'SMOTE': []
}
labels_values = {}
labels_values_fs = {}
for train_i, test_i in skf.split(X, y):
trn_data = prepfunctions.data_balancing(dt.iloc[train_i].copy(),
'DEATH_EVENT')
tst_data = {
'Original': dt.iloc[test_i].copy(),
'UnderSample': dt.iloc[test_i].copy(),
'OverSample': dt.iloc[test_i].copy(),
'SMOTE': dt.iloc[test_i].copy()
}
trn_data_fs = prepfunctions.mask_feature_selection(
trn_data.copy(), 'DEATH_EVENT', False,
'./Results/FeatureSelection/HFCR Feature Selection - Features')
tst_data_fs = prepfunctions.mask_feature_selection(
tst_data.copy(), 'DEATH_EVENT', False,
'./Results/FeatureSelection/HFCR Feature Selection - Features')
for category in ['Original', 'UnderSample', 'OverSample', 'SMOTE']:
# Train
trn_y_b: np.ndarray = trn_data[category].pop('DEATH_EVENT').values
trn_X_b: np.ndarray = trn_data[category].values
labels_values[category] = trn_data[category].columns.values
# Test
tst_y_b: np.ndarray = tst_data[category].pop('DEATH_EVENT').values
tst_X_b: np.ndarray = tst_data[category].values
trn_x_b_lst[category].append(trn_X_b.copy())
graphsDir = './Results/Random Forests/'
if not os.path.exists(graphsDir):
os.makedirs(graphsDir)
print('-------------------------------')
print('- -')
print('- HFCR Random Forests -')
print('- -')
print('-------------------------------')
data: pd.DataFrame = pd.read_csv(
'../Dataset/heart_failure_clinical_records_dataset.csv')
datas = prepfunctions.prepare_dataset(data, 'DEATH_EVENT', True, True)
featured_datas = prepfunctions.mask_feature_selection(
datas, 'DEATH_EVENT', False,
'./Results/FeatureSelection/HFCR Feature Selection - Features')
best_accuracies = {}
for key in datas:
for do_feature_eng in [False, True]:
if (do_feature_eng):
data = featured_datas[key]
subDir = graphsDir + 'FeatureEng/' + key + '/'
if not os.path.exists(subDir):
os.makedirs(subDir)
else:
data = datas[key]
subDir = graphsDir + key + '/'
if not os.path.exists(subDir):
os.makedirs(subDir)
if not os.path.exists(graphsDir):
os.makedirs(graphsDir)
data: pd.DataFrame = pd.read_csv('../Dataset/qsar_oral_toxicity.csv',
sep=';',
header=None)
train, test = train_test_split(data,
train_size=0.7,
stratify=data[1024].values)
testDatas = {}
datas = prepfunctions.prepare_dataset(train, 1024, False, False)
for key in datas:
testDatas[key] = test.copy()
featured_datas = prepfunctions.mask_feature_selection(
datas, 1024, True,
'./Results/FeatureSelection/QOT Feature Selection - Features')
featured_test_datas = prepfunctions.mask_feature_selection(
testDatas, 1024, True,
'./Results/FeatureSelection/QOT Feature Selection - Features')
best_accuracies = {
"Original": [0.9992055926278995, 0.9458858413639734],
"Original with FS": [0.9817286304416905, 0.9414381022979985],
"UnderSample": [1.0, 0.9347664936990363],
"UnderSample with FS": [1.0, 0.933283914010378],
"OverSample": [0.9992207792207792, 0.9432913269088213],
"OverSample with FS": [0.9992207792207792, 0.9429206819866568],
"SMOTE": [0.9993939393939394, 0.9403261675315048],
"SMOTE with FS": [0.9993939393939394, 0.9425500370644923]
}
print('-------------------------------')
print('- -')
print('- HFCR Random Forests -')
print('- -')
print('-------------------------------')
data: pd.DataFrame = pd.read_csv('../../Dataset/heart_failure_clinical_records_dataset.csv')
datas = prepfunctions.prepare_dataset(data.copy(), 'DEATH_EVENT', False, False)
datas_outliers = prepfunctions.prepare_dataset(data.copy(), 'DEATH_EVENT', False, True)
datas_outliers_scaling = prepfunctions.prepare_dataset(data.copy(), 'DEATH_EVENT', True, True)
datas_outliers_featureselection = prepfunctions.mask_feature_selection(datas_outliers.copy(), 'DEATH_EVENT', False, './Results/FeatureSelection/HFCR Feature Selection - Features')
datas_outliers_scaling_featureselection = prepfunctions.mask_feature_selection(datas_outliers_scaling.copy(), 'DEATH_EVENT', False, './Results/FeatureSelection/HFCR Feature Selection - Features')
datas_scaling = prepfunctions.prepare_dataset(data.copy(), 'DEATH_EVENT', True, False)
datas_scaling_featureselection = prepfunctions.mask_feature_selection(datas_scaling.copy(), 'DEATH_EVENT', False, './Results/FeatureSelection/HFCR Feature Selection - Features')
datas_featureselection = prepfunctions.mask_feature_selection(datas.copy(), 'DEATH_EVENT', False, './Results/FeatureSelection/HFCR Feature Selection - Features')
all_datas = [datas, datas_outliers, datas_scaling, datas_featureselection, datas_outliers_scaling, datas_outliers_featureselection, datas_outliers_scaling_featureselection]
all_datas_names = ['', ' - No Outliers', ' - Scaling', ' - Feature Selection', ' - No Outliers & Scaling', ' - No Outliers & Feature Selection', ' - No Outliers, Scaling & Feature Selection']
provisorio_data_scaling = ' - Scaling & Feature Selection'
accuracies = {}
for key in datas:
last_name = 'None'