import pandas as pd
import numpy as np


def distance(v1, v2):
    """
    距离计算
    :param v1:点1
    :param v2: 点2
    :return: 距离
    """
    dist = np.sqrt(np.sum(np.power((v1 - v2), 2)))
    return dist


# 加载数据
data = pd.read_excel("./电影分类数据.xlsx")
print("data:\n", data)
print("*" * 80)
# 获取训练集
train = data.iloc[:, :6]
print("train:\n", train)
# 获取训练集的特征值   与目标值
train_x = train.iloc[:, :-1]
train_y = train.iloc[:, -1]
# 获取测试集
print("*" * 80)
test = data.columns[-4:]
print("test:\n", test)

# 进行计算距离
# 循环计算训练集每一个样本与测试集的距离
for i in range(train.shape[0]):

    # 计算距离
    dist = distance(train_x.iloc[i,2:5],test[1:])

    train.loc[i,‘dist‘] = dist



print(train)
#  对距离按照升序进行排序
train.sort_values(by=‘dist‘,inplace=True)
print("*" * 80)
print("排序后的train:\n",train)

# 确定K 值 k值不同结果不同
k =5
res = train.loc[:,‘电影类型‘][:k].mode()[0]
print("*" * 80)
print(res)