首页 > 代码库 > NumPy常用函数(一)——构造数组函数及代码示例
NumPy常用函数(一)——构造数组函数及代码示例
NumPy是Python的一个科学计算的基本模块。它是一个Python库,提供了一个多维数组对象,各种衍生对象(如屏蔽数组和矩阵),以及用于数组,数学,逻辑,形状操纵,排序,选择,I/O等快速操作的各种例程 离散傅里叶变换,基本线性代数,基本统计运算,随机模拟等等。
本文主要列出构造数组常用的函数或者成为子模块
一、0-1数组
empty(shape [,dtype,order]) 返回给定形状和类型的新数组,而不初始化条目。
empty_like(a [,dtype,order,subok]) 返回与给定数组相同的形状和类型的新数组。
eye(N [,M,k,dtype]) 返回一个2-D数组,其中有一个对角线和零。
identity(n [,dtype]) 返回标识数组。
ones(shape[,dtype,order]) 返回一个给定形状和类型的新数组,填充一个。
ones_like(a [,dtype,order,subok]) 返回与给定数组相同的形状和类型的数组。
zeros(shape[,dtype,order]) 返回一个给定形状和类型的新数组,填充零。
zeros_like(a [,dtype,order,subok]) 返回与给定数组相同的形状和类型的零数组。
full(shape,fill_value [,dtype,order]) 返回一个给定形状和类型的新数组,填充fill_value。
full_like(a,fill_value [,dtype,order,subok]) 返回与给定数组相同的形状和类型的完整数组。
代码示例:
1.empty(shape [,dtype,order]) >>> np.empty([2, 2]) array([[ -9.74499359e+001, 6.69583040e-309], [ 2.13182611e-314, 3.06959433e-309]]) #random >>> np.empty([2, 2], dtype=int) array([[-1073741821, -1067949133], [ 496041986, 19249760]]) #random
2.empty_like(a [,dtype,order,subok]) >>> a = ([1,2,3], [4,5,6]) # a is array-like >>> np.empty_like(a) array([[-1073741821, -1073741821, 3], #random [ 0, 0, -1073741821]]) >>> a = np.array([[1., 2., 3.],[4.,5.,6.]]) >>> np.empty_like(a) array([[ -2.00000715e+000, 1.48219694e-323, -2.00000572e+000],#random [ 4.38791518e-305, -2.00000715e+000, 4.17269252e-309]])
3. eye(N [,M,k,dtype]) >>> np.eye(2, dtype=int) array([[1, 0], [0, 1]]) >>> np.eye(3, k=1) array([[ 0., 1., 0.], [ 0., 0., 1.], [ 0., 0., 0.]])
4.identity(n [,dtype]) >>> np.identity(3) array([[ 1., 0., 0.], [ 0., 1., 0.], [ 0., 0., 1.]])
5.ones(shape[,dtype,order]) >>> np.ones(5) array([ 1., 1., 1., 1., 1.]) >>> np.ones((5,), dtype=np.int) array([1, 1, 1, 1, 1]) >>> np.ones((2, 1)) array([[ 1.], [ 1.]]) >>> s = (2,2) >>> np.ones(s) array([[ 1., 1.], [ 1., 1.]])
6.ones_like(a, dtype=None, order=’K’, subok=True) Examples >>> x = np.arange(6) >>> x = x.reshape((2, 3)) >>> x array([[0, 1, 2], [3, 4, 5]]) >>> np.ones_like(x) array([[1, 1, 1], [1, 1, 1]]) >>> y = np.arange(3, dtype=np.float) >>> y array([ 0., 1., 2.]) >>> np.ones_like(y) array([ 1., 1., 1.])
7.zeros(shape, dtype=float, order=’C’) >>> np.zeros(5) array([ 0., 0., 0., 0., 0.]) >>> np.zeros((5,), dtype=np.int) array([0, 0, 0, 0, 0]) >>> np.zeros((2, 1)) array([[ 0.], [ 0.]]) >>> s = (2,2) >>> np.zeros(s) array([[ 0., 0.], [ 0., 0.]]) >>> np.zeros((2,), dtype=[(‘x‘, ‘i4‘), (‘y‘, ‘i4‘)]) # custom dtype array([(0, 0), (0, 0)], dtype=[(‘x‘, ‘<i4‘), (‘y‘, ‘<i4‘)])
8.zeros_like(a, dtype=None, order=’K’, subok=True) Examples >>> x = np.arange(6) >>> x = x.reshape((2, 3)) >>> x array([[0, 1, 2], [3, 4, 5]]) >>> np.zeros_like(x) array([[0, 0, 0], [0, 0, 0]]) >>> y = np.arange(3, dtype=np.float) >>> y array([ 0., 1., 2.]) >>> np.zeros_like(y) array([ 0., 0., 0.])
9.full(shape, fill_value, dtype=None, order=’C’) >>> np.full((2, 2), np.inf) array([[ inf, inf], [ inf, inf]]) >>> np.full((2, 2), 10) array([[10, 10], [10, 10]])
10.full_like(a, fill_value, dtype=None, order=’K’, subok=True) >>> x = np.arange(6, dtype=np.int) >>> np.full_like(x, 1) array([1, 1, 1, 1, 1, 1]) >>> np.full_like(x, 0.1) array([0, 0, 0, 0, 0, 0]) >>> np.full_like(x, 0.1, dtype=np.double) array([ 0.1, 0.1, 0.1, 0.1, 0.1, 0.1]) >>> np.full_like(x, np.nan, dtype=np.double) array([ nan, nan, nan, nan, nan, nan]) >>> y = np.arange(6, dtype=np.double) >>> np.full_like(y, 0.1) array([ 0.1, 0.1, 0.1, 0.1, 0.1, 0.1])
二、从现有数据创建数组
array(object[, dtype, copy, order, subok, ndmin]) 创建数组
asarray(a[, dtype, order]) 将输入转为数组
asanyarray(a[, dtype, order]) 将输入转换为ndarray,但通过ndarray子类.
asmatrix(data[, dtype]) 将输入解释为矩阵。
copy(a[, order]) 返回一个从已有数组的复制数组
frombuffer(buffer[, dtype, count, offset]) 将缓冲区解释为一维数组。.
fromfile(file[, dtype, count, sep]) 从文本或二进制文件中的数据构造数组.
fromfunction(function, shape, **kwargs) 通过在每坐标上执行一个函数来构造数组。
fromiter(iterable, dtype[, count]) 从一个可迭代的对象创建一个新的1维数组。
fromstring(string[, dtype, count, sep]) 从原始二进制或字符串中的文本数据初始化的新的1-D数组。
loadtxt(fname[, dtype, comments, delimiter, ...]) 从文本文件加载数据。
1. array >>> np.array([1, 2, 3]) array([1, 2, 3]) Upcasting: >>> np.array([1, 2, 3.0]) array([ 1., 2., 3.]) More than one dimension: >>> np.array([[1, 2], [3, 4]]) array([[1, 2], [3, 4]]) Minimum dimensions 2: >>> np.array([1, 2, 3], ndmin=2) array([[1, 2, 3]]) Type provided: >>> np.array([1, 2, 3], dtype=complex) array([ 1.+0.j, 2.+0.j, 3.+0.j]) Data-type consisting of more than one element: >>> x = np.array([(1,2),(3,4)],dtype=[(‘a‘,‘<i4‘),(‘b‘,‘<i4‘)]) >>> x[‘a‘] array([1, 3]) Creating an array from sub-classes: >>> np.array(np.mat(‘1 2; 3 4‘)) array([[1, 2], [3, 4]]) >>> np.array(np.mat(‘1 2; 3 4‘), subok=True) matrix([[1, 2], [3, 4]]) 2. asarray Convert a list into an array: >>> a = [1, 2] >>> np.asarray(a) array([1, 2]) Existing arrays are not copied: >>> a = np.array([1, 2]) >>> np.asarray(a) is a True If dtype is set, array is copied only if dtype does not match: >>> a = np.array([1, 2], dtype=np.float32) >>> np.asarray(a, dtype=np.float32) is a True >>> np.asarray(a, dtype=np.float64) is a False Contrary to asanyarray, ndarray subclasses are not passed through: >>> issubclass(np.matrix, np.ndarray) True >>> a = np.matrix([[1, 2]]) >>> np.asarray(a) is a False >>> np.asanyarray(a) is a True 3.asanyarray Convert a list into an array: >>> a = [1, 2] >>> np.asanyarray(a) array([1, 2]) Instances of ndarray subclasses are passed through as-is: >>> a = np.matrix([1, 2]) >>> np.asanyarray(a) is a True 4. asmatrix >>> x = np.array([[1, 2], [3, 4]]) >>> m = np.asmatrix(x) >>> x[0,0] = 5 >>> m matrix([[5, 2], [3, 4]]) 5. copy Create an array x, with a reference y and a copy z: >>> x = np.array([1, 2, 3]) >>> y = x >>> z = np.copy(x) Note that, when we modify x, y changes, but not z: >>> x[0] = 10 >>> x[0] == y[0] True >>> x[0] == z[0] False 6.frombuffer >>> s = ‘hello world‘ >>> np.frombuffer(s, dtype=‘S1‘, count=5, offset=6) array([‘w‘, ‘o‘, ‘r‘, ‘l‘, ‘d‘], dtype=‘|S1‘) 7.fromfile >>> dt = np.dtype([(‘time‘, [(‘min‘, int), (‘sec‘, int)]), ... (‘temp‘, float)]) >>> x = np.zeros((1,), dtype=dt) >>> x[‘time‘][‘min‘] = 10; x[‘temp‘] = 98.25 >>> x array([((10, 0), 98.25)], dtype=[(‘time‘, [(‘min‘, ‘<i4‘), (‘sec‘, ‘<i4‘)]), (‘temp‘, ‘<f8‘)]) Save the raw data to disk: >>> import os >>> fname = os.tmpnam() >>> x.tofile(fname) Read the raw data from disk: >>> np.fromfile(fname, dtype=dt) array([((10, 0), 98.25)], dtype=[(‘time‘, [(‘min‘, ‘<i4‘), (‘sec‘, ‘<i4‘)]), (‘temp‘, ‘<f8‘)]) The recommended way to store and load data: >>> np.save(fname, x) >>> np.load(fname + ‘.npy‘) array([((10, 0), 98.25)], dtype=[(‘time‘, [(‘min‘, ‘<i4‘), (‘sec‘, ‘<i4‘)]), (‘temp‘, ‘<f8‘)])
8.fromfunction >>> np.fromfunction(lambda i, j: i == j, (3, 3), dtype=int) array([[ True, False, False], [False, True, False], [False, False, True]], dtype=bool) >>> np.fromfunction(lambda i, j: i + j, (3, 3), dtype=int) array([[0, 1, 2], [1, 2, 3], [2, 3, 4]]) 9.fromiter >>> iterable = (x*x for x in range(5)) >>> np.fromiter(iterable, np.float) array([ 0., 1., 4., 9., 16.]) 10.fromstring >>> np.fromstring(‘\x01\x02‘, dtype=np.uint8) array([1, 2], dtype=uint8) >>> np.fromstring(‘1 2‘, dtype=int, sep=‘ ‘) array([1, 2]) >>> np.fromstring(‘1, 2‘, dtype=int, sep=‘,‘) array([1, 2]) >>> np.fromstring(‘\x01\x02\x03\x04\x05‘, dtype=np.uint8, count=3) array([1, 2, 3], dtype=uint8) 11. loadtxt >>> from io import StringIO # StringIO behaves like a file object >>> c = StringIO("0 1\n2 3") >>> np.loadtxt(c) array([[ 0., 1.], [ 2., 3.]]) >>> d = StringIO("M 21 72\nF 35 58") >>> np.loadtxt(d, dtype={‘names‘: (‘gender‘, ‘age‘, ‘weight‘), ... ‘formats‘: (‘S1‘, ‘i4‘, ‘f4‘)}) array([(‘M‘, 21, 72.0), (‘F‘, 35, 58.0)], dtype=[(‘gender‘, ‘|S1‘), (‘age‘, ‘<i4‘), (‘weight‘, ‘<f4‘)]) >>> c = StringIO("1,0,2\n3,0,4") >>> x, y = np.loadtxt(c, delimiter=‘,‘, usecols=(0, 2), unpack=True) >>> x array([ 1., 3.]) >>> y array([ 2., 4.])
三、生成序列
arange([start,] stop[, step,][, dtype]) 返回给定间隔内均匀间隔的值。
linspace(start, stop[, num, endpoint, ...]) 在指定的间隔内返回均匀间隔的数字。
logspace(start, stop[, num, endpoint, base, ...]) 返回数字在对数量级上均匀间隔。
geomspace(start, stop[, num, endpoint, dtype]) 返回数字在对数刻度上平均间隔(几何级数)。
meshgrid(*xi, **kwargs) 从坐标向量返回坐标矩阵。.
mgrid 实例返回一个密集的多维“meshgrid”。.
ogrid 实例返回一个开放的多维“meshgrid”
1.arange >>> np.arange(3) array([0, 1, 2]) >>> np.arange(3.0) array([ 0., 1., 2.]) >>> np.arange(3,7) array([3, 4, 5, 6]) >>> np.arange(3,7,2) array([3, 5]) 2. linspace >>> np.linspace(2.0, 3.0, num=5) array([ 2. , 2.25, 2.5 , 2.75, 3. ]) >>> np.linspace(2.0, 3.0, num=5, endpoint=False) array([ 2. , 2.2, 2.4, 2.6, 2.8]) >>> np.linspace(2.0, 3.0, num=5, retstep=True) (array([ 2. , 2.25, 2.5 , 2.75, 3. ]), 0.25) Graphical illustration: >>> import matplotlib.pyplot as plt >>> N = 8 >>> y = np.zeros(N) >>> x1 = np.linspace(0, 10, N, endpoint=True) >>> x2 = np.linspace(0, 10, N, endpoint=False) >>> plt.plot(x1, y, ‘o‘) [<matplotlib.lines.Line2D object at 0x...>] >>> plt.plot(x2, y + 0.5, ‘o‘) [<matplotlib.lines.Line2D object at 0x...>] >>> plt.ylim([-0.5, 1]) (-0.5, 1) >>> plt.show() 3. logspace >>> y = np.linspace(start, stop, num=num, endpoint=endpoint) ... >>> power(base, y).astype(dtype) ... Examples >>> np.logspace(2.0, 3.0, num=4) array([ 100. , 215.443469 , 464.15888336, 1000. ]) >>> np.logspace(2.0, 3.0, num=4, endpoint=False) array([ 100. , 177.827941 , 316.22776602, 562.34132519]) >>> np.logspace(2.0, 3.0, num=4, base=2.0) array([ 4. , 5.0396842 , 6.34960421, 8. ]) Graphical illustration: >>> import matplotlib.pyplot as plt >>> N = 10 >>> x1 = np.logspace(0.1, 1, N, endpoint=True) >>> x2 = np.logspace(0.1, 1, N, endpoint=False) >>> y = np.zeros(N) >>> plt.plot(x1, y, ‘o‘) [<matplotlib.lines.Line2D object at 0x...>] >>> plt.plot(x2, y + 0.5, ‘o‘) [<matplotlib.lines.Line2D object at 0x...