def test_tuple(self):
a = Babe().pull(stream=StringIO("a,b\n1,2:3\n4,5:6\n"), format="csv")
a = a.flatMap(
lambda row: [row._replace(b=i) for i in row.b.split(':')])
buf = StringIO()
a.push(stream=buf, format="csv")
self.assertEquals(buf.getvalue(), "a,b\n1,2\n1,3\n4,5\n4,6\n")
def wordcount():
a = Babe().pull(protocol='http',
host='www.ietf.org',
filename='rfc/rfc1149.txt')
a = a.flatMap(lambda row: [(w, 1) for w in re.findall('\w+', row.text)],
columns=['word', 'count'])
a = a.groupBy(key='word',
reducer=lambda word, rows:
(word, sum([row.count for row in rows])))
a = a.maxN(column='count', n=10)
a.push(stream=sys.stdout, format='csv')
def wordcount():
a = Babe().pull(protocol='http',
host='www.ietf.org',
filename='rfc/rfc1149.txt')
a = a.flatMap(lambda row: [(w, 1) for w in re.findall('\w+', row.text)],
columns=['word', 'count'])
a = a.groupBy(key='word',
reducer=lambda word, rows: (word, sum([row.count for row in rows])))
a = a.maxN(column='count',
n=10)
a.push(stream=sys.stdout,
format='csv')
def test_tuple(self):
a = Babe().pull(stream=StringIO("a,b\n1,2:3\n4,5:6\n"), format="csv")
a = a.flatMap(lambda row: [row._replace(b=i) for i in row.b.split(':')])
self.assertEquals(a.to_string(), "a,b\n1,2\n1,3\n4,5\n4,6\n")
