【機械学習アルゴリズム学習備忘録】Boosting – グリッドサーチ grid search –

import numpy as np
import matplolib.pyplot as plt
import pandas as pd

dataset = pd.read_csv('ファイル名.csv')
X = dataset.iloc[:, [2,3]].values
y = dataset.iloc[:, -1].values

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X = sc.fit_transform(X)
# 今回はKernel SVMを使っていくので、フィーチャースケーリング必須

from sklearn.model_selection impot rain_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

from sklearn.svm import SVC
classifier = SVC(kernel = 'rbf', random_state = 0)
classifier.fit(X_train, y_train)

y_pred = classifier.predict(X_test)

from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
print(cm)

from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator = classifier, X = X_train, y = y_train, cv = 10)
print('Accuracy: {:.2f} %'.format(accuracies.mean()*100))
print('Standard Deviation: {:.2f} %'.format(accuracies.std()*100))

from sklearn.model_selection import GridSearchCV
# ハイパーパラメータの格子（グリッド）の設定
parameters = [{'C':[1,10,100,1000], 'kernel':['linear']},
            {'C':[1,10,100,1000], 'kernel':['rbf'], 'gamma':[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]}
]

grid_search = GridSearchCV(estimator = classifier,
                            param_grid = parameters,
                            scoring = 'accuracy',
                            cv = 10,
                            n_jobs = -1
)
# scoring : それぞれのハイパーパラメータの場合を評価する指標。
# 今回はaccuracyを基準に各パラメータの組み合わせを評価する。
# cv : データのバイアス等を避けるため、10階に分けて計算を行う。

grid_search = grid_search.fit(X_train, y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
print("Best Accuracy: {:.2f} %".format(best_accuracy*100))
print("Best Parameters: ", best_parameters)

# 出力結果は↓こんな感じ
# Best Accuracy: 91.00 %
# Best Parameters:  {'C': 1, 'gamma': 0.7, 'kernel': 'rbf'}