机器学习实战之knn算法pandas实现

开始学习机器学习实战这本书，打算看完了再回头看 周志华的 机器学习。机器学习实战的代码都是用numpy写的，有些麻烦，所以考虑用pandas来实现代码，也能回顾之前学的 用python进行数据分析。感觉目前章节的测试方法太渣，留着以后学了更多再回头写。

# coding: gbk
import pandas as pd
import numpy as np


def getdata(path):
    data = pd.read_csv(path, header=None, sep='\t')
    character = data.iloc[:, :-1]
    label = data.iloc[:, -1]
    chara_max = character.max()
    chara_min = character.min()
    chara_range = chara_max - chara_min
    normal_chara = (character - chara_min) / chara_range
    return normal_chara, label  # 获得归一化特征值和标记


def knn(inX, normal_chara, label, k):
    data_sub = normal_chara - inX
    data_square = data_sub.applymap(np.square)
    data_sum = data_square.sum(axis=1)
    data_sqrt = data_sum.map(np.sqrt)
    dis_sort = data_sqrt.argsort()
    k_label = label[dis_sort[:k]]
    label_sort = k_label.value_counts()
    res_label = label_sort.index[0]
    return res_label  # knn算法分类