可以說knn是機器學習中非常特殊的沒有模型的演算法,為了和其他演算法統一,可以認為新聯資料集就是模型本身
import numpy as np
import matplotlib.pyplot as plt
from math import sqrt
from collections import counter
# 特徵集合
raw_data_x = [[3.393533211, 2.331273381],
[3.110073483, 1.781539638],
[1.343808831, 3.368360954],
[3.582294042, 4.679179110],
[2.280362439, 2.866990263],
[7.423469421, 4.694522875],
[5.745051997, 3.533989803],
[9.172168622, 2.511101045],
[7.792783481, 3.424088941],
[7.939820817, 0.791637231]]
# 每乙個特徵的類別
raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
# 訓練集
x_train = np.array(raw_data_x)
y_train = np.array(raw_data_y)
# 來了乙個新的資料 要判斷它的特徵值
new = np.array([8.093607318, 3.365731514])
# 原資料
plt.scatter(x_train[y_train == 0, 0], x_train[y_train == 0, 1], color='g')
plt.scatter(x_train[y_train == 1, 0], x_train[y_train == 1, 1], color='r')
# 新資料
plt.scatter(new[0], new[1], color='b')
# plt.show()
# 由圖可知,它一定輸入特徵值為 1
# knn的過程
distances =
# np.sum((x - new) ** 2) 等價於 (x[0] - new[0]) ** 2 + (x[1] - new[1]) ** 2
for x in x_train:
d = sqrt(np.sum((x - new) ** 2))
# 一句話搞定
# distances = [sqrt(np.sum((x - new) ** 2)) for x in x_train]
nearest = np.argsort(distances)
k = 6
# 最近距離y座標
topk_y = [y_train[i] for i in nearest[:k]]
# 投票過程
votes = counter(topk_y)
# **結果值
predict_y = votes.most_common(1)[0][0]
print(predict_y)
很容易把上述的過程整理出來寫出乙個函式
import numpy as np
from math import sqrt
from collections import counter
defknn_classify
(k, x_train, y_train, new):
# 校驗引數
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] == new.shape[0], "th feature number of x must be equal to x_train"
# 距離陣列
distance = [sqrt(np.sum((x - new) ** 2)) for x in x_train]
nearest = np.argsort(distance)
topk_y = [y_train[i] for i in nearest[:k]]
# 投票
votes = counter(topk_y)
return votes.most_common(1)[0][0]
from sklearn.neighbors import kneighborsclassifier
import numpy as np
# 特徵集合
raw_data_x = [[3.393533211, 2.331273381],
[3.110073483, 1.781539638],
[1.343808831, 3.368360954],
[3.582294042, 4.679179110],
[2.280362439, 2.866990263],
[7.423469421, 4.694522875],
[5.745051997, 3.533989803],
[9.172168622, 2.511101045],
[7.792783481, 3.424088941],
[7.939820817, 0.791637231]]
# 每乙個特徵的類別
raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
# 訓練集
x_train = np.array(raw_data_x)
y_train = np.array(raw_data_y)
new = np.array([[8.093607318, 3.365731514]])
knn_classifier = kneighborsclassifier(n_neighbors=6)
knn_classifier.fit(x_train, y_train)
print(knn_classifier.predict(new))
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
1<= k, "k must be valid "
self.k = k
self._x_train = none
self._y_train = none
deffit
(self, x_train, y_train):
""""根據訓練資料集x_train,y_train訓練knn分類器"""
assert x_train.shape[0] == y_train.shape[0], "the size of x_train must equal to the size of y_train"
assert self.k <= x_train.shape[0], "th feature number of x must be equal to x_train"
self._x_train = x_train
self._y_train = y_train
return self
defpredict
(self, new):
""""給定待**資料集new,返回表示new的結果向量"""
assert self._x_train is
notnone
and self._y_train is
notnone, "must fit before predict!"
assert new.shape[1] == self._x_train.shape[1], "the feature number of new must be equal to x_train"
y_predict = [self._predict(x) for x in new]
return np.array(y_predict)
def_predict
(self, x):
""""給定單個待**資料x,返回x_predict的**結果值"""
assert x.shape[0] == self._x_train.shape[1], "the feature number of x must be equal to x_train"
# 距離陣列
distance = [sqrt(np.sum((i - x) ** 2)) for i in self._x_train]
nearest = np.argsort(distance)
topk_y = [self._y_train[i] for i in nearest[:self.k]]
# 投票
votes = counter(topk_y)
return votes.most_common(1)[0][0]
機器學習 kNN(1)
knn k nearest neighbor 工作原理 存在乙個樣本資料集合,也稱為訓練樣本集,並且樣本集中每個資料都存在標籤,即我們知道樣本集中每一資料與所屬分類對應的關係。輸入沒有標籤的資料後,將新資料中的每個特徵與樣本集中資料對應的特徵進行比較,提取出樣本集中特徵最相似資料 最近鄰 的分類標籤...
機器學習之 K近鄰演算法(KNN)
k近鄰演算法是機器學習中的最基礎的演算法之一,也是必須會講解的演算法之一。因為其簡單,易懂。但是k近鄰演算法在實際應用中卻很少使用到,由於其侷限性很強,執行效率低下。那麼所謂的k近鄰中的近鄰是指 已有乙個訓練資料集,現給定乙個新的資料,利用現有資料集對其進行 那麼 方法便是尋找與給定資料距離最近的k...
機器學習 k 近鄰 kNN 演算法
一 基本原理 存在乙個樣本資料集合 也稱訓練樣本集 並且樣本集中每個資料都存在標籤。輸入沒有標籤的新資料後,將新資料的每個特徵與樣本集中資料對應的特徵進行比較,然後演算法提取樣本集中特徵最相似資料 最近鄰 的分類標籤。我們一般只選擇樣本集中前k k通常是不大於20的整數 個最相似的資料,最後選擇k個...