def test_qcut_include_lowest(self):
values = np.arange(10)
cats = qcut(values, 4)
ex_levels = ["[0, 2.25]", "(2.25, 4.5]", "(4.5, 6.75]", "(6.75, 9]"]
self.assert_((cats.levels == ex_levels).all())
def test_qcut_include_lowest(self):
values = np.arange(10)
cats = qcut(values, 4)
ex_levels = ['[0, 2.25]', '(2.25, 4.5]', '(4.5, 6.75]', '(6.75, 9]']
self.assertTrue((cats.categories == ex_levels).all())
def test_qcut_include_lowest(self):
values = np.arange(10)
cats = qcut(values, 4)
ex_levels = ['[0, 2.25]', '(2.25, 4.5]', '(4.5, 6.75]', '(6.75, 9]']
self.assertTrue((cats.categories == ex_levels).all())
def test_qcut_return_categorical(self):
s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
res = qcut(s, [0, 0.333, 0.666, 1])
exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
["[0, 2.664]",
"(2.664, 5.328]", "(5.328, 8]"],
ordered=True))
tm.assert_series_equal(res, exp)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
tm.assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_categorical_equal(labels, ex_levels)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, 0.25, 0.5, 0.75, 1.0])
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_(np.array_equal(labels, ex_levels))
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
tm.assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_categorical_equal(labels, ex_levels)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
ex_bins[0] -= (arr.max() - arr.min()) * 0.001
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins)
self.assert_(np.array_equal(labels, ex_levels))
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values, [0, 0, 1, 1])
tm.assert_almost_equal(bins, [-0.003, 1.5, 3])
result, bins = qcut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values, [0, 0, 1, 1])
tm.assert_almost_equal(bins, [0, 1.5, 3])
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
ex_bins[0] -= (arr.max() - arr.min()) * 0.001
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins)
self.assert_(np.array_equal(labels, ex_levels))
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
assert_equal(result.cat.codes.values, [0, 0, 1, 1])
assert_almost_equal(bins, [-0.003, 1.5, 3])
result, bins = qcut(s, 2, retbins=True)
assert_equal(result.cat.codes.values, [0, 0, 1, 1])
assert_almost_equal(bins, [0, 1.5, 3])
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values,
np.array([0, 0, 1, 1], dtype=np.int8))
tm.assert_numpy_array_equal(bins, np.array([-0.003, 1.5, 3]))
result, bins = qcut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values,
np.array([0, 0, 1, 1], dtype=np.int8))
tm.assert_numpy_array_equal(bins, np.array([0, 1.5, 3]))
def test_qcut_duplicates_bin(self):
# GH 7751
values = [0, 0, 0, 0, 1, 2, 3]
result_levels = ['[0, 1]', '(1, 3]']
cats = qcut(values, 3, duplicates='drop')
self.assertTrue((cats.categories == result_levels).all())
self.assertRaises(ValueError, qcut, values, 3)
self.assertRaises(ValueError, qcut, values, 3, duplicates='raise')
# invalid
self.assertRaises(ValueError, qcut, values, 3, duplicates='foo')
def test_qcut_duplicates_bin(self):
# GH 7751
values = [0, 0, 0, 0, 1, 2, 3]
result_levels = ['[0, 1]', '(1, 3]']
cats = qcut(values, 3, duplicates='drop')
self.assertTrue((cats.categories == result_levels).all())
self.assertRaises(ValueError, qcut, values, 3)
self.assertRaises(ValueError, qcut, values, 3, duplicates='raise')
# invalid
self.assertRaises(ValueError, qcut, values, 3, duplicates='foo')
def test_qcut_binning_issues(self):
# #1978, 1979
path = os.path.join(tm.get_data_path(), 'cut_data.csv')
arr = np.loadtxt(path)
result = qcut(arr, 20)
starts = []
ends = []
for lev in result.categories:
s, e = lev[1:-1].split(',')
self.assertTrue(s != e)
starts.append(float(s))
ends.append(float(e))
for (sp, sn), (ep, en) in zip(zip(starts[:-1], starts[1:]),
zip(ends[:-1], ends[1:])):
self.assertTrue(sp < sn)
self.assertTrue(ep < en)
self.assertTrue(ep <= sn)
def test_qcut_binning_issues(self):
