一、介绍
二、编程实战
1、贝努利朴素贝叶斯make_blobs数据集的分类
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import train_test_split
X, y = make_blobs(n_samples=500, centers=5, random_state=8)
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=8)
nb = BernoulliNB()
nb.fit(X_train,y_train)
x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
xx, yy = np.meshgrid(np.arange(x_min, x_max, .02), np.arange(y_min, y_max, .02))
z = nb.predict(np.c_[(xx.ravel(), yy.ravel())]).reshape(xx.shape)
plt.pcolormesh(xx, yy, z, cmap=plt.cm.Pastel1)
plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=plt.cm.cool, edgecolors='k')
plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=plt.cm.cool, marker='*')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.show()
2、高斯朴素贝叶斯make_blobs数据集的分类
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(X_train, y_train)
z = gnb.predict(np.c_[(xx.ravel(),yy.ravel())]).reshape(xx.shape)
plt.pcolormesh(xx,yy,z,cmap=plt.cm.Pastel1)
plt.scatter(X_train[:,0],X_train[:,1],c=y_train,cmap=plt.cm.cool,edgecolor='k')
plt.scatter(X_test[:,0],X_test[:,1],c=y_test,cmap=plt.cm.cool,marker='*',edgecolor='k')
plt.xlim(xx.min(),xx.max())
plt.ylim(yy.min(),yy.max())
plt.show()
print('模型得分: {:.3f}'.format(gnb.score(X_test, y_test)))
3、高斯朴素贝叶斯的学习曲线
from sklearn.model_selection import learning_curve
from sklearn.model_selection import ShuffleSplit
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel("Training examples")
plt.ylabel("Score")
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
train_scores_mean = np.mean(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
plt.grid()
plt.plot(train_sizes, train_scores_mean, 'o-', color="r", label="Training score")
plt.plot(train_sizes, test_scores_mean, 'o-', color="g", label="Cross-validation score")
plt.legend(loc="lower right")
return plt
title = "Learning Curves (Naive Bayes)"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
estimator = GaussianNB()
plot_learning_curve(estimator, title, X, y, ylim=(0.9, 1.01), cv=cv, n_jobs=4)
plt.show()
