def preprocess(percentage, basicNN=False):
printOn.blockPrint()
if basicNN == True:
test, unlabel, label, true, x, y, x_true, y_true, x_test, y_test = read.read(
file='diabetes.csv',
drop=None,
retNum=1,
chopNum=1,
unlabel_percentage=percentage,
ytrain=True)
else:
test, unlabel, label, true, x, y, x_true, y_true = read.read(
file='diabetes.csv',
drop=None,
retNum=1,
chopNum=1,
unlabel_percentage=percentage)
clfs = classifiers.ensemble(x, y)
printOn.enablePrint()
for point in test:
point.insert(0, point.pop())
if basicNN == True:
return unlabel, clfs, true, x, y, test, y_test, x_test
else:
return unlabel, clfs, true, x, y, test
def mleadaboost(unlabel, clfs, true, x, y, test):
printOn.blockPrint()
noisy_labels, confusion_matrixs, count_vi, answer = wrapperDS.run(
unlabel, clfs, true)
printOn.enablePrint()
df_noise_x, df_noise_y, noiseLabel = shuffle.run(unlabel, noisy_labels, x,
y)
bdt = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1),
algorithm="SAMME",
n_estimators=20)
bdt.fit(df_noise_x, df_noise_y)
err1 = errorTest.test(bdt, test, 2)
return err1
def preprocess(percentage, basicNN=False):
printOn.blockPrint()
if basicNN == True:
test, unlabel, label, true, x, y, x_true, y_true, x_test, y_test = read.read(
file='data.csv',
drop=['id'],
retNum=1,
chopNum=0,
unlabel_percentage=percentage,
ytrain=True)
else:
test, unlabel, label, true, x, y, x_true, y_true = read.read(
file='data.csv',
drop=['id'],
retNum=1,
chopNum=0,
unlabel_percentage=percentage)
clfs = classifiers.ensemble(x, y)
printOn.enablePrint()
if basicNN == True:
return unlabel, clfs, true, x, y, test, y_test, x_test
else:
return unlabel, clfs, true, x, y, test