def test_repr_truncation(self):
max_len = 20
with option_context("display.max_colwidth", max_len):
df = DataFrame({
'A':
np.random.randn(10),
'B': [
tm.rands(np.random.randint(max_len - 1, max_len + 1))
for i in range(10)
]
})
r = repr(df)
r = r[r.find('\n') + 1:]
_strlen = fmt._strlen_func()
for line, value in zip(r.split('\n'), df['B']):
if _strlen(value) + 1 > max_len:
self.assert_('...' in line)
else:
self.assert_('...' not in line)
with option_context("display.max_colwidth", 999999):
self.assert_('...' not in repr(df))
with option_context("display.max_colwidth", max_len + 2):
self.assert_('...' not in repr(df))
def test_wide_repr_multiindex_cols(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays(
[np.array(col(10, 5)),
np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays(
[np.array(col(20, 3)),
np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)],
index=midx,
columns=mcols)
df.index.names = ['Level 0', 'Level 1']
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
self.assert_(len(wide_repr.splitlines()) == 14 * 10 - 1)
reset_option('display.expand_frame_repr')
def test_repr_truncation(self):
max_len = 20
with option_context("display.max_colwidth", max_len):
df = DataFrame(
{
"A": np.random.randn(10),
"B": [tm.rands(np.random.randint(max_len - 1, max_len + 1)) for i in range(10)],
}
)
r = repr(df)
r = r[r.find("\n") + 1 :]
_strlen = fmt._strlen_func()
for line, value in zip(r.split("\n"), df["B"]):
if _strlen(value) + 1 > max_len:
self.assert_("..." in line)
else:
self.assert_("..." not in line)
with option_context("display.max_colwidth", 999999):
self.assert_("..." not in repr(df))
with option_context("display.max_colwidth", max_len + 2):
self.assert_("..." not in repr(df))
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
float_series = Series(np.random.randn(5))
obj_series = Series(np.random.randn(5), dtype=object)
assert (isinstance(notnull(float_series), Series))
assert (isinstance(notnull(obj_series), Series))
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert (isinstance(isnull(s), Series))
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
for s in [tm.makeFloatSeries(),tm.makeStringSeries(),
tm.makeObjectSeries(),tm.makeTimeSeries(),tm.makePeriodSeries()]:
assert(isinstance(isnull(s), Series))
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
float_series = Series(np.random.randn(5))
obj_series = Series(np.random.randn(5), dtype=object)
assert(isinstance(notnull(float_series), Series))
assert(isinstance(notnull(obj_series), Series))
def test_repr_chop_threshold(self):
df = DataFrame([[0.1, 0.5],[0.5, -0.1]])
pd.reset_option("display.chop_threshold") # default None
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
with option_context("display.chop_threshold", 0.2 ):
self.assertEqual(repr(df), ' 0 1\n0 0.0 0.5\n1 0.5 0.0')
with option_context("display.chop_threshold", 0.6 ):
self.assertEqual(repr(df), ' 0 1\n0 0 0\n1 0 0')
with option_context("display.chop_threshold", None ):
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
def test_repr_chop_threshold(self):
df = DataFrame([[0.1, 0.5], [0.5, -0.1]])
pd.reset_option("display.chop_threshold") # default None
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
with option_context("display.chop_threshold", 0.2):
self.assertEqual(repr(df), ' 0 1\n0 0.0 0.5\n1 0.5 0.0')
