参考[Numpy文档]https://docs.scipy.org/doc/numpy-dev/user/quickstart.html
Numpy的安装
MacOS
#使用Python3+
pip3 install numpy
#使用Python2+
pip install numpy
Ubuntu
在terminal中运行:
sudo apt-get install python-numpy
Numpy的属性
使用Numpy首先应当导入Module
import numpy as np
列表转化为矩阵
array = np.array([[1,2,3],[2,3,4]]
print(array)
"""
array([[1, 2, 3],
[2, 3, 4]])
"""
Numpy的重要属性:
nidm:维度
shape:行数和列数
size:元素个数
print('number of dim:',array.ndim) # 维度
# number of dim: 2
print('shape :',array.shape) # 行数和列数
# shape : (2, 3)
print('size:',array.size) # 元素个数
# size: 6
Numpy的创建array
关键字
array:创建数组
dtype:指定数据类型
zeros:创建数据全为0
ones:创建数据全为1
empty:创建数据接近0
arrange:按指定范围创建数据
linspace:创建线段
创建数组
a = np.array([2,23,4]) #list 1d
print(a)
#[2,23,4]
指定数据的type
a = np.array([2,23,4],dtype=np.int)
print(a.dtype)
# int 64
a = np.array([2,23,4],dtype=np.int32)
print(a.dtype)
# int32
a = np.array([2,23,4],dtype=np.float)
print(a.dtype)
# float64
a = np.array([2,23,4],dtype=np.float32)
print(a.dtype)
# float32
创建特定数据
注意array与ndarray的区别,array一般只用来处理向量,功能也相对较少。ndarray可以处理多维矩阵。
a = np.array([[2,23,4],[2,32,4]]) # 2d 矩阵 2行3列
print(a)
"""
[[ 2 23 4]
[ 2 32 4]]
"""
a = np.zeros((3,4)) # 数据全为0,3行4列
"""
array([[ 0., 0., 0., 0.],
[ 0., 0., 0., 0.],
[ 0., 0., 0., 0.]])
"""
a = np.ones((3,4),dtype = np.int) # 数据为1, 3行4列
"""
array([[1, 1, 1, 1],
[1, 1, 1, 1],
[1, 1, 1, 1]])
"""
a = np.empty((3,4)) # 数据为empty,3行4列
"""
array([[ 0.00000000e+000, 4.94065646e-324, 9.88131292e-324,
1.48219694e-323],
[ 1.97626258e-323, 2.47032823e-323, 2.96439388e-323,
3.45845952e-323],
[ 3.95252517e-323, 4.44659081e-323, 4.94065646e-323,
5.43472210e-323]])
"""
a = np.arange(10,20,2) # 10-19 的数据,2步长
"""
array([10, 12, 14, 16, 18])
"""
a = np.arange(12).reshape((3,4)) # 3行4列,0到11
"""
array([[ 0, 1, 2, 3],
[ 4, 5, 6, 7],
[ 8, 9, 10, 11]])
"""
a = np.linspace(1,10,20) # 开始端1,结束端10,且分割成20个数据,生成线段
"""
array([ 1. , 1.47368421, 1.94736842, 2.42105263,
2.89473684, 3.36842105, 3.84210526, 4.31578947,
4.78947368, 5.26315789, 5.73684211, 6.21052632,
6.68421053, 7.15789474, 7.63157895, 8.10526316,
8.57894737, 9.05263158, 9.52631579, 10. ])
"""
a = np.linspace(1,10,20).reshape((5,4)) # 更改shape
"""
array([[ 1. , 1.47368421, 1.94736842, 2.42105263],
[ 2.89473684, 3.36842105, 3.84210526, 4.31578947],
[ 4.78947368, 5.26315789, 5.73684211, 6.21052632],
[ 6.68421053, 7.15789474, 7.63157895, 8.10526316],
[ 8.57894737, 9.05263158, 9.52631579, 10. ]])
"""
注意,这里调用的许多方法中的参数都是tuple,其中arange()函数中的步长可以是float,由于浮点数的性质可能在运算前不知道这样的操作会产生长度几何的数据,所以一般使用linspace()做代替。
Numpy基础运算
从一个脚本开始聊Numpy相关的运算:
import numpy as np
a=np.array([10,20,30,40]) # array([10, 20, 30, 40])
