SVM

2021.3.26 2021.3.26 Data_Science/Machine_Learning 361 2 mins

Support Vector Machine

`가장 가까운 K개 점을 선택헤 분류 및 예측

1
2


import numpy as np
import matplotlib.pyplot as plt

함수 불러오기

1
2
3
4
5
6
7
8


from sklearn import svm, datasets
iris=datasets.load_iris()
X=iris.data[:,:2]
y=iris.target

C=1
clf=svm.SVC(kernel='linear',C=C)
clf.fit(X,y)

SVC(C=1, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='linear',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

1
2
3


from sklearn.metrics import confusion_matrix
y_pred=clf.predict(X)
confusion_matrix(y,y_pred)  

array([[50,  0,  0],
       [ 0, 38, 12],
       [ 0, 15, 35]])

2. kernel SVM 적합 및 비교

LinearSVC

1
2
3
4


clf=svm.LinearSVC(C=C,max_iter=10000)
clf.fit(X,y)
y_pred=clf.predict(X)
confusion_matrix(y,y_pred)

array([[49,  1,  0],
       [ 2, 30, 18],
       [ 0,  9, 41]])

radial basis function

1
2
3
4


clf=svm.SVC(kernel='rbf',gamma=0.7,C=C,max_iter=10000)
clf.fit(X,y)
y_pred=clf.predict(X)
confusion_matrix(y,y_pred)

array([[50,  0,  0],
       [ 0, 37, 13],
       [ 0, 13, 37]])

polynomial kernel

1
2
3
4


clf=svm.SVC(kernel='poly',degree=3,C=C,gamma='auto')
clf.fit(X,y)
y_pred=clf.predict(X)
confusion_matrix(y,y_pred)

array([[50,  0,  0],
       [ 0, 38, 12],
       [ 0, 16, 34]])

시각적 비교
함수 정의

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13


def make_meshgrid(x, y, h=.02):
    x_min, x_max = x.min() - 1, x.max() + 1
    y_min, y_max = y.min() - 1, y.max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    return xx, yy


def plot_contours(ax, clf, xx, yy, **params):
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    out = ax.contourf(xx, yy, Z, **params)
    return out

데이터 불러오기

1
2
3
4


iris = datasets.load_iris()

X = iris.data[:, :2]
y = iris.target

모델정의 및 피팅

1
2
3
4
5
6


C = 1.0 #Regularization parameter
models = (svm.SVC(kernel='linear', C=C),
          svm.LinearSVC(C=C, max_iter=10000),
          svm.SVC(kernel='rbf', gamma=0.7, C=C),
          svm.SVC(kernel='poly', degree=3, gamma='auto', C=C))
models = (clf.fit(X, y) for clf in models)

1
2
3
4


titles = ('SVC with linear kernel',
          'LinearSVC (linear kernel)',
          'SVC with RBF kernel',
          'SVC with polynomial (degree 3) kernel')

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19


fig, sub = plt.subplots(2, 2)
plt.subplots_adjust(wspace=0.4, hspace=0.4)

X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)

for clf, title, ax in zip(models, titles, sub.flatten()):
    plot_contours(ax, clf, xx, yy,
                  cmap=plt.cm.coolwarm, alpha=0.8)
    ax.scatter(X0, X1, c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xlabel('Sepal length')
    ax.set_ylabel('Sepal width')
    ax.set_xticks(())
    ax.set_yticks(())
    ax.set_title(title)

plt.show()

Load Comments?