import pandas as pd
import numpy as np

print(pd.Series(name_of_array).value_counts())

我对此也很感兴趣，所以我做了一点性能比较(使用perfplot，我的一个爱好项目)。结果:

y = np.bincount(a)
ii = np.nonzero(y)[0]
out = np.vstack((ii, y[ii])).T

是目前为止最快的。(请注意对数缩放。)

代码生成的情节:

import numpy as np
import pandas as pd
import perfplot
from scipy.stats import itemfreq


def bincount(a):
    y = np.bincount(a)
    ii = np.nonzero(y)[0]
    return np.vstack((ii, y[ii])).T


def unique(a):
    unique, counts = np.unique(a, return_counts=True)
    return np.asarray((unique, counts)).T


def unique_count(a):
    unique, inverse = np.unique(a, return_inverse=True)
    count = np.zeros(len(unique), dtype=int)
    np.add.at(count, inverse, 1)
    return np.vstack((unique, count)).T


def pandas_value_counts(a):
    out = pd.value_counts(pd.Series(a))
    out.sort_index(inplace=True)
    out = np.stack([out.keys().values, out.values]).T
    return out


b = perfplot.bench(
    setup=lambda n: np.random.randint(0, 1000, n),
    kernels=[bincount, unique, itemfreq, unique_count, pandas_value_counts],
    n_range=[2 ** k for k in range(26)],
    xlabel="len(a)",
)
b.save("out.png")
b.show()

Most of simple problems get complicated because simple functionality like order() in R that gives a statistical result in both and descending order is missing in various python libraries. But if we devise our thinking that all such statistical ordering and parameters in python are easily found in pandas, we can can result sooner than looking in 100 different places. Also, development of R and pandas go hand-in-hand because they were created for same purpose. To solve this problem I use following code that gets me by anywhere:

unique, counts = np.unique(x, return_counts=True)
d = {'unique':unique, 'counts':count}  # pass the list to a dictionary
df = pd.DataFrame(d) #dictionary object can be easily passed to make a dataframe
df.sort_values(by = 'count', ascending=False, inplace = True)
df = df.reset_index(drop=True) #optional only if you want to use it further

使用pandas模块:

>>> import pandas as pd
>>> import numpy as np
>>> x = np.array([1,1,1,2,2,2,5,25,1,1])
>>> pd.value_counts(x)
1     5
2     3
25    1
5     1
dtype: int64

numpy。Bincount可能是最好的选择。如果你的数组除了包含小的密集整数之外还包含任何东西，那么像这样包装它可能是有用的:

def count_unique(keys):
    uniq_keys = np.unique(keys)
    bins = uniq_keys.searchsorted(keys)
    return uniq_keys, np.bincount(bins)

例如:

>>> x = array([1,1,1,2,2,2,5,25,1,1])
>>> count_unique(x)
(array([ 1,  2,  5, 25]), array([5, 3, 1, 1]))

使用numpy。唯一的return_counts=True (NumPy 1.9+):

import numpy as np

x = np.array([1,1,1,2,2,2,5,25,1,1])
unique, counts = np.unique(x, return_counts=True)

>>> print(np.asarray((unique, counts)).T)
 [[ 1  5]
  [ 2  3]
  [ 5  1]
  [25  1]]

与scipy.stats.itemfreq相比:

In [4]: x = np.random.random_integers(0,100,1e6)

In [5]: %timeit unique, counts = np.unique(x, return_counts=True)
10 loops, best of 3: 31.5 ms per loop

In [6]: %timeit scipy.stats.itemfreq(x)
10 loops, best of 3: 170 ms per loop