with option_context("display.chop_threshold", 0.6):
self.assertEqual(repr(df), ' 0 1\n0 0 0\n1 0 0')
with option_context("display.chop_threshold", None):
self.assertEqual(repr(df), ' 0 1\n0 0.1 0.5\n1 0.5 -0.1')
def test_wide_repr_unicode(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_wide_repr_unicode(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.randu(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option('display.expand_frame_repr')
def test_wide_repr(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
set_option("print.expand_frame_repr", False)
rep_str = repr(df)
set_option("print.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("print.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
reset_option("print.expand_frame_repr")
def test_wide_repr_wide_long_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame({'a': ['a'*30, 'b'*30], 'b': ['c'*70, 'd'*80]})
result = repr(df)
self.assertTrue('ccccc' in result)
self.assertTrue('ddddd' in result)
def test_unicode_print(self):
if PY3:
_rep = repr
else:
_rep = unicode # noqa
c = Categorical(['aaaaa', 'bb', 'cccc'] * 20)
expected = u"""\
[aaaaa, bb, cccc, aaaaa, bb, ..., bb, cccc, aaaaa, bb, cccc]
Length: 60
Categories (3, object): [aaaaa, bb, cccc]"""
assert _rep(c) == expected
c = Categorical([u'ああああ', u'いいいいい', u'ううううううう'] * 20)
expected = u"""\
[ああああ, いいいいい, ううううううう, ああああ, いいいいい, ..., いいいいい, ううううううう, ああああ, いいいいい, ううううううう]
Length: 60
Categories (3, object): [ああああ, いいいいい, ううううううう]""" # noqa
assert _rep(c) == expected
# unicode option should not affect to Categorical, as it doesn't care
# the repr width
with option_context('display.unicode.east_asian_width', True):
c = Categorical([u'ああああ', u'いいいいい', u'ううううううう'] * 20)
expected = u"""[ああああ, いいいいい, ううううううう, ああああ, いいいいい, ..., いいいいい, ううううううう, ああああ, いいいいい, ううううううう]
Length: 60
Categories (3, object): [ああああ, いいいいい, ううううううう]""" # noqa
assert _rep(c) == expected
def test_unicode_print(self):
if PY3:
_rep = repr
else:
_rep = unicode # noqa
c = Categorical(['aaaaa', 'bb', 'cccc'] * 20)
expected = u"""\
[aaaaa, bb, cccc, aaaaa, bb, ..., bb, cccc, aaaaa, bb, cccc]
Length: 60
Categories (3, object): [aaaaa, bb, cccc]"""
assert _rep(c) == expected
c = Categorical([u'ああああ', u'いいいいい', u'ううううううう'] * 20)
expected = u"""\
[ああああ, いいいいい, ううううううう, ああああ, いいいいい, ..., いいいいい, ううううううう, ああああ, いいいいい, ううううううう]
Length: 60
Categories (3, object): [ああああ, いいいいい, ううううううう]""" # noqa
assert _rep(c) == expected
# unicode option should not affect to Categorical, as it doesn't care
# the repr width
with option_context('display.unicode.east_asian_width', True):
c = Categorical([u'ああああ', u'いいいいい', u'ううううううう'] * 20)
expected = u"""[ああああ, いいいいい, ううううううう, ああああ, いいいいい, ..., いいいいい, ううううううう, ああああ, いいいいい, ううううううう]
Length: 60
Categories (3, object): [ああああ, いいいいい, ううううううう]""" # noqa
assert _rep(c) == expected
def test_wide_repr_wide_long_columns(self):
with option_context("mode.sim_interactive", True):
df = DataFrame({"a": ["a" * 30, "b" * 30], "b": ["c" * 70, "d" * 80]})
result = repr(df)
self.assertTrue("ccccc" in result)
self.assertTrue("ddddd" in result)
def test_transform_mixed_type(self):
index = MultiIndex.from_arrays([[0, 0, 0, 1, 1, 1], [1, 2, 3, 1, 2,
3]])
df = DataFrame(
{
'd': [1., 1., 1., 2., 2., 2.],
'c': np.tile(['a', 'b', 'c'], 2),
'v': np.arange(1., 7.)
