numpy get started

导入numpy库，并查看numpy版本

import numpy as np

np.__version__

'1.13.0'

import matplotlib.pyplot as plt

cat = plt.imread('cat.jpg')

print(cat)

[[[231 186 131]
  [232 187 132]
  [233 188 133]
  ...,
  [100  54  54]
  [ 92  48  47]
  [ 85  43  44]]

 [[232 187 132]
  [232 187 132]
  [233 188 133]
  ...,
  [100  54  54]
  [ 92  48  47]
  [ 84  42  43]]

 [[232 187 132]
  [233 188 133]
  [233 188 133]
  ...,
  [ 99  53  53]
  [ 91  47  46]
  [ 83  41  42]]

 ...,
 [[199 119  82]
  [199 119  82]
  [200 120  83]
  ...,
  [189  99  65]
  [187  97  63]
  [187  97  63]]

 [[199 119  82]
  [199 119  82]
  [199 119  82]
  ...,
  [188  98  64]
  [186  96  62]
  [188  95  62]]

 [[199 119  82]
  [199 119  82]
  [199 119  82]
  ...,
  [188  98  64]
  [188  95  62]
  [188  95  62]]]

type(cat)

numpy.ndarray

cat.shape

(456, 730, 3)

plt.imshow(cat)
plt.show()

#请问电影是什么，nd.array 四维
#(x,456,760,3)

一、创建ndarray

1. 使用np.array()由python list创建

参数为列表：
[1, 4, 2, 5, 3]

注意：

numpy默认ndarray的所有元素的类型是相同的
如果传进来的列表中包含不同的类型，则统一为同一类型，优先级：str>float>int

l = [3,1,4,5,9,6]
n = np.array(l)

display(n,l)

array([3, 1, 4, 5, 9, 6])

[3, 1, 4, 5, 9, 6]

display(n.shape,l.shape)

--------------------------------------------------------------

AttributeError               Traceback (most recent call last)

<ipython-input-15-5eeacc6c47ae> in <module>()
----> 1 display(n.shape,l.shape)

AttributeError: 'list' object has no attribute 'shape'

n2 = np.array([[3,4,7,1],[3,0,1,8],[2,4,6,8]])
display(n2.shape)

(3, 4)

n3 = np.array(['0',9.18,20])
n3

array(['0', '9.18', '20'],
      dtype='<U4')

n4 = np.array([1,2,3.14])
n4

array([ 1.  ,  2.  ,  3.14])

2. 使用np的routines函数创建

包含以下常见创建方法：

1) np.ones(shape, dtype=None, order=‘C‘)

n = np.ones((4,5))
n

array([[1., 1., 1., 1., 1.],
       [1., 1., 1., 1., 1.],
       [1., 1., 1., 1., 1.],
       [1., 1., 1., 1., 1.]])

n2 = np.ones((4,5,6), dtype=int)
n2

array([[[1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1]],

       [[1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1]],

       [[1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1]],

       [[1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1],
        [1, 1, 1, 1, 1, 1]]])

2) np.zeros(shape, dtype=float, order=‘C‘)

n3 = np.zeros((4,5))
n3

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

3) np.full(shape, fill_value, dtype=None, order=‘C‘)

n = np.full((4,5), dtype=int, fill_value=8)
n

array([[8, 8, 8, 8, 8],
       [8, 8, 8, 8, 8],
       [8, 8, 8, 8, 8],
       [8, 8, 8, 8, 8]])

4) np.eye(N, M=None, k=0, dtype=float)
对角线为1其他的位置为0

n = np.eye(4,5)
n
# 满秩矩阵

# x + y = 10
# x - y = 5
# 1  1
# 1  -1

# 第二行减去第一行
# 1   1
# 0   -2

# 1/2乘于第二行
# 1   1
# 0   -1

# 第二行加上第一行
# 1   0
# 0   -1

# 第二行乘与-1
# 1   0
# 0   1

# x + y
# 2x + 2Y
# 无解
# 1    1
# 2    2

array([[1., 0., 0., 0., 0.],
       [0., 1., 0., 0., 0.],
       [0., 0., 1., 0., 0.],
       [0., 0., 0., 1., 0.]])

