Python数据分析与机器学习-SVM调参实例

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from sklearn.svm import SVC
from sklearn.datasets.samples_generator import make_blobs


# X, y = make_blobs(n_samples=200, centers=2, cluster_std=0.6, random_state=0)


# plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap="autumn")
# model = SVC(kernel="linear")
# model.fit(X, y)

# 绘图函数
def plot_svc_decision_function(model, ax=None, plot_support=True):
    """Plot the decision function for a 2D SVC"""
    if ax is None:
        ax = plt.gca()
    xlim = ax.get_xlim()
    ylim = ax.get_ylim()

    # create grid to evaluate model
    x = np.linspace(xlim[0], xlim[1], 30)
    y = np.linspace(ylim[0], ylim[1], 30)
    Y, X = np.meshgrid(y, x)
    xy = np.vstack([X.ravel(), Y.ravel()]).T
    P = model.decision_function(xy).reshape(X.shape)

    # plot decision boundary and margins
    ax.contour(X, Y, P, colors='k',
               levels=[-1, 0, 1], alpha=0.5,
               linestyles=['--', '-', '--'])

    # plot support vectors
    if plot_support:
        ax.scatter(model.support_vectors_[:, 0],
                   model.support_vectors_[:, 1],
                   s=300, linewidth=1, facecolors='none');
    ax.set_xlim(xlim)
    ax.set_ylim(ylim)


# plot_svc_decision_function(model)
# plt.show()

'''引入核函数的SVM'''
from sklearn.datasets.samples_generator import make_circles

# X, y = make_circles(n_samples=100, noise=.1, factor=.1, random_state=1)

# clf = SVC(kernel="linear").fit(X,y)
# plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
# plot_svc_decision_function(clf,plot_support=False)
# plt.show()

'''加入径向基函数==高斯核函数'''
# clf = SVC(kernel="rbf")
# clf.fit(X, y)
# plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
# plot_svc_decision_function(clf)
# plt.show()

'''调节SVM参数: Soft Margin问题'''
'''
调节C参数
当C趋近于无穷大时：意味着分类严格不能有错误
当C趋近于很小的时：意味着可以有更大的错误容忍
'''
# X, y = make_blobs(n_samples=100, centers=2, random_state=0, cluster_std=0.8)
#
# fig, ax = plt.subplots(1, 2, figsize=(16, 6))
#
# for axi, C in zip(ax, [10.0, 0.1]):
#     model = SVC(kernel='linear', C=C).fit(X, y)
#     axi.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
#     plot_svc_decision_function(model, axi)
#     axi.scatter(model.support_vectors_[:, 0], model.support_vectors_[:, 1], s=300, lw=1, facecolors='none');
#     axi.set_title('C = {0:.1f}'.format(C), size=14)
# plt.show()


'''gamma控制模型的复杂程度,值越大模型越复杂'''
# X, y = make_blobs(n_samples=100, centers=2, random_state=0, cluster_std=1.1)
# fig, ax = plt.subplots(1, 2, figsize=(16, 6))
#
# for axi, gamma in zip(ax, [10.0, 0.1]):  # gamma控制模型的复杂程度,值越大模型越复杂
#     model = SVC(kernel='rbf', gamma=gamma).fit(X, y)
#     axi.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
#     plot_svc_decision_function(model, axi)
#     axi.scatter(model.support_vectors_[:, 0], model.support_vectors_[:, 1], s=300, lw=1, facecolors='none');
#     axi.set_title('gamma = {0:.1f}'.format(gamma), size=14)
# plt.show()

'''Example: Face Recognition'''
from sklearn.datasets import fetch_lfw_people  # fetch_lfw_people人脸数据集

faces = fetch_lfw_people(min_faces_per_person=60)  # min_faces_per_person 每个人有60个人脸
print(faces.target_names)
print(faces.images.shape)

fig, ax = plt.subplots(3, 5)
for i, axi in enumerate(ax.flat):
    axi.imshow(faces.images[i], cmap='bone')
    axi.set(xticks=[], yticks=[], xlabel=faces.target_names[faces.target[i]])

from sklearn.svm import SVC
# from sklearn.decomposition import RandomizedPCA
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline

pca = PCA(n_components=150, whiten=True)
svc = SVC(kernel='rbf', class_weight='balanced')
model = make_pipeline(pca, svc)

from sklearn.model_selection import train_test_split

Xtrain, Xtest, ytrain, ytest = train_test_split(faces.data, faces.target, random_state=40)

from sklearn.model_selection import GridSearchCV  # GridSearchCV做差数选择

param_grid = {'svc__C': [1, 5, 10],
              'svc__gamma': [0.0001, 0.0005, 0.001]}
grid = GridSearchCV(model, param_grid)

grid.fit(Xtrain, ytrain)
print(grid.best_params_)

model = grid.best_estimator_
yfit = model.predict(Xtest)
yfit.shape

fig, ax = plt.subplots(4, 6)
for i, axi in enumerate(ax.flat):
    axi.imshow(Xtest[i].reshape(62, 47), cmap='bone')
    axi.set(xticks=[], yticks=[])
    axi.set_ylabel(faces.target_names[yfit[i]].split()[-1],
                   color='black' if yfit[i] == ytest[i] else 'red')
fig.suptitle('Predicted Names; Incorrect Labels in Red', size=14);

from sklearn.metrics import classification_report

print(classification_report(ytest, yfit,
                            target_names=faces.target_names))

from sklearn.metrics import confusion_matrix  # 混淆矩阵
import seaborn as sns;

mat = confusion_matrix(ytest, yfit)
sns.heatmap(mat.T, square=True, annot=True, fmt='d', cbar=False,
            xticklabels=faces.target_names,
            yticklabels=faces.target_names)
plt.xlabel('true label')
plt.ylabel('predicted label');