莫烦numpy&pandas笔记一
参考资料：
https://blog.csdn.net/weixin_42758462?t=1
https://www.cnblogs.com/nxld/tag/pandas/
https://morvanzhou.github.io/tutorials/data-manipulation/np-pd/
http://pandas.pydata.org/
https://www.yiibai.com/pandas
Why Numpy & Pandas?
今天我们介绍两个科学运算当中最为重要的两个模块，一个是 numpy,一个是 pandas。任何关于数据分析的模块都少不了它们两个。
应用
- 数据分析
- 机器学习
- 深度学习
- 运算速度快：numpy 和 pandas 都是采用 C 语言编写, pandas 又是基于 numpy, 是 numpy 的升级版本。
- 消耗资源少：采用的是矩阵运算，会比 python 自带的字典或者列表快好多。
Numpy 属性
这次我们会介绍几种 numpy 的属性:
ndim：维度shape：行数和列数size：元素个数
使用numpy首先要导入模块：
import numpy as np #为了方便使用numpy 采用np简写列表转化为矩阵：
array = np.array([[1,2,3],[2,3,4]]) #列表转化为矩阵
print(array)
"""
array([[1, 2, 3],
[2, 3, 4]])
"""numpy 的几种属性
接着我们看看这几种属性的结果:
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: 6Numpy 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0ones：创建数据全为1empty：创建数据接近0arrange：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 dtype
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
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. ]])
"""Numpy 基础运算1
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])
c=a-b # array([10, 19, 28, 37])
c=a+b # array([10, 21, 32, 43])
c=a*b # array([ 0, 20, 60, 120])
c=b**2 # array([0, 1, 4, 9])
c=10*np.sin(a)
# array([-5.44021111, 9.12945251, -9.88031624, 7.4511316 ])
print(b<3)
# array([True, True, True, False], dtype=bool)
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]])
-----------------------------------------------------------------
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
#如果你需要对行或者列进行查找运算，就需要在上述代码中为 axis 进行赋值。
#当axis的值为0的时候，将会以列作为查找单元， 当axis的值为1的时候，将会以行作为查找单元。
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 基础运算2
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
print(np.mean(A)) # 7.5
print(np.average(A)) # 7.5
print(A.mean()) # 7.5
print(A.median()) # 7.5
print(np.cumsum(A)) #生成的每一项矩阵元素均是从原矩阵首项累加到对应项的元素之和
# [2 5 9 14 20 27 35 44 54 65 77 90]
print(np.diff(A)) #该函数计算的便是每一行中后一项与前一项之差
# [[1 1 1]
# [1 1 1]
# [1 1 1]]
print(np.nonzero(A))
#这个函数将所有非零元素的行与列坐标分割开，重构成两个分别关于行和列的矩阵。
# (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]))
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]])
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]])
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
import numpy as np
A = np.arange(3,15)
# array([3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14])
print(A[3]) # 6
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]
print(A[1][1]) # 8
print(A[1, 1]) # 8
print(A[1, 1:3]) # [8 9]
for row in A:
print(row)
"""
[ 3, 4, 5, 6]
[ 7, 8, 9, 10]
[11, 12, 13, 14]
"""
for column in A.T: #逐列打印
print(column)
"""
[ 3, 7, 11]
[ 4, 8, 12]
[ 5, 9, 13]
[ 6, 10, 14]
"""
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
#flatten是一个展开性质的函数，将多维的矩阵进行展开成1行的数列。而flat是一个迭代器，本身是一个object属性Numpy array 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]]
"""
C = np.vstack((A,B))
print(A.shape,C.shape)
# (3,) (2,3)
D = np.hstack((A,B)) # horizontal stack
print(D)
# [1,1,1,2,2,2]
print(A.shape,D.shape)
# (3,) (6,)
import numpy as np
A = np.array([1,1,1])[:,np.newaxis]
B = np.array([2,2,2])[:,np.newaxis]
C = np.vstack((A,B)) # vertical stack
D = np.hstack((A,B)) # horizontal stack
print(D)
"""
[[1 2]
[1 2]
[1 2]]
"""
print(A.shape,D.shape)
# (3,1) (3,2)
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 array 分割
A = np.arange(12).reshape((3, 4))
print(A)
"""
array([[ 0, 1, 2, 3],
[ 4, 5, 6, 7],
[ 8, 9, 10, 11]])
"""
print(np.split(A, 2, axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2, 3],
[ 6, 7],
[10, 11]])]
"""
print(np.split(A, 3, axis=0))
# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8, 9, 10, 11]])]
print(np.array_split(A, 3, axis=1))
"""
[array([[0, 1],
[4, 5],
[8, 9]]), array([[ 2],
[ 6],
[10]]), array([[ 3],
[ 7],
[11]])]
"""
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
import numpy as np
a = np.arange(4)
# array([0, 1, 2, 3])
b = a
c = a
d = b
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])
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])