Allow `None` as input for categorical/continuous

[alistairewj]

Instead of requiring an empty list, it would seem appropriate to allow the continuous and categorical inputs to be None. At the moment this will throw an error. Example:

import pandas as pd
import numpy as np
from tableone import TableOne

n = 10000
data_sample = pd.DataFrame(index=range(n))

mu, sigma = 10, 1
data_sample['normal'] = np.random.normal(mu, sigma, n)
data_sample['nonnormal'] = np.random.noncentral_chisquare(20,nonc=2,size=n)

TableOne(data_sample, continuous = ['normal'], categorical = None)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-29-d1c5f121e36f> in <module>()
     10 data_sample['nonnormal'] = np.random.noncentral_chisquare(20,nonc=2,size=n)
     11 
---> 12 TableOne(data_sample, continuous = ['normal'], categorical = None)

/home/alistairewj/git/tableone/tableone.py in __init__(self, data, continuous, categorical, strata_col, nonnormal, pval)
     35         if nonnormal and type(nonnormal) == str:
     36             nonnormal = [nonnormal]
---> 37 
     38         self.__check_input_arguments_for_overlap(continuous,categorical,'continuous','categorical')
     39         self.__check_input_arguments_in_df(data.columns,continuous+categorical+nonnormal)

/home/alistairewj/git/tableone/tableone.py in __check_input_arguments_for_overlap(self, a, b, a_name, b_name)
     93         """
     94         Check the input argument for duplicate columns
---> 95         """
     96         if bool(set(a) & set(b)):
     97             overlap = [val for val in a if val in b]

TypeError: 'NoneType' object is not iterable

[tompollard]

We can implement this, but is there a reason why you wouldn't just omit the categorical argument altogether?

e.g.

# only continuous variables 

import pandas as pd
import numpy as np
from tableone import TableOne

n = 10000
data_sample = pd.DataFrame(index=range(n))

mu, sigma = 10, 1
data_sample['normal'] = np.random.normal(mu, sigma, n)
data_sample['nonnormal'] = np.random.noncentral_chisquare(20,nonc=2,size=n)

TableOne(data_sample, continuous = ['normal', 'nonnormal'], nonnormal=['nonnormal'])

Outputs:

Overall
                          overall
------------------------  -------------------
n                         10000
normal (mean (std))       10.00 (1.00)
nonnormal (median [IQR])  21.23 [17.04,26.30]