特征缩放的重要性
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.naive_bayes import GaussianNB
from sklearn import metrics
import matplotlib.pyplot as plt
from sklearn.datasets import load_wine
from sklearn.pipeline import make_pipeline
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
RANDOM_STATE = 42
FIG_SIZE = (10, 7)
features, target = load_wine(return_X_y=True)
# 使用30％的测试大小进行训练/测试拆分
X_train, X_test, y_train, y_test = train_test_split(features, target,
test_size=0.30,
random_state=RANDOM_STATE)
# 使用管道式GNB和PCA拟合数据并进行预测
unscaled_clf = make_pipeline(PCA(n_components=2), GaussianNB())
unscaled_clf.fit(X_train, y_train)
pred_test = unscaled_clf.predict(X_test)
# 使用管道缩放，GNB和PCA拟合数据并进行预测。
std_clf = make_pipeline(StandardScaler(), PCA(n_components=2), GaussianNB())
std_clf.fit(X_train, y_train)
pred_test_std = std_clf.predict(X_test)
# 在缩放和非缩放数据中显示预测精度
print('\nPrediction accuracy for the normal test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test)))
print('\nPrediction accuracy for the standardized test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test_std)))
# 从管道中提取PCA
pca = unscaled_clf.named_steps['pca']
pca_std = std_clf.named_steps['pca']
# 展示第一主成分
print('\nPC 1 without scaling:\n', pca.components_[0])
print('\nPC 1 with scaling:\n', pca_std.components_[0])
# 可视化使用了缩放和未使用缩放时的PCA
X_train_transformed = pca.transform(X_train)
scaler = std_clf.named_steps['standardscaler']
X_train_std_transformed = pca_std.transform(scaler.transform(X_train))
# 使用PCA可视化标准化和未修改的数据集
fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=FIG_SIZE)
for l, c, m in zip(range(0, 3), ('blue', 'red', 'green'), ('^', 's', 'o')):
ax1.scatter(X_train_transformed[y_train == l, 0],
X_train_transformed[y_train == l, 1],
color=c,
label='class %s' % l,
alpha=0.5,
marker=m
)
for l, c, m in zip(range(0, 3), ('blue', 'red', 'green'), ('^', 's', 'o')):
ax2.scatter(X_train_std_transformed[y_train == l, 0],
X_train_std_transformed[y_train == l, 1],
color=c,
label='class %s' % l,
alpha=0.5,
marker=m
)
ax1.set_title('PCA后的培训数据集')
ax2.set_title('PCA后的标准化培训数据集')
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()
fig.suptitle("特征缩放的重要性", x=0.5,y=1.1,fontsize=25)
plt.show()
