線形判別分析による教師ありデータ圧縮

// TODO P151 理論はあとで、、

Coding（scikit-learn）

code: Python

import pandas as pd

from sklearn.cross_validation import train_test_split

from sklearn.preprocessing import StandardScaler

# 2列目以降のデータをXに、1列目のデータをyに格納

# トレーニングデータとテストデータに分割

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0, stratify=y)

# 平均と標準偏差を用いて標準化

sc = StandardScaler()

X_train_std = sc.fit_transform(X_train)

X_test_std = sc.transform(X_test)

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA

# 次元数を指定して、LDAのインスタンスを生成

lda = LDA(n_components=2)

X_train_lda = lda.fit_transform(X_train_std, y_train)

from sklearn.linear_model import LogisticRegression

lr = LogisticRegression()

lr = lr.fit(X_train_lda, y_train)

plot_decision_regions(X_train_lda, y_train, classifier=lr)

plt.xlabel('LD 1')

plt.ylabel('LD 2')

plt.legend(loc='lower left')

plt.tight_layout()

plt.show()

https://gyazo.com/6251761a712e8d3c168fefd289ca2eed

code: Python

X_test_lda = lda.transform(X_test_std)

plot_decision_regions(X_test_lda, y_test, classifier=lr)

plt.xlabel('LD 1')

plt.ylabel('LD 2')

plt.legend(loc='lower left')

plt.tight_layout()

plt.show()

https://gyazo.com/eca3f17adc58f4d1fa81a831d46b3c77