数据归一化处理方法

最值归一化 Normalization

# 最值归一化 Normalization
import numpy as np

x = np.random.randint(1,100,size=100)
#进行最值归一化
x = (x - np.min(x)) / (np.max(x) - np.min(x))

#多维数组的最值归一化
X = np.random.randint(1,100,(50,2))
X = np.array(X,dtype=float)
for i in range(2):
    X[:,i] = (X[:,i] - np.min(X[:,i])) / (np.max(X[:,i]) - np.min(X[:,i]))
    
import matplotlib.pyplot as plt
plt.scatter(X[:,0],X[:,1])
plt.show()

适用于极值有范围的数据集

均值方差归一化Standardization

均值为0 方差为1

# 均值方差归一化Standardization
x2 = np.random.randint(1,100,(50,2))
x2 = np.array(x2, dtype=float)
for i in range(2):
    x2[:,i] = (x2[:,i] - np.mean(x2[:,i])) / np.std(x2[:,i])
    
plt.scatter(x2[:,0],x2[:,1])
plt.show()

使用sklearn中的StandardScale进行均值方差归一化

#使用sklearn中的StandardScale进行均值方差归一化

from sklearn import datasets

iris = datasets.load_iris()
x = iris.data
y = iris.target

from sklearn.model_selection import train_test_split
x_train, x_test,y_train,  y_test = train_test_split(x,y,test_size = 0.2,random_state = 666)

#数据预处理包中加载 StandardScaler
from sklearn.preprocessing import StandardScaler
standerdsclaer = StandardScaler()
standerdsclaer.fit(x_train)
x_train = standerdsclaer.transform(x_train)
x_test_standard = standerdsclaer.transform(x_test)

from sklearn.neighbors import KNeighborsClassifier

knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(x_train,y_train)

print(knn_clf.score(x_test_standard, y_test))

1.0