5) np.linspace(start, stop, num=50, endpoint=True, retstep=False, dtype=None)

n = np.linspace(0, 100, num=50, dtype=int,retstep=True, endpoint=False)
n

(array([ 0,  2,  4,  6,  8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30, 32,
        34, 36, 38, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 60, 62, 64, 66,
        68, 70, 72, 74, 76, 78, 80, 82, 84, 86, 88, 90, 92, 94, 96, 98]), 2.0)

n = np.linspace(0, 150, num=50, dtype=np.int8)
n
# line
# 2^(n-1) -1
# lin = linear algebra

array([   0,    3,    6,    9,   12,   15,   18,   21,   24,   27,   30,
         33,   36,   39,   42,   45,   48,   52,   55,   58,   61,   64,
         67,   70,   73,   76,   79,   82,   85,   88,   91,   94,   97,
        101,  104,  107,  110,  113,  116,  119,  122,  125, -128, -125,
       -122, -119, -116, -113, -110, -106], dtype=int8)

6) np.arange([start, ]stop, [step, ]dtype=None)

n = np.arange(10)
n

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

n = np.arange(1, 11, step=2)
n

array([1, 3, 5, 7, 9])

7) np.random.randint(low, high=None, size=None, dtype=‘l‘)

n = np.random.randint(10)
n

n = np.random.randint(0, 255, size=(3,4,5))
n

array([[[ 89,  68,  18, 202,  49],
        [118, 159,  48, 190, 227],
        [177, 104, 232, 158,  64],
        [112, 125,   0,   7, 216]],

       [[  2, 180,  33, 152, 244],
        [ 46,  66, 185, 155, 253],
        [180, 135,  80, 135,  86],
        [ 64, 218,  69, 128,  90]],

       [[163,   7,  55,  60,  12],
        [ 15,  14, 181,  87,  62],
        [218,   7, 166, 100, 217],
        [137,   0,  42,  49, 194]]])

image = np.random.randint(0,255, size=(456,730,3))
image.shape

(456, 730, 3)

plt.imshow(image)
plt.show(image)

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-97-a28aaec0347e> in <module>()
      1 plt.imshow(image)
----> 2 plt.show(image)

C:\ProgramData\Anaconda3\lib\site-packages\matplotlib\pyplot.py in show(*args, **kw)
    251     """
    252     global _show
--> 253     return _show(*args, **kw)
    254
    255

C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\pylab\backend_inline.py in show(close, block)
     39         # only call close('all') if any to close
     40         # close triggers gc.collect, which can be slow
---> 41         if close and Gcf.get_all_fig_managers():
     42             matplotlib.pyplot.close('all')
     43

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

8) np.random.randn(d0, d1, ..., dn)

标准正太分布

n = np.random.randn(10)
n

array([-0.4173303 , -0.41736696, -0.11888109, -0.51925789,  1.24985884,
        1.52967696,  0.05327912,  0.84738899,  1.03118302, -0.64532473])

9)np.random.normal(loc=0.0, scale=1.0, size=None)

n = np.random.normal(175, scale=5.0, size=50)
n

array([177.62703208, 176.50746247, 173.26956915, 162.29355083,
       172.05271936, 177.61948035, 172.52243162, 175.43294252,
       181.14225673, 175.21450574, 179.56055092, 170.883815  ,
       170.91435313, 176.25008762, 176.3347509 , 183.90347049,
       178.91856559, 168.84725605, 176.32881783, 172.77973728,
       173.12257339, 174.75054378, 166.60349541, 171.68263799,
       168.83419713, 174.25085091, 175.66113435, 174.12039025,
       177.22772738, 169.01523024, 175.57587527, 172.89083838,
       179.52153939, 173.70318334, 179.06473552, 176.50099117,
       175.83008746, 174.78059027, 175.58909128, 178.11274357,
       183.45771692, 172.43399789, 179.56800892, 182.14239994,
       176.43701867, 177.37866513, 179.55215095, 174.5389049 ,
       175.48698667, 168.73145269])

