点击关注|设为星标|干货速递
Numpy是Python做数据分析所必须要掌握的基础库之一,以下题是github上的开源项目,主要为了检测你的Numpy能力,同时对你的学习作为一个补充。
(提示: import … as …)
import numpy as np
(提示: np.version, np.show_config)
print(np.__version__)
print(np.show_config())
(提示: np.zeros)
Z = np.zeros(10)
print(Z)
(提示: size, itemsize)
Z = np.zeros((10,10))
print("%d bytes" % (Z.size * Z.itemsize))
(提示: np.info)
import numpy
numpy.info(numpy.add)
(提示: array[4])
Z = np.zeros(10)
Z[4] = 1
print(Z)
(提示: np.arange)
Z = np.arange(10,50)
print(Z)
(提示: array[::-1])
Z = np.arange(50)
Z = Z[::-1]
print(Z)
(提示: reshape)
Z = np.arange(9).reshape(3,3)
print(Z)
(提示: np.nonzero)
nz = np.nonzero([1,2,0,0,4,0])
print(nz)
(提示: np.eye)
Z = np.eye(3)
print(Z)
(提示: np.random.random)
Z = np.random.random((3,3,3))
print(Z)
(提示: min, max)
Z = np.random.random((10,10))
Zmin, Zmax = Z.min(), Z.max()
print(Zmin, Zmax)
(提示: mean)
Z = np.random.random(30)
m = Z.mean()
print(m)
(提示: array[1:-1, 1:-1])
Z = np.ones((10,10))
Z[1:-1,1:-1] = 0
print(Z)
(提示: np.pad)
Z = np.ones((5,5))
Z = np.pad(Z, pad_width=1, mode='constant', constant_values=0)
print(Z)
(提示: NaN = not a number, inf = infinity) (提示:NaN : 不是一个数,inf : 无穷)
# 表达式 # 结果
0 * np.nan nan
np.nan == np.nan False
np.inf > np.nan False
np.nan - np.nan nan
0.3 == 3 * 0.1 False
(提示: np.diag)
Z = np.diag(1+np.arange(4),k=-1)
print(Z)
(提示: array[::2])
Z = np.zeros((8,8),dtype=int)
Z[1::2,::2] = 1
Z[::2,1::2] = 1
print(Z)
(提示: np.unravel_index)
print(np.unravel_index(100,(6,7,8)))
(提示: np.tile)
Z = np.tile( np.array([[0,1],[1,0]]), (4,4))
print(Z)
(提示: (x - min) / (max - min))
Z = np.random.random((5,5))
Zmax, Zmin = Z.max(), Z.min()
Z = (Z - Zmin)/(Zmax - Zmin)
print(Z)
(提示: np.dtype)
color = np.dtype([("r", np.ubyte, 1),
("g", np.ubyte, 1),
("b", np.ubyte, 1),
("a", np.ubyte, 1)])
color
(提示: np.dot | @)
Z = np.dot(np.ones((5,3)), np.ones((3,2)))
print(Z)
(提示: >, <=)
Z = np.arange(11)
Z[(3 < Z) & (Z <= 8)] *= -1
print(Z)
(提示: np.sum)
# Author: Jake VanderPlas # 结果
print(sum(range(5),-1)) 9
from numpy import *
print(sum(range(5),-1)) 10 #numpy.sum(a, axis=None)
(提示:这里还有“位运算符”)
Z**Z True
2 << Z >> 2 False
Z <- Z True
1j*Z True #复数
Z/1/1 True
ZZ False
np.array(0) / np.array(0) nan
np.array(0) // np.array(0) 0
np.array([np.nan]).astype(int).astype(float) -2.14748365e+09
(提示: np.uniform, np.copysign, np.ceil, np.abs)
# Author: Charles R Harris
Z = np.random.uniform(-10,+10,10)
print (np.copysign(np.ceil(np.abs(Z)), Z))
(提示: np.intersect1d)
Z1 = np.random.randint(0, 10, 10)
Z2 = np.random.randint(0, 10, 10)
print (np.intersect1d(Z1, Z2))
(提示: np.seterr, np.errstate)
# Suicide mode on
defaults = np.seterr(all="ignore")
Z = np.ones(1) / 0
# Back to sanity
_ = np.seterr(**defaults)
# 另一个等价的方式, 使用上下文管理器(context manager)
with np.errstate(divide='ignore'):
Z = np.ones(1) / 0
(提示: 虚数)
np.sqrt(-1) == np.emath.sqrt(-1) Faslse
(提示: np.datetime64, np.timedelta64)
