tanu/ML_AI_training
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

added and ran hyperparam script for all different classifiers, but couldn't successfully run the feature selection and hyperparam together

Browse source
This commit is contained in:
Tanushree Tunstall 2022-05-20 08:09:24 +01:00
parent 74af5ef890
commit 37bda41f44
18 changed files with 131 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

28
uq_ml_models/UQ_XGB.py
View file

@ -5,7 +5,18 @@ Created on Wed May 18 06:03:24 2022
@author: tanu
"""
#%% RandomForest + hyperparam: BaseEstimator: ClfSwitcher()
#%%
#https://www.datatechnotes.com/2019/07/classification-example-with.html
# XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
# colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
# max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
# n_estimators=100, n_jobs=1, nthread=None,
# objective='multi:softprob', random_state=0, reg_alpha=0,
# reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,
# subsample=1, verbosity=1)
#%% XGBoost + hyperparam: BaseEstimator: ClfSwitcher()
class ClfSwitcher(BaseEstimator):
def __init__(
self,
@ -32,12 +43,11 @@ class ClfSwitcher(BaseEstimator):
parameters = [
{
'clf__estimator': [XGBClassifier(**rs
, **njobs]
'clf__estimator': [XGBClassifier(**rs , **njobs, verbose = 3)]
, 'clf__estimator__learning_rate': [0.01, 0.05, 0.1, 0.2]
, 'clf__estimator__max_depth': [4, 6, 8, 10, 12, 16, 20]
, 'clf__estimator__min_samples_leaf': [4, 8, 12, 16, 20]
, 'clf__estimator__max_features': ['auto', 'sqrt']
#, 'clf__estimator__min_samples_leaf': [4, 8, 12, 16, 20]
#, 'clf__estimator__max_features': ['auto', 'sqrt']
}
]
@ -66,7 +76,7 @@ gscv_xgb_fit_be_res = gscv_xgb_fit.cv_results_
print('Best model:\n', gscv_xgb_fit_be_mod)
print('Best models score:\n', gscv_xgb_fit.best_score_, ':' , round(gscv_xgb_fit.best_score_, 2))
print('\nMean test score from fit results:', round(mean(gscv_xgb_fit_be_re['mean_test_mcc']),2))
print('\nMean test score from fit results:', round(mean(gscv_xgb_fit_be_res['mean_test_mcc']),2))
print('\nMean test score from fit results:', round(np.nanmean(gscv_xgb_fit_be_res['mean_test_mcc']),2))
######################################
@ -104,17 +114,15 @@ xgb_bts_dict['bts_jaccard'] = round(jaccard_score(y_bts, test_predict),2)
xgb_bts_dict
# Create a df from dict with all scores
pd.DataFrame.from_dict(xgb_bts_dict, orient = 'index', columns = 'best_model')
xgb_bts_df = pd.DataFrame.from_dict(xgb_bts_dict,orient = 'index')
xgb_bts_df.columns = ['Logistic_Regression']
xgb_bts_df.columns = ['XGBoost']
print(xgb_bts_df)
# Create df with best model params
model_params = pd.Series(['best_model_params', list(gscv_xgb_fit_be_mod.items() )])
model_params_df = model_params.to_frame()
model_params_df
model_params_df.columns = ['Logistic_Regression']
model_params_df.columns = ['XGBoost']
model_params_df.columns
# Combine the df of scores and the best model params