10) np.random.random(size=None)

生成0到1的随机数，左闭右开

n = np.random.random(10)
n

array([0.22608606, 0.62764532, 0.62219649, 0.05348086, 0.94994404,
       0.29048963, 0.49340728, 0.04651386, 0.59005488, 0.59901244])

二、ndarray的属性

4个必记参数：
ndim：维度
shape：形状（各维度的长度）
size：总长度

dtype：元素类型

cat.ndim

cat.shape

(456, 730, 3)

cat.size

cat.dtype

dtype('uint8')

三、ndarray的基本操作

1. 索引

一维与列表完全一致
多维时同理

l = [1,2,3,4,5]
l[2:4]

[3, 4]

n = np.array(l)
n[2]

# 找一个二维ndarray中的某个数
n2 = np.random.randint(0,255, size=(4,4))
n2

array([[  8, 117, 209,  86],
       [156, 192, 117, 180],
       [ 33,  70,  53, 179],
       [ 56, 236,  72,  45]])

# 查找53
n2[2][2]

n2[2,2]

n3 = np.random.randint(0,255, size=(4,5,6))
n3

array([[[128,  60, 108,  12, 112,  60],
        [234, 111, 237,  54,  22,  95],
        [127, 226,  30, 181,  20,  85],
        [239, 233, 210, 165, 186,  57],
        [ 27,  17,  72, 237, 208, 120]],

       [[199, 169, 190, 153, 181,  75],
        [179, 205, 116,  33, 239, 228],
        [154, 204, 138,   5, 231,  97],
        [ 55, 193, 245, 105,  78, 210],
        [157, 227, 239, 230, 242, 185]],

       [[ 67, 232, 113, 189, 245, 206],
        [220,  56, 241, 141, 146,  59],
        [ 46, 206, 152, 240, 105, 105],
        [176, 252, 185, 212, 180, 127],
        [165, 130, 206,  77,  11,  56]],

       [[194,  82,  72,  80,  94, 237],
        [179, 143, 191,  56,  37, 236],
        [194,  65, 223,  45, 223, 125],
        [ 92, 162,  94,  93,  69,   3],
        [ 39, 179, 213, 180,  23, 141]]])

n3[1,2,3]

np.random.seed(100)

np.random.seed(100)
np.random.randn(10)

array([-1.74976547,  0.3426804 ,  1.1530358 , -0.25243604,  0.98132079,
        0.51421884,  0.22117967, -1.07004333, -0.18949583,  0.25500144])

n = np.array([1,2,3,np.nan])
np.sum(n)
np.nansum(n)

6.0

根据索引修改数据

n3[1,2,3] = 8
n3

array([[[128,  60, 108,  12, 112,  60],
        [234, 111, 237,  54,  22,  95],
        [127, 226,  30, 181,  20,  85],
        [239, 233, 210, 165, 186,  57],
        [ 27,  17,  72, 237, 208, 120]],

       [[199, 169, 190, 153, 181,  75],
        [179, 205, 116,  33, 239, 228],
        [154, 204, 138,   8, 231,  97],
        [ 55, 193, 245, 105,  78, 210],
        [157, 227, 239, 230, 242, 185]],

       [[ 67, 232, 113, 189, 245, 206],
        [220,  56, 241, 141, 146,  59],
        [ 46, 206, 152, 240, 105, 105],
        [176, 252, 185, 212, 180, 127],
        [165, 130, 206,  77,  11,  56]],

       [[194,  82,  72,  80,  94, 237],
        [179, 143, 191,  56,  37, 236],
        [194,  65, 223,  45, 223, 125],
        [ 92, 162,  94,  93,  69,   3],
        [ 39, 179, 213, 180,  23, 141]]])

