文章目录
一、排序
1.numpy.sort():
import numpy as np
import warnings
warnings.filterwarnings("ignore")
np.random.seed(20200612)
x = np.random.rand(5, 5) * 10
x = np.around(x, 2)
print(x)
# [[2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [0.01 4.23 0.19 1.73 9.27]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
y = np.sort(x)
print(y)
# [[1.73 2.32 6.22 7.54 9.78]
# [5.17 6.93 8.25 9.28 9.76]
# [0.01 0.19 1.73 4.23 9.27]
# [0.88 4.29 4.97 7.32 7.99]
# [0.07 6.99 7.9 8.95 9.05]]
y = np.sort(x, axis=0)
print(y)
# [[0.01 0.07 0.19 1.73 4.29]
# [2.32 4.23 0.88 1.73 6.22]
# [6.93 4.97 8.95 7.32 6.99]
# [7.99 5.17 9.28 7.9 8.25]
# [9.05 7.54 9.78 9.76 9.27]]
y = np.sort(x, axis=1)
print(y)
# [[1.73 2.32 6.22 7.54 9.78]
# [5.17 6.93 8.25 9.28 9.76]
# [0.01 0.19 1.73 4.23 9.27]
# [0.88 4.29 4.97 7.32 7.99]
# [0.07 6.99 7.9 8.95 9.05]]
import numpy as np
dt = np.dtype([('name', 'S10'), ('age', np.int)])
a = np.array([("Mike", 21), ("Nancy", 25), ("Bob", 17), ("Jane", 27)], dtype=dt)
b = np.sort(a, order='name')
print(b)
# [(b'Bob', 17) (b'Jane', 27) (b'Mike', 21) (b'Nancy', 25)]
b = np.sort(a, order='age')
print(b)
# [(b'Bob', 17) (b'Mike', 21) (b'Nancy', 25) (b'Jane', 27)]
2.numpy.argsort()
对数组沿给定轴执行间接排序,并使用指定排序类型返回数据的索引数组。这个索引数组用于构造排序后的数组。
import numpy as np
np.random.seed(20200612)
x = np.random.randint(0, 10, 10)
print(x)
# [6 1 8 5 5 4 1 2 9 1]
y = np.argsort(x)
print(y)
# [1 6 9 7 5 3 4 0 2 8]
print(x[y])
# [1 1 1 2 4 5 5 6 8 9]
y = np.argsort(-x)
print(y)
# [8 2 0 3 4 5 7 1 6 9]
print(x[y])
# [9 8 6 5 5 4 2 1 1 1]
import numpy as np
np.random.seed(20200612)
x = np.random.rand(5, 5) * 10
x = np.around(x, 2)
print(x)
# [[2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [0.01 4.23 0.19 1.73 9.27]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
y = np.argsort(x)
print(y)
# [[3 0 4 1 2]
# [1 0 4 2 3]
# [0 2 3 1 4]
# [2 4 1 3 0]
# [1 4 3 2 0]]
y = np.argsort(x, axis=0)
print(y)
# [[2 4 2 0 3]
# [0 2 3 2 0]
# [1 3 4 3 4]
# [3 1 1 4 1]
# [4 0 0 1 2]]
y = np.argsort(x, axis=1)
print(y)
# [[3 0 4 1 2]
# [1 0 4 2 3]
# [0 2 3 1 4]
# [2 4 1 3 0]
# [1 4 3 2 0]]
y = np.array([np.take(x[i], np.argsort(x[i])) for i in range(5)])
#numpy.take(a, indices, axis=None, out=None, mode='raise')沿轴从数组中获取元素。
print(y)
# [[1.73 2.32 6.22 7.54 9.78]
# [5.17 6.93 8.25 9.28 9.76]
# [0.01 0.19 1.73 4.23 9.27]
# [0.88 4.29 4.97 7.32 7.99]
# [0.07 6.99 7.9 8.95 9.05]]
3.numpy.lexsort()
按照第一列的升序或者降序对整体数据进行排序
import numpy as np
np.random.seed(20200612)
x = np.random.rand(5, 5) * 10
x = np.around(x, 2)
print(x)
