sklearn.preprocessing.scale(X)

scaler = sklearn.preprocessing.StandardScaler().fit(train)
scaler.transform(train)
scaler.transform(test)

min_max_scaler = sklearn.preprocessing.MinMaxScaler()
min_max_scaler.fit_transform(X_train)

X = [[ 1, -1, 2],[ 2, 0, 0], [ 0, 1, -1]]
sklearn.preprocessing.normalize(X, norm='l2')

array([[ 0.40, -0.40, 0.81], [ 1, 0, 0], [ 0, 0.70, -0.70]])

binarizer = sklearn.preprocessing.Binarizer(threshold=1.1)
binarizer.transform(X)

lb = sklearn.preprocessing.LabelBinarizer()

enc = preprocessing.OneHotEncoder()
enc.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])
enc.transform([[0, 1, 3]]).toarray() #array([[ 1., 0., 0., 1., 0., 0., 0., 0., 1.]])

newdf=pd.get_dummies(df,columns=["gender","title"],dummy_na=True) 

le = sklearn.preprocessing.LabelEncoder() 
le.fit([1, 2, 2, 6]) 
le.transform([1, 1, 2, 6]) #array([0, 0, 1, 2]) 
#非数值型转化为数值型
le.fit(["paris", "paris", "tokyo", "amsterdam"])
le.transform(["tokyo", "tokyo", "paris"]) #array([2, 2, 1])

sklearn.preprocessing.robust_scale

poly = sklearn.preprocessing.PolynomialFeatures(2)
poly.fit_transform(X)