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

46
UQ_LR_p1.py
View file

@ -34,12 +34,7 @@ from xgboost import XGBClassifier
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
#%% Get train-test split and scoring functions
# X_train, X_test, y_train, y_test = train_test_split(num_df_wtgt[numerical_FN]
# , num_df_wtgt['mutation_class']
# , test_size = 0.33
# , random_state = 2
# , shuffle = True
# , stratify = num_df_wtgt['mutation_class'])
y.to_frame().value_counts().plot(kind = 'bar')
blind_test_df['dst_mode'].to_frame().value_counts().plot(kind = 'bar')
@ -90,22 +85,22 @@ parameters = [
'clf__estimator__max_iter': list(range(100,800,100)),
'clf__estimator__solver': ['saga']
},
# {
# 'clf__estimator': [LogisticRegression(**rs)],
# #'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
# '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']
# },
# {
# 'clf__estimator': [LogisticRegression(**rs)],
# #'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
# 'clf__estimator__C': np.logspace(0, 4, 10),
# 'clf__estimator__penalty': ['l1', 'l2'],
# 'clf__estimator__max_iter': list(range(100,800,100)),
# 'clf__estimator__solver': ['liblinear']
# }
{
'clf__estimator': [LogisticRegression(**rs)],
#'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
'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']
},
{
'clf__estimator': [LogisticRegression(**rs)],
#'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
'clf__estimator__C': np.logspace(0, 4, 10),
'clf__estimator__penalty': ['l1', 'l2'],
'clf__estimator__max_iter': list(range(100,800,100)),
'clf__estimator__solver': ['liblinear']
}
]
@ -120,7 +115,8 @@ gscv_lr = GridSearchCV(pipeline
, parameters
#, scoring = 'f1', refit = 'f1'
, scoring = mcc_score_fn, refit = 'mcc'
, cv = skf_cv
#, cv = skf_cv
, cv = rskf_cv
, **njobs
, return_train_score = False
, verbose = 3)
@ -138,7 +134,6 @@ print('\nMean test score from fit results:', round(np.nanmean(gscv_lr_fit_be_res
###############################################################################
######################################
# Blind test
######################################
@ -186,7 +181,7 @@ print(lr_bts_df)
# d3
# Create df with best model params
model_params = pd.Series(['best_model_params', list(gscv_lr_fit_be_mod.items() )])
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']
@ -209,3 +204,4 @@ lr_df
print(confusion_matrix(y_bts, test_predict))
cm = confusion_matrix(y_bts, test_predict)