python机器学习之KNN算法

K邻近算法（kNeighbrClassifier/KNN）：原理为 欧几里得距离+最近+投票(权重)+概率

　　根据距离的远近进行分类

　　欧几里得距离：多维空间中各点之间的距离

　　　

　　缺点：时间复杂度和空间复杂度较大

　　注意：当训练样本数据少的时候，样本比例一定要相同；训练的数据不能是string

　　KNN算法分类电影

 

import numpy

import pandas   #导入Excel文件

from sklearn.neighbors import KNeighborsClassifier   #机器学习算法库，没有深度学习算法

movie=pandas.read_excel(r"D:Python代码Machine-Learn1-KNNdatamovie.xlsx",sheet_name=0)

movie

 

 

	电影名称	武打镜头	接吻镜头	分类情况
0	大话西游	36	1	动作片
1	杀破狼	43	2	动作片
2	前任3	0	10	爱情片
3	战狼2	59	1	动作片
4	泰坦尼克号	1	15	爱情片
5	新余心愿	2	19	爱情片

movie=pandas.read_excel(r"D:Python代码Machine-Learn1-KNNdatamovie.xlsx",sheet_name=0)
x=movie[["武打镜头","接吻镜头"]]    #取出训练数据中的训练数据
y=movie["分类情况"]                 #取出目标值
knn=KNeighborsClassifier(n_neighbors=5)
knn.fit(x,y)       #训练数据
#预测电影《飞车》武打镜头50，接吻镜头2
x_text=pandas.DataFrame({"武打镜头":[50,3],"接吻镜头":[2,50]})
x_text

	武打镜头	接吻镜头
0	50	2
1	3	50

get_result=knn.predict(x_text)
get_proba=knn.predict_proba(x_text)
print("概率：{}".format(get_proba))
print("分类结果：{}".format(get_result))

概率：[[0.6 0.4]
 [0.4 0.6]]
分类结果：['动作片' '爱情片']

电影分类运行原理

s=((movie["武打镜头"]-50)**2+(movie["接吻镜头"]-2)**2)**0.5     #根据knn算法求距离
index=s.sort_values().index     #先将数据排序然后取出索引
fljg=movie["分类情况"][index[:5]]
print("
{}".format(index),"
分类：
{}".format(fljg))

Int64Index([1, 3, 0, 2, 4, 5], dtype='int64') 
分类：
1    动作片
3    动作片
0    动作片
2    爱情片
4    爱情片
Name: 分类情况, dtype: object

识别梵文

import numpy
import os
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
img=plt.imread(r"D:Python代码Machine-Learn1-KNNdata手写字母测试与训练梵文识别学习Testcharacter_1_ka1339.png")
plt.imshow(img,cmap=plt.cm.gray)

<matplotlib.image.AxesImage at 0x1af31dcc048> 

　　　　  

#将读取的图片保存到数组data中
def img_read(dir_name,data):
    for filename in os.listdir(dir_name):
        img=plt.imread(dir_name+"\"+filename)
        data.append(img)
def readTain():      #获取训练数据
    data=[]
    dir_path=r"D:Python代码Machine-Learn1-KNNdata手写字母测试与训练梵文识别学习Train"
    for dir_name in os.listdir(dir_path)[36:]:
        dir_name=dir_path+"\"+dir_name
        img_read(dir_name,data)
    return data
def readTest():     #获取测试数据
    data_test=[]
    dir_test_path=r"D:Python代码Machine-Learn1-KNNdata手写字母测试与训练梵文识别学习Test"
    for dir_name in os.listdir(dir_test_path)[36:]:
        dir_name=dir_test_path+"\"+dir_name
        img_read(dir_name,data_test)
    return data_test
x=readTain()        #训练数据
train_x=numpy.array(x)
train_x_shape={}
train_x_shape["图片数量"]=test_x.shape[0]
train_x_shape["宽度"]=str(test_x.shape[1])+"px"
train_x_shape["高度"]=str(test_x.shape[2])+"px"
train_x_shape

