Neighbors

#-＊-conding: utf-8-＊-
# k近邻
from sklearn.neighbors import KNeighborsClassifier
import numpy as np
data = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
target = np.array([1, 2, 3])
knb = KNeighborsClassifier(n_neighbors=3, weights='uniform', algorithm='auto', leaf_size=30, p=2, n_jobs=1)
knb.fit(data, target)
rst = knb.predict([[2, 3, 4]])
print(rst)

# 聚类算法

import matplotlib.pyplot as plt 
from sklearn.datasets.samples_generator import make_blobs
from sklearn.cluster import KMeans
X, y = make_blobs(
 n_samples=1000,
 n_features=2,
 centers=[[-1, -1], [0, 0], [1, 1], [2, 2]],
 cluster_std =[0.4, 0.2, 0.2, 0.2],
 random_state=9
)
estimator = KMeans(n_clusters=4, random_state=2019)
y_pred = estimator.fit_predict(X) 
labelpred = estimator.labels_  #获取聚类标签
centroids = estimator.cluster_centers_  #获取聚类中心
inertia = estimator.inertia_  #获取聚类准则的总和
plt.scatter(X[:, 0], X[:, 1], c=y_pred)
plt.show()

# 评估聚类分数
from sklearn import metrics
score = metrics.calinski_harabaz_score(X, y_pred)
print(score)