如何使用 scikit-learn 可视化两个类的边界/决策函数

Question

我在机器学习方面还很陌生，所以我仍然不明白如何在词袋案例中可视化两个类之间的边界。

我发现以下 exaplpe 来绘制数据

绘制文档 tfidf 二维图

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
import matplotlib.pyplot as plt

newsgroups_train = fetch_20newsgroups(subset='train', 
                                      categories=['alt.atheism', 'sci.space'])
pipeline = Pipeline([
    ('vect', CountVectorizer()),
    ('tfidf', TfidfTransformer()),
])        
X = pipeline.fit_transform(newsgroups_train.data).todense()

pca = PCA(n_components=2).fit(X)
data2D = pca.transform(X)
plt.scatter(data2D[:,0], data2D[:,1], c=newsgroups_train.target)
plt.show()

在我的项目中，我使用 SVC 估算器

clf = SVC(random_state=241, kernel = 'linear')
clf.fit(X,newsgroups_train.target)

我曾尝试使用示例 http://scikit-learn.org/stable/auto_examples/svm/plot_iris.html 但它在文本分类案例中不起作用

那么如何将两个类的边界添加到这个图中呢？

谢谢！

Answer 1

问题是您只需选择 2 个特征即可创建二维决策曲面图。我将提供2个例子。第一使用iris数据和第二使用your数据。

我还在这里写了一篇关于此的文章： https://towardsdatascience.com/support-vector-machines-svm-clearly-explained-a-python-tutorial-for-classification-problems-29c539f3ad8 ?source=friends_link&sk=80f72ab272550d76a0cc3730d7c8af35

在这两种情况下，我只选择 2 个特征来创建绘图。

使用虹膜数据的示例 1：

from sklearn.svm import SVC
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets

iris = datasets.load_iris()
X = iris.data[:, :2]  # we only take the first two features.
y = iris.target

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

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

fig, ax = plt.subplots()
# title for the plots
title = ('Decision surface of linear SVC ')
# Set-up grid for plotting.
X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)

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_ylabel('y label here')
ax.set_xlabel('x label here')
ax.set_xticks(())
ax.set_yticks(())
ax.set_title(title)
ax.legend()
plt.show()

结果

使用您的数据的示例 2：

from sklearn.svm import SVC
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
import matplotlib.pyplot as plt

newsgroups_train = fetch_20newsgroups(subset='train', 
                                      categories=['alt.atheism', 'sci.space'])
pipeline = Pipeline([('vect', CountVectorizer()), ('tfidf', TfidfTransformer())])        
X = pipeline.fit_transform(newsgroups_train.data).todense()

# Select ONLY 2 features
X = np.array(X)
X = X[:, [0,1]]
y = newsgroups_train.target

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

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

fig, ax = plt.subplots()
# title for the plots
title = ('Decision surface of linear SVC ')
# Set-up grid for plotting.
X0, X1 = X[:, 0], X[:, 1]
xx, yy = make_meshgrid(X0, X1)

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_ylabel('y label here')
ax.set_xlabel('x label here')
ax.set_xticks(())
ax.set_yticks(())
ax.set_title(title)
ax.legend()
plt.show()

结果

重要的提示：

在第二种情况下，绘图并不好，因为我们只随机选择了 2 个特征来创建它。使其变得更好的一种方法如下：您可以使用（例如 ANOVA F 值测试）并从您最初拥有的特征中univariate ranking method找到最佳特征。然后使用这些你可以创建一个漂亮的分离曲面图。top-222464top-2