{'图片数量': 3000, '宽度': '32px', '高度': '32px'}

x=readTest()       #测试数据
ndarray_x=numpy.array(x)
# 随机抽样测试数据
index=numpy.random.randint(0,3000,size=1000)
test_x=ndarray_x[index]
test_x_shape={}
test_x_shape["图片数量"]=test_x.shape[0]
test_x_shape["宽度"]=str(test_x.shape[1])+"px"
test_x_shape["高度"]=str(test_x.shape[2])+"px"
test_x_shape

{'图片数量': 1000, '宽度': '32px', '高度': '32px'}

# 对应的数字
num=[0,1,2,3,4,5,6,7,8,9]*300
test_y=numpy.array(num)
test_y.sort()
test_y=test_y[index]
test_y

array([0, 9, 8, 0, 3, 3, 0, 6, 6, 2, 1, 0, 2, 9, 0, 5, 5, 1, 7, 3, 1, 9,
       7, 3, 0, 8, 8, 4, 0, 5, 7, 7, 4, 3, 3, 1, 8, 2, 6, 1, 5, 0, 8, 6,
       0, 2, 7, 4, 3, 1, 9, 8, 9, 4, 2, 7, 5, 3, 0, 5, 9, 4, 1, 8, 5, 7,
       6, 5, 0, 9, 9, 1, 4, 9, 9, 5, 2, 6, 4, 6, 2, 2, 2, 6, 7, 7, 4, 3,
       8, 7, 2, 5, 4, 2, 6, 0, 9, 9, 5, 8, 4, 3, 7, 5, 0, 1, 5, 7, 1, 3,
       3, 9, 5, 8, 6, 6, 7, 5, 6, 5, 1, 6, 0, 3, 6, 3, 5, 3, 4, 5, 8, 9,
       7, 2, 3, 9, 5, 6, 6, 0, 3, 2, 3, 5, 8, 8, 8, 2, 3, 0, 7, 9, 6, 0,
       9, 8, 8, 6, 6, 6, 9, 2, 8, 6, 6, 7, 4, 6, 1, 7, 2, 4, 2, 6, 6, 7,
       9, 4, 9, 0, 7, 6, 6, 7, 9, 9, 5, 3, 1, 1, 8, 1, 0, 6, 6, 3, 5, 4,
       7, 3, 3, 5, 0, 3, 1, 9, 2, 9, 7, 0, 6, 1, 2, 6, 4, 2, 3, 0, 4, 3,
       4, 9, 2, 6, 8, 4, 2, 1, 5, 1, 0, 7, 9, 2, 4, 8, 4, 4, 5, 0, 4, 1,
       1, 5, 0, 4, 4, 7, 4, 1, 2, 1, 0, 1, 2, 5, 6, 6, 1, 7, 6, 7, 6, 5,
       0, 2, 4, 8, 7, 7, 9, 8, 1, 7, 9, 8, 5, 0, 2, 9, 7, 8, 2, 0, 5, 4,
       3, 3, 6, 1, 4, 5, 9, 9, 5, 4, 0, 9, 9, 4, 3, 9, 8, 2, 3, 5, 6, 4,
       8, 5, 0, 2, 6, 5, 5, 7, 2, 1, 8, 6, 4, 7, 9, 7, 2, 6, 4, 4, 3, 9,
       5, 4, 4, 0, 5, 1, 5, 8, 9, 6, 5, 3, 2, 3, 4, 1, 6, 0, 0, 8, 1, 3,
       0, 4, 0, 6, 5, 9, 0, 8, 7, 5, 4, 2, 0, 3, 8, 4, 3, 2, 0, 5, 0, 8,
       3, 1, 2, 5, 6, 3, 6, 0, 5, 9, 9, 8, 2, 3, 2, 1, 4, 6, 1, 7, 9, 2,
       1, 5, 4, 1, 3, 3, 9, 5, 1, 4, 0, 1, 7, 2, 4, 3, 4, 0, 0, 0, 3, 5,
