欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

【机器学习】特征数据预处理-标准化和归一化

程序员文章站 2022-07-16 18:45:47
...

加载数据

import pandas as pd
import numpy as np

df = pd.read_csv(
    '../data/wine_data.csv',  #葡萄酒数据集
     header=None,     #用哪行当做列名,我们自己来指定
     usecols=[0,1,2]  #返回一个子集,我们拿部分特征举例就可以了
    )

df.columns=['Class label', 'Alcohol', 'Malic acid']

df.head()

在数据中,Alcohol和Malic acid 衡量的标准应该是不同的,特征之间数值差异较大
【机器学习】特征数据预处理-标准化和归一化
标准化和归一化

from sklearn.preprocessing import StandardScaler,MinMaxScaler

std_scale = StandardScaler().fit(df[['Alcohol', 'Malic acid']])
df_std = std_scale.transform(df[['Alcohol', 'Malic acid']])

minmax_scale = MinMaxScaler().fit(df[['Alcohol', 'Malic acid']])
df_minmax = minmax_scale.transform(df[['Alcohol', 'Malic acid']])

print('Mean after standardization:\nAlcohol={:.2f}, Malic acid={:.2f}'
      .format(df_std[:,0].mean(), df_std[:,1].mean()))
print('\nStandard deviation after standardization:\nAlcohol={:.2f}, Malic acid={:.2f}'
      .format(df_std[:,0].std(), df_std[:,1].std()))


Mean after standardization:
Alcohol=-0.00, Malic acid=-0.00

Standard deviation after standardization:
Alcohol=1.00, Malic acid=1.00


print('Min-value after min-max scaling:\nAlcohol={:.2f}, Malic acid={:.2f}'
      .format(df_minmax[:,0].min(), df_minmax[:,1].min()))
print('\nMax-value after min-max scaling:\nAlcohol={:.2f}, Malic acid={:.2f}'
      .format(df_minmax[:,0].max(), df_minmax[:,1].max()))

Min-value after min-max scaling:
Alcohol=0.00, Malic acid=0.00

Max-value after min-max scaling:
Alcohol=1.00, Malic acid=1.00
%matplotlib inline
from matplotlib import pyplot as plt

def plot():
    plt.figure(figsize=(8,6))

    plt.scatter(df['Alcohol'], df['Malic acid'], 
            color='green', label='input scale', alpha=0.5)

    plt.scatter(df_std[:,0], df_std[:,1], color='red', 
            label='Standardized [$N  (\mu=0, \; \sigma=1)$]', alpha=0.3)

    plt.scatter(df_minmax[:,0], df_minmax[:,1], 
            color='blue', label='min-max scaled [min=0, max=1]', alpha=0.3)

    plt.title('Alcohol and Malic Acid content of the wine dataset')
    plt.xlabel('Alcohol')
    plt.ylabel('Malic Acid')
    plt.legend(loc='upper left')
    plt.grid()
    
    plt.tight_layout()

plot()
plt.show()

我们将原始的和变换后都放到了同一个图上,再看看数据是否被打乱了
【机器学习】特征数据预处理-标准化和归一化

fig, ax = plt.subplots(3, figsize=(6,14))

for a,d,l in zip(range(len(ax)), 
               (df[['Alcohol', 'Malic acid']].values, df_std, df_minmax),
               ('Input scale', 
                'Standardized [$N  (\mu=0, \; \sigma=1)$]', 
                'min-max scaled [min=0, max=1]')
                ):
    for i,c in zip(range(1,4), ('red', 'blue', 'green')):
        ax[a].scatter(d[df['Class label'].values == i, 0], 
                  d[df['Class label'].values == i, 1],
                  alpha=0.5,
                  color=c,
                  label='Class %s' %i
                  )
    ax[a].set_title(l)
    ax[a].set_xlabel('Alcohol')
    ax[a].set_ylabel('Malic Acid')
    ax[a].legend(loc='upper left')
    ax[a].grid()
    
plt.tight_layout()

plt.show()

【机器学习】特征数据预处理-标准化和归一化

【机器学习】特征数据预处理-标准化和归一化
【机器学习】特征数据预处理-标准化和归一化

标准化处理对PCA主成分分析的影响

from sklearn.model_selection import train_test_split

X_wine = df.values[:,1:]
y_wine = df.values[:,0]

X_train, X_test, y_train, y_test = train_test_split(X_wine, y_wine,
    test_size=0.30, random_state=12345)


from sklearn import preprocessing

std_scale = preprocessing.StandardScaler().fit(X_train)
X_train_std = std_scale.transform(X_train)
X_test_std = std_scale.transform(X_test)



from sklearn.decomposition import PCA

# on non-standardized data
pca = PCA(n_components=2).fit(X_train)
X_train = pca.transform(X_train)
X_test = pca.transform(X_test)


# om standardized data
pca_std = PCA(n_components=2).fit(X_train_std)
X_train_std = pca_std.transform(X_train_std)
X_test_std = pca_std.transform(X_test_std)

接下来看看效果

%matplotlib inline

from matplotlib import pyplot as plt

fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=(10,4))


for l,c,m in zip(range(1,4), ('blue', 'red', 'green'), ('^', 's', 'o')):
    ax1.scatter(X_train[y_train==l, 0], X_train[y_train==l, 1],
        color=c, 
        label='class %s' %l, 
        alpha=0.5,
        marker=m
        )

for l,c,m in zip(range(1,4), ('blue', 'red', 'green'), ('^', 's', 'o')):
    ax2.scatter(X_train_std[y_train==l, 0], X_train_std[y_train==l, 1],
        color=c, 
        label='class %s' %l, 
        alpha=0.5,
        marker=m
        )

ax1.set_title('Transformed NON-standardized training dataset after PCA')    
ax2.set_title('Transformed standardized training dataset after PCA')    
    
for ax in (ax1, ax2):

    ax.set_xlabel('1st principal component')
    ax.set_ylabel('2nd principal component')
    ax.legend(loc='upper right')
    ax.grid()
plt.tight_layout()

plt.show()

【机器学习】特征数据预处理-标准化和归一化

可以清晰的看到经过标准化的数据可分性更强