def test_flatten_column_with_differing_size_vectors(self):
data = [[1,[1,2,3],[8,7]],[2,[4,5,6],[6,5]],[3,[7,8,9],[4,3]],[4,[10,11,12],[2,1]]]
schema = [('a', ta.int32), ('b', ta.vector(3)), ('c', ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data,schema))
test_frame.flatten_columns(['b','c'])
# expected data after flattening
expected_data = [
[1,1.0,8.0],
[1,2.0,7.0],
[1,3.0,0.0],
[2,4.0,6.0],
[2,5.0,5.0],
[2,6.0,0.0],
[3,7.0,4.0],
[3,8.0,3.0],
[3,9.0,0.0],
[4,10.0,2.0],
[4,11.0,1.0],
[4,12.0,0.0]
]
self.assertEqual(test_frame.row_count, 12)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_column_with_differing_size_vectors(self):
data = [[1,[1,2,3],[8,7]],[2,[4,5,6],[6,5]],[3,[7,8,9],[4,3]],[4,[10,11,12],[2,1]]]
schema = [('a', ta.int32), ('b', ta.vector(3)), ('c', ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data,schema))
test_frame.flatten_columns(['b','c'])
# expected data after flattening
expected_data = [
[1,1.0,8.0],
[1,2.0,7.0],
[1,3.0,0.0],
[2,4.0,6.0],
[2,5.0,5.0],
[2,6.0,0.0],
[3,7.0,4.0],
[3,8.0,3.0],
[3,9.0,0.0],
[4,10.0,2.0],
[4,11.0,1.0],
[4,12.0,0.0]
]
self.assertEqual(test_frame.row_count, 12)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_multiple_vectors(self):
data = [[1, [1, 2], [8, 7]], [2, [3, 4], [6, 5]], [3, [5, 6], [4, 3]],
[4, [7, 8], [2, 1]]]
schema = [('a', ta.int32), ('b', ta.vector(2)), ('c', ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data, schema))
test_frame.flatten_columns(['b', 'c'])
# expected data after flattening
expected_data = [[1, 1.0, 8.0], [1, 2.0, 7.0], [2, 3.0, 6.0],
[2, 4.0, 5.0], [3, 5.0, 4.0], [3, 6.0, 3.0],
[4, 7.0, 2.0], [4, 8.0, 1.0]]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_inspect_nones(self):
schema = [('s', str), ('v', ta.vector(2))]
rows = [['super', [1.0095, 2.034]],
[None, None]]
result = repr(ui.RowsInspection(rows, schema, offset=0, format_settings=ui.InspectSettings(wrap=2, round=2, truncate=4)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
print result
def test_flatten_columns_with_strings_and_vectors_with_one_delimiter(self):
data = [
[1, "1:2", [1, 2], "a:b"],
[2, "3:4", [3, 4], "c:d"],
[3, "5:6", [5, 6], "e:f"],
[4, "7:8", [7, 8], "g:h"],
]
schema = [("a", ta.int32), ("b", str), ("c", ta.vector(2)), ("d", str)]
test_frame = ta.Frame(ta.UploadRows(data, schema))
test_frame.flatten_columns(["b", "c", "d"], ":")
# expected data after flattening
expected_data = [
[1, "1", 1.0, "a"],
[1, "2", 2.0, "b"],
[2, "3", 3.0, "c"],
[2, "4", 4.0, "d"],
[3, "5", 5.0, "e"],
[3, "6", 6.0, "f"],
[4, "7", 7.0, "g"],
[4, "8", 8.0, "h"],
]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_strings_and_vectors_with_default_delimiter(self):
data = [[1,"1,2",[1,2],"a,b"],[2,"3,4",[3,4],"c,d"],[3,"5,6",[5,6],"e,f"],[4,"7,8",[7,8],"g,h"]]
schema = [('a', ta.int32),('b', str), ('c', ta.vector(2)), ('d', str)]
test_frame = ta.Frame(ta.UploadRows(data,schema))
