def test_plot_boxes(self):
x = pd.DataFrame(
[[0.1, 0, 'a'], [0.2, 1, 'b'], [0.3, 2, 'a'], [0.4, 3, 'b'],
[0.5, 4, 'a'], [0.6, 5, 'a'], [0.7, 6, 'b'], [0.8, 7, 'a'],
[0.9, 8, 'b'], [1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0], ), dtype=np.int)
logical = (x.a > 0.5) & (x.c != 'a')
y[logical] = 1
logical = (x.a < 0.5) & (x.c != 'b')
y[logical] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim1 = box_init.copy()
boxlim1.a = [0.5, 1]
boxlim1.c = [
set('b', ),
] * 2
boxlim2 = box_init.copy()
boxlim2.a = [0.1, 0.5]
boxlim2.c = [
set('a', ),
] * 2
sdutil.plot_boxes(x, [boxlim1, boxlim2], together=True)
sdutil.plot_boxes(x, [boxlim1, boxlim2], together=False)
plt.draw()
plt.close('all')
def test_plot_pairwise_scatter(self):
x = pd.DataFrame([[0.1, 0, 'a'],
[0.2, 1, 'b'],
[0.3, 2, 'a'],
[0.4, 3, 'b'],
[0.5, 4, 'a'],
[0.6, 5, 'a'],
[0.7, 6, 'b'],
[0.8, 7, 'a'],
[0.9, 8, 'b'],
[1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0],), dtype=np.int)
y[(x.a>0.5) & (x.c!='a')] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim = box_init.copy()
boxlim.a = [0.5, 1.0]
boxlim.c = [set('b',),]*2
restricted_dims = ['a', 'c']
sdutil.plot_pair_wise_scatter(x, y, boxlim, box_init, restricted_dims)
plt.draw()
plt.close('all')
def test_plot_boxes(self):
x = pd.DataFrame([[0.1, 0, 'a'],
[0.2, 1, 'b'],
[0.3, 2, 'a'],
[0.4, 3, 'b'],
[0.5, 4, 'a'],
[0.6, 5, 'a'],
[0.7, 6, 'b'],
[0.8, 7, 'a'],
[0.9, 8, 'b'],
[1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0],), dtype=np.int)
logical = (x.a>0.5) & (x.c!='a')
y[logical] = 1
logical = (x.a<0.5) & (x.c!='b')
y[logical] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim1 = box_init.copy()
boxlim1.a = [0.5, 1]
boxlim1.c = [set('b',),]*2
boxlim2 = box_init.copy()
boxlim2.a = [0.1, 0.5]
boxlim2.c = [set('a',),]*2
sdutil.plot_boxes(x, [boxlim1, boxlim2], together=True)
sdutil.plot_boxes(x, [boxlim1, boxlim2], together=False)
plt.draw()
plt.close('all')
def test_get_sorted_box_lims(self):
x = pd.DataFrame([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
columns=['a', 'b', 'c'])
box_init = sdutil._make_box(x)
box_lim = pd.DataFrame([(0, 1, 1), (2, 5, 2)], columns=['a', 'b', 'c'])
_, uncs = sdutil._get_sorted_box_lims([box_lim], box_init)
self.assertEqual(uncs, ['c', 'a'])
def test_get_sorted_box_lims(self):
x = np.array([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
dtype=[('a', np.float), ('b', np.float), ('c', np.float)])
box_init = sdutil._make_box(x)
box_lim = np.array([(0, 1, 1), (2, 5, 2)],
dtype=[('a', np.float), ('b', np.float),
('c', np.float)])
box_lims, uncs = sdutil._get_sorted_box_lims([box_lim], box_init)
self.assertEqual(uncs, ['c', 'a'])
def test_determine_nr_restricted_dims(self):
x = np.random.rand(5, 2)
x = pd.DataFrame(x, columns=['a', 'b'])
# all dimensions the same
box_init = sdutil._make_box(x)
n = sdutil._determine_nr_restricted_dims(box_init, box_init)
self.assertEqual(n, 0)
# dimensions 1 different and dimension 2 the same
b = pd.DataFrame([(1, 1), (0, 1)], columns=['a', 'b'])
n = sdutil._determine_nr_restricted_dims(b, box_init)
self.assertEqual(n, 2)
def test_make_box(self):
x = np.array([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
dtype=[('a', np.float), ('b', np.float), ('c', np.float)])
box_lims = sdutil._make_box(x)
# some test on the box
self.assertEqual(np.min(box_lims['a']), 0, 'min a fails')
