1. 1.数据前处理

# 标准化

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler().fit(X_train)
standardized_X = scaler.transform(X_train)
standardized_X_test = scaler.transform(X_test)

# 归一化
from sklearn.preprocessing import Normalizer
scaler = Normalizer().fit(X_train)
normalized_X = scaler.transform(X_train)
normalized_X_test = scaler.transform(X_test)

# 二值化
from sklearn.preprocessing import Binarizer
binarizer = Binarizer(threshold=0.0).fit(X)
binary_X = binarizer.transform(X)

# 编码分类特征
from sklearn.preprocessing import LabelEncoder
enc = LabelEncoder()
y = enc.fit_transform(y)

# 输入缺失值
from sklearn.preprocessing import Imputer
imp = Imputer(missing_values=0, strategy='mean', axis=0)
imp.fit_transform(X_train)

# 生成多项式特征
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(5)
poly.fit_transform(X)