# there are only 2 string columns. giving 3 delimiters should give an exception.
with self.assertRaises(Exception):
test_frame.flatten_columns(['b', 'c', 'd'], [',',',',','])
test_frame.flatten_columns(['b', 'c', 'd'])
# expected data after flattening
expected_data = [
[1,"1",1.0,"a"],
[1,"2",2.0,"b"],
[2,"3",3.0,"c"],
[2,"4",4.0,"d"],
[3,"5",5.0,"e"],
[3,"6",6.0,"f"],
[4,"7",7.0,"g"],
[4,"8",8.0,"h"]
]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_strings_and_vectors_with_default_delimiter(self):
data = [[1,"1,2",[1,2],"a,b"],[2,"3,4",[3,4],"c,d"],[3,"5,6",[5,6],"e,f"],[4,"7,8",[7,8],"g,h"]]
schema = [('a', ta.int32),('b', str), ('c', ta.vector(2)), ('d', str)]
test_frame = ta.Frame(ta.UploadRows(data,schema))
# there are only 2 string columns. giving 3 delimiters should give an exception.
with self.assertRaises(Exception):
test_frame.flatten_columns(['b', 'c', 'd'], [',',',',','])
test_frame.flatten_columns(['b', 'c', 'd'])
# expected data after flattening
expected_data = [
[1,"1",1.0,"a"],
[1,"2",2.0,"b"],
[2,"3",3.0,"c"],
[2,"4",4.0,"d"],
[3,"5",5.0,"e"],
[3,"6",6.0,"f"],
[4,"7",7.0,"g"],
[4,"8",8.0,"h"]
]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_add_columns_and_copy_where(self):
"""
Tests UDFs for add_columns and copy(where), and uses the vector type
Changes the 2 population strings to a vector, and then uses the vector
to compute the change, and then copy out all the incorrect ones
"""
frame = ta.Frame(csv)
self.assertEquals(frame.row_count, 20, "frame should have 20 rows")
frame.add_columns(
lambda row: [
float(row['pop_2010'].translate({ord(','): None})),
float(row['population_2013'].translate({ord(','): None}))
], ("vpops", ta.vector(2)))
self.assertEquals(frame.row_count, 20, "frame should have 20 rows")
self.assertEquals(frame.column_names, [
'rank', 'city', 'population_2013', 'pop_2010', 'change', 'county',
'vpops'
])
frame.add_columns(
lambda row: (row.vpops[1] - row.vpops[0]) / row.vpops[0],
("comp_change", ta.float64))
#print frame.inspect(20)
bad_cities = frame.copy(columns=['city', 'change', 'comp_change'],
where=lambda row: row.change != "%.2f%%" %
round(100 * row.comp_change, 2))
self.assertEquals(bad_cities.column_names,
['city', 'change', 'comp_change'])
self.assertEquals(bad_cities.row_count, 1)
#print bad_cities.inspect()
row = bad_cities.take(1)[0]
row[2] = round(row[2], 5)
self.assertEquals(row, [u'Tualatin', u'4.17%', 0.03167
]) # should just be one bad one, Tualatin
def test_inspect_round(self):
schema = [('f32', ta.float32), ('f64', ta.float64),
('v', ta.vector(2))]
rows = [[0.1234, 9.87654321, [1.0095, 2.034]],
[1234.5, 9876.54321, [99.999, 33.33]]]
result = repr(
ui.RowsInspection(rows,
schema,
offset=0,
format_settings=ui.InspectSettings(wrap=2,
round=2)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[#] f32 f64 v
======================================
[0] 0.12 9.88 [1.01, 2.03]
[1] 1234.50 9876.54 [100.00, 33.33]'''
self.assertEqual(expected, result)
result = repr(
ui.RowsInspection(rows,
schema,
offset=0,
format_settings=ui.InspectSettings(
wrap='stripes', round=3)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[0]-
f32=0.123
f64=9.877
v =[1.010, 2.034]
[1]-
f32=1234.500
f64=9876.543
v =[99.999, 33.330]'''
self.assertEqual(expected, result)
def test_frame_upload_raw_list_data(self):
"""does round trip with list data --> upload to frame --> 'take' back to list and compare"""
data = [[1, 'one', [1.0, 1.1]], [2, 'two', [2.0, 2.2]], [3, 'three', [3.0, 3.3]]]
schema = [('n', int), ('s', str), ('v', ta.vector(2))]
frame = ta.Frame(ta.UploadRows(data, schema))
