比较特征约简技术
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.decomposition import PCA, NMF
from sklearn.feature_selection import SelectKBest, chi2
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
pipe = Pipeline([
# the reduce_dim stage is populated by the param_grid
('reduce_dim', 'passthrough'),
('classify', LinearSVC(dual=False, max_iter=10000))
])
N_FEATURES_OPTIONS = [2, 4, 8]
C_OPTIONS = [1, 10, 100, 1000]
param_grid = [
{
'reduce_dim': [PCA(iterated_power=7), NMF()],
'reduce_dim__n_components': N_FEATURES_OPTIONS,
'classify__C': C_OPTIONS
},
{
'reduce_dim': [SelectKBest(chi2)],
'reduce_dim__k': N_FEATURES_OPTIONS,
'classify__C': C_OPTIONS
},
]
reducer_labels = ['PCA', 'NMF', 'KBest(chi2)']
grid = GridSearchCV(pipe, n_jobs=1, param_grid=param_grid)
X, y = load_digits(return_X_y=True)
grid.fit(X, y)
mean_scores = np.array(grid.cv_results_['mean_test_score'])
# 分数按param_grid迭代的顺序排列，按字母顺序排列
mean_scores = mean_scores.reshape(len(C_OPTIONS), -1, len(N_FEATURES_OPTIONS))
# 选择最佳C的分数
mean_scores = mean_scores.max(axis=0)
bar_offsets = (np.arange(len(N_FEATURES_OPTIONS)) *
(len(reducer_labels) + 1) + .5)
plt.figure()
COLORS = 'bgrcmyk'
for i, (label, reducer_scores) in enumerate(zip(reducer_labels, mean_scores)):
plt.bar(bar_offsets + i, reducer_scores, label=label, color=COLORS[i])
plt.title("比较特征约简技术")
plt.xlabel('Reduced number of features')
plt.xticks(bar_offsets + len(reducer_labels) / 2, N_FEATURES_OPTIONS)
plt.ylabel('Digit classification accuracy')
plt.ylim((0, 1))
plt.legend(loc='upper left')
plt.show()
