score_train = grid.score(X_train, y_train)
score_test = grid.score(X_test, y_test)
best_p = grid.best_params_
bp = pd.DataFrame(best_p, index=[i])
bp['accuracy_train'] = score_train
bp['accuracy_test'] = score_test
bp['random_state_k_fold'] = i*42
df = df.append(bp, ignore_index=True)
#create folder and save
save_output.function_save_output(df, name_clf)
#Designate distributions to sample hyperparameters from
C_range = np.power(2, np.arange(-10, 8, dtype=float))
n_features_to_test = [0.85, 0.9, 0.95]
clf = TransformedTargetRegressor(regressor=SVR(kernel='linear'),
transformer=MinMaxScaler())
#SVM
steps = [('scaler', StandardScaler()), ('red_dim', PCA()), ('clf', clf)]
pipeline = Pipeline(steps)
parameteres = [{
'scaler': [StandardScaler()],
'red_dim': [PCA(random_state=42)],
'red_dim__n_components': list(n_features_to_test),
'clf__regressor__C': list(C_range)
}, {
'scaler': [StandardScaler()],
'red_dim': [None],
'clf__regressor__C': list(C_range)
}]
results = GSCV.function_GSCV(data_train, labels_train, data_test, labels_test,
pipeline, parameteres)
#create folder and save
save_output.function_save_output(results, name_clf)
#implmentation of steps
scaler = scaler_
#pca = PCA(n_components=n_comp_pca, whiten=whiten_, random_state=random_state_PCA)
svm = SVC(kernel='rbf', probability=True, random_state=random_state_clf)
steps = [('scaler', scaler), ('clf', svm)]
pipeline = Pipeline(steps)
df_score_value, df_mean_std = score_cv_3_classes.function_score_cv(
public_data, public_labels, pipeline, RS_outer_KF)
df_tot = pd.concat([df_best_params, df_score_value, df_mean_std],
axis=1,
ignore_index=False)
return df_tot
for j in range(1, 2):
df_MMS = create_score_csv_default_HP(MinMaxScaler(), 2 * j)
save_output.function_save_output(df_MMS, 'MMS', name, 2 * j)
df_STDS = create_score_csv_default_HP(StandardScaler(), 2 * j)
save_output.function_save_output(df_STDS, 'STDS', name, 2 * j)
df_RBT = create_score_csv_default_HP(RobustScaler(), 2 * j)
save_output.function_save_output(df_RBT, 'RBT', name, 2 * j)
df_NONE = create_score_csv_default_HP(None, 2 * j)
save_output.function_save_output(df_NONE, 'NONE', name, 2 * j)
steps = [('scaler', MinMaxScaler()), ('red_dim', PCA()), ('clf', SVC(kernel='linear', probability=True, random_state=503))]
pipeline = Pipeline(steps)
#MMS
parameteres_1 = [{'scaler':[MinMaxScaler()], 'red_dim':[PCA(random_state=42)], 'red_dim__n_components':list(n_features_to_test),
'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']}]
for j in range(1,6):
results, best_estimators_dict = nested_cv.function_nested_cv(public_data, public_labels, pipeline, parameteres_1, j*2)
#create folder and save
save_output.function_save_output(results, dim_reduction, name_1, j*2)
#RBTS
parameteres_2 = [{'scaler':[RobustScaler()], 'red_dim':[PCA(random_state=42)], 'red_dim__n_components':list(n_features_to_test),
'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']}]
for j in range(1,6):
results, best_estimators_dict = nested_cv.function_nested_cv(public_data, public_labels, pipeline, parameteres_2, j*2)
#create folder and save
save_output.function_save_output(results, dim_reduction, name_2, j*2)
from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler
scalers_to_test = [StandardScaler(), RobustScaler(), MinMaxScaler()]
#Designate distributions to sample hyperparameters from
C_range = np.power(2, np.arange(-10, 9, dtype=float))
n_features_to_test = [0.85, 0.9, 0.95]
#SVM
steps = [('scaler', MinMaxScaler()), ('red_dim', PCA()), ('clf', SVC(kernel='linear', probability=True))]
pipeline = Pipeline(steps)
parameteres = [{'scaler':[MinMaxScaler()], 'red_dim':[PCA(random_state=42)], 'red_dim__n_components':list(n_features_to_test),
'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']},
{'scaler':[MinMaxScaler()], 'red_dim':[SelectPercentile(f_classif, percentile=10)],
'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']},
{'scaler':[MinMaxScaler()], 'red_dim':[SelectPercentile(mutual_info_classif, percentile=10)],
'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']},
{'scaler':[MinMaxScaler()], 'red_dim':[None], 'clf__C':list(C_range), 'clf__class_weight':[None, 'balanced']}]
for j in range(1,2):
results, best_estimators_dict = nested_cv.function_nested_cv(public_data, public_labels, pipeline, parameteres, j*2)
#create folder and save
save_output.function_save_output(results, name, j*2)
#MMS
parameteres_1 = [{
'scaler': [MinMaxScaler()],
'red_dim': [PCA(random_state=42)],
'red_dim__n_components': list(n_features_to_test),
'clf__C': list(C_range),
'clf__class_weight': [None, 'balanced']
}]
results_1 = nested_cv.function_nested_cv(public_data, public_labels, pipeline,
parameteres_1)
#create folder and save
save_output.function_save_output(results_1, dim_reduction, name_1)
#RBTS
parameteres_2 = [{
'scaler': [RobustScaler()],
'red_dim': [PCA(random_state=42)],
'red_dim__n_components': list(n_features_to_test),
'clf__C': list(C_range),
'clf__class_weight': [None, 'balanced']
}]
results_2 = nested_cv.function_nested_cv(public_data, public_labels, pipeline,
parameteres_2)
#create folder and save
