グリッドサーチを使ったチューニング

サポートベクトルマシンのパイプラインのトレーニング

from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC

import numpy as np
import pandas as pd

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data',
                header=None)

X = df.loc[:, 2:].values
y = df.loc[:, 1].values

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

pipe_svc = make_pipeline(StandardScaler(), SVC(random_state=1))
param_range = [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0]

## C : 誤分類に、寛容かどうか。 γ : 過学習する度合いを制御。のパラメータ
param_grid = [
    {'svc__C': param_range, 'svc__kernel': ['linear']},
    {'svc__C': param_range, 'svc__gamma': param_range, 'svc__kernel': ['rbf']}
]
gs = GridSearchCV(
    estimator=pipe_svc,
    param_grid=param_grid,
    scoring='accuracy',
    cv=10,
    n_jobs=-1
)
gs.fit(X_train, y_train)
print(gs.best_score_)
print(gs.best_params_)

0.9846153846153847
{'svc__C': 100.0, 'svc__gamma': 0.001, 'svc__kernel': 'rbf'}

• テスト結果

clf = gs.best_estimator_
clf.fit(X_train, y_train)
print('Test accuracy : %.3f' % clf.score(X_test, y_test))

Test accuracy : 0.974

入れ子式動作検証 (5 x 2 交差検証)

モデル同士の比較に使える

• サポートベクトルマシン

gs = GridSearchCV(
    estimator=pipe_svc,
    param_grid=param_grid,
    scoring='accuracy',
    cv=2,
    n_jobs=-1
)

scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

CV accuracy: 0.974 +/- 0.015

• 決定木分類器

from sklearn.tree import DecisionTreeClassifier

gs = GridSearchCV(
    estimator=DecisionTreeClassifier(random_state=0),
    param_grid=[{'max_depth': [1, 2, 3, 4, 5, 6, 7, None]}],
    scoring='accuracy',
    cv=2,
    n_jobs=-1
)
    
scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

CV accuracy: 0.934 +/- 0.016