sklearn 朴素贝叶斯分类示例

代码参考 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/07.01-Implementing-Our-First-Bayesian-Classifier.ipynb：

from sklearn import datasets
import numpy as np
from sklearn import model_selection as ms
import matplotlib.pyplot as plt
from sklearn import naive_bayes

X, y = datasets.make_blobs(100, 2, centers=2, random_state=1701, cluster_std=2)
plt.style.use('ggplot')
plt.figure(figsize=(10, 6))
plt.scatter(X[:, 0], X[:, 1], c=y, s=50)
X_train, X_test, y_train, y_test = ms.train_test_split(
    X.astype(np.float32), y, test_size=0.1
)
model_naive = naive_bayes.GaussianNB()
model_naive.fit(X_train, y_train)
model_naive.score(X_test, y_test)
yprob = model_naive.predict_proba(X_test)
yprob.round(2)


def plot_proba(model, X_test, y_test):
    # create a mesh to plot in
    h = 0.02  # step size in mesh
    x_min, x_max = X_test[:, 0].min() - 1, X_test[:, 0].max() + 1
    y_min, y_max = X_test[:, 1].min() - 1, X_test[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))

    X_hypo = np.column_stack((xx.ravel().astype(np.float32),
                              yy.ravel().astype(np.float32)))
    if hasattr(model, 'predictProb'):
        _, _, y_proba = model.predictProb(X_hypo)
    else:
        y_proba = model.predict_proba(X_hypo)

    zz = y_proba[:, 1] - y_proba[:, 0]
    zz = zz.reshape(xx.shape)

    plt.contourf(xx, yy, zz, cmap=plt.cm.coolwarm, alpha=0.8)
    plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, s=200)


plt.figure(figsize=(10, 6))
plot_proba(model_naive, X, y)
plt.show()

运算结果如下：