self.assertEqual(np.max(box_lims['a']), 3, 'max a fails')
self.assertEqual(np.min(box_lims['b']), 1, 'min b fails')
self.assertEqual(np.max(box_lims['b']), 5, 'max c fails')
self.assertEqual(np.min(box_lims['c']), 1, 'min c fails')
self.assertEqual(np.max(box_lims['c']), 6, 'max c fails')
def test_determine_nr_restricted_dims(self):
x = np.random.rand(10, )
x = np.asarray(x, dtype=[('a', np.float), ('b', np.float)])
# all dimensions the same
box_init = sdutil._make_box(x)
n = sdutil._determine_nr_restricted_dims(box_init, box_init)
self.assertEqual(n, 0)
# dimensions 1 different and dimension 2 the same
b = np.array([(1, 1), (0, 1)],
dtype=[('a', np.float), ('b', np.float)])
n = sdutil._determine_nr_restricted_dims(b, box_init)
self.assertEqual(n, 2)
def test_make_box(self):
x = pd.DataFrame([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
columns=['a', 'b', 'c'])
box_lims = sdutil._make_box(x)
# some test on the box
self.assertEqual(np.min(box_lims['a']), 0, 'min a fails')
self.assertEqual(np.max(box_lims['a']), 3, 'max a fails')
self.assertEqual(np.min(box_lims['b']), 1, 'min b fails')
self.assertEqual(np.max(box_lims['b']), 5, 'max c fails')
self.assertEqual(np.min(box_lims['c']), 1, 'min c fails')
self.assertEqual(np.max(box_lims['c']), 6, 'max c fails')
def test_determine_nr_restricted_dims(self):
x = np.random.rand(5, 2)
x = pd.DataFrame(x, columns=['a', 'b'])
# all dimensions the same
box_init = sdutil._make_box(x)
n = sdutil._determine_nr_restricted_dims(box_init, box_init)
self.assertEqual(n, 0)
# dimensions 1 different and dimension 2 the same
b = pd.DataFrame([(1,1),
(0,1)],
columns=['a', 'b'])
n = sdutil._determine_nr_restricted_dims( b, box_init)
self.assertEqual(n, 2)
def test_get_sorted_box_lims(self):
x = pd.DataFrame([(0,1,2),
(2,5,6),
(3,2,1)],
columns=['a', 'b', 'c'])
box_init = sdutil._make_box(x)
box_lim = pd.DataFrame([(0,1,1),
(2,5,2)],
columns=['a', 'b', 'c'])
_, uncs = sdutil._get_sorted_box_lims([box_lim], box_init)
self.assertEqual(uncs, ['c','a'])
def test_make_box(self):
x = pd.DataFrame([(0,1,2),
(2,5,6),
(3,2,1)],
columns=['a', 'b', 'c'])
box_lims = sdutil._make_box(x)
# some test on the box
self.assertEqual(np.min(box_lims['a']), 0, 'min a fails')
self.assertEqual(np.max(box_lims['a']), 3, 'max a fails')
self.assertEqual(np.min(box_lims['b']), 1, 'min b fails')
self.assertEqual(np.max(box_lims['b']), 5, 'max c fails')
self.assertEqual(np.min(box_lims['c']), 1, 'min c fails')
self.assertEqual(np.max(box_lims['c']), 6, 'max c fails')
def test_normalize(self):
x = pd.DataFrame([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
columns=['a', 'b', 'c'])
box_init = sdutil._make_box(x)
box_lim = pd.DataFrame([(0, 1, 1), (2, 5, 2)], columns=['a', 'b', 'c'])
uncs = box_lim.columns.values.tolist()
normalized = sdutil._normalize(box_lim, box_init, uncs)
for i, lims in enumerate([(0, 2 / 3), (0, 1), (0, 0.2)]):
lower, upper = lims
self.assertAlmostEqual(normalized[i, 0],
lower,
msg='lower unequal for ' + uncs[i])
self.assertAlmostEqual(normalized[i, 1],
upper,
msg='upper unequal for ' + uncs[i])
def test_determine_nr_restricted_dims(self):
x = np.random.rand(10, )
x = np.asarray(x, dtype=[('a', np.float),
('b', np.float)])
# all dimensions the same
box_init = sdutil._make_box(x)
n = sdutil._determine_nr_restricted_dims(box_init, box_init)