taken = frame.take(5)
self.assertEqual(len(data),len(taken))
for r, row in enumerate(taken):
self.assertEqual(len(data[r]),len(row))
for c, column in enumerate(row):
self.assertEqual(data[r][c], column)
def test_inspect_nones(self):
schema = [('s', str), ('v', ta.vector(2))]
rows = [['super', [1.0095, 2.034]], [None, None]]
result = repr(
ui.RowsInspection(rows,
schema,
offset=0,
format_settings=ui.InspectSettings(wrap=2,
round=2,
truncate=4)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
print result
def test_frame_upload_raw_list_data(self):
"""does round trip with list data --> upload to frame --> 'take' back to list and compare"""
data = [[1, 'one', [1.0, 1.1]], [2, 'two', [2.0, 2.2]],
[3, 'three', [3.0, 3.3]]]
schema = [('n', int), ('s', str), ('v', ta.vector(2))]
frame = ta.Frame(ta.UploadRows(data, schema))
taken = frame.take(5)
self.assertEqual(len(data), len(taken))
for r, row in enumerate(taken):
self.assertEqual(len(data[r]), len(row))
for c, column in enumerate(row):
self.assertEqual(data[r][c], column)
def test_flatten_columns_with_multiple_vectors(self):
data = [[1,[1,2],[8,7]],[2,[3,4],[6,5]],[3,[5,6],[4,3]],[4,[7,8],[2,1]]]
schema = [('a', ta.int32), ('b', ta.vector(2)), ('c', ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data,schema))
test_frame.flatten_columns(['b','c'])
# expected data after flattening
expected_data = [
[1,1.0,8.0],
[1,2.0,7.0],
[2,3.0,6.0],
[2,4.0,5.0],
[3,5.0,4.0],
[3,6.0,3.0],
[4,7.0,2.0],
[4,8.0,1.0]
]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_single_vector(self):
data = [[1, [1, 2]], [2, [3, 4]], [3, [5, 6]], [4, [7, 8]]]
schema = [("a", ta.int32), ("b", ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data, schema))
test_frame.flatten_columns("b")
# expected data after flattening
expected_data = [[1, 1.0], [1, 2.0], [2, 3.0], [2, 4.0], [3, 5.0], [3, 6.0], [4, 7.0], [4, 8.0]]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_single_vector(self):
data = [[1, [1, 2]], [2, [3, 4]], [3, [5, 6]], [4, [7, 8]]]
schema = [('a', ta.int32), ('b', ta.vector(2))]
test_frame = ta.Frame(ta.UploadRows(data, schema))
test_frame.flatten_columns('b')
# expected data after flattening
expected_data = [[1, 1.0], [1, 2.0], [2, 3.0], [2, 4.0], [3, 5.0],
[3, 6.0], [4, 7.0], [4, 8.0]]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_flatten_columns_with_strings_and_vectors_with_one_delimiter(self):
data = [[1, "1:2", [1, 2], "a:b"], [2, "3:4", [3, 4], "c:d"],
[3, "5:6", [5, 6], "e:f"], [4, "7:8", [7, 8], "g:h"]]
schema = [('a', ta.int32), ('b', str), ('c', ta.vector(2)), ('d', str)]
test_frame = ta.Frame(ta.UploadRows(data, schema))
test_frame.flatten_columns(['b', 'c', 'd'], ':')
# expected data after flattening
expected_data = [[1, "1", 1.0, "a"], [1, "2", 2.0, "b"],
[2, "3", 3.0, "c"], [2, "4", 4.0, "d"],
[3, "5", 5.0, "e"], [3, "6", 6.0, "f"],
[4, "7", 7.0, "g"], [4, "8", 8.0, "h"]]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_frame_upload_pandas(self):
"""does round trip pandas DF --> upload to frame --> download back to pandas and compare"""
import pandas as pd
from pandas.util.testing import assert_frame_equal
import numpy as np
data = [[1, 'one', [1.0, 1.1]], [2, 'two', [2.0, 2.2]], [3, 'three', [3.0, 3.3]]]
schema = [('n', ta.int64), ('s', str), ('v', ta.vector(2))] # 'n' is int64, pandas default
source = dict(zip(zip(*schema)[0], zip(*data)))
df0 = pd.DataFrame(source)
self.assertEqual(np.int64, df0['n'].dtype)
self.assertEqual(np.object, df0['s'].dtype)
self.assertEqual(np.object, df0['v'].dtype)
p = ta.Pandas(df0, schema)