2. 切片

一维与列表完全一致
多维时同理

l = [1,2,3,4,5]
l[::-1]

[5, 4, 3, 2, 1]

l[::-2]
l

[1, 2, 3, 4, 5]

将数据反转，例如[1,2,3]---->[3,2,1]

n = np.random.randint(0, 255, size=(4,5))
n

array([[211, 112,  94, 165,   6],
       [ 86,  15, 241,  38, 139],
       [185, 247,  99,  91,  31],
       [221,  33,  40, 137, 162]])

两个::进行切片

n[::-1]
n

array([[211, 112,  94, 165,   6],
       [ 86,  15, 241,  38, 139],
       [185, 247,  99,  91,  31],
       [221,  33,  40, 137, 162]])

3. 变形

使用reshape函数，注意参数是一个tuple！

n = np.arange(6)
n

array([0, 1, 2, 3, 4, 5])

n2 = np.reshape(n,(3,2))
n2

array([[0, 1],
       [2, 3],
       [4, 5]])

cat.shape

(456, 730, 3)

n = np.reshape(cat, (8322, 120))
n

array([[231, 186, 131, ..., 235, 190, 135],
       [237, 192, 137, ..., 237, 192, 137],
       [237, 192, 137, ..., 239, 192, 138],
       ...,
       [203, 125,  89, ..., 201, 121,  86],
       [200, 120,  85, ..., 197, 117,  82],
       [197, 117,  82, ..., 188,  95,  62]], dtype=uint8)

4. 级联

np.concatenate()
级联需要注意的点：

级联的参数是列表：一定要加中括号或小括号
维度必须相同
形状相符
【重点】级联的方向默认是shape这个tuple的第一个值所代表的维度方向
可通过axis参数改变级联的方向

n1 = np.random.randint(0,255, size=(5,6))
n2 = np.random.randint(0,255, size=(5,6))
display(n1,n2)

array([[ 67, 115, 248,  66, 212, 248],
       [ 66, 156, 231, 250,  39, 195],
       [248, 172,  19,  21, 200, 206],
       [139,  25,   3,  18,   3,  49],
       [ 55,  21,  12,   6, 218, 116]])

array([[182, 251, 137,  33,  60,   6],
       [169, 117, 245, 218,  96, 168],
       [231,  59, 117, 179,  76,  84],
       [  6,  24,  25,  51, 136,  89],
       [ 67, 156, 135, 101, 147,  90]])

np.concatenate((n1,n2),axis=1)

array([[ 67, 115, 248,  66, 212, 248, 182, 251, 137,  33,  60,   6],
       [ 66, 156, 231, 250,  39, 195, 169, 117, 245, 218,  96, 168],
       [248, 172,  19,  21, 200, 206, 231,  59, 117, 179,  76,  84],
       [139,  25,   3,  18,   3,  49,   6,  24,  25,  51, 136,  89],
       [ 55,  21,  12,   6, 218, 116,  67, 156, 135, 101, 147,  90]])

np.hstack与np.vstack
水平级联与垂直级联,处理自己，进行维度的变更

# hstack h
new_image = np.hstack((cat, image))
plt.imshow(new_image)
plt.show()

# vstack vertical
new_image = np.vstack((cat, image))
plt.imshow(new_image)
plt.show()

5. 切分

与级联类似，三个函数完成切分工作：

np.split
np.vsplit
np.hsplit

n = np.random.randint(0,100,size = (4,6))
n

array([[92,  7, 55,  5, 20, 53],
       [42, 61, 91, 64, 95, 18],
       [25, 93, 48, 35, 39, 13],
       [42, 97, 73, 57, 14, 59]])

np.vsplit(n,(1,2))