self.assertEqual(n, 0)
# dimensions 1 different and dimension 2 the same
b = np.array([(1,1),
(0,1)],
dtype=[('a', np.float),
('b', np.float)])
n = sdutil._determine_nr_restricted_dims( b, box_init)
self.assertEqual(n, 2)
def test_make_box(self):
x = np.array([(0,1,2),
(2,5,6),
(3,2,1)],
dtype=[('a', np.float),
('b', np.float),
('c', np.float)])
box_lims = sdutil._make_box(x)
# some test on the box
self.assertEqual(np.min(box_lims['a']), 0, 'min a fails')
self.assertEqual(np.max(box_lims['a']), 3, 'max a fails')
self.assertEqual(np.min(box_lims['b']), 1, 'min b fails')
self.assertEqual(np.max(box_lims['b']), 5, 'max c fails')
self.assertEqual(np.min(box_lims['c']), 1, 'min c fails')
self.assertEqual(np.max(box_lims['c']), 6, 'max c fails')
def test_normalize(self):
x = pd.DataFrame([(0,1,2),
(2,5,6),
(3,2,1)],
columns=['a', 'b', 'c'])
box_init = sdutil._make_box(x)
box_lim = pd.DataFrame([(0,1,1),
(2,5,2)],
columns=['a', 'b', 'c'])
uncs = box_lim.columns.values.tolist()
normalized = sdutil._normalize(box_lim, box_init, uncs)
for i, lims in enumerate([(0, 2/3),(0, 1),(0,0.2)]):
lower, upper = lims
self.assertAlmostEqual(normalized[i, 0], lower,
msg='lower unequal for '+uncs[i])
self.assertAlmostEqual(normalized[i, 1], upper,
msg='upper unequal for '+uncs[i])
def test_get_sorted_box_lims(self):
x = np.array([(0,1,2),
(2,5,6),
(3,2,1)],
dtype=[('a', np.float),
('b', np.float),
('c', np.float)])
box_init = sdutil._make_box(x)
box_lim = np.array([(0,1,1),
(2,5,2)],
dtype=[('a', np.float),
('b', np.float),
('c', np.float)])
box_lims, uncs = sdutil._get_sorted_box_lims([box_lim], box_init)
self.assertEqual(uncs, ['c','a'])
def test_normalize(self):
x = np.array([(0, 1, 2), (2, 5, 6), (3, 2, 1)],
dtype=[('a', np.float), ('b', np.float), ('c', np.float)])
box_init = sdutil._make_box(x)
box_lim = np.array([(0, 1, 1), (2, 5, 2)],
dtype=[('a', np.float), ('b', np.float),
('c', np.float)])
uncs = np.lib.recfunctions.get_names(
box_init.dtype) # @UndefinedVariable
normalized = sdutil._normalize(box_lim, box_init, uncs)
for i, lims in enumerate([(0, 2 / 3), (0, 1), (0, 0.2)]):
lower, upper = lims
self.assertAlmostEqual(normalized[i, 0],
lower,
msg='lower unequal for ' + uncs[i])
self.assertAlmostEqual(normalized[i, 1],
upper,
msg='upper unequal for ' + uncs[i])
def test_plot_pairwise_scatter(self):
x = pd.DataFrame(
[[0.1, 0, 'a'], [0.2, 1, 'b'], [0.3, 2, 'a'], [0.4, 3, 'b'],
[0.5, 4, 'a'], [0.6, 5, 'a'], [0.7, 6, 'b'], [0.8, 7, 'a'],
[0.9, 8, 'b'], [1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0], ), dtype=np.int)
y[(x.a > 0.5) & (x.c != 'a')] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim = box_init.copy()
boxlim.a = [0.5, 1.0]
boxlim.c = [
set('b', ),
] * 2
restricted_dims = ['a', 'c']
sdutil.plot_pair_wise_scatter(x, y, boxlim, box_init, restricted_dims)
plt.draw()
plt.close('all')
def test_normalize(self):
x = np.array([(0,1,2),
(2,5,6),
(3,2,1)],
dtype=[('a', np.float),
('b', np.float),
('c', np.float)])
box_init = sdutil._make_box(x)
box_lim = np.array([(0,1,1),
(2,5,2)],
dtype=[('a', np.float),
('b', np.float),
('c', np.float)])
uncs = np.lib.recfunctions.get_names(box_init.dtype) # @UndefinedVariable
normalized = sdutil._normalize(box_lim, box_init, uncs)
for i, lims in enumerate([(0, 2/3),(0, 1),(0,0.2)]):
lower, upper = lims
self.assertAlmostEqual(normalized[i, 0], lower,
