def detect_label_outliers(y, encoder=None):
# remove outliers
# TODO per-class outlier removal also
# if an encoder is provided, use it to invert the encoding before computing stats.
if encoder:
y = encoder.inverse_transform(y)
# perform outlier removal on mean/var-normalized samples (after filling missing data).
y_std = RobustScaler().fit_transform(
Imputer(strategy="median").fit_transform(
y.reshape([-1, 1])
)
).reshape([-1])
mask = (y_std < y_std.mean() - 3*y_std.std()) | (y_std > y_std.mean() + 3*y_std.std())
logger.info("Filtering {}/{} as outliers.".format(mask.sum(), len(mask)))
return mask
X_scale=scale(X)
elif c==2:#线性归一化
X_scale=minmax_scale(X)
elif c==0:#不进行归一化
X_scale=X
elif c==3:#鲁棒性归一化
from sklearn.preprocessing import RobustScaler
X_scale=RobustScaler().fit_transform(X)
print 'the standar result of X is:',X_scale
##测试X_scale,正常情况下均值为0，方差为1
#1.
print 'mean=',X_scale.mean()
print 'std=',X_scale.std()
#2.
print 'min=',X_scale.min()
print 'max=',X_scale.max()
csv_file1.close()
##为了理解方便、表示方法简单
X=X_scale
##归一化之后的统计信息
##获得X的统计信息
statistics(X)
##频率分布图
#drawHist(X,'AOD','Frequency','the Frequency of standar AOD')
##频率累计图
