files with 2425 additions and 1202 deletions
|
|
@ -12,78 +12,154 @@ Created on Tue Mar 15 11:09:50 2022
|
|||
|
||||
@author: tanu
|
||||
"""
|
||||
parameters = [
|
||||
#cv = rskf_cv
|
||||
cv = skf_cv
|
||||
|
||||
# LogisticRegression: Feature Selelction + GridSearch CV + Pipeline
|
||||
|
||||
###############################################################################
|
||||
# Define estimator
|
||||
estimator = LogisticRegression(**rs)
|
||||
|
||||
# Define pipleline with steps
|
||||
pipe_lr = Pipeline([
|
||||
('pre', MinMaxScaler())
|
||||
, ('fs', RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
|
||||
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
|
||||
, ('clf', estimator)])
|
||||
|
||||
# Define hyperparmeter space to search for
|
||||
param_grid_lr = [
|
||||
|
||||
{'fs__min_features_to_select' : [1,2]
|
||||
# , 'fs__cv': [rskf_cv]
|
||||
},
|
||||
|
||||
{
|
||||
'clf': [LogisticRegression(**rs)],
|
||||
#'clf__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
# 'clf': [LogisticRegression(**rs)],
|
||||
'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__penalty': ['none', 'l1', 'l2', 'elasticnet'],
|
||||
'clf__max_iter': list(range(100,800,100)),
|
||||
'clf__solver': ['saga']
|
||||
},
|
||||
{
|
||||
'clf': [LogisticRegression(**rs)],
|
||||
#'clf__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
# 'clf': [LogisticRegression(**rs)],
|
||||
'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__penalty': ['l2', 'none'],
|
||||
'clf__max_iter': list(range(100,800,100)),
|
||||
'clf__solver': ['newton-cg', 'lbfgs', 'sag']
|
||||
},
|
||||
{
|
||||
'clf': [LogisticRegression(**rs)],
|
||||
#'clf__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
# 'clf': [LogisticRegression(**rs)],
|
||||
'clf__C': np.logspace(0, 4, 10),
|
||||
'clf__penalty': ['l1', 'l2'],
|
||||
'clf__max_iter': list(range(100,800,100)),
|
||||
'clf__solver': ['liblinear']
|
||||
}
|
||||
|
||||
]
|
||||
]
|
||||
|
||||
# Create pipeline
|
||||
pipeline = Pipeline([
|
||||
('pre', MinMaxScaler()),
|
||||
('clf', ClfSwitcher()),
|
||||
])
|
||||
# Define GridSearch CV
|
||||
gscv_fs = GridSearchCV(pipe_lr
|
||||
, param_grid_lr
|
||||
, cv = rskf_cv
|
||||
, scoring = mcc_score_fn
|
||||
, refit = 'mcc'
|
||||
, verbose = 1
|
||||
, return_train_score = True
|
||||
, **njobs)
|
||||
###############################################################################
|
||||
#------------------------------
|
||||
# Fit gscv containing pipeline
|
||||
#------------------------------
|
||||
gscv_fs.fit(X, y)
|
||||
|
||||
# Grid search i.e hyperparameter tuning and refitting on mcc
|
||||
gscv_lr = GridSearchCV(pipeline
|
||||
, parameters
|
||||
#, scoring = 'f1', refit = 'f1'
|
||||
, scoring = mcc_score_fn, refit = 'mcc'
|
||||
, cv = skf_cv
|
||||
, **njobs
|
||||
, return_train_score = False
|
||||
, verbose = 3)