# [[2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [0.01 4.23 0.19 1.73 9.27]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
index = np.lexsort([x[:, 0]])
print(index)
# [2 0 1 3 4]
y = x[index]
print(y)
# [[0.01 4.23 0.19 1.73 9.27]
# [2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
index = np.lexsort([-1 * x[:, 0]])
print(index)
# [4 3 1 0 2]
y = x[index]
print(y)
# [[9.05 0.07 8.95 7.9 6.99]
# [7.99 4.97 0.88 7.32 4.29]
# [6.93 5.17 9.28 9.76 8.25]
# [2.32 7.54 9.78 1.73 6.22]
# [0.01 4.23 0.19 1.73 9.27]]
import numpy as np
x = np.array([1, 5, 1, 4, 3, 4, 4])
y = np.array([9, 4, 0, 4, 0, 2, 1])
a = np.lexsort([x])
b = np.lexsort([y])
print(a)
# [0 2 4 3 5 6 1]
print(x[a])
# [1 1 3 4 4 4 5]
print(b)
# [2 4 6 5 1 3 0]
print(y[b])
# [0 0 1 2 4 4 9]
z = np.lexsort([y, x])
print(z)
# [2 0 4 6 5 3 1]
print(x[z])
# [1 1 3 4 4 4 5]
z = np.lexsort([x, y])
print(z)
# [2 4 6 5 3 1 0]
print(y[z])
# [0 0 1 2 4 4 9]
4.numpy.partition()
以索引是 kth 的元素为基准,将元素分成两部分,即大于该元素的放在其后面,小于该元素的放在其前面,这里有点类似于快排
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
y = np.sort(x, axis=0)
print(y)
# [[ 3 5 3]
# [ 3 11 3]
# [ 8 15 4]
# [ 9 17 12]
# [16 22 16]
# [17 24 17]
# [18 25 21]
# [29 27 25]]
z = np.partition(x, kth=2, axis=0)
print(z)
# [[ 3 5 3]
# [ 3 11 3]
# [ 8 15 4]
# [ 9 22 21]
# [17 24 16]
# [18 17 25]
# [16 25 12]
# [29 27 17]]
选取每一列第三小的数
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
z = np.partition(x, kth=2, axis=0)
print(z[2])
# [ 8 15 4]
选取每一列第三大的数据
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
z = np.partition(x, kth=-3, axis=0)
print(z[-3])
# [17 24 17]
numpy.argpartition()
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
y = np.argsort(x, axis=0)
print(y)
# [[3 6 3]
# [4 2 4]
# [1 4 0]
# [0 5 6]
# [6 3 1]
# [2 1 7]
# [5 0 2]
# [7 7 5]]
z = np.argpartition(x, kth=2, axis=0)
print(z)
# [[3 6 3]
# [4 2 4]
# [1 4 0]
# [0 3 2]
# [2 1 1]
# [5 5 5]
# [6 0 6]
# [7 7 7]]
选取每一列第三小的数的索引
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
z = np.argpartition(x, kth=2, axis=0)
print(z[2])
# [1 4 0]
选取每一列第三大的数的索引
import numpy as np
np.random.seed(100)
x = np.random.randint(1, 30, [8, 3])
print(x)
# [[ 9 25 4]
# [ 8 24 16]
# [17 11 21]
# [ 3 22 3]
# [ 3 15 3]
# [18 17 25]
# [16 5 12]
# [29 27 17]]
z = np.argpartition(x, kth=-3, axis=0)
print(z[-3])
# [2 1 7]
二、搜索
1.numpy.argmax()
import numpy as np
np.random.seed(20200612)
x = np.random.rand(5, 5) * 10
x = np.around(x, 2)
print(x)
# [[2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [0.01 4.23 0.19 1.73 9.27]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
y = np.argmax(x)
print(y) # 2
y = np.argmax(x, axis=0)
print(y)
# [4 0 0 1 2]
y = np.argmax(x, axis=1)
print(y)
# [2 3 4 0 0]
2.numpy.argmin()
import numpy as np
np.random.seed(20200612)
x = np.random.rand(5, 5) * 10
x = np.around(x, 2)
print(x)
# [[2.32 7.54 9.78 1.73 6.22]
# [6.93 5.17 9.28 9.76 8.25]
# [0.01 4.23 0.19 1.73 9.27]
# [7.99 4.97 0.88 7.32 4.29]
# [9.05 0.07 8.95 7.9 6.99]]
y = np.argmin(x)
print(y) # 10
y = np.argmin(x, axis=0)
print(y)
# [2 4 2 0 3]
y = np.argmin(x, axis=1)
print(y)
# [3 1 0 2 1]
3.numppy.nonzero()
一维数组
import numpy as np
x = np.array([0, 2, 3])
print(x) # [0 2 3]
print(x.shape) # (3,)
print(x.ndim) # 1
y = np.nonzero(x)
print(y) # (array([1, 2], dtype=int64),)
print(np.array(y)) # [[1 2]]
print(np.array(y).shape) # (1, 2)
print(np.array(y).ndim) # 2
print(np.transpose(y))
# [[1]
# [2]]
print(x[np.nonzero(x)])
#[2, 3]
二维数组
import numpy as np
x = np.array([[3, 0, 0], [0, 4, 0], [5, 6, 0]])
print(x)
# [[3 0 0]
# [0 4 0]
# [5 6 0]]
print(x.shape) # (3, 3)
print(x.ndim) # 2
y = np.nonzero(x)
print(y)
# (array([0, 1, 2, 2], dtype=int64), array([0, 1, 0, 1], dtype=int64))
print(np.array(y))
# [[0 1 2 2]
# [0 1 0 1]]
print(np.array(y).shape) # (2, 4)
print(np.array(y).ndim) # 2
y = x[np.nonzero(x)]
print(y) # [3 4 5 6]
y = np.transpose(np.nonzero(x))
print(y)
# [[0 0]
# [1 1]
# [2 0]
# [2 1]]
三维数组
import numpy as np
x = np.array([[[0, 1], [1, 0]], [[0, 1], [1, 0]], [[0, 0], [1, 0]]])
print(x)
# [[[0 1]
# [1 0]]
#
# [[0 1]
# [1 0]]
#
# [[0 0]
# [1 0]]]
print(np.shape(x)) # (3, 2, 2)
print(x.ndim) # 3
y = np.nonzero(x)
print(np.array(y))
# [[0 0 1 1 2]
# [0 1 0 1 1]
# [1 0 1 0 0]]
print(np.array(y).shape) # (3, 5)
print(np.array(y).ndim) # 2
print(y)
# (array([0, 0, 1, 1, 2], dtype=int64), array([0, 1, 0, 1, 1], dtype=int64), array([1, 0, 1, 0, 0], dtype=int64))
print(x[np.nonzero(x)])
#[1 1 1 1 1]
4.nonzero()
将布尔数组转换成整数数组进行操作
import numpy as np
x = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
print(x)
# [[1 2 3]
# [4 5 6]
# [7 8 9]]
y = x > 3
print(y)
# [[False False False]
# [ True True True]
# [ True True True]]
y = np.nonzero(x > 3)
print(y)
# (array([1, 1, 1, 2, 2, 2], dtype=int64), array([0, 1, 2, 0, 1, 2], dtype=int64))
y = x[np.nonzero(x > 3)]
print(y)
# [4 5 6 7 8 9]
y = x[x > 3]
print(y)
# [4 5 6 7 8 9]
5.numpy.where()
满足条件condition,输出x,不满足输出y
import numpy as np
x = np.arange(10)
print(x)
# [0 1 2 3 4 5 6 7 8 9]
y = np.where(x < 5, x, 10 * x)
print(y)
# [ 0 1 2 3 4 50 60 70 80 90]
x = np.array([[0, 1, 2],
