特征数据预处理-标准化与归一化

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

Standardization and Min-Max scaling

from sklearn import preprocessing

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

minmax_scale = preprocessing.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()))

输出：
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()))

输出：
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

Plotting

%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，观察下结果吧！接下来我们再看看数据是否被打乱了呢？

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()

在机器学习中，如果我们对训练集做了上述处理，那么同样的对测试集也必须要经过相同的处理

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

标准化处理对PCA主成分分析的影响

主成分分析（PCA）和一个非常有用的套路，接下来，咱们来看看数据经过标准化处理和未经标准化处理后使用PCA的效果

Reading in the dataset

import pandas as pd

df = pd.read_csv(
    '../data/wine_data.csv', 
    header=None,
    )
df.head()

Dividing the dataset into a separate training and test dataset

In this step, we will randomly divide the wine dataset into a training dataset and a test dataset where the training dataset will contain 70% of the samples and the test dataset will contain 30%, respectively.

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)

Feature Scaling - Standardization

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)

使用PCA进行降维

现在，我们在标准化和非标准化数据集上执行PCA，将数据集转换成二维特征子空间。

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)

来看看效果咋样吧

%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()