from sklearn.model_selection import cross_val_score
import configparser
from preprocess import load_arff, fill_miss
if __name__ == '__main__':
config = configparser.ConfigParser()
config.read('../config.ini')
with open(os.path.join(config['path']['OUTPUT_PATH'], 'bagging_acc.md'), 'w') as of:
of.write('||naive bayes|decision tree|KNN|MLP|LinearSVM|\n|:---:|:---:|:---:|:---:|:---:|:---:|\n')
for i in range(10):
fpath = config['path']['df' + f'{i}']
data = load_arff(fpath)
X, Y = fill_miss(data)
of.write(f"|{fpath[fpath.rfind('/')+1:fpath.rfind('.')]}|")
for i in range(5):
print(fpath[fpath.rfind('/') + 1:fpath.rfind('.')] + '\t' + config['alg']['alg' + f'{i}'], end='\t')
start_time = time.time()
if i == 0:
clf = BaggingClassifier(base_estimator=GaussianNB(),
n_estimators=10,
max_samples=0.5,
max_features=0.5)
elif i == 1:
clf = BaggingClassifier(base_estimator=DecisionTreeClassifier(random_state=0, criterion='gini'),
n_estimators=10,
max_samples=0.5,
max_features=0.5)
elif i == 2:
import configparser
from preprocess import load_arff, fill_miss
if __name__ == '__main__':
config = configparser.ConfigParser()
config.read('../config.ini')
with open(
os.path.join(config['path']['OUTPUT_PATH'],
'decision_tree_gini.md'), 'w') as of:
of.write('| |accuracy|auc|\n|:---:|:---:|:---:|\n')
for i in range(10):
start_time = time.time()
fpath = config['path']['df' + f'{i}']
print(fpath[fpath.rfind('/') + 1:fpath.rfind('.')], end='\t')
data = load_arff(fpath)
X, y = fill_miss(data)
clf = DecisionTreeClassifier(random_state=0, criterion='gini')
# clf = DecisionTreeClassifier(random_state=0, criterion='entropy')
skf = StratifiedKFold(n_splits=10)
skf_accuracy1 = []
skf_accuracy2 = []
n_classes = np.arange(np.unique(y).size)
for train, test in skf.split(X, y):
clf.fit(X[train], y[train])
skf_accuracy1.append(clf.score(X[test], y[test]))
if n_classes.size < 3:
skf_accuracy2.append(
roc_auc_score(y[test],
clf.predict_proba(X[test])[:, 1],
average='micro'))
else: