Numpy 函数使用技巧

import numpy as np
data = np.genfromtxt("world_alcohol.txt",delimiter=",",dtype=str,skip_header=1)
print data
print type(data)

[[      nan       nan       nan       nan       nan]
 [1.986e+03       nan       nan       nan 0.000e+00]
 [1.986e+03       nan       nan       nan 5.000e-01]
 ...
 [1.987e+03       nan       nan       nan 7.500e-01]
 [1.989e+03       nan       nan       nan 1.500e+00]
 [1.985e+03       nan       nan       nan 3.100e-01]]
<type 'numpy.ndarray'>

data = np.array([1,2,3,4])
print data

[1 2 3 4]

data1 = np.array([[1,2,3,4],[5,6,7,8],[2,2,2,2]])
print data1

[[1 2 3 4]
 [5 6 7 8]
 [2 2 2 2]]

print data.shape

(4L,)

print data1.shape

(3L, 4L)

data = np.array([1,2,3,4.0])
print data
data.dtype

[1. 2. 3. 4.]





dtype('float64')

data = np.array([1,2,3,"4"])
print data
data.dtype #数据类型

['1' '2' '3' '4']





dtype('S11')

data = np.genfromtxt("world_alcohol.txt",delimiter=",",dtype=str,skip_header=1)
print data

[['1986' 'Western Pacific' 'Viet Nam' 'Wine' '0']
 ['1986' 'Americas' 'Uruguay' 'Other' '0.5']
 ['1985' 'Africa' "Cte d'Ivoire" 'Wine' '1.62']
 ...
 ['1987' 'Africa' 'Malawi' 'Other' '0.75']
 ['1989' 'Americas' 'Bahamas' 'Wine' '1.5']
 ['1985' 'Africa' 'Malawi' 'Spirits' '0.31']]

print data[1][1] #矩阵取值

Americas

vector=np.array([5,10,15,20])
print (vector[0:3]) #从左至右取

[ 5 10 15]

data = np.genfromtxt("world_alcohol.txt",delimiter=",",dtype=str,skip_header=1)
data1 = np.array(data)
print data1[:,0:2]#取整列数据

[['1986' 'Western Pacific']
 ['1986' 'Americas']
 ['1985' 'Africa']
 ...
 ['1987' 'Africa']
 ['1989' 'Americas']
 ['1985' 'Africa']]

data1 = np.array([[1,2,3,4],[5,6,7,8],[2,2,2,2]])
data1==1  #判断

array([[ True, False, False, False],
       [False, False, False, False],
       [False, False, False, False]])

data1 = np.array([[1,2,3,4],[5,6,7,8],[2,2,2,2]])
new_array = (data1==1) 
print data1[new_array]  #定位元素

[1]

data1 = np.array([1,2,3,4])
data2 = (data1==2)&(data1==1)
print data2  #判断

[False False False False]

data1 = np.array([1,2,3,4])
data2 = (data1==2)|(data1==1)
print data2

[ True  True False False]

data1 = np.array([1,2,3,4])
print data1.dtype
print data1.astype(str)

int32
['1' '2' '3' '4']

data1 = np.array([1,2,3,4])
print data1.min()
print data1.max()

1
4

data1 = np.array([[1,2,3,4],[5,6,7,8],[2,4,1,0]])
data1.sum(axis=1)   #按行求和

array([10, 26,  7])

data1 = np.array([[1,2,3,4],[5,6,7,8],[2,4,1,0]])
data1.sum(axis=0) #按列求和

array([ 8, 12, 11, 12])

a = np.arange(15).reshape(3,5)
print a
print a.shape
print a.ndim
print a.dtype.name
print a.size

[[ 0  1  2  3  4]
 [ 5  6  7  8  9]
 [10 11 12 13 14]]
(3L, 5L)
2
int32
15

np.zeros((5,6))  #矩阵初始化

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

np.ones((2,3,4),dtype=np.int32)

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]]])

np.arange(10,100,5)

array([10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90,
       95])

np.random.random((2,3))

array([[0.53674074, 0.23305677, 0.19391963],
       [0.93416765, 0.11027397, 0.93512683]])

a = np.random.random((2,2))
b = np.random.random((2,2))

print np.hstack((a,b))  #数据拼接

[[0.54036568 0.7651197  0.85174038 0.09345969]
 [0.99133994 0.12584765 0.24050664 0.60018397]]

a = np.random.random((2,2))
b = np.random.random((2,2))

print np.vstack((a,b))  #数据拼接

[[0.2035504  0.86393637]
 [0.63149806 0.89757755]
 [0.02250936 0.52304954]
 [0.90389327 0.20683611]]

a = np.random.random((2,2))
b = np.random.random((2,2))
c = np.vstack((a,b))  #数据拼接
print c
print (np.hsplit(c,2))
print (np.hsplit(c,(3,4)))

[[0.88881143 0.81362197]
 [0.41975241 0.69932274]
 [0.20557389 0.62099524]
 [0.96080627 0.9970264 ]]
[array([[0.88881143],
       [0.41975241],
       [0.20557389],
       [0.96080627]]), array([[0.81362197],
       [0.69932274],
       [0.62099524],
       [0.9970264 ]])]
[array([[0.88881143, 0.81362197],
       [0.41975241, 0.69932274],
       [0.20557389, 0.62099524],
       [0.96080627, 0.9970264 ]]), array([], shape=(4L, 0L), dtype=float64), array([], shape=(4L, 0L), dtype=float64)]

a = np.arange(12)
b = a
print a
print b
print b is a
b.shape = 3,4
print a
print id(a)
print id(b)   #复制操作，两个变量指向了一个值，改变任何一个值都会改变整个数据

[ 0  1  2  3  4  5  6  7  8  9 10 11]
[ 0  1  2  3  4  5  6  7  8  9 10 11]
True
[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
122267168
122267168

a = np.arange(12)
b = a.copy()
print a
print b
print a is b
b.shape = 3,4
print b
print a
print id(a)
print id(b)

[ 0  1  2  3  4  5  6  7  8  9 10 11]
[ 0  1  2  3  4  5  6  7  8  9 10 11]
False
[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
[ 0  1  2  3  4  5  6  7  8  9 10 11]
122267728
122267648