KNN Classifier

原创转载请注明出处：https://www.cnblogs.com/agilestyle/p/12668372.html

准备数据

import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_blobs
from sklearn.neighbors import KNeighborsClassifier

centers = [[1, 1], [-1, -1], [1, -1]]

X, y = make_blobs(n_samples=100, n_features=2, centers=centers, cluster_std=0.4, random_state=0)

# (100, 2)
X.shape
# (100,)
y.shape

plt.figure(figsize=(12, 8))
plt.scatter(X[:, 0], X[:, 1], s=100, c=y)

建模训练

# KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
#                      metric_params=None, n_jobs=None, n_neighbors=10, p=2,
#                      weights='uniform')
knn = KNeighborsClassifier(n_neighbors=10)
knn.fit(X, y)

评价模型

X_test = np.array([0.25, 0])
# (2,)
X_test.shape

X_test = X_test.reshape(1, -1)
# (1, 2)
X_test.shape
# 0.25
X_test[0][0]
# 0.0
X_test[0][1]

y_test = knn.predict(X_test)
# (1,)
y_test.shape

neighbors = knn.kneighbors(X_test, return_distance=False)
# array([[78, 37, 69, 89, 87, 71, 96, 46, 58, 21]])
neighbors

plt.figure(figsize=(12, 8))
plt.scatter(X[:, 0], X[:, 1], c=y, s=100, cmap='cool')
plt.scatter(X_test[0][0], X_test[0][1], s=200, c='orange')

for i in neighbors[0]:
    plt.plot([X[i][0], X_test[0][0]], [X[i][1], X_test[0][1]], 'g', linewidth=1)

# 1.0
knn.score(X, y)