},
index=index)
def f(group):
group['g'] = group['d'] * 2
return group[:1]
grouped = df.groupby('c')
result = grouped.apply(f)
assert result['d'].dtype == np.float64
# this is by definition a mutating operation!
with option_context('mode.chained_assignment', None):
for key, group in grouped:
res = f(group)
assert_frame_equal(res, result.loc[key])
def test_print_none_width(self):
# GH10087
a = Series(Categorical([1, 2, 3, 4]))
exp = u("0 1\n1 2\n2 3\n3 4\n" +
"dtype: category\nCategories (4, int64): [1, 2, 3, 4]")
with option_context("display.width", None):
assert exp == repr(a)
def test_print_none_width(self):
# GH10087
a = Series(Categorical([1, 2, 3, 4]))
exp = u("0 1\n1 2\n2 3\n3 4\n" +
"dtype: category\nCategories (4, int64): [1, 2, 3, 4]")
with option_context("display.width", None):
assert exp == repr(a)
def test_repr_obeys_max_seq_limit(self):
import pandas.core.common as com
# unlimited
reset_option("display.max_seq_items")
self.assertTrue(len(com.pprint_thing(range(1000))) > 2000)
with option_context("display.max_seq_items", 5):
self.assertTrue(len(com.pprint_thing(range(1000))) < 100)
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null",False):
assert notnull(np.inf)
assert notnull(-np.inf)
with cf.option_context("mode.use_inf_as_null",True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
with cf.option_context("mode.use_inf_as_null",False):
float_series = Series(np.random.randn(5))
obj_series = Series(np.random.randn(5), dtype=object)
assert(isinstance(notnull(float_series), Series))
assert(isinstance(notnull(obj_series), Series))
def test_matplotlib_formatters(self):
units = pytest.importorskip("matplotlib.units")
assert Timestamp in units.registry
ctx = cf.option_context("plotting.matplotlib.register_converters",
False)
with ctx:
assert Timestamp not in units.registry
assert Timestamp in units.registry
def test_wide_repr_multiindex_cols(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)), np.array(col(10, 5))])
mcols = pandas.MultiIndex.from_arrays([np.array(col(20, 3)), np.array(col(20, 3))])
df = DataFrame([col(20, 25) for _ in range(10)], index=midx, columns=mcols)
df.index.names = ["Level 0", "Level 1"]
set_option("display.expand_frame_repr", False)
rep_str = repr(df)
set_option("display.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("display.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
self.assert_(len(wide_repr.splitlines()) == 14 * 10 - 1)
reset_option("display.expand_frame_repr")
def test_matplotlib_formatters(self):
units = pytest.importorskip("matplotlib.units")
assert Timestamp in units.registry
ctx = cf.option_context("plotting.matplotlib.register_converters",
False)
with ctx:
assert Timestamp not in units.registry
assert Timestamp in units.registry
def test_wide_repr_wide_long_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame({
'a': ['a' * 30, 'b' * 30],
'b': ['c' * 70, 'd' * 80]
})
result = repr(df)
self.assertTrue('ccccc' in result)
self.assertTrue('ddddd' in result)
def test_wide_repr_multiindex(self):
with option_context("mode.sim_interactive", True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
midx = pandas.MultiIndex.from_arrays([np.array(col(10, 5)), np.array(col(10, 5))])
df = DataFrame([col(20, 25) for _ in range(10)], index=midx)
df.index.names = ["Level 0", "Level 1"]
set_option("print.expand_frame_repr", False)
rep_str = repr(df)
set_option("print.expand_frame_repr", True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context("print.line_width", 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_("Level 0 Level 1" in line)
reset_option("print.expand_frame_repr")
def test_sparse_frame(self):
# GH 13110
df = pd.DataFrame({'A': [True, False, True, False, True],
'B': [True, False, True, False, True],
'C': [0, 0, 3, 0, 5],
'D': [np.nan, np.nan, np.nan, 1, 2]})
sparse = df.to_sparse()
self.assertEqual(repr(sparse), repr(df))
with option_context("display.max_rows", 3):
self.assertEqual(repr(sparse), repr(df))
def test_wide_repr_named(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
df.index.name = 'DataFrame Index'