frame = ta.Frame(p)
df1 = frame.download()
# print repr(df0)
# print repr(df1)
assert_frame_equal(df0, df1)
def test_frame_upload_pandas(self):
"""does round trip pandas DF --> upload to frame --> download back to pandas and compare"""
import pandas as pd
from pandas.util.testing import assert_frame_equal
import numpy as np
data = [[1, 'one', [1.0, 1.1]], [2, 'two', [2.0, 2.2]],
[3, 'three', [3.0, 3.3]]]
schema = [('n', ta.int64), ('s', str),
('v', ta.vector(2))] # 'n' is int64, pandas default
source = dict(zip(zip(*schema)[0], zip(*data)))
df0 = pd.DataFrame(source)
self.assertEqual(np.int64, df0['n'].dtype)
self.assertEqual(np.object, df0['s'].dtype)
self.assertEqual(np.object, df0['v'].dtype)
p = ta.Pandas(df0, schema)
frame = ta.Frame(p)
df1 = frame.download()
# print repr(df0)
# print repr(df1)
assert_frame_equal(df0, df1)
def test_flatten_columns_with_strings_and_vectors(self):
data = [[1,"1:2",[1,2],"a|b"],[2,"3:4",[3,4],"c|d"],[3,"5:6",[5,6],"e|f"],[4,"7:8",[7,8],"g|h"]]
schema = [('a', ta.int32),('b', str), ('c', ta.vector(2)), ('d', str)]
test_frame = ta.Frame(ta.UploadRows(data,schema))
test_frame.flatten_columns(['b', 'c', 'd'], [':','|'])
# expected data after flattening
expected_data = [
[1,"1",1.0,"a"],
[1,"2",2.0,"b"],
[2,"3",3.0,"c"],
[2,"4",4.0,"d"],
[3,"5",5.0,"e"],
[3,"6",6.0,"f"],
[4,"7",7.0,"g"],
[4,"8",8.0,"h"]
]
self.assertEqual(test_frame.row_count, 8)
self.assertEqual(test_frame.take(test_frame.row_count), expected_data)
def test_add_columns_and_copy_where(self):
"""
Tests UDFs for add_columns and copy(where), and uses the vector type
Changes the 2 population strings to a vector, and then uses the vector
to compute the change, and then copy out all the incorrect ones
"""
frame = ta.Frame(csv)
self.assertEquals(frame.row_count, 20, "frame should have 20 rows")
frame.add_columns(lambda row: [float(row['pop_2010'].translate({ord(','): None})),
float(row['population_2013'].translate({ord(','): None}))],
("vpops", ta.vector(2)))
self.assertEquals(frame.row_count, 20, "frame should have 20 rows")
self.assertEquals(frame.column_names, ['rank', 'city', 'population_2013', 'pop_2010', 'change', 'county', 'vpops'])
frame.add_columns(lambda row: (row.vpops[1] - row.vpops[0])/row.vpops[0], ("comp_change", ta.float64))
#print frame.inspect(20)
bad_cities = frame.copy(columns=['city', 'change', 'comp_change'], where=lambda row: row.change != "%.2f%%" % round(100*row.comp_change, 2))
self.assertEquals(bad_cities.column_names, ['city', 'change', 'comp_change'])
self.assertEquals(bad_cities.row_count, 1)
#print bad_cities.inspect()
row = bad_cities.take(1)[0]
row[2] = round(row[2], 5)
self.assertEquals(row, [u'Tualatin', u'4.17%', 0.03167]) # should just be one bad one, Tualatin
def test_inspect_round(self):
schema = [('f32', ta.float32), ('f64', ta.float64), ('v', ta.vector(2))]
rows = [[0.1234, 9.87654321, [1.0095, 2.034]],
[1234.5, 9876.54321, [99.999, 33.33]]]
result = repr(ui.RowsInspection(rows, schema, offset=0, format_settings=ui.InspectSettings(wrap=2, round=2)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[#] f32 f64 v
======================================
[0] 0.12 9.88 [1.01, 2.03]
[1] 1234.50 9876.54 [100.00, 33.33]'''
self.assertEqual(expected, result)
result = repr(ui.RowsInspection(rows, schema, offset=0, format_settings=ui.InspectSettings(wrap='stripes', round=3)))
result = '\n'.join([line.rstrip() for line in result.splitlines()])
expected = '''[0]-
f32=0.123
f64=9.877
v =[1.010, 2.034]
[1]-
f32=1234.500
f64=9876.543
v =[99.999, 33.330]'''
self.assertEqual(expected, result)
