gistfile1.py

from collections import defaultdict
#declare the dictionary in dictionary for names counting in accordance to tld
counter = defaultdict(lambda: defaultdict(int))
#fetching the data about all domain names and counting the number of names in accordance with names lenghts
with open('gtld.csv','rb') as f:
        for x in f:
            #to exclude more than second level domains like co.uk and so on, just because we can
            if x.count('.') == 1:
                fname = x.split(".",1)[1].rstrip('\r\n')
                counter[fname][x.rfind('.')] += 1
import pandas as pd
import numpy as np
count_df = pd.DataFrame(counter)
count_df = count_df.ix[1:15, :]
#swap none values with zeros for future processing
count_df[np.isnan(count_df)] = 0
#let's check info about how many gTLDs we've got in total
print len(counter)