def check_mixedcolumn_sorting():
dm = DataMatrix(length=24)
dm.c = [
1, '1', 2, '2', 1.1, '1.1', 2.1, '2.1', INF, -INF, 'inf', '-inf', NAN,
NAN, 'nan', 'nan', None, None, None, None, 'alpha', 'beta', 'None', ''
]
dm.c = ops.shuffle(dm.c)
dm = ops.sort(dm, by=dm.c)
check_col(dm.c, [
-INF,
-INF,
1,
1,
1.1,
1.1,
2,
2,
2.1,
2.1,
INF,
INF,
'',
'None',
'alpha',
'beta',
None,
None,
None,
None,
NAN,
NAN,
NAN,
NAN,
])
def test_group(): dm = DataMatrix(length=4) dm.a = 'b', 'b', 'a', 'a' dm.b = 'x', 'x', 'x', 'y' dm.c = IntColumn dm.c = 0, 1, 2, 3 dm = ops.group(dm, [dm.a, dm.b]) check_series(dm.c, [[2, np.nan], [3, np.nan], [0, 1]])
def test_group():
dm = DataMatrix(length=4)
dm.a = 'b', 'b', 'a', 'a'
dm.b = 'x', 'x', 'x', 'y'
dm.c = IntColumn
dm.c = 0, 1, 2, 3
dm = ops.group(dm, [dm.a, dm.b])
check_series(dm.c, [[3, np.nan], [2, np.nan], [0, 1]]) # Order guaranteed?
def check_intcolumn_sorting(): dm = DataMatrix(length=8, default_col_type=IntColumn) dm.c = [ 1, '1', 2, '2', 1.1, '1.1', 2.1, '2.8', ] dm.c = ops.shuffle(dm.c) dm = ops.sort(dm, by=dm.c) check_col(dm.c, [ 1, 1, 1, 1, 2, 2, 2, 2 ])
def test_properties():
dm = DataMatrix(length=0)
dm.c = -1
assert dm.empty
dm = DataMatrix(length=1)
assert dm.empty
dm = DataMatrix(length=1)
dm.c = -1
assert not dm.empty
dm = DataMatrix(length=3)
dm.c = -1
dm.d = -1
assert len(dm) == 3
def generatedata(effectsize=EFFECTSIZE,
blinksinbaseline=BLINKSINBASELINE,
**kwargs):
dm = DataMatrix(length=TRACES)
dm.c = IntColumn
dm.c[:TRACES // 2] = 1
dm.c[TRACES // 2:] = 2
dm.y = SeriesColumn(depth=TRACELEN)
dm.y.setallrows(a)
dm.y += np.random.randint(NOISERANGE[0], NOISERANGE[1], TRACES)
dm.y[TRACES // 2:] += np.linspace(0, effectsize, TRACELEN)
# Inroduce blinks
for i, row in enumerate(dm):
blinklen = np.random.randint(BLINKLEN[0], BLINKLEN[1], BLINKS)
if i < blinksinbaseline:
blinkstart = np.array([1])
else:
blinkstart = np.random.randint(BASELINE[1], TRACELEN, BLINKS)
blinkend = blinkstart + blinklen
for start, end in zip(blinkstart, blinkend):
end = min(TRACELEN - 1, end)
if end - start < 2 * BLINKMARGIN:
continue
row.y[start:start+BLINKMARGIN] = \
np.linspace(row.y[start-1], 0, BLINKMARGIN)
row.y[end-BLINKMARGIN:end] = \
np.linspace(0, row.y[end], BLINKMARGIN)
row.y[start:end] = np.random.randint(0, 100, end - start)
return dm
def _test_numeric_properties(coltype, nan):
dm = DataMatrix(length=4, default_col_type=coltype)
dm.c = 1, 1, nan, 4
dm.d = [nan] * 4
assert dm.c.mean == 2
assert dm.c.median == 1
assert dm.c.std == np.std([1, 1, 4], ddof=1)