yesterday = np.datetime64('today', 'D') - np.timedelta64(1, 'D')
today = np.datetime64('today', 'D')
tomorrow = np.datetime64('today', 'D') + np.timedelta64(1, 'D')
(提示: np.arange(dtype=datetime64['D']))
Z = np.arange('2016-07', '2016-08', dtype='datetime64[D]')
print (Z)
(提示: np.add(out=), np.negative(out=), np.multiply(out=), np.divide(out=))
A = np.ones(3) * 1
B = np.ones(3) * 1
C = np.ones(3) * 1
np.add(A, B, out=B)
np.divide(A, 2, out=A)
np.negative(A, out=A)
np.multiply(A, B, out=A)
(提示: %, np.floor, np.ceil, astype, np.trunc)
Z = np.random.uniform(0, 10, 10)
print (Z - Z % 1)
print (np.floor(Z))
print (np.cell(Z)-1)
print (Z.astype(int))
print (np.trunc(Z))
(提示: np.arange)
Z = np.zeros((5, 5))
Z += np.arange(5)
print (Z)
(提示: np.fromiter)
def generate():
for x in range(10):
yield x
Z = np.fromiter(generate(), dtype=float, count=-1)
print (Z)
(提示: np.linspace)
Z = np.linspace(0, 1, 12, endpoint=True)[1: -1]
print (Z)
(提示: sort)
Z = np.random.random(10)
Z.sort()
print (Z)
(提示: np.add.reduce)
# Author: Evgeni Burovski
Z = np.arange(10)
np.add.reduce(Z)
# np.add.reduce 是numpy.add模块中的一个ufunc(universal function)函数,C语言实现
(提示: np.allclose, np.array_equal)
A = np.random.randint(0, 2, 5)
B = np.random.randint(0, 2, 5)
# 假设array的形状(shape)相同和一个误差容限(tolerance)
equal = np.allclose(A,B)
print(equal)
# 检查形状和元素值,没有误差容限(值必须完全相等)
equal = np.array_equal(A,B)
print(equal)
(提示: flags.writeable)
Z = np.zeros(5)
Z.flags.writeable = False
Z[0] = 1
(提示: np.sqrt, np.arctan2)
Z = np.random.random((10, 2))
X, Y = Z[:, 0], Z[:, 1]
R = np.sqrt(X**2 + Y**2)
T = np.arctan2(Y, X)
print (R)
print (T)
(提示: argmax)
Z = np.random.random(10)
Z[Z.argmax()] = 0
print (Z)
(提示: np.meshgrid)
Z = np.zeros((5, 5), [('x', float), ('y', float)])
Z['x'], Z['y'] = np.meshgrid(np.linspace(0, 1, 5), np.linspace(0, 1, 5))
print (Z)
(提示: np.subtract.outer)
# Author: Evgeni Burovski
X = np.arange(8)
Y = X + 0.5
C = 1.0 / np.subtract.outer(X, Y)
print (C)
print(np.linalg.det(C)) # 计算行列式
(提示: np.iinfo, np.finfo, eps)
for dtype in [np.int8, np.int32, np.int64]:
print(np.iinfo(dtype).min)
print(np.iinfo(dtype).max)
for dtype in [np.float32, np.float64]:
print(np.finfo(dtype).min)
print(np.finfo(dtype).max)
print(np.finfo(dtype).eps)
(提示: np.set_printoptions)
np.set_printoptions(threshold=np.nan)
Z = np.zeros((16,16))
print(Z)
(提示: argmin)
Z = np.arange(100)
v = np.random.uniform(0, 100)
index = (np.abs(Z-v)).argmin()
print(Z[index])
(提示: dtype)
Z = np.zeros(10, [('position', [('x', float, 1),
('y', float, 1)]),
('color', [('r', float, 1),
('g', float, 1),
('b', float, 1)])])
print (Z)
(提示: np.atleast_2d, T, np.sqrt)
Z = np.random.random((100, 2))
X, Y = np.atleast_2d(Z[:, 0], Z[:, 1])
D = np.sqrt((X-X.T)**2 + (Y-Y.T)**2)
print (D)
# 使用scipy库可以更快
import scipy.spatial
Z = np.random.random((100,2))
D = scipy.spatial.distance.cdist(Z,Z)
print(D)
(提示: astype(copy=False))
Z = np.arange(10, dtype=np.int32)
Z = Z.astype(np.float32, copy=False)
print(Z)
(提示: np.genfromtxt)
1, 2, 3, 4, 5
6, , , 7, 8
, , 9,10,11
# 先把上面保存到文件example.txt中
# 这里不使用StringIO, 因为Python2 和Python3 在这个地方有兼容性问题
Z = np.genfromtxt("example.txt", delimiter=",")
print(Z)
(提示: np.ndenumerate, np.ndindex)
Z = np.arange(9).reshape(3,3)
for index, value in np.ndenumerate(Z):
print(index, value)
for index in np.ndindex(Z.shape):
print(index, Z[index])
(提示: np.meshgrid, np.exp)
X, Y = np.meshgrid(np.linspace(-1, 1, 10), np.linspace(-1, 1, 10))
D = np.sqrt(X**2 + Y**2)
sigma, mu = 1.0, 0.0
G = np.exp(-( (D-mu)**2 / (2.0*sigma**2) ))
print (G)
(提示: np.put, np.random.choice)
# Author: Divakar
n = 10
p = 3
Z = np.zeros((n,n))
np.put(Z, np.random.choice(range(n*n), p, replace=False),1)
print(Z)
(提示: mean(axis=,keepdims=))
# Author: Warren Weckesser
X = np.random.rand(5, 10)
# 新
Y = X - X.mean(axis=1, keepdims=True)
# 旧
Y = X - X.mean(axis=1).reshape(-1, 1)
print(Y)
(提示: argsort)
# Author: Steve Tjoa
Z = np.random.randint(0,10,(3,3))
print(Z)
print(Z[ Z[:,1].argsort() ])
(提示: any, ~)
# Author: Warren Weckesser
Z = np.random.randint(0,3,(3,10))
print((~Z.any(axis=0)).any())
(提示: np.abs, argmin, flat)
Z = np.random.uniform(0,1,10)
z = 0.5
m = Z.flat[np.abs(Z - z).argmin()]
print(m)
(提示: np.nditer)
A = np.arange(3).reshape(3, 1)
B = np.arange(3).reshape(1, 3)
it = np.nditer([A, B, None])
for x, y, z in it:
z[...] = x + y
print (it.operands[2])
(提示: class method)
class NameArray(np.ndarray):
def __new__(cls, array, name="no name"):
obj = np.asarray(array).view(cls)
obj.name = name
return obj
def __array_finalize__(self, obj):
if obj is None: return
self.info = getattr(obj, 'name', "no name")
Z = NameArray(np.arange(10), "range_10")
print (Z.name)
(提示: np.bincount | np.add.at)
# Author: Brett Olsen
Z = np.ones(10)
I = np.random.randint(0,len(Z),20)
Z += np.bincount(I, minlength=len(Z))
print(Z)
# Another solution
# Author: Bartosz Telenczuk
np.add.at(Z, I, 1)
print(Z)
(提示: np.bincount)
# Author: Alan G Isaac
X = [1,2,3,4,5,6]
I = [1,3,9,3,4,1]
F = np.bincount(I,X)
print(F)
(提示: np.unique)
# Author: Nadav Horesh
w,h = 16,16
I = np.random.randint(0,2,(h,w,3)).astype(np.ubyte)
F = I[...,0]*256*256 + I[...,1]*256 +I[...,2]
n = len(np.unique(F))
print(np.unique(I))
(提示: sum(axis=(-2,-1)))
A = np.random.randint(0,10,(3,4,3,4))
# 传递一个元组(numpy 1.7.0)
sum = A.sum(axis=(-2,-1))
print(sum)
# 将最后两个维度压缩为一个
# (适用于不接受轴元组参数的函数)
sum = A.reshape(A.shape[:-2] + (-1,)).sum(axis=-1)
print(sum)
(提示: np.bincount)
# Author: Jaime Fernández del Río
D = np.random.uniform(0,1,100)
S = np.random.randint(0,10,100)
D_sums = np.bincount(S, weights=D)
D_counts = np.bincount(S)
D_means = D_sums / D_counts
print(D_means)
# Pandas solution as a reference due to more intuitive code
import pandas as pd
print(pd.Series(D).groupby(S).mean())
(提示: np.diag)
# Author: Mathieu Blondel
A = np.random.uniform(0,1,(5,5))
B = np.random.uniform(0,1,(5,5))
# Slow version
np.diag(np.dot(A, B))
# Fast version
np.sum(A * B.T, axis=1)
# Faster version
np.einsum("ij,ji->i", A, B)
(提示: array[::4])
# Author: Warren Weckesser
Z = np.array([1,2,3,4,5])
nz = 3
Z0 = np.zeros(len(Z) + (len(Z)-1)*(nz))
Z0[::nz+1] = Z
print(Z0)
(提示: array[:, :, None])
A = np.ones((5,5,3))
B = 2*np.ones((5,5))
print(A * B[:,:,None])
(提示: array[[]] = array[[]])
# Author: Eelco Hoogendoorn
A = np.arange(25).reshape(5,5)
A[[0,1]] = A[[1,0]]
print(A)
(提示: repeat, np.roll, np.sort, view, np.unique)
# Author: Nicolas P. Rougier
faces = np.random.randint(0,100,(10,3))
F = np.roll(faces.repeat(2,axis=1),-1,axis=1)
F = F.reshape(len(F)*3,2)
F = np.sort(F,axis=1)
G = F.view( dtype=[('p0',F.dtype),('p1',F.dtype)] )
G = np.unique(G)
print(G)
(提示: np.repeat)
# Author: Jaime Fernández del Río
C = np.bincount([1,1,2,3,4,4,6])
A = np.repeat(np.arange(len(C)), C)
print(A)
(提示: np.cumsum)
# Author: Jaime Fernández del Río
def moving_average(a, n=3) :
ret = np.cumsum(a, dtype=float)
ret[n:] = ret[n:] - ret[:-n]
return ret[n - 1:] / n
Z = np.arange(20)
print(moving_average(Z, n=3))
(提示: from numpy.lib import stride_tricks)
# Author: Joe Kington / Erik Rigtorp
from numpy.lib import stride_tricks
def rolling(a, window):
shape = (a.size - window + 1, window)
strides = (a.itemsize, a.itemsize)
return stride_tricks.as_strided(a, shape=shape, strides=strides)
Z = rolling(np.arange(10), 3)
print(Z)
(提示: np.logical_not, np.negative)
# Author: Nathaniel J. Smith
Z = np.random.randint(0,2,100)
np.logical_not(Z, out=Z)
Z = np.random.uniform(-1.0,1.0,100)
np.negative(Z, out=Z)
def distance(P0, P1, p):
T = P1 - P0
L = (T**2).sum(axis=1)
U = -((P0[:,0]-p[...,0])*T[:,0] + (P0[:,1]-p[...,1])*T[:,1]) / L
U = U.reshape(len(U),1)
D = P0 + U*T - p
return np.sqrt((D**2).sum(axis=1))
P0 = np.random.uniform(-10,10,(10,2))
P1 = np.random.uniform(-10,10,(10,2))
p = np.random.uniform(-10,10,( 1,2))
print(distance(P0, P1, p))
# Author: Italmassov Kuanysh
# based on distance function from previous question
P0 = np.random.uniform(-10, 10, (10,2))
P1 = np.random.uniform(-10,10,(10,2))
p = np.random.uniform(-10, 10, (10,2))
print(np.array([distance(P0,P1,p_i) for p_i in p]))
(提示: minimum, maximum)
# Author: Nicolas Rougier
Z = np.random.randint(0,10,(10,10))
shape = (5,5)
fill = 0
position = (1,1)
R = np.ones(shape, dtype=Z.dtype)*fill
P = np.array(list(position)).astype(int)
Rs = np.array(list(R.shape)).astype(int)
Zs = np.array(list(Z.shape)).astype(int)R_start = np.zeros((len(shape),)).astype(int)
R_stop = np.array(list(shape)).astype(int)
Z_start = (P-Rs//2)
Z_stop = (P+Rs//2)+Rs%2
R_start = (R_start - np.minimum(Z_start,0)).tolist()
Z_start = (np.maximum(Z_start,0)).tolist()
R_stop = np.maximum(R_start, (R_stop - np.maximum(Z_stop-Zs,0))).tolist()
Z_stop = (np.minimum(Z_stop,Zs)).tolist()
r = [slice(start,stop) for start,stop in zip(R_start,R_stop)]
