gistfile1.py

fill_ratio_1 = defaultdict(lambda: defaultdict(int))
fill_ratio = 0
for col in count_df.columns:
    if count_df[col].max() > 100000:
        a = count_df[col]
        for length, count in maxcombinations.items():
            fill_ratio = float(a[length])/float(count)
            fill_ratio_1[col][length] = fill_ratio
%matplotlib inline
import matplotlib
matplotlib.use('agg')
import matplotlib.pyplot as plt
for tld,counters in counter.items():
     if sum(counter[tld].values()) > 1000000:
        plt.bar(maxcombinations.keys(), maxcombinations.values(), color = '0.75')
        plt.bar(counter[tld].keys(), counter[tld].values(), color='g')
        plt.axis([2, 25, 1, max(counter[tld].values())*4])
        plt.xlabel('Characters')
        plt.ylabel('# of domains')
        plt.title('Number of domain names + available combinations/length for .{}'.format(tld))
        plt.xticks([i for i in range(0,25)])
        plt.grid(True, which='both')
        plt.show()