import numpy as np
a = [154, 400, 1124, 82, 94, 108]
print np.percentile(a,95) # gives the 95th percentile

顺便说一下，有一个百分位数函数的纯python实现，以防人们不想依赖scipy。函数复制如下:

## {{{ http://code.activestate.com/recipes/511478/ (r1)
import math
import functools

def percentile(N, percent, key=lambda x:x):
    """
    Find the percentile of a list of values.

    @parameter N - is a list of values. Note N MUST BE already sorted.
    @parameter percent - a float value from 0.0 to 1.0.
    @parameter key - optional key function to compute value from each element of N.

    @return - the percentile of the values
    """
    if not N:
        return None
    k = (len(N)-1) * percent
    f = math.floor(k)
    c = math.ceil(k)
    if f == c:
        return key(N[int(k)])
    d0 = key(N[int(f)]) * (c-k)
    d1 = key(N[int(c)]) * (k-f)
    return d0+d1

# median is 50th percentile.
median = functools.partial(percentile, percent=0.5)
## end of http://code.activestate.com/recipes/511478/ }}}

要计算一个系列的百分位数，运行:

from scipy.stats import rankdata
import numpy as np

def calc_percentile(a, method='min'):
    if isinstance(a, list):
        a = np.asarray(a)
    return rankdata(a, method=method) / float(len(a))

例如:

a = range(20)
print {val: round(percentile, 3) for val, percentile in zip(a, calc_percentile(a))}
>>> {0: 0.05, 1: 0.1, 2: 0.15, 3: 0.2, 4: 0.25, 5: 0.3, 6: 0.35, 7: 0.4, 8: 0.45, 9: 0.5, 10: 0.55, 11: 0.6, 12: 0.65, 13: 0.7, 14: 0.75, 15: 0.8, 16: 0.85, 17: 0.9, 18: 0.95, 19: 1.0}

对于系列:用于描述函数

假设df具有以下列sales和id。你想计算销售额的百分比，它是这样工作的，

df['sales'].describe(percentiles = [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1])

0.0: .0: minimum
1: maximum 
0.1 : 10th percentile and so on

下面是如何在没有numpy的情况下，仅使用python来计算百分比。

import math

def percentile(data, perc: int):
    size = len(data)
    return sorted(data)[int(math.ceil((size * perc) / 100)) - 1]

percentile([10.0, 9.0, 8.0, 7.0, 6.0, 5.0, 4.0, 3.0, 2.0, 1.0], 90)
# 9.0
percentile([142, 232, 290, 120, 274, 123, 146, 113, 272, 119, 124, 277, 207], 50)
# 146

我引导数据，然后绘制出10个样本的置信区间。置信区间表示概率在5%到95%之间的范围。

 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
 import numpy as np
 import json
 import dc_stat_think as dcst

 data = [154, 400, 1124, 82, 94, 108]
 #print (np.percentile(data,[0.5,95])) # gives the 95th percentile

 bs_data = dcst.draw_bs_reps(data, np.mean, size=6*10)

 #print(np.reshape(bs_data,(24,6)))

 x= np.linspace(1,6,6)
 print(x)
 for (item1,item2,item3,item4,item5,item6) in bs_data.reshape((10,6)):
     line_data=[item1,item2,item3,item4,item5,item6]
     ci=np.percentile(line_data,[.025,.975])
     mean_avg=np.mean(line_data)
     fig, ax = plt.subplots()
     ax.plot(x,line_data)
     ax.fill_between(x, (line_data-ci[0]), (line_data+ci[1]), color='b', alpha=.1)
     ax.axhline(mean_avg,color='red')
     plt.show()