z = [slice(start,stop) for start,stop in zip(Z_start,Z_stop)]
R[r] = Z[z]
print(Z)
print(R)
(提示: stride_tricks.as_strided)
# Author: Stefan van der Walt
Z = np.arange(1,15,dtype=np.uint32)
R = stride_tricks.as_strided(Z,(11,4),(4,4))
print(R)
(提示: np.linalg.svd)
# Author: Stefan van der Walt
Z = np.random.uniform(0,1,(10,10))
U, S, V = np.linalg.svd(Z) # Singular Value Decomposition
rank = np.sum(S > 1e-10)
print(rank)
(提示: np.bincount, argmax)
Z = np.random.randint(0,10,50)
print(np.bincount(Z).argmax())
(提示: stride_tricks.as_strided)
# Author: Chris Barker
Z = np.random.randint(0,5,(10,10))
n = 3
i = 1 + (Z.shape[0]-3)
j = 1 + (Z.shape[1]-3)
C = stride_tricks.as_strided(Z, shape=(i, j, n, n), strides=Z.strides + Z.strides)
print(C)
(提示: class method)
# Author: Eric O. Lebigot
# Note: only works for 2d array and value setting using indices
class Symetric(np.ndarray):
def __setitem__(self, index, value):
i,j = index
super(Symetric, self).__setitem__((i,j), value)
super(Symetric, self).__setitem__((j,i), value)
def symetric(Z):
return np.asarray(Z + Z.T - np.diag(Z.diagonal())).view(Symetric)
S = symetric(np.random.randint(0,10,(5,5)))
S[2,3] = 42
print(S)
(提示: np.tensordot)
# Author: Stefan van der Walt
p, n = 10, 20
M = np.ones((p,n,n))
V = np.ones((p,n,1))
S = np.tensordot(M, V, axes=[[0, 2], [0, 1]])
print(S)
# It works, because:
# M is (p,n,n)
# V is (p,n,1)
# Thus, summing over the paired axes 0 and 0 (of M and V independently),
# and 2 and 1, to remain with a (n,1) vector.
(提示: np.add.reduceat)
# Author: Robert Kern
Z = np.ones((16,16))
k = 4
S = np.add.reduceat(np.add.reduceat(Z, np.arange(0, Z.shape[0], k), axis=0), np.arange(0, Z.shape[1], k), axis=1)
print(S)
(提示: Game of Life , Game of Life有哪些图形?)
# Author: Nicolas Rougier
def iterate(Z):
# Count neighbours
N = (Z[0:-2,0:-2] + Z[0:-2,1:-1] + Z[0:-2,2:] +
Z[1:-1,0:-2] + Z[1:-1,2:] +
Z[2: ,0:-2] + Z[2: ,1:-1] + Z[2: ,2:])
# Apply rules
birth = (N==3) & (Z[1:-1,1:-1]==0)
survive = ((N==2) | (N==3)) & (Z[1:-1,1:-1]==1)
Z[...] = 0
Z[1:-1,1:-1][birth | survive] = 1
return Z
Z = np.random.randint(0,2,(50,50))
for i in range(100): Z = iterate(Z)
print(Z)
(提示: np.argsort | np.argpartition)
Z = np.arange(10000)
np.random.shuffle(Z)
n = 5
# Slow
print (Z[np.argsort(Z)[-n:]])
# Fast
print (Z[np.argpartition(-Z,n)[:n]])
(提示: np.indices)
# Author: Stefan Van der Walt
def cartesian(arrays):
arrays = [np.asarray(a) for a in arrays]
shape = (len(x) for x in arrays)
ix = np.indices(shape, dtype=int)
ix = ix.reshape(len(arrays), -1).T
for n, arr in enumerate(arrays):
ix[:, n] = arrays[n][ix[:, n]]
return ix
print (cartesian(([1, 2, 3], [4, 5], [6, 7])))
(提示: np.core.records.fromarrays)
Z = np.array([("Hello", 2.5, 3),
("World", 3.6, 2)])
R = np.core.records.fromarrays(Z.T,
names='col1, col2, col3',
formats = 'S8, f8, i8')
print(R)
(提示: np.power, *, np.einsum)
