def test_stringpatterns(): table = ( ("foo", "bar"), ("Mr. Foo", "123-1254"), ("Mrs. Bar", "234-1123"), ("Mr. Spo", "123-1254"), (u"Mr. Baz", u"321 1434"), (u"Mrs. Baz", u"321 1434"), ("Mr. Quux", "123-1254-XX"), ) actual = stringpatterns(table, "foo") expect = ( ("pattern", "count", "frequency"), ("Aa. Aaa", 3, 3.0 / 6), ("Aaa. Aaa", 2, 2.0 / 6), ("Aa. Aaaa", 1, 1.0 / 6), ) ieq(expect, actual) actual = stringpatterns(table, "bar") expect = ( ("pattern", "count", "frequency"), ("999-9999", 3, 3.0 / 6), ("999 9999", 2, 2.0 / 6), ("999-9999-AA", 1, 1.0 / 6), ) ieq(expect, actual)
def test_stringpatterns(): table = (('foo', 'bar'), ('Mr. Foo', '123-1254'), ('Mrs. Bar', '234-1123'), ('Mr. Spo', '123-1254'), (u'Mr. Baz', u'321 1434'), (u'Mrs. Baz', u'321 1434'), ('Mr. Quux', '123-1254-XX')) actual = stringpatterns(table, 'foo') expect = (('pattern', 'count', 'frequency'), ('Aa. Aaa', 3, 3. / 6), ('Aaa. Aaa', 2, 2. / 6), ('Aa. Aaaa', 1, 1. / 6)) ieq(expect, actual) actual = stringpatterns(table, 'bar') expect = (('pattern', 'count', 'frequency'), ('999-9999', 3, 3. / 6), ('999 9999', 2, 2. / 6), ('999-9999-AA', 1, 1. / 6)) ieq(expect, actual)
def test_stringpatterns(): table = (('foo', 'bar'), ('Mr. Foo', '123-1254'), ('Mrs. Bar', '234-1123'), ('Mr. Spo', '123-1254'), ('Mr. Baz', '321 1434'), ('Mrs. Baz', '321 1434'), ('Mr. Quux', '123-1254-XX')) actual = stringpatterns(table, 'foo') expect = (('pattern', 'count', 'frequency'), ('Aa. Aaa', 3, 3./6), ('Aaa. Aaa', 2, 2./6), ('Aa. Aaaa', 1, 1./6)) ieq(expect, actual) actual = stringpatterns(table, 'bar') expect = (('pattern', 'count', 'frequency'), ('999-9999', 3, 3./6), ('999 9999', 2, 2./6), ('999-9999-AA', 1, 1./6)) ieq(expect, actual)
etl.typecounts(table, 'bar') etl.typecounts(table, 'baz') # stringpatterns() ################## import petl as etl table = [['foo', 'bar'], ['Mr. Foo', '123-1254'], ['Mrs. Bar', '234-1123'], ['Mr. Spo', '123-1254'], [u'Mr. Baz', u'321 1434'], [u'Mrs. Baz', u'321 1434'], ['Mr. Quux', '123-1254-XX']] etl.stringpatterns(table, 'foo') etl.stringpatterns(table, 'bar') # rowlengths() ############### import petl as etl table = [['foo', 'bar', 'baz'], ['A', 1, 2], ['B', '2', '3.4'], [u'B', u'3', u'7.8', True], ['D', 'xyz', 9.0], ['E', None], ['F', 9]] etl.rowlengths(table)