       0, 4, 3, 5, 3, 0, 7, 7, 5, 1, 7, 2, 5, 8, 0, 0, 5, 1, 9, 5, 8, 8,
       5, 4, 9, 7, 4, 2, 9, 2, 9, 5, 8, 8, 4, 9, 7, 1, 5, 1, 1, 0, 6, 9,
       1, 6, 3, 3, 7, 1, 6, 0, 7, 8, 7, 3, 6, 7, 9, 1, 1, 1, 8, 8, 8, 9,
       1, 4, 5, 1, 0, 7, 3, 2, 9, 3, 7, 7, 1, 7, 6, 8, 3, 8, 3, 0, 4, 3,
       1, 0, 3, 3, 2, 5, 6, 6, 6, 2, 9, 4, 6, 3, 7, 6, 1, 8, 8, 4, 2, 6,
       3, 7, 8, 0, 6, 4, 4, 9, 9, 2, 3, 5, 9, 2, 1, 4, 3, 9, 5, 8, 9, 5,
       5, 2, 2, 7, 4, 5, 4, 6, 4, 0, 5, 9, 6, 4, 6, 9, 2, 0, 4, 6, 6, 7,
       5, 8, 8, 8, 5, 8, 9, 0, 0, 3, 2, 7, 7, 3, 3, 4, 5, 2, 3, 3, 1, 0,
       9, 1, 1, 8, 1, 3, 9, 8, 7, 1, 6, 9, 1, 7, 8, 4, 9, 5, 6, 4, 2, 3,
       8, 3, 4, 8, 3, 8, 7, 5, 5, 0, 6, 2, 9, 8, 6, 6, 6, 5, 2, 9, 0, 1,
       8, 1, 2, 6, 6, 6, 5, 4, 3, 2, 0, 6, 6, 3, 4, 5, 3, 8, 6, 4, 5, 4,
       7, 6, 5, 4, 5, 8, 9, 4, 5, 5, 2, 5, 1, 5, 6, 4, 4, 1, 4, 1, 9, 8,
       8, 7, 1, 9, 3, 5, 2, 5, 8, 0, 2, 7, 2, 2, 7, 5, 8, 0, 6, 0, 7, 0,
       4, 2, 8, 6, 3, 3, 3, 8, 3, 6, 7, 5, 3, 9, 3, 8, 5, 8, 6, 2, 2, 0,
       1, 9, 2, 6, 2, 8, 6, 0, 7, 0, 3, 4, 9, 4, 1, 2, 2, 3, 5, 5, 7, 9,
       9, 7, 0, 6, 5, 8, 3, 1, 6, 8, 4, 1, 6, 7, 3, 9, 5, 1, 4, 5, 7, 1,
       0, 5, 9, 4, 9, 5, 3, 6, 2, 2, 2, 3, 9, 0, 0, 2, 3, 2, 9, 9, 1, 8,
       4, 7, 1, 1, 2, 4, 3, 4, 9, 7, 4, 7, 8, 6, 0, 4, 8, 7, 0, 6, 0, 5,
       4, 0, 9, 7, 2, 9, 4, 0, 3, 0, 8, 4, 3, 5, 4, 5, 2, 2, 2, 7, 9, 0,
       7, 2, 1, 5, 3, 6, 5, 3, 3, 1, 3, 4, 6, 4, 1, 5, 7, 7, 0, 7, 0, 3,
       1, 2, 2, 3, 6, 1, 8, 3, 9, 5, 9, 7, 7, 8, 4, 3, 0, 1, 5, 1, 7, 5,
       8, 5, 8, 5, 1, 7, 4, 8, 0, 2, 8, 8, 3, 2, 8, 6, 2, 1, 0, 2, 7, 3,
       4, 2, 6, 3, 3, 9, 9, 1, 8, 9, 7, 4, 9, 8, 4, 4, 7, 0, 7, 0, 2, 0,
       0, 2, 8, 7, 3, 6, 6, 2, 4, 2, 0, 4, 9, 0, 4, 3, 7, 5, 7, 7, 2, 6,
       9, 3, 1, 0, 4, 1, 7, 8, 4, 5, 1, 4, 1, 0, 9, 3, 9, 3, 7, 1, 9, 2,
       0, 2, 5, 2, 9, 1, 6, 0, 2, 1, 8, 5, 0, 1, 8, 2, 0, 0, 8, 3, 1, 1,
       9, 5, 9, 7, 5, 6, 5, 7, 1, 1])

