notebook.community

Edit and run

3章 分類問題 - 機械学習ライブラリ scikit-learn の活用

3.2 scikit-learn 活用へのファーストステップ





In [21]:



    


from sklearn import datasets
import numpy as np
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target



    











In [22]:



    


print("Class labels:", np.unique(y))



    


















    






Class labels: [0 1 2]

















In [23]:



    


from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
len(X), len(X_train), len(X_test)



    


















    
Out[23]:








(150, 105, 45)

















In [24]:



    


from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)



    











In [25]:



    


from sklearn.linear_model import Perceptron
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0, shuffle=True)
ppn.fit(X_train_std, y_train)



    


















    
Out[25]:








Perceptron(alpha=0.0001, class_weight=None, eta0=0.1, fit_intercept=True,
      n_iter=40, n_jobs=1, penalty=None, random_state=0, shuffle=True,
      verbose=0, warm_start=False)

















In [26]:



    


y_pred = ppn.predict(X_test_std)
print('Misclassified samples: {}'.format((y_test != y_pred).sum()))



    


















    






Misclassified samples: 4

















In [27]:



    


from sklearn.metrics import accuracy_score
print('Accuracy: {:.2f}'.format(accuracy_score(y_test, y_pred)))



    


















    






Accuracy: 0.91

















In [28]:



    


from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt

def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    # マーカーとカラーマップの準備
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # 決定領域のプロット
    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    
    # グリッドポイントの生成
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                           np.arange(x2_min, x2_max, resolution))
    
    # 各特徴量を1次元配列に変換して予測と実行
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    # 予測結果を元のぐり一度ポイントのデータサイズに変換
    Z = Z.reshape(xx1.shape)
    
    # グリッドポイントの等高線のプロット
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    
    # 軸の範囲の設定
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    
    # クラスごとにサンプルをプロット
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha = 0.8, c=cmap(idx), marker=markers[idx], label=cl)
               
    # テストサンプルを目立たせる
    if test_idx:
        X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='',
                    alpha=1.0, linewidths=1, marker='o',
                    s=55, label='test set')



    











In [29]:



    


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=ppn, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()

3.3 ロジスティック回帰分析





In [30]:



    


import matplotlib.pyplot
import numpy as np
def sigmoid(z):
    return 1.0 / (1.0 + np.exp(-z))

z = np.arange(-7, 7, 0.1)
phi_z = sigmoid(z)
plt.plot(z, phi_z)
plt.axvline(0.0, color='k')
plt.ylim(-0.1, 1.1)
plt.xlabel('z')
plt.ylabel('$\phi (z)$')
plt.yticks([0.0, 0.5, 1.0])
ax = plt.gca()
ax.yaxis.grid(True)
plt.show()



    


















    
























In [31]:



    


from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=lr, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [32]:



    


lr.predict_proba(X_test_std[0,:].reshape(1, -1))



    


















    
Out[32]:








array([[  2.05743774e-11,   6.31620264e-02,   9.36837974e-01]])

















In [33]:



    


weights, params = [], []
for c in np.arange(-5, 5):
    lr = LogisticRegression(C=10**c, random_state=0)
    lr.fit(X_train_std, y_train)
    weights.append(lr.coef_[1])
    params.append(10**c)
    
weights = np.array(weights)
plt.plot(params, weights[:, 0], label='petal length')
plt.plot(params, weights[:, 1], linestyle='--', label='petal width')
plt.ylabel('weight coefficient')
plt.xlabel('C')
plt.legend(loc='upper left')
plt.xscale('log')
plt.show()

3.4 サポートベクトルマシンによる最大マージン分類





In [34]:



    


from sklearn.svm import SVC
# 線形SVMのインスタンスを生成
svm = SVC(kernel='linear', C=1.0, random_state=0)
# 線形SVMのモデルにトレーニングデータを適合させる
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]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [35]:



    


from sklearn.linear_model import SGDClassifier
ppn = SGDClassifier(loss='perceptron')
lr = SGDClassifier(loss='log')
svm = SGDClassifier(loss='hinge')

3.5 カーネルSVMを使った非線形問題の求解





In [36]:



    


np.random.seed(0)
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.show()



    


















    
























In [37]:



    


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.show()



    


















    
























In [38]:



    


svm = SVC(kernel='linear', 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.show()



    


















    
























In [39]:



    


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]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [40]:



    


svm = SVC(kernel='rbf', random_state=0, gamma=100.0, 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]')
plt.legend(loc='upper left')
plt.show()

3.6 決定木学習





In [43]:



    


from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='entropy', max_depth=3, random_state=0)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined, y_combined, classifier=tree, test_idx=(range(105, 150)))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [48]:



    


from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='gini', max_depth=5, random_state=0)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined, y_combined, classifier=tree, test_idx=(range(105, 150)))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [52]:



    


from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='entropy', n_estimators=10, random_state=1, n_jobs=2)
forest.fit(X_train, y_train)
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.show()

3.7 k近傍方: 怠惰学習アルゴリズム





In [53]:



    


from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=knn, test_idx=(range(105, 150)))
plt.xlabel('petal length [standadized]')
plt.ylabel('petal width [standadized]')
plt.legend(loc='upper left')
plt.show()



    


















    
























In [ ]:

Content source: takanory/python-machine-learning

Similar notebooks:

notebook.community | gallery | about