|
||||
#Fitting 10 folds for each of 4 candidates, totalling 80 fits
|
||||
# QUESTION: HOW??
|
||||
gscv_fs.best_params_
|
||||
gscv_fs.best_score_
|
||||
|
||||
# Fit
|
||||
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_
|
||||
# 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)
|
||||
round(gscv_fs.cv_results_['mean_test_mcc'].max(),2)
|
||||
|
||||
print('Best model:\n', gscv_lr_fit_be_mod)
|
||||
print('Best models score:\n', gscv_lr_fit.best_score_, ':' , round(gscv_lr_fit.best_score_, 2))
|
||||
# Training results
|
||||
gscv_tr_resD = gscv_fs.cv_results_
|
||||
mod_refit_param = gscv_fs.refit
|
||||
|
||||
#print('\nMean test score from fit results:', round(mean(gscv_lr_fit_be_res['mean_test_mcc']),2))
|
||||
print('\nMean test score from fit results:', round(np.nanmean(gscv_lr_fit_be_res['mean_test_mcc']),2))
|
||||
# sanity check
|
||||
if train_bscore == round(gscv_tr_resD['mean_test_mcc'].max(),2):
|
||||
print('\nVerified training score (MCC):', train_bscore )
|
||||
else:
|
||||
print('\nTraining score could not be internatlly verified. Please check training results dict')
|
||||
|
||||
# Blind test: REAL check!
|
||||
tp = gscv_fs.predict(X_bts)
|
||||
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, tp),2))
|
||||
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, tp),2))
|
||||
|
||||
######################################
|
||||
# Blind test
|
||||
######################################
|
||||
# See how it does on the BLIND test
|
||||
#print('\nBlind test score, mcc:', ))
|
||||
############
|
||||
# info extraction
|
||||
############
|
||||
# gives input vals??
|
||||
gscv_fs._check_n_features
|
||||
|
||||
test_predict = gscv_lr_fit.predict(X_bts)
|
||||
print(test_predict)
|
||||
print(np.array(y_bts))
|
||||
y_btsf = np.array(y_bts)
|
||||
# gives gscv params used
|
||||
gscv_fs._get_param_names()
|
||||
|
||||
print(accuracy_score(y_bts, test_predict))
|
||||
print(matthews_corrcoef(y_bts, test_predict))
|
||||
# gives ??
|
||||
gscv_fs.best_estimator_
|
||||
gscv_fs.best_params_ # gives best estimator params as a dict
|
||||
gscv_fs.best_estimator_._final_estimator # similar to above, doesn't contain max_iter
|
||||
gscv_fs.best_estimator_.named_steps['fs'].get_support()
|
||||
gscv_fs.best_estimator_.named_steps['fs'].ranking_ # array of ranks for the features
|
||||
|
||||
gscv_fs.best_estimator_.named_steps['fs'].grid_scores_.mean()
|
||||
gscv_fs.best_estimator_.named_steps['fs'].grid_scores_.max()
|
||||
#gscv_fs.best_estimator_.named_steps['fs'].grid_scores_
|
||||
|
||||
###############################################################################
|
||||
#============
|
||||
# FS results
|
||||
#============
|
||||
# Now get the features out
|
||||
all_features = gscv_fs.feature_names_in_
|
||||
n_all_features = gscv_fs.n_features_in_
|
||||
#all_features = gsfit.feature_names_in_
|
||||
|
||||
sel_features = X.columns[gscv_fs.best_estimator_.named_steps['fs'].get_support()]
|
||||
n_sf = gscv_fs.best_estimator_.named_steps['fs'].n_features_
|
||||
|
||||
# get model name
|
||||
model_name = gscv_fs.best_estimator_.named_steps['clf']
|
||||
b_model_params = gscv_fs.best_params_
|
||||
|
||||
print('\n========================================'
|
||||
, '\nRunning model:'
|
||||
, '\nModel name:', model_name
|
||||
, '\n==============================================='
|
||||
, '\nRunning feature selection with RFECV for model'
|
||||
, '\nTotal no. of features in model:', len(all_features)
|
||||
, '\nThese are:\n', all_features, '\n\n'
|
||||
, '\nNo of features for best model: ', n_sf
|
||||
, '\nThese are:', sel_features, '\n\n'
|
||||
, '\nBest Model hyperparams:', b_model_params
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
############################## OUTPUT #########################################
|
||||
###############################################################################
|
||||
#=========================
|
||||