# 对应的数字
num=[0,1,2,3,4,5,6,7,8,9]*1700
train_y=numpy.array(num)
train_y.sort()
train_y

array([0, 0, 0, ..., 9, 9, 9])

# 将三维数据变为二维，fit训练数据不支持二维以上数据
train_x.reshape(17000,1024)
test_x.reshape(1000,1024)

array([[0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       ...,
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.]], dtype=float32)

# %%time
# 训练数据
knn=KNeighborsClassifier(n_neighbors=5)
knn.fit(train_x.reshape(17000,-1),train_y)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
                     metric_params=None, n_jobs=None, n_neighbors=5, p=2,
                     weights='uniform')

# %%time
# 获得结果
y_result=knn.predict(test_x.reshape(1000,1024))
print("预测结果：
{}".format(y_result[500:700]),"
实际结果：
{}".format(test_y[500:700]))

预测结果：
[6 3 2 8 5 0 2 8 4 3 7 2 7 7 9 1 5 3 4 0 9 5 2 0 5 2 0 0 0 8 0 9 0 4 9 9 4
 1 3 6 0 8 6 4 6 8 2 0 7 3 2 5 6 1 4 7 7 4 5 9 7 9 0 7 0 2 1 8 7 5 4 9 2 4
 7 9 8 2 6 7 3 1 6 9 6 8 7 0 1 0 2 2 0 3 3 0 5 9 5 2 2 8 2 9 7 9 8 3 9 8 9
 0 7 4 2 4 9 0 3 4 3 8 6 2 2 9 5 3 1 8 2 5 1 3 7 2 7 3 2 8 1 3 5 2 1 7 9 4
 4 6 9 2 9 8 9 4 5 2 2 9 1 4 9 1 9 4 1 7 2 1 2 0 3 1 8 3 5 9 0 8 3 6 6 8 1
 6 1 2 0 0 0 2 1 0 5 7 9 2 7 9] 
实际结果：
[6 3 2 8 5 0 2 8 4 3 7 2 7 7 9 1 5 3 4 6 9 5 2 0 3 2 0 0 0 8 0 9 0 4 9 9 4
 1 3 6 0 8 6 4 6 8 2 0 7 3 2 5 6 1 4 7 7 4 5 9 7 9 0 7 0 2 1 8 7 5 4 9 2 4
 7 9 8 2 6 7 3 1 6 9 6 8 7 0 1 0 2 2 0 3 3 0 5 9 5 2 2 8 2 9 7 9 8 3 9 8 9
 0 7 4 2 4 9 0 3 4 3 8 6 2 2 9 3 3 1 8 2 5 1 3 7 2 7 3 2 8 1 3 5 2 1 7 9 4
 4 6 9 2 9 8 9 4 5 5 2 9 1 4 9 1 9 4 1 7 2 1 2 0 3 1 8 3 5 9 0 8 3 6 6 8 1
 6 1 2 0 0 0 2 1 0 5 7 9 2 7 9]

# 准确率
acc=(test_y==y_result).mean()
print("准确率为：{}".format(acc))

准确率为：0.984

提高准确率

# 准确率与邻居数无关
knn=KNeighborsClassifier(n_neighbors=10)
knn.fit(train_x.reshape(17000,-1),train_y)
# score（）方法既可以预测还可以求出准确率
knn.score(test_x.reshape(1000,1024),test_y)

0.974

# 改变权重为邻居数距离越近权重越高，距离越远权重越低；有的时候可以提高，有的时候不能提高
knn=KNeighborsClassifier(n_neighbors=5,weights="distance")
knn.fit(train_x.reshape(17000,-1),train_y)
# score（）方法既可以预测还可以求出准确率
knn.score(test_x.reshape(1000,1024),test_y)

0.981

# p=1，使用曼哈顿距离为算法核心
# n_jobs是进程数，当=-1时，CPU有几个核就开启几个进程，提高运行速度
knn=KNeighborsClassifier(n_neighbors=5,weights="distance",n_jobs=-1)
knn.fit(train_x.reshape(17000,-1),train_y)
# score（）方法既可以预测还可以求出准确率
knn.score(test_x.reshape(1000,1024),test_y)

0.981