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('DataFrame Index' in line)
reset_option('display.expand_frame_repr')
def test_sparse_frame(self):
# GH 13110
df = pd.DataFrame({'A': [True, False, True, False, True],
'B': [True, False, True, False, True],
'C': [0, 0, 3, 0, 5],
'D': [np.nan, np.nan, np.nan, 1, 2]})
sparse = df.to_sparse()
assert repr(sparse) == repr(df)
with option_context("display.max_rows", 3):
assert repr(sparse) == repr(df)
def test_wide_repr_named(self):
with option_context('mode.sim_interactive', True):
col = lambda l, k: [tm.rands(k) for _ in xrange(l)]
df = DataFrame([col(20, 25) for _ in range(10)])
df.index.name = 'DataFrame Index'
set_option('display.expand_frame_repr', False)
rep_str = repr(df)
set_option('display.expand_frame_repr', True)
wide_repr = repr(df)
self.assert_(rep_str != wide_repr)
with option_context('display.line_width', 120):
wider_repr = repr(df)
self.assert_(len(wider_repr) < len(wide_repr))
for line in wide_repr.splitlines()[1::13]:
self.assert_('DataFrame Index' in line)
reset_option('display.expand_frame_repr')
def test_sparsea_max_row_truncated(self):
s = pd.Series([1, np.nan, np.nan, 3, np.nan]).to_sparse()
dfm = self.dtype_format_for_platform
with option_context("display.max_rows", 3):
# GH 10560
result = repr(s)
exp = ("0 1.0\n ... \n4 NaN\n"
"Length: 5, dtype: Sparse[float64, nan]\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
assert result == exp
def test_sparsea_max_row_truncated(self):
s = pd.Series([1, np.nan, np.nan, 3, np.nan]).to_sparse()
dfm = self.dtype_format_for_platform
with option_context("display.max_rows", 3):
# GH 10560
result = repr(s)
exp = ("0 1.0\n ... \n4 NaN\n"
"Length: 5, dtype: Sparse[float64, nan]\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
assert result == exp
def test_ambiguous_width(self):
adj = fmt.EastAsianTextAdjustment()
assert adj.len(u'¡¡ab') == 4
with cf.option_context('display.unicode.ambiguous_as_wide', True):
adj = fmt.EastAsianTextAdjustment()
assert adj.len(u'¡¡ab') == 6
data = [[u'あ', 'b', 'c'], ['dd', u'ええ', 'ff'],
['ggg', u'¡¡ab', u'いいい']]
expected = u'あ dd ggg \nb ええ ¡¡ab\nc ff いいい'
adjoined = adj.adjoin(2, *data)
assert adjoined == expected
def test_ambiguous_width(self):
adj = fmt.EastAsianTextAdjustment()
assert adj.len(u'¡¡ab') == 4
with cf.option_context('display.unicode.ambiguous_as_wide', True):
adj = fmt.EastAsianTextAdjustment()
assert adj.len(u'¡¡ab') == 6
data = [[u'あ', 'b', 'c'], ['dd', u'ええ', 'ff'],
['ggg', u'¡¡ab', u'いいい']]
expected = u'あ dd ggg \nb ええ ¡¡ab\nc ff いいい'
adjoined = adj.adjoin(2, *data)
assert adjoined == expected
def test_sparse_max_row(self):
s = pd.Series([1, np.nan, np.nan, 3, np.nan]).to_sparse()
result = repr(s)
dfm = self.dtype_format_for_platform
exp = ("0 1.0\n1 NaN\n2 NaN\n3 3.0\n"
"4 NaN\ndtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
# GH 10560
result = repr(s)
exp = ("0 1.0\n ... \n4 NaN\n"
"Length: 5, dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
def test_sparse_max_row(self):
s = pd.Series([1, np.nan, np.nan, 3, np.nan]).to_sparse()
result = repr(s)
dfm = self.dtype_format_for_platform
exp = ("0 1.0\n1 NaN\n2 NaN\n3 3.0\n"
"4 NaN\ndtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
# GH 10560
result = repr(s)
exp = ("0 1.0\n ... \n4 NaN\n"
"dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
def test_sparse_int(self):
# GH 13110
s = pd.SparseSeries([0, 1, 0, 0, 1, 0], fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 0\n1 1\n2 0\n3 0\n4 1\n"
"5 0\ndtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 0\n ..\n5 0\n"
"dtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
def test_sparse_int(self):
# GH 13110
s = pd.SparseSeries([0, 1, 0, 0, 1, 0], fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 0\n1 1\n2 0\n3 0\n4 1\n"
"5 0\ndtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 0\n ..\n5 0\n"
"dtype: int64\nBlockIndex\n"
"Block locations: array([1, 4]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
def test_sparse_bool(self):
# GH 13110
s = pd.SparseSeries([True, False, False, True, False, False],
fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 True\n1 False\n2 False\n"
"3 True\n4 False\n5 False\n"
"dtype: bool\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 True\n ... \n5 False\n"
"Length: 6, dtype: bool\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
def test_sparse_bool(self):
# GH 13110
s = pd.SparseSeries([True, False, False, True, False, False],
fill_value=False)
result = repr(s)
dtype = '' if use_32bit_repr else ', dtype=int32'
exp = ("0 True\n1 False\n2 False\n"
"3 True\n4 False\n5 False\n"
"dtype: bool\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
result = repr(s)
exp = ("0 True\n ... \n5 False\n"
"dtype: bool\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dtype))
self.assertEqual(result, exp)
def test_transform_mixed_type(self):
index = MultiIndex.from_arrays([[0, 0, 0, 1, 1, 1], [1, 2, 3, 1, 2, 3]
])
df = DataFrame({'d': [1., 1., 1., 2., 2., 2.],
'c': np.tile(['a', 'b', 'c'], 2),
'v': np.arange(1., 7.)}, index=index)
def f(group):
group['g'] = group['d'] * 2
return group[:1]
grouped = df.groupby('c')
result = grouped.apply(f)
assert result['d'].dtype == np.float64
# this is by definition a mutating operation!
with option_context('mode.chained_assignment', None):
for key, group in grouped:
res = f(group)
assert_frame_equal(res, result.loc[key])
def test_sparse_mi_max_row(self):
idx = pd.MultiIndex.from_tuples([('A', 0), ('A', 1), ('B', 0),
('C', 0), ('C', 1), ('C', 2)])
s = pd.Series([1, np.nan, np.nan, 3, np.nan, np.nan],
index=idx).to_sparse()
result = repr(s)
dfm = self.dtype_format_for_platform
exp = ("A 0 1.0\n 1 NaN\nB 0 NaN\n"
"C 0 3.0\n 1 NaN\n 2 NaN\n"
"dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
# GH 13144
result = repr(s)
exp = ("A 0 1.0\n ... \nC 2 NaN\n"
"dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
def test_sparse_mi_max_row(self):
idx = pd.MultiIndex.from_tuples([('A', 0), ('A', 1), ('B', 0),
('C', 0), ('C', 1), ('C', 2)])
s = pd.Series([1, np.nan, np.nan, 3, np.nan, np.nan],
index=idx).to_sparse()
result = repr(s)
dfm = self.dtype_format_for_platform
exp = ("A 0 1.0\n 1 NaN\nB 0 NaN\n"
"C 0 3.0\n 1 NaN\n 2 NaN\n"
"dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
with option_context("display.max_rows", 3):
# GH 13144
result = repr(s)
exp = ("A 0 1.0\n ... \nC 2 NaN\n"
"dtype: float64\nBlockIndex\n"
"Block locations: array([0, 3]{0})\n"
"Block lengths: array([1, 1]{0})".format(dfm))
self.assertEqual(result, exp)
def test_option_no_warning(self):
pytest.importorskip("matplotlib.pyplot")
ctx = cf.option_context("plotting.matplotlib.register_converters",
False)
plt = pytest.importorskip("matplotlib.pyplot")
s = Series(range(12), index=date_range('2017', periods=12))
_, ax = plt.subplots()
converter._WARN = True
# Test without registering first, no warning
with ctx:
with tm.assert_produces_warning(None) as w:
ax.plot(s.index, s.values)
assert len(w) == 0
# Now test with registering
converter._WARN = True
register_matplotlib_converters()
with ctx:
with tm.assert_produces_warning(None) as w:
ax.plot(s.index, s.values)
assert len(w) == 0
def test_option_no_warning(self):
pytest.importorskip("matplotlib.pyplot")
ctx = cf.option_context("plotting.matplotlib.register_converters",
False)
plt = pytest.importorskip("matplotlib.pyplot")
s = Series(range(12), index=date_range('2017', periods=12))
_, ax = plt.subplots()
converter._WARN = True
# Test without registering first, no warning
with ctx:
with tm.assert_produces_warning(None) as w:
ax.plot(s.index, s.values)
assert len(w) == 0
# Now test with registering
converter._WARN = True
register_matplotlib_converters()
with ctx:
with tm.assert_produces_warning(None) as w:
ax.plot(s.index, s.values)
assert len(w) == 0
def test_repr_summary(self):
with cf.option_context('display.max_seq_items', 10):
r = repr(pd.Index(np.arange(1000)))
self.assertTrue(len(r) < 200)
self.assertTrue("..." in r)
def test_string_categorical_index_repr(self):
# short
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'])