msg='lower unequal for '+uncs[i])
self.assertAlmostEqual(normalized[i, 1], upper,
msg='upper unequal for '+uncs[i])
def test_OutputFormatterMixin(self):
x = pd.DataFrame(
[[0.1, 0, 'a'], [0.2, 1, 'b'], [0.3, 2, 'a'], [0.4, 3, 'b'],
[0.5, 4, 'a'], [0.6, 5, 'a'], [0.7, 6, 'b'], [0.8, 7, 'a'],
[0.9, 8, 'b'], [1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0], ), dtype=np.int)
logical = (x.a > 0.5) & (x.c != 'a')
y[logical] = 1
logical = (x.a < 0.5) & (x.c != 'b')
y[logical] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim1 = box_init.copy()
boxlim1.a = [0.5, 1]
boxlim1.c = [
set('b', ),
] * 2
boxlim2 = box_init.copy()
boxlim2.a = [0.1, 0.5]
boxlim2.c = [
set('a', ),
] * 2
with self.assertRaises(AttributeError):
class WrongTestFormatter(sdutil.OutputFormatterMixin):
pass
formatter = WrongTestFormatter()
formatter.boxes = [boxlim1, boxlim2]
formatter.stats = [{
'coverage': 0.5,
'density': 1
}, {
'coverage': 0.5,
'density': 1
}]
class TestFormatter(sdutil.OutputFormatterMixin):
boxes = []
stats = []
formatter = TestFormatter()
formatter.boxes = [boxlim1, boxlim2]
formatter.stats = [{
'coverage': 0.5,
'density': 1
}, {
'coverage': 0.5,
'density': 1
}]
formatter.x = x
formatter.show_boxes()
plt.draw()
plt.close('all')
boxes = formatter.boxes_to_dataframe()
expected_boxes = pd.DataFrame(
[[{'b'}, {'b'}, {'a'}, {'a'}], [0.5, 1, 0.1, 0.5]],
index=['c', 'a'],
columns=pd.MultiIndex(levels=[['box 1', 'box 2'], ['max', 'min']],
codes=[[0, 0, 1, 1], [1, 0, 1, 0]]))
self.assertTrue(expected_boxes.equals(boxes))
# check stats
stats = formatter.stats_to_dataframe()
expected_stats = pd.DataFrame([[0.5, 1], [0.5, 1]],
index=['box 1', 'box 2'],
columns=['coverage', 'density'])
self.assertTrue(expected_stats.equals(stats))
def test_OutputFormatterMixin(self):
x = pd.DataFrame([[0.1, 0, 'a'],
[0.2, 1, 'b'],
[0.3, 2, 'a'],
[0.4, 3, 'b'],
[0.5, 4, 'a'],
[0.6, 5, 'a'],
[0.7, 6, 'b'],
[0.8, 7, 'a'],
[0.9, 8, 'b'],
[1.0, 9, 'a']],
columns=['a', 'b', 'c'])
y = np.zeros((x.shape[0],), dtype=np.int)
logical = (x.a>0.5) & (x.c!='a')
y[logical] = 1
logical = (x.a<0.5) & (x.c!='b')
y[logical] = 1
x['c'] = x['c'].astype('category')
box_init = sdutil._make_box(x)
boxlim1 = box_init.copy()
boxlim1.a = [0.5, 1]
boxlim1.c = [set('b',),]*2
boxlim2 = box_init.copy()
boxlim2.a = [0.1, 0.5]
boxlim2.c = [set('a',),]*2
with self.assertRaises(AttributeError):
class WrongTestFormatter(sdutil.OutputFormatterMixin):
pass
formatter = WrongTestFormatter()
formatter.boxes = [boxlim1, boxlim2]
formatter.stats = [{'coverage':0.5, 'density':1},
{'coverage':0.5, 'density':1}]
class TestFormatter(sdutil.OutputFormatterMixin):
boxes = []
stats = []
formatter = TestFormatter()
formatter.boxes = [boxlim1, boxlim2]
formatter.stats = [{'coverage':0.5, 'density':1},
{'coverage':0.5, 'density':1}]
formatter.x = x
formatter.show_boxes()
plt.draw()
plt.close('all')
boxes = formatter.boxes_to_dataframe()
expected_boxes = pd.DataFrame([[{'b'}, {'b'}, {'a'}, {'a'}],
[0.5, 1, 0.1, 0.5]], index=['c', 'a'],
columns=pd.MultiIndex(levels=[['box 1', 'box 2'],
['max', 'min']],
codes=[[0, 0, 1, 1], [1, 0, 1, 0]]))
self.assertTrue(expected_boxes.equals(boxes))
# check stats
stats = formatter.stats_to_dataframe()
expected_stats = pd.DataFrame([[0.5, 1], [0.5, 1]],
index=['box 1', 'box 2'],
columns=['coverage', 'density'])
self.assertTrue(expected_stats.equals(stats))