# Author: Ryan G.
x = np.random.rand(5e7)
%timeit np.power(x,3)
%timeit x*x*x
%timeit np.einsum('i,i,i->i',x,x,x)
(提示: np.where)
# Author: Gabe Schwartz
A = np.random.randint(0,5,(8,3))
B = np.random.randint(0,5,(2,2))
C = (A[..., np.newaxis, np.newaxis] == B)
rows = np.where(C.any((3,1)).all(1))[0]
print(rows)
# Author: Robert Kern
Z = np.random.randint(0,5,(10,3))
print(Z)
# solution for arrays of all dtypes (including string arrays and record arrays)
E = np.all(Z[:,1:] == Z[:,:-1], axis=1)
U = Z[~E]
print(U)
# soluiton for numerical arrays only, will work for any number of columns in Z
U = Z[Z.max(axis=1) != Z.min(axis=1),:]
print(U)
(提示: np.unpackbits)
# Author: Warren Weckesser
I = np.array([0, 1, 2, 3, 15, 16, 32, 64, 128])
B = ((I.reshape(-1,1) & (2**np.arange(8))) != 0).astype(int)
print(B[:,::-1])
# Author: Daniel T. McDonald
I = np.array([0, 1, 2, 3, 15, 16, 32, 64, 128], dtype=np.uint8)
print(np.unpackbits(I[:, np.newaxis], axis=1))
(提示: np.ascontiguousarray)
# Author: Jaime Fernández del Río
Z = np.random.randint(0,2,(6,3))
T = np.ascontiguousarray(Z).view(np.dtype((np.void, Z.dtype.itemsize * Z.shape[1])))
_, idx = np.unique(T, return_index=True)
uZ = Z[idx]
print(uZ)
(提示: np.einsum)
# Author: Alex Riley
# Make sure to read: http://ajcr.net/Basic-guide-to-einsum/
A = np.random.uniform(0,1,10)
B = np.random.uniform(0,1,10)
np.einsum('i->', A) # np.sum(A)
np.einsum('i,i->i', A, B) # A * B
np.einsum('i,i', A, B) # np.inner(A, B)
np.einsum('i,j->ij', A, B) # np.outer(A, B)
(提示: np.cumsum, np.interp)
# Author: Bas Swinckels
phi = np.arange(0, 10*np.pi, 0.1)
a = 1
x = a*phi*np.cos(phi)
y = a*phi*np.sin(phi)
dr = (np.diff(x)**2 + np.diff(y)**2)**.5 # segment lengths
r = np.zeros_like(x)
r[1:] = np.cumsum(dr) # integrate path
r_int = np.linspace(0, r.max(), 200) # regular spaced path
x_int = np.interp(r_int, r, x) # integrate path
y_int = np.interp(r_int, r, y)
(提示: np.logical_and.reduce, np.mod)
# Author: Evgeni Burovski
X = np.asarray([[1.0, 0.0, 3.0, 8.0],
[2.0, 0.0, 1.0, 1.0],
[1.5, 2.5, 1.0, 0.0]])
n = 4
M = np.logical_and.reduce(np.mod(X, 1) == 0, axis=-1)
M &= (X.sum(axis=-1) == n)
print(X[M])
(提示: np.percentile)
# Author: Jessica B. Hamrick
X = np.random.randn(100) # random 1D array
N = 1000 # number of bootstrap samples
idx = np.random.randint(0, X.size, (N, X.size))
means = X[idx].mean(axis=1)
confint = np.percentile(means, [2.5, 97.5])
print(confint)
来源:https://github.com/rougier/numpy-100
NO.1
往期推荐
Historical articles
详解Python标准库UUID
SQL常用脚本大全,建议收藏!
10 行 Python 代码能实现哪些有趣功能?
7个入门级Python项目代码
分享、收藏、点赞、在看安排一下?