cell_line_snip.py

sorted_data  = sorted(data, key=lambda x: x['Sample name'])
by_sample_name = itertools.groupby(sorted_data, key=lambda x: x.get('Sample name'))
grouped = []
for name, g in by_sample_name:
    d = list(g)
    grouped.append(
        '\t'.join([
            name,
            str(len(d)),
            ','.join(set([x['Primary site'] for x in d])),
            ','.join(set([y['Histology subtype 1'] for y in d]))
        ])
    )