>] >>> plt.ylim([-0.5, 1]) (-0.5, 1) >>> plt.show() 4.geomspace >>> np.geomspace(1, 1000, num=4) array([ 1., 10., 100., 1000.]) >>> np.geomspace(1, 1000, num=3, endpoint=False) array([ 1., 10., 100.]) >>> np.geomspace(1, 1000, num=4, endpoint=False) array([ 1. , 5.62341325, 31.6227766 , 177.827941 ]) >>> np.geomspace(1, 256, num=9) array([ 1., 2., 4., 8., 16., 32., 64., 128., 256.]) Note that the above may not produce exact integers: >>> np.geomspace(1, 256, num=9, dtype=int) array([ 1, 2, 4, 7, 16, 32, 63, 127, 256]) >>> np.around(np.geomspace(1, 256, num=9)).astype(int) array([ 1, 2, 4, 8, 16, 32, 64, 128, 256]) Negative, decreasing, and complex inputs are allowed: >>> geomspace(1000, 1, num=4) array([ 1000., 100., 10., 1.]) >>> geomspace(-1000, -1, num=4) array([-1000., -100., -10., -1.]) >>> geomspace(1j, 1000j, num=4) # Straight line array([ 0. +1.j, 0. +10.j, 0. +100.j, 0.+1000.j]) >>> geomspace(-1+0j, 1+0j, num=5) # Circle array([-1.00000000+0.j , -0.70710678+0.70710678j, 0.00000000+1.j , 0.70710678+0.70710678j, 1.00000000+0.j ]) Graphical illustration of endpoint parameter: >>> import matplotlib.pyplot as plt >>> N = 10 >>> y = np.zeros(N) >>> plt.semilogx(np.geomspace(1, 1000, N, endpoint=True), y + 1, ‘o‘) >>> plt.semilogx(np.geomspace(1, 1000, N, endpoint=False), y + 2, ‘o‘) >>> plt.axis([0.5, 2000, 0, 3]) >>> plt.grid(True, color=‘0.7‘, linestyle=‘-‘, which=‘both‘, axis=‘both‘) >>> plt.show() 5. meshgrid >>> nx, ny = (3, 2) >>> x = np.linspace(0, 1, nx) >>> y = np.linspace(0, 1, ny) >>> xv, yv = meshgrid(x, y) >>> xv array([[ 0. , 0.5, 1. ], [ 0. , 0.5, 1. ]]) >>> yv array([[ 0., 0., 0.], [ 1., 1., 1.]]) >>> xv, yv = meshgrid(x, y, sparse=True) # make sparse output arrays >>> xv array([[ 0. , 0.5, 1. ]]) >>> yv array([[ 0.], [ 1.]]) meshgrid is very useful to evaluate functions on a grid. >>> x = np.arange(-5, 5, 0.1) >>> y = np.arange(-5, 5, 0.1) >>> xx, yy = meshgrid(x, y, sparse=True) >>> z = np.sin(xx**2 + yy**2) / (xx**2 + yy**2) >>> h = plt.contourf(x,y,z) 6.mgrid >>> np.mgrid[0:5,0:5] array([[[0, 0, 0, 0, 0], [1, 1, 1, 1, 1], [2, 2, 2, 2, 2], [3, 3, 3, 3, 3], [4, 4, 4, 4, 4]], [[0, 1, 2, 3, 4], [0, 1, 2, 3, 4], [0, 1, 2, 3, 4], [0, 1, 2, 3, 4], [0, 1, 2, 3, 4]]]) >>> np.mgrid[-1:1:5j] array([-1. , -0.5, 0. , 0.5, 1. ]) 7.ogrid >>> from numpy import ogrid >>> ogrid[-1:1:5j] array([-1. , -0.5, 0. , 0.5, 1. ]) >>> ogrid[0:5,0:5] [array([[0], [1], [2], [3], [4]]), array([[0, 1, 2, 3, 4]])]
NumPy常用函数(一)——构造数组函数及代码示例