X_test_std = sc.transform(X_test)
# train the LogisticRegression
svm = SVC(kernel='linear', C=1.0, random_state=0)
svm.fit(X_train_std, y_train)
# make predictions
y_pred = svm.predict(X_test_std)
print('Misclassified samples: %d' % (y_test != y_pred).sum())
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
# graph decision regions
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined_std, y=y_combined,
classifier=svm, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
# plt.savefig('./figures/support_vector_machine_scikit.png', dpi=300)
plt.show()
svm = SVC(kernel='rbf', random_state=0, gamma=0.2, C=1.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined,
classifier=svm, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
'https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',
header=None)
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
# train用とtest用に分割
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
stratify=y,
random_state=0)
# データ標準化
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)
pca = PCA(n_components=2)
lr = LogisticRegression()
X_train_pca = pca.fit_transform(X_train_std)
X_test_pca = pca.transform(X_test_std)
lr.fit(X_train_pca, y_train)
plot_decision_regions(X_train_pca, y_train, classifier=lr)
plt.legend(loc='lower left')
plt.tight_layout()
plt.show()
y,
test_size=0.3,
random_state=0)
# train the LogisticRegression
forest = RandomForestClassifier(criterion='entropy',
n_estimators=10,
random_state=1,
n_jobs=2)
forest.fit(X_train, y_train)
# make predictions
y_pred = forest.predict(X_test)
print('Misclassified samples: %d' % (y_test != y_pred).sum())
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
# graph decision regions
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined,
y_combined,
classifier=forest,
test_idx=range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.tight_layout()
# plt.savefig('./figures/random_forest.png', dpi=300)
plt.show()
X_xor = np.random.randn(200, 2)
y_xor = np.logical_xor(X_xor[:, 0] > 0,
X_xor[:, 1] > 0)
y_xor = np.where(y_xor, 1, -1)
plt.scatter(X_xor[y_xor == 1, 0],
X_xor[y_xor == 1, 1],
c='b', marker='x',
label='1')
plt.scatter(X_xor[y_xor == -1, 0],
X_xor[y_xor == -1, 1],
c='r',
marker='s',
label='-1')
plt.xlim([-3, 3])
plt.ylim([-3, 3])
plt.legend(loc='best')
plt.tight_layout()
# plt.savefig('./figures/xor.png', dpi=300)
plt.show()
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_xor, y_xor)
plot_decision_regions(X_xor, y_xor,
classifier=svm)
plt.legend(loc='upper left')
plt.tight_layout()
# plt.savefig('./figures/support_vector_machine_rbf_xor.png', dpi=300)
plt.show()
stratify=y)
# データの標準化
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
# パーセプトロン
ppn = Perceptron(max_iter=40, eta0=0.1, random_state=1)
ppn.fit(X_train_std, y_train)
y_pred = ppn.predict(X_test_std)
# ロジスティック回帰
lr = LogisticRegression(C=100.0, random_state=1)
lr.fit(X_train_std, y_train)
#print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))
#print('Accuracy: %.2f' % ppn.score(X_test_std, y_test))
# trainとtestを結合する
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
graph.plot_decision_regions(X=X_combined_std,
y=y_combined,
classifier=lr,
test_idx=range(105, 150))
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
return np.where(self.net_input(X) >= 0.0, 1, -1)
if __name__ == '__main__':
import pandas as pd
import matplotlib.pyplot as plt
import graph
# irisデータセット読み込み
df = pd.read_csv('https://archive.ics.uci.edu/ml/' 'machine-learning-databases/iris/iris.data', header=None)
y = df.iloc[:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[:100, [0, 2]].values
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(X, y)
# グラフ描画
graph.plot_decision_regions(X, y, classifier=ppn)
#plt.plot(range(1, len(ppn.errors_) + 1), ppn.errors_, marker='o')
#plt.xlabel('Epochs')
#plt.ylabel('Number of update')
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc='upper left')
plt.show()
