def test_describe_cols(self):
test_list = [[1, 2],[2, 3],[3, 4],[4, 5],[5, 6],[6, 7]]
test_nd = np.array(test_list)
test_sa = np.array([(1, 2, 'a'), (2, 3, 'b'), (3, 4, 'c'), (4, 5, 'd'),
(5, 6, 'e'), (6, 7, 'f')],
dtype=[('id', int), ('val', float), ('name', 'S1')])
ctrl_list = np.array([('f0', 6, 3.5, 1.707825127659933, 1, 6),
('f1', 6, 4.5, 1.707825127659933, 2, 7)],
dtype=[('Column Name', 'S2'), ('Count', int),
('Mean', float), ('Standard Dev', float),
('Minimum', int), ('Maximum', int)])
ctrl_printout = """
Column Name Count Mean Standard Dev Minimum Maximum
0 f0 6 3.5 1.70782512766 1 6
1 f1 6 4.5 1.70782512766 2 7
""".strip()
with uft.rerout_stdout() as get_stdout:
self.assertTrue(uft.array_equal(ctrl_list,
describe_cols(
test_list)))
self.assertEqual(get_stdout().strip(), ctrl_printout)
self.assertTrue(uft.array_equal(ctrl_list,
describe_cols(
test_nd, verbose=False)))
ctrl_sa = np.array([('id', 6, 3.5, 1.707825127659933, 1, 6),
('val', 6, 4.5, 1.707825127659933, 2, 7),
('name', np.nan, np.nan, np.nan, np.nan, np.nan)],
dtype=[('Column Name', 'S4'), ('Count', float),
('Mean', float), ('Standard Dev', float),
('Minimum', float), ('Maximum', float)])
self.assertTrue(uft.array_equal(ctrl_sa,
describe_cols(
test_sa,
verbose=False)))
def test_pprint_sa(self):
M = [(1, 2, 3), (4, 5, 6), (7, 8, 'STRING')]
ctrl = """
f0 f1 f2
0 1 2 3
1 4 5 6
2 7 8 STRING
""".strip()
with uft.rerout_stdout() as get_stdout:
dsp.pprint_sa(M)
self.assertEqual(get_stdout().strip(), ctrl)
M = np.array([(1000, 'Bill'), (2000, 'Sam'), (3000, 'James')],
dtype=[('number', float), ('name', 'S5')])
row_labels = [name[0] for name in M['name']]
ctrl = """
number name
B 1000.0 Bill
S 2000.0 Sam
J 3000.0 James
""".strip()
with uft.rerout_stdout() as get_stdout:
dsp.pprint_sa(M, row_labels=row_labels)
self.assertEqual(get_stdout().strip(), ctrl)
def test_print_matrix_row_col(self):
M = [(1, 2, 3), (4, 5, 6), (7, 8, 'STRING')]
ctrl = """
f0 f1 f2
0 1 2 3
1 4 5 6
2 7 8 STRING
""".strip()
with uft.rerout_stdout() as get_stdout:
comm.print_matrix_row_col(M)
self.assertEqual(get_stdout().strip(), ctrl)
M = np.array([(1000, 'Bill'), (2000, 'Sam'), (3000, 'James')],
dtype=[('number', float), ('name', 'S5')])
row_labels = [name[0] for name in M['name']]
ctrl = """
number name
B 1000.0 Bill
S 2000.0 Sam
J 3000.0 James
""".strip()
with uft.rerout_stdout() as get_stdout:
comm.print_matrix_row_col(M, row_labels=row_labels)
self.assertEqual(get_stdout().strip(), ctrl)
def test_table(self):
data = np.array(['a', 'b', 'a', 'b', 'b', 'b', 'b', 'a', 'c', 'c',
'b', 'c', 'a'], dtype='O')
ctrl_sa = np.array(
[('a', 4), ('b', 6), ('c', 3)],
dtype=[('col_name', 'S1'), ('count', int)])
ctrl_printout = """
col_name count
0 a 4
1 b 6
2 c 3
""".strip()
with uft.rerout_stdout() as get_stdout:
self.assertTrue(uft.array_equal(ctrl_sa,
table(data)))
self.assertEqual(get_stdout().strip(), ctrl_printout)
def test_crosstab(self):
l1= [1, 2, 7, 7, 2, 1, 2, 1, 1]
l2= [1, 3, 2, 6, 6, 3, 6, 4, 4]
correct = np.array([('1', 1, 0, 1, 2, 0),
('2', 0, 0, 1, 0, 2),
('7', 0, 1, 0, 0, 1)],
dtype=[('col1_value', 'S1'),
('1', int),
('2', int),
('3', int),
('4', int),
('6', int)])
correct_printout = """
col1_value 1 2 3 4 6
0 1 1 0 1 2 0
1 2 0 0 1 0 2
2 7 0 1 0 0 1
""".strip()
with uft.rerout_stdout() as get_stdout:
self.assertTrue(np.array_equal(correct, crosstab(l1,l2)))
self.assertEqual(get_stdout().strip(), correct_printout)
