import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from collections import Counter
from sklearn.neighbors import KNeighborsClassifier


# 建立一个类KNN，用于k-近邻的计算
class KNN:
    # 初始化
    def __init__(self, X_train, y_train, n_neighbors=3, p=2):  # 初始化数据，neighbor表示邻近点，p为欧氏距离
        self.n = n_neighbors
        self.p = p
        self.X_train = X_train
        self.y_train = y_train

    def predict(self, X):
        # X为测试集
        knn_list = []
        # 先遍历指定个邻近点，求范数
        for i in range(self.n):
            # 计算训练集和测试集之间的距离,np.linalg.norm求范数
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)
            knn_list.append((dist, self.y_train[i]))  # 在列表末尾添加一个元素

        # 对于剩下的数据集，求范数，并替换近邻中最大的点
        for i in range(self.n, len(self.X_train)):  # 3-20
            max_index = knn_list.index(max(knn_list, key=lambda x: x[0]))  # 找出列表中距离最大的点
            dist = np.linalg.norm(X - self.X_train[i], ord=self.p)  # 计算训练集和测试集之间的距离
            if knn_list[max_index][0] > dist:  # 若当前数据的距离大于之前得出的距离，就将数值替换
                knn_list[max_index] = (dist, self.y_train[i])

        # 把近邻点中标签提取出
        knn = [k[-1] for k in knn_list]
        # 统计标签的个数,Counter计算数组中每个元素出现的次数
        count_pairs = Counter(knn)
        max_count = sorted(count_pairs, key=lambda x: x)[-1]  # 将标签升序排列
        return max_count

    # 计算测试算法的正确率
    def score(self, X_test, y_test):
        right_count = 0
        n = 10
        for X, y in zip(X_test, y_test):
            label = self.predict(X)
            if label == y:
                right_count += 1
        return right_count / len(X_test)


# 导入数据集
df = pd.read_csv('./iris/Iris.csv', usecols=[1, 2, 3, 4, 5])

# pandas打印表格信息
# print(df.info())

# pandas查看数据集的头5条记录
# print(df.head())

"""数据预处理"""
# 取前100条数据中的：前4个特征+标签，便于训练
data = np.array(df.iloc[:150, [0, 1, 2, 3, -1]])
# 数据类型转换，为了后面的数学计算
X, y = data[:, :-1], data[:, -1]
# 标签不需要是数字，字符串并不影响
# y = np.array([1 if i == 'Iris-setosa' else -1 for i in y])

"""数据集分割"""
# 把数据集分成训练集、测试集，test_size可以限定测试集的个数或占比
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

"""调用自定义kNN算法"""
clf = KNN(X_train, y_train) # 调用KNN算法进行计算
print(clf.score(X_test, y_test)) # 计算正确率

"""调用sklearn提供的kNN算法"""
# 调用
clf_sk = KNeighborsClassifier()
clf_sk.fit(X_train, y_train)
print(clf_sk.score(X_test, y_test)) # 计算正确率