多标签分类#
此示例模拟多标签文档分类问题。数据集是根据以下过程随机生成的
选择标签数量:n ~ Poisson(n_labels)
n 次,选择一个类别 c:c ~ Multinomial(theta)
选择文档长度:k ~ Poisson(length)
k 次,选择一个词:w ~ Multinomial(theta_c)
在上述过程中,使用拒绝采样来确保 n 大于 2,并且文档长度永远不为零。同样,我们拒绝已经选择的类别。分配给两个类别的文档用两个彩色圆圈包围。
分类是通过投影到 PCA 和 CCA 找到的前两个主成分来完成的,用于可视化目的,然后使用 OneVsRestClassifier
元分类器使用两个具有线性核的 SVC 来学习每个类别的判别模型。请注意,PCA 用于执行无监督降维,而 CCA 用于执行监督降维。
注意:在图中,“未标记样本”并不意味着我们不知道标签(如半监督学习中那样),而是样本根本没有标签。
# Authors: Vlad Niculae, Mathieu Blondel
# License: BSD 3 clause
import matplotlib.pyplot as plt
import numpy as np
from sklearn.cross_decomposition import CCA
from sklearn.datasets import make_multilabel_classification
from sklearn.decomposition import PCA
from sklearn.multiclass import OneVsRestClassifier
from sklearn.svm import SVC
def plot_hyperplane(clf, min_x, max_x, linestyle, label):
# get the separating hyperplane
w = clf.coef_[0]
a = -w[0] / w[1]
xx = np.linspace(min_x - 5, max_x + 5) # make sure the line is long enough
yy = a * xx - (clf.intercept_[0]) / w[1]
plt.plot(xx, yy, linestyle, label=label)
def plot_subfigure(X, Y, subplot, title, transform):
if transform == "pca":
X = PCA(n_components=2).fit_transform(X)
elif transform == "cca":
X = CCA(n_components=2).fit(X, Y).transform(X)
else:
raise ValueError
min_x = np.min(X[:, 0])
max_x = np.max(X[:, 0])
min_y = np.min(X[:, 1])
max_y = np.max(X[:, 1])
classif = OneVsRestClassifier(SVC(kernel="linear"))
classif.fit(X, Y)
plt.subplot(2, 2, subplot)
plt.title(title)
zero_class = np.where(Y[:, 0])
one_class = np.where(Y[:, 1])
plt.scatter(X[:, 0], X[:, 1], s=40, c="gray", edgecolors=(0, 0, 0))
plt.scatter(
X[zero_class, 0],
X[zero_class, 1],
s=160,
edgecolors="b",
facecolors="none",
linewidths=2,
label="Class 1",
)
plt.scatter(
X[one_class, 0],
X[one_class, 1],
s=80,
edgecolors="orange",
facecolors="none",
linewidths=2,
label="Class 2",
)
plot_hyperplane(
classif.estimators_[0], min_x, max_x, "k--", "Boundary\nfor class 1"
)
plot_hyperplane(
classif.estimators_[1], min_x, max_x, "k-.", "Boundary\nfor class 2"
)
plt.xticks(())
plt.yticks(())
plt.xlim(min_x - 0.5 * max_x, max_x + 0.5 * max_x)
plt.ylim(min_y - 0.5 * max_y, max_y + 0.5 * max_y)
if subplot == 2:
plt.xlabel("First principal component")
plt.ylabel("Second principal component")
plt.legend(loc="upper left")
plt.figure(figsize=(8, 6))
X, Y = make_multilabel_classification(
n_classes=2, n_labels=1, allow_unlabeled=True, random_state=1
)
plot_subfigure(X, Y, 1, "With unlabeled samples + CCA", "cca")
plot_subfigure(X, Y, 2, "With unlabeled samples + PCA", "pca")
X, Y = make_multilabel_classification(
n_classes=2, n_labels=1, allow_unlabeled=False, random_state=1
)
plot_subfigure(X, Y, 3, "Without unlabeled samples + CCA", "cca")
plot_subfigure(X, Y, 4, "Without unlabeled samples + PCA", "pca")
plt.subplots_adjust(0.04, 0.02, 0.97, 0.94, 0.09, 0.2)
plt.show()
脚本的总运行时间:(0 分钟 0.212 秒)
相关示例