封装kNN算法的主体部分
首先我们还是先看代码,再根据代码来解释。
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
第一步,先导入需要用的库,建立KNNClassifier类。
第二步,初始化我们的kNN分类器,传入K,并断言,K必须大于等于1。同时,应为我们后序要用到X_train和y_train两个数据集,我们先把他们设置为私有属性。
第三步,定义fit模型,传入X_train和y_train两个数据集,并添加断言,保证数据集时有效的。
第四步,定义predict函数。它的作用是接受一个需要送入模型进行预测的数据集X_predict,并把其中的数据一个一个送入我们的kNN之中,最后以向量的形式送出预测结果。
第五步,定义_predict函数,接收来自predict函数送过来的需要预测的单个数据,并求出需要预测的数据与训练集中的所有点欧式距离。之后根绝欧式距离的大小,对训练集的索引进行排序。之后按照索引,在y_test中输出K个对应的距离最近数据的状态值。之后发起投票,根据所找到的K个最近距离的训练集元素的状态值,输出需要预测值的预测状态。
封装kNN准确度预测
实现代码如下。这部分代码逻辑很清晰,就不解释了。
import numpy as np
def accuracy_score(y_true, y_predict):
'''计算y_true和y_predict之间的准确率'''
assert y_true.shape[0] == y_predict.shape[0], \
"the size of y_true must be equal to the size of y_predict"
return sum(y_true == y_predict) / len(y_true)
def score(self, X_test, y_test):
"""根据测试数据集 X_test 和 y_test 确定当前模型的准确度"""
y_predict = self.predict(X_test)
return accuracy_score(y_test, y_predict)
网友评论