如何使用 scikit-learn 可视化两个 类 的 border/decision 函数
How can I visualize border/decision function of two classes using scikit-learn
我是机器学习的新手，所以我仍然不明白如何在词袋案例中可视化 2 类 之间的边界。
我找到了以下示例来绘制数据
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 估计器
clf = SVC(random_state=241, kernel = 'linear')
clf.fit(X,newsgroups_train.target)
我试过用这个例子
http://scikit-learn.org/stable/auto_examples/svm/plot_iris.html
但它在文本分类情况下不起作用
那么如何将两个 类 的边界添加到该图中？
谢谢！
问题是您只需要 select 2 个特征即可创建二维决策曲面图。我将提供 2 个示例。第一个使用 iris 数据，第二个使用 your 数据。
在这两种情况下，我 select 只有 2 个特征才能创建情节。
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
示例 2 使用您的数据：
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
重要提示：
在第二种情况下，情节并不好看，因为我们 select 随机只使用了 2 个特征来创建它。让它变得更好的一种方法如下：您可以使用 univariate ranking method（例如 ANOVA F 值检验）并从您最初拥有的 22464 中找到最好的 top-2 特征。然后使用这些 top-2 你可以创建一个漂亮的分离曲面图。
我是机器学习的新手，所以我仍然不明白如何在词袋案例中可视化 2 类 之间的边界。
我找到了以下示例来绘制数据
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 估计器
clf = SVC(random_state=241, kernel = 'linear')
clf.fit(X,newsgroups_train.target)
我试过用这个例子 http://scikit-learn.org/stable/auto_examples/svm/plot_iris.html 但它在文本分类情况下不起作用
那么如何将两个 类 的边界添加到该图中？
谢谢！
问题是您只需要 select 2 个特征即可创建二维决策曲面图。我将提供 2 个示例。第一个使用 iris 数据，第二个使用 your 数据。
在这两种情况下，我 select 只有 2 个特征才能创建情节。
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
示例 2 使用您的数据：
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
重要提示：
在第二种情况下，情节并不好看，因为我们 select 随机只使用了 2 个特征来创建它。让它变得更好的一种方法如下：您可以使用 univariate ranking method（例如 ANOVA F 值检验）并从您最初拥有的 22464 中找到最好的 top-2 特征。然后使用这些 top-2 你可以创建一个漂亮的分离曲面图。