机器学习——KNN

导入类库

import numpy as np
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

# 熵增益
# 熵越大，信息量越大，蕴含的不确定性越大

KNN
1.计算待预测值到所有点的距离
2.对所有距离排序
3.找出前K个样本里面类别最多的类，作为待预测值的类别

代码


A = np.array([[1, 1], [1, 1.5], [0.5, 1.5]])
B = np.array([[3.0, 3.0], [3.0, 3.5], [2.8, 3.1]])


def knn_pre_norm(point):
    a_len = np.linalg.norm(point - A, axis=1)
    b_len = np.linalg.norm(point - B, axis=1)
    print(a_len.min())
    print(b_len.min())


def knn_predict_rev(point):
    X = np.array([[1, 1], [1, 1.5], [0.5, 1.5], [3.0, 3.0], [3.0, 3.5], [2.8, 3.1]])
    Y = np.array([0, 0, 0, 1, 1, 1])

    knn = KNeighborsClassifier(n_neighbors=2)
    knn.fit(X, Y)

    print(knn.predict(np.array([[1.0, 3.0]])))


def iris_linear():
    # 加载iris数据
    li = load_iris()
    # 散点图
    # plt.scatter(li.data[:, 0], li.data[:, 1], c=li.target)
    # plt.scatter(li.data[:, 2], li.data[:, 3], c=li.target)
    # plt.show()
    # 分割测试集和训练集，测试集占整个数据集的比例是0.25
    x_train, x_test, y_train, y_test = train_test_split(li.data, li.target, test_size=0.25)
    # 创建KNN分类，使用最少5个邻居作为类别判断标准
    knn = KNeighborsClassifier(n_neighbors=5)
    # 训练数据
    knn.fit(x_train, y_train)
    # 预测测试集
    # print(knn.predict(x_test))
    # 预测np.array([[6.3, 3, 5.2, 2.3]])
    print(knn.predict(np.array([[6.3, 3, 5.2, 2.3]])))
    # 预测np.array([[6.3, 3, 5.2, 2.3]])所属各个类别的概率
    print(knn.predict_proba(np.array([[6.3, 3, 5.2, 2.3]])))


if __name__ == '__main__':
    # knn_predict_rev(None)
    # knn_pre_norm(np.array([2.3,2.3]))
    iris_linear()