k分割交差検証を使ったモデルの性能の評価

Coding

code: Python

import pandas as pd

X = df.loc:, 2:.values

y = df.loc:, 1.values

# yのカテゴリ変数「M」「B」を数値に変換する

from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()

y = le.fit_transform(y)

le.transform('B', 'M')

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, stratify=y, random_state=1)

from sklearn.preprocessing import StandardScaler

from sklearn.decomposition import PCA

from sklearn.linear_model import LogisticRegression

from sklearn.pipeline import make_pipeline

# 連結する処理としてスケーリング、主成分分析、ロジスティック回帰を指定

pipe_lr = make_pipeline(StandardScaler(), PCA(n_components=2), LogisticRegression(random_state=1))

import numpy as np

from sklearn.model_selection import cross_val_score

# 交差検証のcross_val_score関数でモデルの正解率を算出

# 推定器estimator、トレーニングデータX、予測値y、分割数cv、CPU数n_jobsを指定

scores = cross_val_score(estimator=pipe_lr, X=X_train, y=y_train, cv=10, n_jobs=1)

print('CV accuracy scores: %s' % scores)

print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

--------------------------------------------------------------------------------

CV accuracy scores: [0.93478261 0.93478261 0.95652174 0.95652174 0.93478261 0.95555556

0.97777778 0.93333333 0.95555556 0.95555556]

CV accuracy: 0.950 +/- 0.014

--------------------------------------------------------------------------------