大数据最全【数模之数据分析-2】_数模数据分析，2024年最新2024年不想被公司优化-CSDN博客

本文链接：https://blog.csdn.net/2401_84181340/article/details/138517978

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！

bz = help(np.info(np.add))
print(bz)

4-创建一个2~20的数组，并将其逆序

sz = np.arange(2, 21, 1)
print(sz)
sz = sz[::-1]
print(sz)

5-找到一个数组中不为0的索引

sy = np.nonzero([2, 53, 12, 43, 0, 0, 0, 23, 90])
print(sy)

6-随机构造一个3*3矩阵，并打印其中最大与最小值

zz = np.random.random((3, 3))
print(zz.max())
print(zz.min())

7-构造一个5*5的矩阵，令其值都为1，并在最外层加上一圈0

jz = np.ones((5, 5))
jz = np.pad(jz, pad_width=1, mode='constant', constant_values=0)
print(jz)

print(help(np.pad))     # 帮助文档

8-构造一个shape为(6, 7, 8)的矩阵，并找到第100个元素的索引值

sy8 = np.unravel_index(100, (6, 7, 8))
print(sy8)

9-对一个5*5的矩阵做归一化操作

cz = np.random.random((5, 5))
cz_max = cz.max()
cz_min = cz.min()
cz = (cz-cz_min)/(cz_max-cz_min)
print(cz)

10-找到两个数组中相同的值

sz1 = np.random.randint(0, 20, 8)
sz2 = np.random.randint(0, 20, 8)
print(sz1)
print(sz2)

print(np.intersect1d(sz1, sz2))

相关程序运行如下：

0.9786237847073697
0.10837689046425514
[[0. 0. 0. 0. 0. 0. 0.]
 [0. 1. 1. 1. 1. 1. 0.]
 [0. 1. 1. 1. 1. 1. 0.]
 [0. 1. 1. 1. 1. 1. 0.]
 [0. 1. 1. 1. 1. 1. 0.]
 [0. 1. 1. 1. 1. 1. 0.]
 [0. 0. 0. 0. 0. 0. 0.]]
Help on function pad in module numpy:

pad(array, pad_width, mode='constant', \*\*kwargs)
    Pad an array.
    
    Parameters
    ----------
    array : array_like of rank N
        The array to pad.
    pad_width : {sequence, array_like, int}
        Number of values padded to the edges of each axis.
        ((before_1, after_1), ... (before_N, after_N)) unique pad widths
        for each axis.
        ((before, after),) yields same before and after pad for each axis.
        (pad,) or int is a shortcut for before = after = pad width for all
        axes.
    mode : str or function, optional
        One of the following string values or a user supplied function.
    
        'constant' (default)
            Pads with a constant value.
        'edge'
            Pads with the edge values of array.
        'linear\_ramp'
            Pads with the linear ramp between end_value and the
            array edge value.
        'maximum'
            Pads with the maximum value of all or part of the
            vector along each axis.
        'mean'
            Pads with the mean value of all or part of the
            vector along each axis.
        'median'
            Pads with the median value of all or part of the
            vector along each axis.
        'minimum'
            Pads with the minimum value of all or part of the
            vector along each axis.
        'reflect'
            Pads with the reflection of the vector mirrored on
            the first and last values of the vector along each
            axis.
        'symmetric'
            Pads with the reflection of the vector mirrored
            along the edge of the array.
        'wrap'
            Pads with the wrap of the vector along the axis.
            The first values are used to pad the end and the
            end values are used to pad the beginning.
        'empty'
            Pads with undefined values.
    
            .. versionadded:: 1.17
    
        <function>
            Padding function, see Notes.
    stat_length : sequence or int, optional
        Used in 'maximum', 'mean', 'median', and 'minimum'.  Number of
        values at edge of each axis used to calculate the statistic value.
    
        ((before_1, after_1), ... (before_N, after_N)) unique statistic
        lengths for each axis.
    
        ((before, after),) yields same before and after statistic lengths
        for each axis.
    
        (stat_length,) or int is a shortcut for before = after = statistic
        length for all axes.
    
        Default is ``None``, to use the entire axis.
    constant_values : sequence or scalar, optional
        Used in 'constant'.  The values to set the padded values for each
        axis.
    
        ``((before_1, after_1), ... (before_N, after_N))`` unique pad constants
        for each axis.
    
        ``((before, after),)`` yields same before and after constants for each
        axis.
    
        ``(constant,)`` or ``constant`` is a shortcut for ``before = after = constant`` for
        all axes.
    
        Default is 0.
    end_values : sequence or scalar, optional
        Used in 'linear\_ramp'.  The values used for the ending value of the
        linear_ramp and that will form the edge of the padded array.
    
        ``((before_1, after_1), ... (before_N, after_N))`` unique end values
        for each axis.
    
        ``((before, after),)`` yields same before and after end values for each
        axis.
    
        ``(constant,)`` or ``constant`` is a shortcut for ``before = after = constant`` for
        all axes.
    
        Default is 0.
    reflect_type : {'even', 'odd'}, optional
        Used in 'reflect', and 'symmetric'.  The 'even' style is the
        default with an unaltered reflection around the edge value.  For
        the 'odd' style, the extended part of the array is created by
        subtracting the reflected values from two times the edge value.
    
    Returns
    -------
    pad : ndarray
        Padded array of rank equal to `array` with shape increased
        according to `pad_width`.
    
    Notes
    -----
    .. versionadded:: 1.7.0
    
    For an array with rank greater than 1, some of the padding of later
    axes is calculated from padding of previous axes.  This is easiest to
    think about with a rank 2 array where the corners of the padded array
    are calculated by using padded values from the first axis.
    
    The padding function, if used, should modify a rank 1 array in-place. It
    has the following signature::
    
        padding\_func(vector, iaxis_pad_width, iaxis, kwargs)
    
    where
    
        vector : ndarray
            A rank 1 array already padded with zeros.  Padded values are
            vector[:iaxis_pad_width[0]] and vector[-iaxis_pad_width[1]:].
        iaxis_pad_width : tuple
            A 2-tuple of ints, iaxis_pad_width[0] represents the number of
            values padded at the beginning of vector where
            iaxis_pad_width[1] represents the number of values padded at
            the end of vector.
        iaxis : int
            The axis currently being calculated.
        kwargs : dict
            Any keyword arguments the function requires.
    
    Examples
    --------
    >>> a = [1, 2, 3, 4, 5]
    >>> np.pad(a, (2, 3), 'constant', constant_values=(4, 6))
    array([4, 4, 1, ..., 6, 6, 6])
    
    >>> np.pad(a, (2, 3), 'edge')
    array([1, 1, 1, ..., 5, 5, 5])
    
    >>> np.pad(a, (2, 3), 'linear\_ramp', end_values=(5, -4))
    array([ 5,  3,  1,  2,  3,  4,  5,  2, -1, -4])
    
    >>> np.pad(a, (2,), 'maximum')
    array([5, 5, 1, 2, 3, 4, 5, 5, 5])
    
    >>> np.pad(a, (2,), 'mean')
    array([3, 3, 1, 2, 3, 4, 5, 3, 3])
    
    >>> np.pad(a, (2,), 'median')
    array([3, 3, 1, 2, 3, 4, 5, 3, 3])
    
    >>> a = [[1, 2], [3, 4]]
    >>> np.pad(a, ((3, 2), (2, 3)), 'minimum')
    array([[1, 1, 1, 2, 1, 1, 1],
           [1, 1, 1, 2, 1, 1, 1],
           [1, 1, 1, 2, 1, 1, 1],
           [1, 1, 1, 2, 1, 1, 1],
           [3, 3, 3, 4, 3, 3, 3],
           [1, 1, 1, 2, 1, 1, 1],
           [1, 1, 1, 2, 1, 1, 1]])
    
    >>> a = [1, 2, 3, 4, 5]
    >>> np.pad(a, (2, 3), 'reflect')
    array([3, 2, 1, 2, 3, 4, 5, 4, 3, 2])
    
    >>> np.pad(a, (2, 3), 'reflect', reflect_type='odd')
    array([-1,  0,  1,  2,  3,  4,  5,  6,  7,  8])
    
    >>> np.pad(a, (2, 3), 'symmetric')
    array([2, 1, 1, 2, 3, 4, 5, 5, 4, 3])
    
    >>> np.pad(a, (2, 3), 'symmetric', reflect_type='odd')
    array([0, 1, 1, 2, 3, 4, 5, 5, 6, 7])
    
    >>> np.pad(a, (2, 3), 'wrap')
    array([4, 5, 1, 2, 3, 4, 5, 1, 2, 3])
    
    >>> def pad\_with(vector, pad_width, iaxis, kwargs):
    ...     pad_value = kwargs.get('padder', 10)
    ...     vector[:pad_width[0]] = pad_value
    ...     vector[-pad_width[1]:] = pad_value
    >>> a = np.arange(6)
    >>> a = a.reshape((2, 3))
    >>> np.pad(a, 2, pad_with)
    array([[10, 10, 10, 10, 10, 10, 10],
           [10, 10, 10, 10, 10, 10, 10],
           [10, 10,  0,  1,  2, 10, 10],
           [10, 10,  3,  4,  5, 10, 10],
           [10, 10, 10, 10, 10, 10, 10],
           [10, 10, 10, 10, 10, 10, 10]])
    >>> np.pad(a, 2, pad_with, padder=100)
    array([[100, 100, 100, 100, 100, 100, 100],
           [100, 100, 100, 100, 100, 100, 100],
           [100, 100,   0,   1,   2, 100, 100],
           [100, 100,   3,   4,   5, 100, 100],
           [100, 100, 100, 100, 100, 100, 100],
           [100, 100, 100, 100, 100, 100, 100]])

None
(1, 5, 4)
[[0.275 0.437 0.958 0.833 0.339]
 [0.174 0.376 0.    0.253 0.81 ]
 [0.01  0.608 0.613 0.102 0.386]
 [0.032 0.907 1.    0.056 0.907]
 [0.586 0.756 0.64  0.591 0.015]]
[19 14  0 13 12 10  3  6]
[ 3 15 10 15  3  9 16 11]
[ 3 10]

11-得到昨天、今天、明天的

yes = np.datetime64('today', 'D') - np.timedelta64(1, 'D')
tod = np.datetime64('today', 'D')
tom = np.datetime64('today', 'D') + np.timedelta64(1, 'D')
print(f"昨天是{yes}")
print(f"今天是{tod}")
print(f"明天是{tom}")

12-得到一个月中所有的天

tt = np.arange('2022-08', '2022-09', dtype='datetime64[D]')
print(tt)

13-得到一个数的整数部分

xs = np.random.uniform(0, 20, 8)
print(xs)

print(np.floor(xs))

14-构造一个数组，让它不能被改变–只读

# zz = np.zeros(5)
# zz.flags.writeable = False
# zz[0] = 2
# print(zz[0])

15-打印大数据的部分值

np.set_printoptions(threshold=5)
bq = np.zeros((20, 20))
print(bq)

16-找到一个数组中，最接近一个数的索引

zd = np.arange(100)
vv = np.random.uniform(0, 100)
print(vv)

index = (np.abs(zd-vv)).argmin()
print(zd[index])

17-32位float类型和32位int类型转换

lx = np.arange(10, dtype=np.int32)
print(lx.dtype)
lx = lx.astype(np.float32)
print(lx.dtype)

18-打印数组元素位置坐标与数值

dy = np.arange(12).reshape(3, 4)
for i, val in np.ndenumerate(dy):
    print(i, val)

19-按照数组的某一列进行排序

px = np.random.randint(0, 10, (3, 3))
print(px)
print(px[px[:, 0].argsort()])

20-统计数组中每个数值出现的次数

cs = np.array([3, 5, 23, 5, 2, 5, 6, 7, 2, 3, 5])
print(np.bincount(cs))

21-如何对一个四维数组的最后两维求和

szzz = np.random.randint(0, 10, [4, 4, 4, 4])
qh = szzz.sum(axis=(-2, -1))
print(qh)

22-交换矩阵中的两行

sz = np.arange(16).reshape(4, 4)
sz[[0, 1]] = sz[[1, 0]]
print(sz)

23-找到一个数组中最常出现的数字

sz = np.random.randint(0, 20, 20)
print(np.bincount(sz).argmax())

24-快速查找TOP K

sz = np.arange(1000)
np.random.shuffle(sz)
x = 66
print(sz[np.argpartition(-sz, x)[:x]])

25-去除掉一个数组中所有元素都相同的数据

np.set_printoptions(threshold=6)
sz = np.random.randint(0, 5, (10, 3))
print(sz)

sj = np.all(sz[:, 1:] == sz[:, :-1], axis=1)
print(sj)

sj2 = np.any(sz[:, 1:] == sz[:, :-1], axis=1)
print(sj2)