[array([[92,  7, 55,  5, 20, 53]]),
 array([[42, 61, 91, 64, 95, 18]]),
 array([[25, 93, 48, 35, 39, 13],
        [42, 97, 73, 57, 14, 59]])]

n = np.random.randint(0,100, size=(6,6))
n

array([[48, 77, 69, 24, 83, 20],
       [80, 92, 21, 97, 16, 37],
       [52, 99,  2, 33, 28,  3],
       [ 5, 53, 34,  3,  0, 95],
       [27, 73, 95, 85,  8, 48],
       [30, 54, 49, 75, 44, 90]])

np.vsplit(n, (2,5))

[array([[48, 77, 69, 24, 83, 20],
        [80, 92, 21, 97, 16, 37]]), array([[52, 99,  2, 33, 28,  3],
        [ 5, 53, 34,  3,  0, 95],
        [27, 73, 95, 85,  8, 48]]), array([[30, 54, 49, 75, 44, 90]])]

np.split(n, 3, axis=1)

[array([[48, 77],
        [80, 92],
        [52, 99],
        [ 5, 53],
        [27, 73],
        [30, 54]]), array([[69, 24],
        [21, 97],
        [ 2, 33],
        [34,  3],
        [95, 85],
        [49, 75]]), array([[83, 20],
        [16, 37],
        [28,  3],
        [ 0, 95],
        [ 8, 48],
        [44, 90]])]

np.vsplit(n, 3)

[array([[48, 77, 69, 24, 83, 20],
        [80, 92, 21, 97, 16, 37]]), array([[52, 99,  2, 33, 28,  3],
        [ 5, 53, 34,  3,  0, 95]]), array([[27, 73, 95, 85,  8, 48],
        [30, 54, 49, 75, 44, 90]])]

np.hsplit(n, 3)

[array([[48, 77],
        [80, 92],
        [52, 99],
        [ 5, 53],
        [27, 73],
        [30, 54]]), array([[69, 24],
        [21, 97],
        [ 2, 33],
        [34,  3],
        [95, 85],
        [49, 75]]), array([[83, 20],
        [16, 37],
        [28,  3],
        [ 0, 95],
        [ 8, 48],
        [44, 90]])]

np.hsplit(n,(2,4))

[array([[33, 46],
        [98, 40],
        [47, 53],
        [34, 91]]), array([[53,  7],
        [12, 55],
        [69, 50],
        [32, 52]]), array([[56, 43],
        [18, 64],
        [69,  7],
        [83, 38]])]

cat.shape

(456, 730, 3)

456
730

result = np.split(cat, 2, axis = 0)

plt.imshow(result[0])
plt.show()

s_result = np.split(cat,2,axis = 1)

len(s_result)

plt.imshow(s_result[0])
plt.show()

6. 副本

所有赋值运算不会为ndarray的任何元素创建副本。对赋值后的对象的操作也对原来的对象生效。

l = [1,2,3,4]
l2 = l
l2[2] = 5
l

[1, 2, 5, 4]

n1 = np.arange(10)
n2 = n1
n2[3] = 100
n1

array([  0,   1,   2, 100,   4,   5,   6,   7,   8,   9])

n3 = n1.copy()
n3[5]  = 200
n1

array([  0,   1,   2, 100,   4,   5,   6,   7,   8,   9])

可使用copy()函数创建副本

四、ndarray的聚合操作

1. 求和np.sum

n = np.arange(11)
n

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

np.sum(n)

n = np.random.randint(0,100, size=(5,6))
n

array([[80, 20, 30, 66, 48, 50],
       [52, 33,  3, 76, 35,  9],
       [70, 99, 69, 50, 44, 31],
       [40, 13, 52, 50, 33, 45],
       [69, 42, 55, 30, 61, 22]])

np.sum(n, axis=1)

array([294, 208, 363, 233, 279])

2. 最大最小值：np.max/ np.min

同理

n = np.arange(11)
n

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

np.median(n)

5.0

np.mean(n)

5.0

n = np.random.randint(0,100,size=10)
n

array([42, 64, 40,  7,  0, 79, 32, 95, 95, 59])

np.mean(n)

51.3

np.median(n)