# #1978, 1979
path = os.path.join(tm.get_data_path(), 'cut_data.csv')
arr = np.loadtxt(path)
result = qcut(arr, 20)
starts = []
ends = []
for lev in result.categories:
s, e = lev[1:-1].split(',')
self.assertTrue(s != e)
starts.append(float(s))
ends.append(float(e))
for (sp, sn), (ep, en) in zip(zip(starts[:-1], starts[1:]),
zip(ends[:-1], ends[1:])):
self.assertTrue(sp < sn)
self.assertTrue(ep < en)
self.assertTrue(ep <= sn)
def test_qcut_nas(self):
arr = np.random.randn(100)
arr[:20] = np.nan
result = qcut(arr, 4)
self.assertTrue(com.isnull(result[:20]).all())
def test_qcut_bounds(self):
np.random.seed(12345)
arr = np.random.randn(1000)
factor = qcut(arr, 10, labels=False)
self.assert_(len(np.unique(factor)) == 10)
def test_qcut_specify_quantiles(self):
arr = np.random.randn(100)
factor = qcut(arr, [0, .25, .5, .75, 1.])
expected = qcut(arr, 4)
tm.assert_categorical_equal(factor, expected)
def test_qcut_bounds(self):
arr = np.random.randn(1000)
factor = qcut(arr, 10, labels=False)
self.assertEqual(len(np.unique(factor)), 10)
def test_qcut_bounds(self):
np.random.seed(12345)
arr = np.random.randn(1000)
factor = qcut(arr, 10, labels=False)
self.assert_(len(np.unique(factor)) == 10)
def test_single_quantile(self):
# issue 15431
expected = Series([0, 0])
s = Series([9., 9.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0, 0], ["[9, 9]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([-9., -9.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0, 0], ["[-9, -9]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([0., 0.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0, 0], ["[0, 0]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
expected = Series([0])
s = Series([9])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0], ["[9, 9]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([-9])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0], ["[-9, -9]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([0])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0], ["[0, 0]"],
ordered=True))
tm.assert_series_equal(result, exp_lab)
def test_qcut_specify_quantiles(self):
arr = np.random.randn(100)
factor = qcut(arr, [0, .25, .5, .75, 1.])
expected = qcut(arr, 4)
self.assert_(factor.equals(expected))
def test_qcut_specify_quantiles(self):
arr = np.random.randn(100)
factor = qcut(arr, [0, .25, .5, .75, 1.])
expected = qcut(arr, 4)
tm.assert_categorical_equal(factor, expected)
def test_qcut_bounds(self):
arr = np.random.randn(1000)
factor = qcut(arr, 10, labels=False)
self.assertEqual(len(np.unique(factor)), 10)
def test_qcut_specify_quantiles(self):
arr = np.random.randn(100)
factor = qcut(arr, [0, .25, .5, .75, 1.])
expected = qcut(arr, 4)
self.assert_(factor.equals(expected))
def test_single_quantile(self):
# issue 15431
expected = Series([0, 0])
s = Series([9., 9.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(
Categorical.from_codes([0, 0], ["[9, 9]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([-9., -9.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(
Categorical.from_codes([0, 0], ["[-9, -9]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([0., 0.])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(
Categorical.from_codes([0, 0], ["[0, 0]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
expected = Series([0])
s = Series([9])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0], ["[9, 9]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([-9])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(
Categorical.from_codes([0], ["[-9, -9]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
s = Series([0])
result = qcut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
result = qcut(s, 1)
exp_lab = Series(Categorical.from_codes([0], ["[0, 0]"], ordered=True))
tm.assert_series_equal(result, exp_lab)
def test_qcut_nas(self):
arr = np.random.randn(100)
arr[:20] = np.nan
result = qcut(arr, 4)
self.assertTrue(com.isnull(result[:20]).all())
