KNN算法（2）
机器学习算法封装
scikit-learn中的机器学习算法封装
在python chame中将算法写好
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]
将所需要的数据提前准备好
使用魔法命令%run调用函数
%run KNN.py
执行即可得到预测结果
k近邻算法是非常特殊的，可以被认为是没有模型的算法，为了和其他的算法统一，可以认为训练数据集就是魔性本身
使用scikit-learn中的kNN
需要调用KNeighborsClassifier类
创建实例，其中n_neighbors=6相当于k=6
然后进行fit操作
kNN_classifier.fit(X_train,y_train)
其返回值就是自身，可以不用接参数
调用predict方法即可实现
不过需要注意的是，这个必须是一个矩阵，不能是一维数组
因此我们先reshape改变结构
最后就可以得到预测的类别
重新整理我们的kNN代码
在同一个文件夹下创建一个kNN1.py的文件
写入KNN算法
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], \
"this 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
同上操作，即可得到
