1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
| import tensorflow as tf
import numpy as np
import pandas as pd
TRAIN_URL='http://download.tensorflow.org/data/iris_training.csv'
train_path=tf.keras.utils.get_file(TRAIN_URL.split('/')[-1],TRAIN_URL)
print('Download location', train_path)
class KNN:
def __init__(self,k):
self.k=k
def fit(self,X,y):
self.X=np.asarray(X)
self.y=np.asarray(y)
def predict(self,X):
X=np.asarray(X)
result=[]
for x in X:
dis=np.sqrt(np.sum((x-self.X)**2,axis=1))
index=dis.argsort() # 对dis中的元素排序，返回排序的元素的索引
index=index[:self.k]
count=np.bincount(self.y[index]) # 对y的类别的计数器，以列表的形式表示数字的数量，比如np.bincount([1,2,1,2,3,4])=[0,2,2,1,1],ls=[0,2,2,1,1],ls[0]=0,ls[1]=2...
result.append(count.argmax())
return np.asarray(result)
# csv文件的第一行是乱的数据，从第二行开始读，并起列名。
data=pd.read_csv(train_path,skiprows=1,names=['a','b','c','d','label'])
print(data,type(data))
# 打乱
data=data.sample(frac=1)
print(data)
train_X=data.iloc[:90,:-1]
train_y=data.iloc[:90,-1]
test_X=data.iloc[90:,:-1]
test_y=data.iloc[90:,-1]
print(train_X,train_y)
knn=KNN(k=10)
knn.fit(train_X,train_y)
result=knn.predict(test_X)
print('accuracy',np.sum(result==test_y)/len(result))
|