b=np.arange(4) # array([0, 1, 2, 3])
Numpy的几种基本运算
矩阵的减法:
c = a - b # array([10, 19, 28, 37])
矩阵加法:
c = a + b
矩阵乘法: (这里的乘法指的是矩阵中的元素对应相乘)
c = a * b
矩阵乘方:
c=b**2 # array([0, 1, 4, 9])
Numpy中调用一些基本函数都需要从Numpy的Module中获得:
c=10*np.sin(a)
# array([-5.44021111, 9.12945251, -9.88031624, 7.4511316 ])
对多维矩阵而言:
a=np.array([[1,1],[0,1]])
b=np.arange(4).reshape((2,2))
print(a)
# array([[1, 1],
# [0, 1]])
print(b)
# array([[0, 1],
# [2, 3]])
标准的矩阵相乘:
c_dot = np.dot(a,b)
# array([[2, 4],
# [2, 3]])
针对大小比较而言,我们可以直接使用大小符号进行布尔运算,也可以通过Numpy自带的Module对最大值等数值特征进行计算:
import numpy as np
a=np.random.random((2,4))
print(a)
# array([[ 0.94692159, 0.20821798, 0.35339414, 0.2805278 ],
# [ 0.04836775, 0.04023552, 0.44091941, 0.21665268]])
np.sum(a) # 4.4043622002745959
np.min(a) # 0.23651223533671784
np.max(a) # 0.90438450240606416
print("a =",a)
# a = [[ 0.23651224 0.41900661 0.84869417 0.46456022]
# [ 0.60771087 0.9043845 0.36603285 0.55746074]]
print("sum =",np.sum(a,axis=1))
# sum = [ 1.96877324 2.43558896]
print("min =",np.min(a,axis=0))
# min = [ 0.23651224 0.41900661 0.36603285 0.46456022]
print("max =",np.max(a,axis=1))
# max = [ 0.84869417 0.9043845 ]
Numpy索引
import numpy as np
A = np.arange(2,14).reshape((3,4))
# array([[ 2, 3, 4, 5]
# [ 6, 7, 8, 9]
# [10,11,12,13]])
print(np.argmin(A)) # 0
print(np.argmax(A)) # 11
num中的基本统计运算
求平均:
print(np.mean(A)) # 7.5
print(np.average(A)) # 7.5
print(A.mean())
求中位数:
print(A.median())
求相邻和:
print(np.cumsum(A))
# [2 5 9 14 20 27 35 44 54 65 77 90]
求相邻差:
print(np.diff(A))
# [[1 1 1]
# [1 1 1]
# [1 1 1]]
nonzero()函数(将所有非零元素的行与列坐标隔开,重构成两个分别关于行和列的矩阵):
print(np.nonzero(A))
# (array([0,0,0,0,1,1,1,1,2,2,2,2]),array([0,1,2,3,0,1,2,3,0,1,2,3]))
排序(每一行从大到小):
import numpy as np
A = np.arange(14,2, -1).reshape((3,4))
# array([[14, 13, 12, 11],
# [10, 9, 8, 7],
# [ 6, 5, 4, 3]])
print(np.sort(A))
# array([[11,12,13,14]
# [ 7, 8, 9,10]
# [ 3, 4, 5, 6]])
矩阵的转置:(这里的转置不适用与向量)
print(np.transpose(A))
print(A.T)
# array([[14,10, 6]
# [13, 9, 5]
# [12, 8, 4]
# [11, 7, 3]])
# array([[14,10, 6]
# [13, 9, 5]
# [12, 8, 4]
# [11, 7, 3]])
有趣的clip()函数:
#clip(Array,Array_min,Array_max)
#Array指的是将要被执行用的矩阵,而后面的最小值最大值则用于让函数判断矩阵中元素是否有比最小值小的或者比最大值大的元素,并将这些指定的元素转换为最小值或者最大值。
print(A)
# array([[14,13,12,11]
# [10, 9, 8, 7]
# [ 6, 5, 4, 3]])
print(np.clip(A,5,9))
# array([[ 9, 9, 9, 9]
# [ 9, 9, 8, 7]
# [ 6, 5, 5, 5]])
Numpy索引
一维索引
与一般的Python list 相同
多维索引
A = np.arange(3,15).reshape((3,4))
"""
array([[ 3, 4, 5, 6]
[ 7, 8, 9, 10]
[11, 12, 13, 14]])
"""
print(A[2])
# [11 12 13 14]
取以上二位矩阵中的元素:
print(A[1][1]) # 8
print(A[1, 1]) # 8
元素的slice:
