Demo for thinking in functions workshop with imdb database

thinking_in_functions.py

import csv
import itertools
from collections import Counter, defaultdict
import json
import re
"""
get Blockbuster Database dataset from http://www.crowdflower.com/data-for-everyone
"""
f = open("top_ten_movies_per_year_DFE.csv")
r = csv.DictReader(f)
data = [x for x in r]
f.close()
gross_by_studio = defaultdict(list)
[
	gross_by_studio[a].append(b)
	for a, b in
	list(
		itertools.chain(*[
			[
				(y.strip(), float("".join([
					a for a in
					re.split("[^.0-9]", x.get('worldwide_gross'))]))
					if '$' in x.get('worldwide_gross') else 0)
					for y in x.get('studio').split("/")
				] for x in data
			]
		)
	)
]
gross_by_studio = dict([
	(x, sum(y))
	for x, y in
	gross_by_studio.items()
])
print json.dumps(gross_by_studio, indent=4)

genre_count = dict(
	Counter([
		a for a in
		list(itertools.chain(*[
			[
				x.get('Genre_%d'%y) for y in [1,2,3] if x.get('Genre_%d'%y)]
				for x in data])) if a
			]
		)
	)

def to_gross(q):
	print q
	return float("".join([
					a for a in
					re.split("[^.0-9]", q)]) if q else 0)


print json.dumps(genre_count, indent=4)
gross_rating = [(a.get('title'), a.get('imdb_rating'), a.get('adjusted'), a.get('year')) for a in sorted(data, key=lambda x:(-to_gross(x.get('adjusted')), -to_gross(x.get('imdb_rating'))))][:10]
print json.dumps(gross_rating, indent=4)