k邻近法 KNN

import numpy as np
import tensorflow as tf
from sklearn import datasets

iris = datasets.load_iris()
x_vals = iris.data
y_vals = iris.target

#data process
x_vals_norm = (x_vals - x_vals.min(0))/(x_vals.max(0) - x_vals.min(0))# data standardization
train_indices = np.random.choice(len(x_vals),round(len(x_vals)*0.9),replace=False)
test_indices = np.array(list(set(range(len(x_vals))) - set(train_indices)))
x_train = x_vals_norm[train_indices,:]
x_test = x_vals_norm[test_indices,:]
y_train = y_vals[train_indices]
y_test = y_vals[test_indices]

def distance(x_train,x_test):
    dis = np.sum(np.square(x_train - x_test),1)
    return dis

def class_iris(dis,y_train,k):
    a = 0
    b = 0
    c = 0
    for i in range(k):
        index = np.argmin(dis)
        if y_train[index]==0:
            a = a+1
        elif y_train[index]==1:
            b = b+1
        else:
            c = c+1
        dis[index] = dis.max()
    d = np.array([a,b,c])
    ans = d.argmax()  
    return ans

def model(x_train,y_train,x_test,y_test,k = 10):
    num = x_test.shape[0]
    t = 0
    for i in range(num):
        dis = distance(x_train,x_test[i,:])
        ans = class_iris(dis,y_train,k)
        if ans == y_test[i]:
            t = t+1
    accuracy = t/num
    print('accurayc:' + str(accuracy))

model(x_train,y_train,x_test,y_test)