print(A[1, 1:3]) # [8 9]
迭代:
for row in A: #遍历每一行
print(row)
"""
[ 3, 4, 5, 6]
[ 7, 8, 9, 10]
[11, 12, 13, 14]
"""
for column in A.T:
print(column)
"""
[ 3, 7, 11]
[ 4, 8, 12]
[ 5, 9, 13]
[ 6, 10, 14]
"""
flatten是一个展开性质的函数,将多维的矩阵展开成一行的数列。flat是一个迭代器,本身是object属性。
import numpy as np
A = np.arange(3,15).reshape((3,4))
print(A.flatten())
# array([3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14])
for item in A.flat:
print(item)
# 3
# 4
……
# 14
Numpy合并
np.vstack():按垂直方向的合并
import numpy as np
A = np.array([1,1,1])
B = np.array([2,2,2])
print(np.vstack((A,B))) # vertical stack
"""
[[1,1,1]
[2,2,2]]
"""
np.hstack():按水平方向的合并
D = np.hstack(A,B)
print(D)
# [1,1,1,2,2,2]
print(A.shape,D.shape)
# (3,) (6,)# [1,1,1,2,2,2]
print(A.shape,D.shape)
# (3,) (6,)
前一节中说的向量不可以使用 .T 进行转置操作,这里给出应当采用的方法:
print(A[np.newaxis,:])
# [[1 1 1]]
print(A[np.newaxis,:].shape)
# (1,3)
print(A[:,np.newaxis])
"""
[[1]
[1]
[1]]
"""
print(A[:,np.newaxis].shape)
# (3,1)
针对多个矩阵和序列的合并方法:
C = np.concatenate((A,B,B,A),axis=0)
print(C)
"""
array([[1],
[1],
[1],
[2],
[2],
[2],
[2],
[2],
[2],
[1],
[1],
[1]])
"""
D = np.concatenate((A,B,B,A),axis=1)
print(D)
"""
array([[1, 2, 2, 1],
[1, 2, 2, 1],
[1, 2, 2, 1]])
"""
Numpy分割
创建数据:
import numpy as np
A = np.arange(12).reshape((3, 4))
print(A)
"""
array([[ 0, 1, 2, 3],
[ 4, 5, 6, 7],
[ 8, 9, 10, 11]])
"""
纵向分割:
print(np.split(A, 2, axis=1)) #只是等分成2份
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2, 3],
[ 6, 7],
[10, 11]])]
"""
横向分割:
print(np.split(A,2,axis=0))
# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8, 9, 10, 11]])]
不等量的分割:np.array_split()
print(np.array_split(A,3,axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2],
[ 6],
[10]]), array([[ 3],
[ 7],
[11]])]
"""
其他分割:
np.vsplit()
np.hsplit()
print(np.vsplit(A, 3)) #等于 print(np.split(A, 3, axis=0))
# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8, 9, 10, 11]])]
print(np.hsplit(A, 2)) #等于 print(np.split(A, 2, axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2, 3],
[ 6, 7],
[10, 11]])]
"""
Numpy copy & deep copy
注意在Numpy中和一般的Python中变量赋值的区别:
= 的赋值带有关联性:
import numpy as np
a = np.arange(4)
# array([0, 1, 2, 3])
b = a
c = a
d = b
改变a的第一个值,b,c,d的第一个值也会改变:
a[0] = 11
print(a)
# array([11, 1, 2, 3])
#确认b,c,d是否与a相同
b is a # True
c is a # True
d is a # True
d[1:3] = [22, 33] # array([11, 22, 33, 3])
print(a) # array([11, 22, 33, 3])
print(b) # array([11, 22, 33, 3])
print(c) # array([11, 22, 33, 3])
copy()的赋值方法没有关联性:
b = a.copy() # deep copy
print(b) # array([11, 22, 33, 3])
a[3] = 44
print(a) # array([11, 22, 33, 44])
print(b) # array([11, 22, 33, 3])