50.5

np.max(n)

np.min(n)

n = np.random.randint(0,100, size=(5,6))
n

array([[82, 44,  0, 33, 72, 99],
       [66, 25, 36, 88, 74, 78],
       [ 3, 53, 33, 76, 96, 69],
       [62, 10, 16, 22, 12, 31],
       [41, 57, 43, 79, 34,  7]])

np.max(n, axis=0)

array([82, 57, 43, 88, 96, 99])

3. 其他聚合操作

Function Name   NaN-safe Version    Description
np.sum  np.nansum   Compute sum of elements
np.prod np.nanprod  Compute product of elements
np.mean np.nanmean  Compute mean of elements
np.std  np.nanstd   Compute standard deviation
np.var  np.nanvar   Compute variance
np.min  np.nanmin   Find minimum value
np.max  np.nanmax   Find maximum value
np.argmin   np.nanargmin    Find index of minimum value
np.argmax   np.nanargmax    Find index of maximum value
np.median   np.nanmedian    Compute median of elements
np.percentile   np.nanpercentile    Compute rank-based statistics of elements
np.any  N/A Evaluate whether any elements are true
np.all  N/A Evaluate whether all elements are true
np.power 幂运算

np.argmin(n, axis=0)

array([2, 3, 0, 3, 3, 4], dtype=int64)

cat.shape

(456, 730, 3)

cat2 = cat.reshape((-1,3))
cat2.shape

(332880, 3)

n = np.random.randint(0,10, size=(4,5))
n

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

np.reshape(n,(-1,))

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

cat3 = cat.reshape((456*730,3))
cat3.shape

(332880, 3)

cat3.max(axis = 0)

array([255, 242, 219], dtype=uint8)

max_cat = cat.max(axis = (0,1))

max_cat

array([255, 242, 219], dtype=uint8)

max_cat.shape

(3,)

cat.min()

np.sum 和 np.nansum 的区别
nan not a number

a = np.array([1,2,np.nan])
a

array([ 1.,  2., nan])

np.nansum(a)

3.0

操作文件

使用pandas打开文件president_heights.csv
获取文件中的数据

import pandas as pd
data = pd.read_csv('president_heights.csv')
type(data)
data

.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}

```
.dataframe tbody tr th {
vertical-align: top;
}

.dataframe thead th {
text-align: right;
}

```

	order	name	height(cm)
0	1	George Washington	189
1	2	John Adams	170
2	3	Thomas Jefferson	189
3	4	James Madison	163
4	5	James Monroe	183
5	6	John Quincy Adams	171
6	7	Andrew Jackson	185
7	8	Martin Van Buren	168
8	9	William Henry Harrison	173
9	10	John Tyler	183
10	11	James K. Polk	173
11	12	Zachary Taylor	173
12	13	Millard Fillmore	175
13	14	Franklin Pierce	178
14	15	James Buchanan	183
15	16	Abraham Lincoln	193
16	17	Andrew Johnson	178
17	18	Ulysses S. Grant	173
18	19	Rutherford B. Hayes	174
19	20	James A. Garfield	183
20	21	Chester A. Arthur	183
21	23	Benjamin Harrison	168
22	25	William McKinley	170
23	26	Theodore Roosevelt	178
24	27	William Howard Taft	182
25	28	Woodrow Wilson	180
26	29	Warren G. Harding	183
27	30	Calvin Coolidge	178
28	31	Herbert Hoover	182
29	32	Franklin D. Roosevelt	188
30	33	Harry S. Truman	175
31	34	Dwight D. Eisenhower	179
32	35	John F. Kennedy	183
33	36	Lyndon B. Johnson	193
34	37	Richard Nixon	182
35	38	Gerald Ford	183
36	39	Jimmy Carter	177
37	40	Ronald Reagan	185
38	41	George H. W. Bush	188
39	42	Bill Clinton	188
40	43	George W. Bush	182
41	44	Barack Obama	185

heights = data['height(cm)']
heights
type(heights)

pandas.core.series.Series

np.max(heights)

np.mean(heights)

