import numpy as np
from math import sqrt
from collections import Counter
from .metrics import accuracy_score

class KNNClassifier:

def __init__(self, k):
"""初始化kNN分類器"""
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):
"""根據訓練數據集X_train和y_train訓練kNN分類器"""
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):
"""給定待預測數據集X_predict，返回表示X_predict的結果向量"""
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):
"""給定單個待預測數據x，返回x的預測結果值"""
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 score(self, X_test, y_test):
"""根據測試數據集 X_test 和 y_test 確定當前模型的準確度"""

y_predict = self.predict(X_test)
return accuracy_score(y_test, y_predict)

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

轉載于:https://www.cnblogs.com/heguoxiu/p/10135546.html

總結

以上是生活随笔為你收集整理的KNNClassifier的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。