数据处理：Numpy & Pandas
本文来自B站up莫烦python的视频教学，在此感谢
https://www.bilibili.com/video/BV1Ex411L7oT
文章目录
1 Numpy
导入numpy
import numpy as np
1.1 Numpy数组
创建数组
a = np.array([2,3,4]) # 一维
b = np.array([[2,3,4],[1,2,3]]) # 二维
c = np.zero((3,4)) # 三行四列元素全为0的矩阵
d = np.ones((3,4)) # 三行四列元素全为1的矩阵
"""
array([[1, 1, 1, 1],
[1, 1, 1, 1],
[1, 1, 1, 1]])
"""
e = 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]])
"""
f = np.arange(10,20,2) # 10-19 的数据，2步长
"""
array([10, 12, 14, 16, 18])
"""
指定元素类型
a = np.array([2,3,4],dtype=np.float)
print(a.dtype)
改变形状
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]])
"""
linspace：arrange的“变种”
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. ])
"""
1.2 Numpy的运算1
Numpy支持元素的+、-、*运算
此外还有
乘方
c=b**2 # array([0, 1, 4, 9])
三角函数的运算
c=10*np.sin(a)
# array([-5.44021111, 9.12945251, -9.88031624, 7.4511316 ])
逻辑判断
（返回的是一个bool类型的矩阵）
print(b<3)
# array([ True, True, True, False], dtype=bool)
标准矩阵乘法 dot
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]])
c_dot = np.dot(a,b)
# array([[2, 4],
# [2, 3]])
c_dot_2 = a.dot(b)
# array([[2, 4],
# [2, 3]])
其他运算
Numpy矩阵对 random、max、min、sum 的应用
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]])
# 生成2行4列矩阵，每个元素0-1的随机数
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]
# 按行求合
print("min =",np.min(a,axis=0))
# min = [ 0.23651224 0.41900661 0.36603285 0.46456022]
# 每一列的最小值
print("max =",np.max(a,axis=1))
# max = [ 0.84869417 0.9043845 ]
# 每一行的最大值
1.3 Numpy的运算3
最大值和最小值
求矩阵最小值和最大值的索引
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
均值与中位数
整个矩阵的均值中位数
print(np.mean(A)) # 7.5
print(np.average(A)) # 7.5
print(A.median()) # 7.5
axis的操作同样适用与均值，同时还可以指定权重
b = np.array([1, 2, 3, 4])
wts = np.array([4, 3, 2, 1])
print('不指定权重\n', np.average(b))
print('指定权重\n', np.average(b, weights=wts))
两种矩阵转置
print(np.transpose(A))
print(A.T)
# array([[14,10, 6]
# [13, 9, 5]
# [12, 8, 4]
# [11, 7, 3]])
累加函数与累差函数
print(np.cumsum(A))
# [2 5 9 14 20 27 35 44 54 65 77 90]
print(np.diff(A))
# [[1 1 1]
# [1 1 1]
# [1 1 1]]
# A = array([[ 2, 3, 4, 5]
# [ 6, 7, 8, 9]
# [10,11,12,13]])
其他函数
nonzero()，将矩阵中所有非0元素的行和列拆成两个矩阵
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
print(np.sort(A))
# array([[11,12,13,14]
# [ 7, 8, 9,10]
# [ 3, 4, 5, 6]])
clip()函数：将矩阵中的元素都转换为固定区间的元素
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]])
1.4 Numpy 索引
Numpy 支持[]索引，和数组一样
如果矩阵是二维的，则有
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]
二维索引
访问单个元素的两种办法
print(A[1][1]) # 8
print(A[1, 1]) # 8
切片操作
print(A[1, 1:3]) # [8 9]
逐行输出和逐列输出
for row in A:
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]
"""
迭代输出
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
1.5 Numpy array 合并
上下合并 vstack()
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]]
"""
左右合并 hstack()
D = np.hstack((A,B)) # horizontal stack
print(D)
# [1,1,1,2,2,2]
print(A.shape,D.shape)
# (3,) (6,)
newaxis()
有些矩阵可能无法通过 .T 进行转置，这时候可以借助newaxis()
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)
多个矩阵操作：concatenate()
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]])
"""
1.6 Numpy Array分割
创建array
A = np.arange(12).reshape((3, 4))
print(A)
"""
array([[ 0, 1, 2, 3],
[ 4, 5, 6, 7],
[ 8, 9, 10, 11]])
"""
等量分割
纵向分割
print(np.split(A, 2, axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2, 3],
[ 6, 7],
[10, 11]])]
"""
横向分割
print(np.split(A, 3, axis=0))
# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8, 9, 10, 11]])]
这两种也可以有其他的实现方式
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]])]
"""
不等量的分割
print(np.array_split(A, 3, axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2],
[ 6],
[10]]), array([[ 3],
[ 7],
[11]])]
"""
1.7 Numpy copy
创建变量
import numpy as np
a = np.arange(4)
# array([0, 1, 2, 3])
b = a
c = a
d = b
试着改变值
a[0] = 11
print(a)
# array([11, 1, 2, 3])
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])
使用copy() 则可以使这种关联失效
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])