【scikit-learn】样本预处理

# 2) Loading The Data
# -----------------------------------------------------------
# Your data needs to be numeric and stored as NumPy arrays 
#       or SciPy sparse matrices.
# Other types that are convertible to numeric arrays, 
#       such as Pandas DataFrame, are also acceptable.
import numpy as np
X = np.random.random((10,5))
y = np.array(['M','M','F','F','M','F','M','M','F','F'])
X[X < 0.7] = 0;
# train/test split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=33)
# ===================================================

# 3) Preprocessing The Data
# -------------------------------------------------------
# 3-1) Standardization (每一列，让属性值分布 标准化<钟形分布曲线>)
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler().fit(X_train)
standardized_X = scaler.transform(X_train)
standardized_X_test = scaler.transform(X_test)
print(X_train,'\n',standardized_X);
print('\n');
print(X_test,'\n',standardized_X_test);
print("========================");

# 3-2) Normalizatio  (每一行，每个向量归一化，模长为1)
from sklearn.preprocessing import Normalizer
scaler = Normalizer().fit(X_train)
normalized_X = scaler.transform(X_train)
normalized_X_test = scaler.transform(X_test)
print(X_train,'\n',normalized_X);
print('\n');
print(X_test,'\n',normalized_X_test);
print("========================");

# 3-3) Binarization
from sklearn.preprocessing import Binarizer
binarizer = Binarizer(threshold=0.0).fit(X)
binary_X = binarizer.transform(X);
print(X,'\n',binary_X);
print("========================");

# 3-4) Encoding Categorical Features
from sklearn.preprocessing import LabelEncoder
enc = LabelEncoder()
y = enc.fit_transform(y);
print(y);
print("========================");

# 3-5) Imputing Missing Values (求每列的平均值，补充缺失值)
from sklearn.impute  import SimpleImputer
imp = SimpleImputer(missing_values=0, strategy='mean').fit(X_train)
imp_X_train = imp.transform(X_train)
print(X_train,'\n',imp_X_train);
print("========================");

# 3-6) Generating Polynomial Features
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(5)
poly.fit_transform(X)