def getMaxValues(self,rdd):
setMovies = SetMovies()
regexMoviesTitle = '::([a-z]|[A-Z]|[0-9]|[(]|[)]|[ ])*::'
regexYear = '[(][0-9][0-9][0-9][0-9][)]'
rdd = rdd.map(lambda line : re.search(regexMoviesTitle,line).group())
rdd = rdd.map(lambda movie : (movie,movie.replace('::','').split(" ")))
rdd = rdd.flatMap(lambda titleAndWords : map(lambda word: (word,(1,[titleAndWords[0]])),titleAndWords[1]))
rdd = rdd.filter(lambda wordsAndTitle : not re.match(regexYear, wordsAndTitle[0]) and len(wordsAndTitle[0])>=3)
rdd = rdd.reduceByKey(lambda firstValue,secondValue :(firstValue[0]+secondValue[0],list(set(firstValue[1]+secondValue[1]))))
return setMovies.setWithMaxValues(rdd,lambda value :(value[1][0],(value[0],value[1][1])))
class TestCalculator (unittest.TestCase):
def setUp(self):
conf = SparkConf().setAppName("appTest").setMaster("local[*]")
self.sc = SparkContext(conf=conf)
self.setMovies = SetMovies()
def tearDown(self):
self.sc.stop()
def test_when_calculate_set_word_most_repeater(self):
entry = [('Toy', (1, ['::Toy Story Toy (1995)::'])),
('ToyA', (3, ['::ToyA StoryA ToyA (1995)::'])),
('Story', (1, ['::Toy Story Toy (1995)::'])),
('StoryA', (3, ['::ToyA StoryA ToyA (1995)::']))]
result = (('ToyA', ['::ToyA StoryA ToyA (1995)::']),
("StoryA",["::ToyA StoryA ToyA (1995)::"]))
funcReverseTuple = lambda value :((value[1][0],(value[0],value[1][1])))
rdd = self.sc.parallelize(entry)
self.assertEqual(self.setMovies.setWithMaxValues(rdd,funcReverseTuple),result)
def test_when_calculate_set_word_most_repeater_one(self):
entry = [('Toy', (1, ['::Toy Story Toy (1995)::'])),
('ToyA', (3, ['::ToyA StoryA ToyA (1995)::'])),
('Story', (1, ['::Toy Story Toy (1995)::'])),
('StoryA', (1, ['::ToyA StoryA ToyA (1995)::']))]
result = (('ToyA', ['::ToyA StoryA ToyA (1995)::']))
funcReverseTuple = lambda value :(value[1][0],(value[0],value[1][1]))
rdd = self.sc.parallelize(entry)
self.assertEqual(self.setMovies.setWithMaxValues(rdd,funcReverseTuple),result)
def test_when_calculate_maximum_year(self):
entry = [('(1996)',2),
('(1998)',2),
('(1997)',1)]
result = ('(1996)','(1998)')
rdd = self.sc.parallelize(entry)
funcReverseTuple = lambda value :(value[1],value[0])
self.assertEqual(self.setMovies.setWithMaxValues(rdd,funcReverseTuple),result)
def test_when_calculate_maximum_year_with_only_one(self):
entry = [('(1996)',2),
('(1998)',1),
('(1997)',1),
('(1999)',1)]
result = ('(1996)')
rdd = self.sc.parallelize(entry)
funcReverseTuple = lambda value :(value[1],value[0])
self.assertEqual(self.setMovies.setWithMaxValues(rdd,funcReverseTuple),result)
def setUp(self):
conf = SparkConf().setAppName("appTest").setMaster("local[*]")
self.sc = SparkContext(conf=conf)
self.setMovies = SetMovies()
def getMaxValues(self,rdd): setMovies = SetMovies() regexYearWithParenthesis = '[(][0-9][0-9][0-9][0-9][)]' rdd = rdd.map(lambda line : (re.search(regexYearWithParenthesis,line).group(),1)) rdd = rdd.reduceByKey(lambda firstValue,secondValue :(firstValue+secondValue)) return setMovies.setWithMaxValues(rdd,lambda value :(value[1],value[0]))