assert dm.c.max == 4
assert dm.c.min == 1
assert dm.c.sum == 6
if coltype in (IntColumn, FloatColumn):
with pytest.warns(RuntimeWarning):
all_nan(dm.d.mean, nan)
all_nan(dm.d.median, nan)
all_nan(dm.d.std, nan)
all_nan(dm.d.max, nan)
all_nan(dm.d.min, nan)
all_nan(dm.d.sum, nan)
else:
all_nan(dm.d.mean, nan)
all_nan(dm.d.median, nan)
all_nan(dm.d.std, nan)
all_nan(dm.d.max, nan)
all_nan(dm.d.min, nan)
all_nan(dm.d.sum, nan)
def test_group():
dm = DataMatrix(length=4)
dm.a = 'b', 'b', 'a', 'a'
dm.b = 'x', 'x', 'x', 'y'
dm.c = IntColumn
dm.c = 0, 1, 2, 3
dm = ops.group(dm, [dm.a, dm.b])
# Assert that at least one of the permutations passes
for ref in itertools.permutations([[3, np.nan], [2, np.nan], [0, 1]]):
try:
check_series(dm.c, ref)
break
except AssertionError:
pass
else:
assert (False)
def test_auto_type():
dm = DataMatrix(length=2)
dm.a = 'a', 1
dm.b = 0.1, 1
dm.c = 0, 1
dm = ops.auto_type(dm)
assert isinstance(dm.a, MixedColumn)
assert isinstance(dm.b, FloatColumn)
assert isinstance(dm.c, IntColumn)
def test_auto_type(): dm = DataMatrix(length=2) dm.a = 'a', 1 dm.b = 0.1, 1 dm.c = 0, 1 ops.auto_type(dm) ok_(isinstance(dm.a, MixedColumn)) ok_(isinstance(dm.b, FloatColumn)) ok_(isinstance(dm.c, IntColumn))
def test_keep_only():
dm = DataMatrix(length=2)
dm.a = 'a', 'b'
dm.b = 0, 1
dm.c = 'y', 'z'
for cols in (['b', 'c'], [dm.b, dm.c]):
dm = ops.keep_only(dm, *cols)
assert 'a' not in dm.column_names
assert 'b' in dm.column_names
assert 'c' in dm.column_names
def test_replace():
dm = DataMatrix(length=3)
dm.a = 0, 1, 2
dm.c = FloatColumn
dm.c = np.nan, 1, 2
dm.s = SeriesColumn(depth=3)
dm.s[0] = 0, 1, 2
dm.s[1] = np.nan, 1, 2
dm.s[2] = np.nan, 1, 2
dm.a = ops.replace(dm.a, {0: 100, 2: 200})
dm.c = ops.replace(dm.c, {np.nan: 100, 2: np.nan})
dm.s = ops.replace(dm.s, {np.nan: 100, 2: np.nan})
check_col(dm.a, [100, 1, 200])
check_col(dm.c, [100, 1, np.nan])
check_series(dm.s, [
[0, 1, np.nan],
[100, 1, np.nan],
[100, 1, np.nan],
])
def _test_basic_properties(coltype):
dm = DataMatrix(length=4, default_col_type=coltype)
dm.c = 3, 1, 2, 3
dm.d = dm.c
dm.e = 3, 1, 2, 3
eq_(dm.c.name, ['c', 'd'])
eq_(dm.d.name, ['c', 'd'])
eq_(dm.e.name, 'e')
eq_(list(dm.c.unique), [1, 2, 3])
eq_(dm.c.count, 3)
def _test_basic_properties(coltype):
dm = DataMatrix(length=4, default_col_type=coltype)
dm.c = 3, 1, 2, 3
dm.d = dm.c
dm.e = 3, 1, 2, 3
assert dm.c.name == ['c', 'd']
assert dm.d.name == ['c', 'd']
assert dm.e.name == 'e'
assert list(dm.c.unique) == [1, 2, 3]
