import numpy as np
from math import sqrt
from collections import Counter
class KNNClassifier:
  def __init__(self,k):
    """初始化KNN分類器"""
    assert k >= 1
    """斷言判斷k的值是否合法"""
    self.k = k
    self._X_train = None
    self._y_train = None
  def fit(self,X_train,y_train):
    """根據訓練數(shù)據集X_train和Y_train訓練KNN分類器，形成模型"""
    assert X_train.shape[0] == y_train.shape[0]
    """數(shù)據和標簽的大小必須一樣
    assert self.k <= X_train.shape[0]
    """k的值不能超過數(shù)據的大小"""
    self._X_train = X_train
    self._y_train = y_train
    return self
  def predict(self,X_predict):
    """必須將訓練數(shù)據集和標簽擬合為模型才能進行預測的過程"""
    assert self._X_train is not None and self._y_train is not None
    """訓練數(shù)據和標簽不可以是空的"""
    assert X_predict.shape[1]== self._X_train.shape[1]
    """待預測數(shù)據和訓練數(shù)據的列(特征個數(shù))必須相同"""
    y_predict = [self._predict(x) for x in X_predict]
    return np.array(y_predict)
  def _predict(self,x):
    """給定單個待測數(shù)據x,返回x的預測數(shù)據結果"""
    assert x.shape[0] == self._X_train.shape[1]
    """x表示一行數(shù)據，即一個數(shù)組，那么它的特征數(shù)據個數(shù)，必須和訓練數(shù)據相同
    distances = [sqrt(np.sum((x_train - x)**2))for x_train in self._X_train]
    nearest = np.argsort(distances)
    topk_y = [self._y_train[i] for i in nearest[:self.k]]
    votes = Counter(topk_y)
    return votes.most_common(1)[0][0]

from KNN.py import KNNClassifier
raw_data_x = [[3.393,2.331],
       [3.110,1.781],
       [1.343,3.368],
       [3.582,4.679],
       [2.280,2.866],
       [7.423,4.696],
       [5.745,3.533],
       [9.172,2.511],
       [7.792,3.424],
       [7.939,0.791]]
raw_data_y = [0,0,0,0,0,1,1,1,1,1]
X_train = np.array(raw_data_x)
y_train = np.array(raw_data_y)
x = np.array([9.880,3.555])
# 要將x這個矩陣轉換成2維的矩陣，一行兩列的矩陣
X_predict = x.reshape(1,-1)
"""1，創(chuàng)建一個對象，設置K的值為6"""
knn_clf = KNNClassifier(6)
"""2，將訓練數(shù)據和訓練標簽融合"""
knn_clf.fit(X_train,y_train)
"""3，經過2才能跳到這里，傳入待預測的數(shù)據"""
y_predict = knn_clf.predict(X_predict)
print(y_predict)