[0, 2, 4],
[0, 3, 6]])
y = np.where(x < 4, x, -1)
print(y)
# [[ 0 1 2]
# [ 0 2 -1]
# [ 0 3 -1]]
只有condition,没有x和y,则输出满足条件 (即非0) 元素的坐标 (等价于numpy.nonzero)。这里的坐标以tuple的形式给出,通常原数组有多少维,输出的tuple中就包含几个数组,分别对应符合条件元素的各维坐标
import numpy as np
x = np.array([1, 2, 3, 4, 5, 6, 7, 8])
y = np.where(x > 5)
print(y)
# (array([5, 6, 7], dtype=int64),)
print(x[y])
# [6 7 8]
y = np.nonzero(x > 5)
print(y)
# (array([5, 6, 7], dtype=int64),)
print(x[y])
# [6 7 8]
x = np.array([[11, 12, 13, 14, 15],
[16, 17, 18, 19, 20],
[21, 22, 23, 24, 25],
[26, 27, 28, 29, 30],
[31, 32, 33, 34, 35]])
y = np.where(x > 25)
print(y)
# (array([3, 3, 3, 3, 3, 4, 4, 4, 4, 4], dtype=int64), array([0, 1, 2, 3, 4, 0, 1, 2, 3, 4], dtype=int64))
print(x[y])
# [26 27 28 29 30 31 32 33 34 35]
y = np.nonzero(x > 25)
print(y)
# (array([3, 3, 3, 3, 3, 4, 4, 4, 4, 4], dtype=int64), array([0, 1, 2, 3, 4, 0, 1, 2, 3, 4], dtype=int64))
print(x[y])
# [26 27 28 29 30 31 32 33 34 35]
6.numpy.searchsorted()
import numpy as np
x = np.array([0, 1, 5, 9, 11, 18, 26, 33])
y = np.searchsorted(x, 15)
print(y) # 5
y = np.searchsorted(x, 15, side='right')
print(y) # 5
y = np.searchsorted(x, -1)
print(y) # 0
y = np.searchsorted(x, -1, side='right')
print(y) # 0
y = np.searchsorted(x, 35)
print(y) # 8
y = np.searchsorted(x, 35, side='right')
print(y) # 8
y = np.searchsorted(x, 11)
print(y) # 4
y = np.searchsorted(x, 11, side='right')
print(y) # 5
y = np.searchsorted(x, 0)
print(y) # 0
y = np.searchsorted(x, 0, side='right')
print(y) # 1
y = np.searchsorted(x, 33)
print(y) # 7
y = np.searchsorted(x, 33, side='right')
print(y) # 8
import numpy as np
x = np.array([0, 1, 5, 9, 11, 18, 26, 33])
y = np.searchsorted(x, [-1, 0, 11, 15, 33, 35])
print(y) # [0 0 4 5 7 8]
y = np.searchsorted(x, [-1, 0, 11, 15, 33, 35], side='right')
print(y) # [0 1 5 5 8 8]
import numpy as np
x = np.array([0, 1, 5, 9, 11, 18, 26, 33])
np.random.shuffle(x)
print(x) # [33 1 9 18 11 26 0 5]
x_sort = np.argsort(x)
print(x_sort) # [6 1 7 2 4 3 5 0]
y = np.searchsorted(x, [-1, 0, 11, 15, 33, 35], sorter=x_sort)
print(y) # [0 0 4 5 7 8]
y = np.searchsorted(x, [-1, 0, 11, 15, 33, 35], side='right', sorter=x_sort)
print(y) # [0 1 5 5 8 8]
三、计数
1.numpy.count_nonzero()
返回数组中的非0元素个数
import numpy as np
x = np.count_nonzero(np.eye(4))
print(x) # 4
x = np.count_nonzero([[0, 1, 7, 0, 0], [3, 0, 0, 2, 19]])
print(x) # 5
x = np.count_nonzero([[0, 1, 7, 0, 0], [3, 0, 0, 2, 19]], axis=0)
print(x) # [1 1 1 1 1]
x = np.count_nonzero([[0, 1, 7, 0, 0], [3, 0, 0, 2, 19]], axis=1)
print(x) # [2 3]
参考:阿里云天池