179.73809523809524

np.std(heights)

6.931843442745893

np.min(heights)

五、ndarray的矩阵操作

1. 基本矩阵操作

1) 算术运算符：

加减乘除

n = np.random.randint(0,10, size=(4,5))
n

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

# 加
n + 1

array([[ 3,  6,  1,  5,  7],
       [ 1,  1,  8,  6,  1],
       [ 7,  4,  3, 10,  3],
       [ 6,  8,  1,  5,  6]])

# 减
n - 1

array([[ 1,  4, -1,  3,  5],
       [-1, -1,  6,  4, -1],
       [ 5,  2,  1,  8,  1],
       [ 4,  6, -1,  3,  4]])

# 两个矩阵相加
n2 = np.random.randint(0,10,size=(4,5))
n2

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

n + n2

array([[ 4,  9,  2,  9, 15],
       [ 6,  6, 16, 11,  2],
       [15, 10,  7, 15,  3],
       [ 9, 13,  7,  6, 14]])

n3 = np.random.randint(0,10,size=(2,5))
n3

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

n2 + n3

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-97-5f0861827bc6> in <module>()
----> 1 n2 + n3

ValueError: operands could not be broadcast together with shapes (4,5) (2,5)

2) 矩阵积np.dot()

n1 = np.random.randint(0,10,size=(2,3))
n1

array([[8, 9, 4],
       [1, 7, 5]])

n2 = np.random.randint(0,10, size=(3,4))
n2

array([[4, 4, 2, 7],
       [4, 4, 7, 3],
       [1, 3, 2, 7]])

np.dot(n1,n2)

array([[ 72,  80,  87, 111],
       [ 37,  47,  61,  63]])

2. 广播机制

【重要】ndarray广播机制的两条规则

规则一：为缺失的维度补1
规则二：假定缺失元素用已有值填充

例1：
m = np.ones((2, 3))
a = np.arange(3)
求M+a

m = np.ones((2,3),dtype=int)
m

array([[1, 1, 1],
       [1, 1, 1]])

n = np.arange(3)
n

array([0, 1, 2])

m + n

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

例2：
a = np.arange(3).reshape((3, 1))
b = np.arange(3)
求a+b

a = np.arange(3).reshape((3,1))
a

array([[0],
       [1],
       [2]])

b = np.arange(3)
b

array([0, 1, 2])

a + b

array([[0, 1, 2],
       [1, 2, 3],
       [2, 3, 4]])

习题
a = np.ones((4, 1))
b = np.arange(4)
求a+b

六、ndarray的排序

小测验：
使用以上所学numpy的知识，对一个ndarray对象进行选择排序。

def Sortn(x):

代码越短越好

n = [5,2,3,6,9]

def bubble(n):
    for i in range(len(n) -1):
        for j in range(i+1, len(n)):
            if n[i] > n[j]:
                n[i], n[j] = n[j], n[i]

bubble(n)
n

[2, 3, 5, 6, 9]

# 选择排序
def select(n):
    for i in range(len(n)):
        # 选出最小值的索引
        index = np.argmin(n[i:]) + i
        # 把最小值和当前值的位置换一下
        n[i], n[index] = n[index], n[i]

n = [4, 6,1,0,3]
select(n)
n

[0, 1, 3, 4, 6]

1. 快速排序

np.sort()与ndarray.sort()都可以，但有区别：

np.sort()不改变输入
ndarray.sort()本地处理，不占用空间，但改变输入

n = np.random.randint(0,10,size=6)
n

array([6, 7, 1, 1, 8, 3])

np.sort(n)

array([1, 1, 3, 6, 7, 8])

np.sort(n)
n

array([6, 7, 1, 1, 8, 3])

n.sort()
n

array([1, 1, 3, 6, 7, 8])

原文地址：https://www.cnblogs.com/pankypan/p/11408738.html

时间： 2024-10-06 09:08:47

02_numpy