import numpy as np
import matplotlib.pyplot as plt

raw_data_X = [[3.393533211, 2.331273381],
              [3.110073483, 1.781539638],
              [1.343808831, 3.368360954],
              [3.582294042, 4.679179110],
              [2.280362439, 2.866990263],
              [7.423436942, 4.696522875],
              [5.745051997, 3.533989803],
              [9.172168622, 2.511101045],
              [7.792783481, 3.424088941],
              [7.939820817, 0.791637231]
             ]
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([8.093607318, 3.365731514])

%run kNN_function/kNN.py

predict_y = kNN_classify(6, X_train, y_train, x)

predict_y

1

使用scikit-learn中的kNN

from sklearn.neighbors import KNeighborsClassifier

kNN_classifier = KNeighborsClassifier(n_neighbors=6)

kNN_classifier.fit(X_train, y_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_jobs=1, n_neighbors=6, p=2,
           weights='uniform')

kNN_classifier.predict(x)

/Users/yuanzhang/anaconda/lib/python3.6/site-packages/sklearn/utils/validation.py:395: DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and will raise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
  DeprecationWarning)

array([1])

X_predict = x.reshape(1, -1)

X_predict

array([[ 8.09360732,  3.36573151]])

kNN_classifier.predict(X_predict)

array([1])

y_predict = kNN_classifier.predict(X_predict)

y_predict[0]

1

重新整理我们的kNN的代码

%run kNN/kNN.py

knn_clf = KNNClassifier(3)

knn_clf.fit(X_train, y_train)

KNN(k=3)

y_predict = knn_clf.predict(X_predict)

y_predict

array([1])

y_predict[0]

kNN_function

import numpy as np
from math import sqrt
from collections import Counter


def kNN_classify(k, X_train, y_train, x):

assert 1 <= k <= X_train.shape[0], "k must be valid"
assert X_train.shape[0] == y_train.shape[0], \
"the size of X_train must equal to the size of y_train"
assert X_train.shape[1] == x.shape[0], \
"the feature number of x must be equal to X_train"

distances = [sqrt(np.sum((x_train - x)**2)) for x_train in X_train]
nearest = np.argsort(distances)

topK_y = [y_train[i] for i in nearest[:k]]
votes = Counter(topK_y)

return votes.most_common(1)[0][0]

kNN 

import numpy as np
from math import sqrt
from collections import Counter


class KNNClassifier:

    def __init__(self, k):
        """初始化kNN分类器"""
        assert k >= 1, "k must be valid"
        self.k = k
        self._X_train = None
        self._y_train = None

    def fit(self, X_train, y_train):
        """根据训练数据集X_train和y_train训练kNN分类器"""
        assert X_train.shape[0] == y_train.shape[0], \
            "the size of X_train must be equal to the size of y_train"
        assert self.k <= X_train.shape[0], \
            "the size of X_train must be at least k."

        self._X_train = X_train
        self._y_train = y_train
        return self

    def predict(self, X_predict):
        """给定待预测数据集X_predict，返回表示X_predict的结果向量"""
        assert self._X_train is not None and self._y_train is not None, \
                "must fit before predict!"
        assert X_predict.shape[1] == self._X_train.shape[1], \
                "the feature number of X_predict must be equal to X_train"

        y_predict = [self._predict(x) for x in X_predict]
        return np.array(y_predict)

    def _predict(self, x):
        """给定单个待预测数据x，返回x的预测结果值"""
        assert x.shape[0] == self._X_train.shape[1], \
            "the feature number of x must be equal to X_train"

        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]

    def __repr__(self):
        return "KNN(k=%d)" % self.k