assert dm.c.count == 3
def check_floatcolumn_sorting():
dm = DataMatrix(length=24, default_col_type=FloatColumn)
with pytest.warns(UserWarning):
dm.c = [
1, '1', 2, '2', 1.1, '1.1', 2.1, '2.1', INF, -INF, 'inf', '-inf',
NAN, NAN, 'nan', 'nan', None, None, None, None, 'alpha', 'beta',
'None', ''
]
dm.c = ops.shuffle(dm.c)
dm = ops.sort(dm, by=dm.c)
check_col(dm.c, [
-INF,
-INF,
1,
1,
1.1,
1.1,
2,
2,
2.1,
2.1,
INF,
INF,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
NAN,
])
def _test_numeric_properties(coltype, nan):
dm = DataMatrix(length=4, default_col_type=coltype)
dm.c = 1, 1, nan, 4
dm.d = [nan] * 4
eq_(dm.c.mean, 2)
eq_(dm.c.median, 1)
eq_(dm.c.std, np.std([1, 1, 4], ddof=1))
eq_(dm.c.max, 4)
eq_(dm.c.min, 1)
eq_(dm.c.sum, 6)
all_nan(dm.d.mean, nan)
all_nan(dm.d.median, nan)
all_nan(dm.d.std, nan)
all_nan(dm.d.max, nan)
all_nan(dm.d.min, nan)
all_nan(dm.d.sum, nan)
def _test_numeric_properties(coltype, nan):
dm = DataMatrix(length=4, default_col_type=coltype)
dm.c = 1, 1, nan, 4
dm.d = [nan] * 4
assert dm.c.mean == 2
assert dm.c.median == 1
assert dm.c.std == np.std([1, 1, 4], ddof=1)
assert dm.c.max == 4
assert dm.c.min == 1
assert dm.c.sum == 6
all_nan(dm.d.mean, nan)
all_nan(dm.d.median, nan)
all_nan(dm.d.std, nan)
all_nan(dm.d.max, nan)
all_nan(dm.d.min, nan)
all_nan(dm.d.sum, nan)
def _test_copying(cls):
dm = DataMatrix(length=5)
dm.d = cls
dm2 = dm[:]
dm2.e = dm.d
dm2.f = dm2.d
ok_(dm2 is not dm)
ok_(dm2.d is not dm.d)
ok_(dm2.e is not dm.d)
ok_(dm2.f is dm2.d)
ok_(dm2.d._seq is not dm.d._seq)
dm.c = dm.d
ok_(dm.c is dm.d)
ok_(dm.c._seq is dm.d._seq)
dm.e = dm.d[:]
ok_(dm.e is not dm.d)
ok_(dm.e._seq is not dm.d._seq)
check_integrity(dm)
check_integrity(dm2)
def test_shuffle_horiz(): dm = DataMatrix(length=2) dm.a = 'a', 'b' dm.b = 0, 1 dm.c = '-', '-' while True: dm2 = ops.shuffle_horiz(dm) try: check_row(dm2[0], [0, '-', 'a']) break except: pass while True: dm2 = ops.shuffle_horiz(dm.a, dm.b) try: check_row(dm2[0], [0, 'a', '-']) break except: pass for i in range(1000): dm2 = ops.shuffle_horiz(dm.a, dm.b) check_col(dm.c, ['-', '-'])
def test_shuffle_horiz():
dm = DataMatrix(length=2)
dm.a = 'a', 'b'
dm.b = 0, 1
dm.c = '-', '-'
while True:
dm2 = ops.shuffle_horiz(dm)
try:
check_row(dm2[0], [0, '-', 'a'])
break
except:
pass
while True:
dm2 = ops.shuffle_horiz(dm.a, dm.b)
try:
check_row(dm2[0], [0, 'a', '-'])
break
except:
pass
for i in range(1000):
dm2 = ops.shuffle_horiz(dm.a, dm.b)
check_col(dm.c, ['-', '-'])
ops.shuffle_horiz(dm.a)