# Blind test: BTS results
|
||||
#=========================
|
||||
# Build the final results with all scores for a feature selected model
|
||||
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))
|
||||
|
||||
# create a dict with all scores
|
||||
lr_bts_dict = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
||||
lr_btsD = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
||||
'bts_fscore':None
|
||||
, 'bts_mcc':None
|
||||
, 'bts_precision':None
|
||||
|
|
@ -91,46 +167,47 @@ lr_bts_dict = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
|||
, 'bts_accuracy':None
|
||||
, 'bts_roc_auc':None
|
||||
, 'bts_jaccard':None }
|
||||
lr_bts_dict
|
||||
lr_bts_dict['bts_fscore'] = round(f1_score(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_mcc'] = round(matthews_corrcoef(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_precision'] = round(precision_score(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_recall'] = round(recall_score(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_accuracy'] = round(accuracy_score(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_roc_auc'] = round(roc_auc_score(y_bts, test_predict),2)
|
||||
lr_bts_dict['bts_jaccard'] = round(jaccard_score(y_bts, test_predict),2)
|
||||
lr_bts_dict
|
||||
lr_btsD
|
||||
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)
|
||||
lr_btsD['bts_roc_auc'] = round(roc_auc_score(y_bts, bts_predict),2)
|
||||
lr_btsD['bts_jaccard'] = round(jaccard_score(y_bts, bts_predict),2)
|
||||
lr_btsD
|
||||
|
||||
# Create a df from dict with all scores
|
||||
lr_bts_df = pd.DataFrame.from_dict(lr_bts_dict,orient = 'index')
|
||||
lr_bts_df.columns = ['Logistic_Regression']
|
||||
print(lr_bts_df)
|
||||
#===========================
|
||||
# Add FS related model info
|
||||
#===========================
|
||||
output_modelD = {'model_name': model_name
|
||||
, 'model_refit_param': mod_refit_param
|
||||
, 'Best_model_params': b_model_params
|
||||
, 'n_all_features': n_all_features
|
||||
, 'fs_method': gscv_fs.best_estimator_.named_steps['fs'] # FIXME: doesn't tell you which it has chosen
|
||||
, 'fs_res_array': gscv_fs.best_estimator_.named_steps['fs'].get_support()
|
||||
, '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}
|
||||
output_modelD
|
||||
|
||||
# d2 = {'best_model_params': lis(gscv_lr_fit_be_mod.items() )}
|
||||
# d2
|
||||
# def Merge(dict1, dict2):
|
||||
# res = {**dict1, **dict2}
|
||||
# return res
|
||||
# d3 = Merge(d2, lr_bts_dict)
|
||||
# d3
|
||||
#========================================
|
||||
# Update output_modelD with bts_results
|
||||
#========================================
|
||||
output_modelD.update(lr_btsD)
|
||||
output_modelD
|
||||
|
||||
# Create df with best model params
|
||||
model_params = pd.Series(['best_model_params', list(gscv_lr_fit_be_mod.items() )])
|
||||
model_params_df = model_params.to_frame()
|
||||
model_params_df
|
||||
model_params_df.columns = ['Logistic_Regression']
|
||||
model_params_df.columns
|
||||
#========================================
|
||||
# Write final output file
|
||||
# https://stackoverflow.com/questions/19201290/how-to-save-a-dictionary-to-a-file
|
||||
#========================================
|
||||
# output final dict as a json
|
||||
# outFile = 'LR_FS.json'
|
||||
# with open(outFile, 'w') as f:
|
||||
# json.dump(output_modelD, f)
|
||||
# #
|
||||
# with open(file, 'r') as f:
|
||||
# data = json.load(f)
|
||||
|
||||
# Combine the df of scores and the best model params
|
||||
lr_bts_df.columns
|
||||
lr_output = pd.concat([model_params_df, lr_bts_df], axis = 0)
|
||||
lr_output
|
||||
|
||||
# Format the combined df
|
||||
# Drop the best_model_params row from lr_output
|
||||
lr_df = lr_output.drop([0], axis = 0)
|
||||
lr_df
|
||||
|
||||
#FIXME: tidy the index of the formatted df
|
||||
|
||||
###############################################################################
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue