sum values of columns starting with the same string in pandas dataframe

Question

I have a dataframe with about 100 columns that looks like this:

   Id  Economics-1  English-107  English-2  History-3  Economics-zz  Economics-2  \\
0  56            


        

Answer 1

Using brilliant DSM's idea:

from __future__ import print_function

import pandas as pd

categories = set(['Economics', 'English', 'Histo', 'Literature'])

def correct_categories(cols):
    return [cat for col in cols for cat in categories if col.startswith(cat)]    

df = pd.read_csv('data.csv', sep=r'\s+', index_col='Id')

#print(df)
print(df.groupby(correct_categories(df.columns),axis=1).sum())

Output:

    Economics  English  Histo  Literature
Id
56          1        1      2           1
11          1        0      0           1
6           1        1      0           0
43          2        0      1           1
14          1        1      1           0

Here is another version, which takes care of "Histo/History" problematic..

from __future__ import print_function

import pandas as pd

#categories = set(['Economics', 'English', 'Histo', 'Literature'])

#
# mapping: common starting pattern: desired name
#
categories = {
    'Histo': 'History',
    'Economics': 'Economics',
    'English': 'English',
    'Literature': 'Literature'
}

def correct_categories(cols):
    return [categories[cat] for col in cols for cat in categories.keys() if col.startswith(cat)]

df = pd.read_csv('data.csv', sep=r'\s+', index_col='Id')
#print(df.columns, len(df.columns))
#print(correct_categories(df.columns), len(correct_categories(df.columns)))
#print(df.groupby(pd.Index(correct_categories(df.columns)),axis=1).sum())

rslt = df.groupby(correct_categories(df.columns),axis=1).sum()
print(rslt)
print('History\n', rslt['History'])

Output:

    Economics  English  History  Literature
Id
56          1        1        2           1
11          1        0        0           1
6           1        1        0           0
43          2        0        1           1
14          1        1        1           0
History
 Id
56    2
11    0
6     0
43    1
14    1
Name: History, dtype: int64

PS You may want to add missing categories to categories map/dictionary