I am trying to calculate the percentile associated with individual entries in a dataframe (using the distribution of values in a column). I am certain that I am missing some very basic thing but cannot figure out why I am getting an error when running the following code,
from scipy.stats import percentileofscore as pctl
import pandas as pd
import numpy as np
data = np.arange(100).reshape(20,5)
df = pd.DataFrame(data)
def f(series):
r= series.index
return pctl(series.values, series.iloc[r])
df.apply(f)
Here is the error I get,
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-7-4d3ad4c6f441> in <module>
----> 1 df.apply(f)
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
6012 args=args,
6013 kwds=kwds)
-> 6014 return op.get_result()
6015
6016 def applymap(self, func):
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\apply.py in get_result(self)
316 *self.args, **self.kwds)
317
--> 318 return super(FrameRowApply, self).get_result()
319
320 def apply_broadcast(self):
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\apply.py in get_result(self)
140 return self.apply_raw()
141
--> 142 return self.apply_standard()
143
144 def apply_empty_result(self):
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\apply.py in apply_standard(self)
246
247 # compute the result using the series generator
--> 248 self.apply_series_generator()
249
250 # wrap results
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
275 try:
276 for i, v in enumerate(series_gen):
--> 277 results[i] = self.f(v)
278 keys.append(v.name)
279 except Exception as e:
<ipython-input-6-347aa35ccd44> in f(series)
1 def f(series):
2 r= series.index
----> 3 return pctl(series.values, series.iloc[r])
C:\Python\Miniconda\envs\leiap\lib\site-packages\scipy\stats\stats.py in percentileofscore(a, score, kind)
1785
1786 """
-> 1787 if np.isnan(score):
1788 return np.nan
1789 a = np.asarray(a)
C:\Python\Miniconda\envs\leiap\lib\site-packages\pandas\core\generic.py in __nonzero__(self)
1574 raise ValueError("The truth value of a {0} is ambiguous. "
1575 "Use a.empty, a.bool(), a.item(), a.any() or a.all()."
-> 1576 .format(self.__class__.__name__))
1577
1578 __bool__ = __nonzero__
ValueError: ('The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().', 'occurred at index 0')
The score argument should be either an int or a float as per the documentation. See https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.percentileofscore.html
series.iloc[r] is a series. You need to use a scalar value for score.