from sklearn.feature_selection import VarianceThreshold
from sklearn.feature_selection import SelectPercentile
from sklearn.feature_selection import chi2
from sklearn.svm import SVC
from sklearn.model_selection import StratifiedKFold
from sklearn.feature_selection import RFECV
graphsDir = './Results/FeatureSelection/'
if not os.path.exists(graphsDir):
os.makedirs(graphsDir)
features_file = open(graphsDir + 'HFCR Feature Selection - Features', 'w')
data: pd.DataFrame = pd.read_csv('../Dataset/heart_failure_clinical_records_dataset.csv')
datas = prepfunctions.prepare_dataset(data, 'DEATH_EVENT', False, False)
for key, value in datas.items():
print("Key: ", key)
dataframe_rec = value.copy()
subDir = graphsDir + key + '/'
if not os.path.exists(subDir):
os.makedirs(subDir)
data = dataframe_rec.copy()
y = data.pop('DEATH_EVENT')
print('Original')
labels = ['Original']
values = [data.shape[1]]
print('VarianceThreshold')
data = dataframe_rec.copy()
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import train_test_split
from datetime import datetime
graphsDir = './Results/GradientBoosting/'
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],
print('---------------------------')
print('- -')
print('- HFCR Clustering -')
print('- -')
print('---------------------------')
data: pd.DataFrame = pd.read_csv(
'../Dataset/heart_failure_clinical_records_dataset.csv')
# Original
original_data = data.copy()
original_data.pop('DEATH_EVENT')
# Scaled
data_scaled = prepfunctions.prepare_dataset(data, 'DEATH_EVENT', True,
True)['Original']
data_scaled.pop('DEATH_EVENT')
scaling_pca = [(False, False), (True, False), (False, True), (True, True)]
N_CLUSTERS = [2, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29]
EPS = [2.5, 5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100]
fig, ax = plt.subplots(2, 3, figsize=(3 * 3, 4 * 2), squeeze=False)
fig_values_1 = {}
fig_values_2 = {}
fig_values_3 = {}
fig_values_4 = {}
fig_values_5 = {}
fig_values_6 = {}
import ds_functions as ds
import os
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 + '/'
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.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'
graphsDir = './Results/Log Regression/'
if not os.path.exists(graphsDir):
os.makedirs(graphsDir)
print('--------------------------------------')
print('- -')
print('- QOT Log Regression - Treated -')
print('- -')
print('--------------------------------------')
RANDOM_STATE = 42
data: pd.DataFrame = pd.read_csv('../Dataset/qsar_oral_toxicity.csv',
sep=';',
header=None)
datas = prepfunctions.prepare_dataset(data, 1024, False, False)
featured_datas = prepfunctions.mask_feature_selection(
datas, 1024, True,
'./Results/FeatureSelection/QOT 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 + '/'
