【机器学习-数据科学】第一节：numpy&pandas

安装numpy&pandas

import numpy as np
array=np.array([[1,2,3],
                [2,3,4]])# 将数组转化为矩阵
print(array) #打印矩阵
print('number of dim:',array.ndim)  #几维
print('shape:',array.shape)  #大小，几行几列
print('size:',array.size)  #元素的大小

结果：

[[1 2 3]
 [2 3 4]]
number of dim: 2
shape: (2, 3)
size: 6

Process finished with exit code 0

array创建

import numpy as np
a=np.array([2,23,4],dtype=np.int)  #创建时使用列表 并且确定类型
print(a.dtype)

b=np.zeros((3,4))
print(b)

c=np.ones((3,4),dtype=np.int)
print(c)


d=np.empty((3,4))
print(d)

e=np.arange(10,100,10)
print(e)

f=np.arange(12).reshape((3,4))
print(f)

g=np.linspace(10,100,10)
print(g)

h=np.linspace(10,100,10).reshape((2,5))
print(h)

int32
[[0. 0. 0. 0.]
 [0. 0. 0. 0.]
 [0. 0. 0. 0.]]
[[1 1 1 1]
 [1 1 1 1]
 [1 1 1 1]]
[[0. 0. 0. 0.]
 [0. 0. 0. 0.]
 [0. 0. 0. 0.]]
[10 20 30 40 50 60 70 80 90]
[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
[ 10.  20.  30.  40.  50.  60.  70.  80.  90. 100.]
[[ 10.  20.  30.  40.  50.]
 [ 60.  70.  80.  90. 100.]]

Process finished with exit code 0

numpy的基础运算

1.加减乘除 求和

import numpy as np
a=np.array([10,20,30,40])
b=np.arange(4)
c=a-b    #加减
print(a,b,c)

d=a**2  #平方d
e=10*np.sin(a) #三角函数
print(d,e)

print(b)
print(b<3) #哪些值小于3

#矩阵运算
f=np.array([[10,20],
           [30,40]])
g=np.arange(4).reshape((2,2))
print(f)
print(g)
#
h=f*g
print('逐个相乘结果：\n',h)

h_dot=np.dot(f,g)
h_dot2=f.dot(g)
print('矩阵相乘结果：\n',h_dot)
print('矩阵相乘结果2：\n',h_dot2)

[10 20 30 40] [0 1 2 3] [10 19 28 37]
[ 100  400  900 1600] [-5.44021111  9.12945251 -9.88031624  7.4511316 ]
[0 1 2 3]
[ True  True  True False]
[[10 20]
 [30 40]]
[[0 1]
 [2 3]]
逐个相乘结果：
 [[  0  20]
 [ 60 120]]
矩阵相乘结果：
 [[ 40  70]
 [ 80 150]]
矩阵相乘结果2：
 [[ 40  70]
 [ 80 150]]

Process finished with exit code 0

#求和 最大最小值
import numpy as np
a=np.random.random((2,4))
print(a)
print(np.sum(a))
print(np.sum(a,axis=1))  #axis=1 是在列中求和，axis=0是在行中求和
print(np.min(a))
print(np.min(a,axis=0))
print(np.max(a))

[[0.85663257 0.60903081 0.32588806 0.17383597]
 [0.82810401 0.86504537 0.35610231 0.95728784]]
4.9719269475592105
[1.96538742 3.00653953]
0.17383597454524058
[0.82810401 0.60903081 0.32588806 0.17383597]
0.9572878423829763

Process finished with exit code 0

2.其他运算

import numpy as np
A =np.arange(2,14).reshape((3,4))
print(A)
#最小/大值的索引
print(np.argmin(A))
print(np.argmax(A))

#平均值
print(np.mean(A))
print(A.mean())
print(np.average(A))
#print(A.average()) #这个版本不适用
#中位数
print('中位数：',np.median(A),"\n")

#累计相加
print(A)
print('累计相加:\n',np.cumsum(A),'\n')
#累差
print(A)
print('累差:\n',np.diff(A),'\n')

print('行列:\n',np.nonzero(A),'\n')

A=np.arange(14,2,-1).reshape((3,4))
print(A)
print('排序:\n',np.sort(A),'\n')   #逐行排序


print(A)
print('转置')
print(np.transpose(A))
print(A.T)
print((A.T).dot(A))

print(A)
print('截取给定的数')
print('给定小于5的数等于5，大于9的数等于9\n',np.clip(A,5,9))

print('axis=1 是在列中求和，axis=0是在行中求和')
print('求行中的平均值：')
print(np.mean(A,axis=0))

[[ 2  3  4  5]
 [ 6  7  8  9]
 [10 11 12 13]]
0
11
7.5
7.5
7.5
中位数： 7.5 

[[ 2  3  4  5]
 [ 6  7  8  9]
 [10 11 12 13]]
累计相加:
 [ 2  5  9 14 20 27 35 44 54 65 77 90] 

[[ 2  3  4  5]
 [ 6  7  8  9]
 [10 11 12 13]]
累差:
 [[1 1 1]
 [1 1 1]
 [1 1 1]] 

行列:
 (array([0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2], dtype=int64), array([0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3], dtype=int64)) 

[[14 13 12 11]
 [10  9  8  7]
 [ 6  5  4  3]]
排序:
 [[11 12 13 14]
 [ 7  8  9 10]
 [ 3  4  5  6]] 

[[14 13 12 11]
 [10  9  8  7]
 [ 6  5  4  3]]
转置
[[14 10  6]
 [13  9  5]
 [12  8  4]
 [11  7  3]]
[[14 10  6]
 [13  9  5]
 [12  8  4]
 [11  7  3]]
[[332 302 272 242]
 [302 275 248 221]
 [272 248 224 200]
 [242 221 200 179]]
[[14 13 12 11]
 [10  9  8  7]
 [ 6  5  4  3]]
截取给定的数
给定小于5的数等于5，大于9的数等于9
 [[9 9 9 9]
 [9 9 8 7]
 [6 5 5 5]]
axis=1 是在列中求和，axis=0是在行中求和
求行中的平均值：
[10.  9.  8.  7.]

numpy的索引

import numpy as np
A=np.arange(3,15).reshape((3,4))
print(A,"\n")
print(A[2])
print(A[2][2])
print(A[2,2])  #与上面同样功能
print(A[2,:])  #第二行所有数
print(A[:,1])  #第一列所有数
print('A:\n',A)

print('第二行，第一列到第二列:')
print(A[2,1:3],'\n')  #第二行，第一列到第二列

print(A)
print('打印每一行：')
for row in A:
    print(row)
print('打印每一列：')
for column in A.T:
    print(column)

print('打印出每个项目:')
print(A.flatten())  #返回一个array，flat是一个迭代器
for item in A.flat:
    print(item)

[[ 3  4  5  6]
 [ 7  8  9 10]
 [11 12 13 14]] 

[11 12 13 14]
13
13
[11 12 13 14]
[ 4  8 12]
A:
 [[ 3  4  5  6]
 [ 7  8  9 10]
 [11 12 13 14]]
第二行，第一列到第二列:
[12 13] 

[[ 3  4  5  6]
 [ 7  8  9 10]
 [11 12 13 14]]
打印每一行：
[3 4 5 6]
[ 7  8  9 10]
[11 12 13 14]
打印每一列：
[ 3  7 11]
[ 4  8 12]
[ 5  9 13]
[ 6 10 14]
打印出每个项目:
[ 3  4  5  6  7  8  9 10 11 12 13 14]
3
4
5
6
7
8
9
10
11
12
13
14

Process finished with exit code 0

numpy的 array 合并

import numpy as np
A=np.array([1,1,1])
B=np.array([2,2,2])

C=np.vstack((A,B)) #vertical stack
D=np.hstack((A,B))  #horizontal stack
print(C)
print(D)
print(A.shape,C.shape,D.shape)
print(A.T)
print(A.T.shape) #么有改成列，要怎么改成列呢？看下面

# print(A[np.newaxis,:]) #在行加一个维度
# print(A[:,np.newaxis]) #在列加一个维度
print(A[:,np.newaxis]) #在列加一个维度
print(B[:,np.newaxis])

C= np.concatenate((A,B,B,A),axis=0)
print(C)

[[1 1 1]
 [2 2 2]]
[1 1 1 2 2 2]
(3,) (2, 3) (6,)
[1 1 1]
(3,)
[[1]
 [1]
 [1]]
[[2]
 [2]
 [2]]
[1 1 1 2 2 2 2 2 2 1 1 1]

Process finished with exit code 0

numpy的 array分割

import numpy as np

A =np.arange(12).reshape((3,4))
print(A)

print(np.split(A,3,axis=0))

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
[array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8,  9, 10, 11]])]

Process finished with exit code 0

但是机器学习里经常需要实现不等量分割：

import numpy as np

A =np.arange(12).reshape((3,4))
print(A)

print(np.array_split(A,3,axis=1))

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
[array([[0, 1],
       [4, 5],
       [8, 9]]), array([[ 2],
       [ 6],
       [10]]), array([[ 3],
       [ 7],
       [11]])]

Process finished with exit code 0

另外一种用法：

import numpy as np

A =np.arange(12).reshape((3,4))
print(A)

#print(np.array_split(A,3,axis=1))

print(np.vsplit(A,3))
print(np.hsplit(A,2))

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
[array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8,  9, 10, 11]])]
[array([[0, 1],
       [4, 5],
       [8, 9]]), array([[ 2,  3],
       [ 6,  7],
       [10, 11]])]

Process finished with exit code 0

numpy的 copy & deep copy

import numpy as np
a=np.arange(4)
print(a)
b=a
c=a
d=b
a[0]=11
print(a)
print(b is a)
print(b,c,d)
#改变其中任意一个 都会改变
d[1:3]=[22,23]
print(b,c,d)

#deep copy
b=a.copy()  #把a的值赋给b，但是不关联
a[3]=45
print(a,b)
print(b is a)

[0 1 2 3]
[11  1  2  3]
True
[11  1  2  3] [11  1  2  3] [11  1  2  3]
[11 22 23  3] [11 22 23  3] [11 22 23  3]
[11 22 23 45] [11 22 23  3]
False

Process finished with exit code 0