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc'], categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc'], categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# multiple lines
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 10)
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb',
'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',
u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',
u'a', u'bb', u'ccc', u'a', u'bb', u'ccc'],
categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# truncated
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 100)
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
...
'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
categories=['a', 'bb', 'ccc'], ordered=False, dtype='category', length=300)"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',
u'ccc', u'a',
...
u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
u'bb', u'ccc'],
categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category', length=300)"""
self.assertEqual(unicode(idx), expected)
# larger categories
idx = pd.CategoricalIndex(list('abcdefghijklmmo'))
if PY3:
expected = u"""CategoricalIndex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l',
'm', 'm', 'o'],
categories=['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', ...], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'a', u'b', u'c', u'd', u'e', u'f', u'g', u'h', u'i', u'j',
u'k', u'l', u'm', u'm', u'o'],
categories=[u'a', u'b', u'c', u'd', u'e', u'f', u'g', u'h', ...], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# short
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'])
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう'], categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう'], categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# multiple lines
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 10)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう',
u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# truncated
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
...
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ',
...
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)"""
self.assertEqual(unicode(idx), expected)
# larger categories
idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
if PY3:
expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ', 'し',
'す', 'せ', 'そ'],
categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', u'け', u'こ',
u'さ', u'し', u'す', u'せ', u'そ'],
categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# Emable Unicode option -----------------------------------------
with cf.option_context('display.unicode.east_asian_width', True):
# short
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'])
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう'], categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう'], categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# multiple lines
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 10)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
# truncated
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ',
...
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ',
...
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)"""
self.assertEqual(unicode(idx), expected)
# larger categories
idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
if PY3:
expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ',
'さ', 'し', 'す', 'せ', 'そ'],
categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')"""
self.assertEqual(repr(idx), expected)
else:
expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く',
u'け', u'こ', u'さ', u'し', u'す', u'せ', u'そ'],
categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')"""
self.assertEqual(unicode(idx), expected)
def test_wide_repr_wide_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(randn(5, 3), columns=['a' * 90, 'b' * 90, 'c' * 90])
rep_str = repr(df)
self.assert_(len(rep_str.splitlines()) == 20)
def test_repr_no_backslash(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(np.random.randn(10, 4))
self.assertTrue('\\' not in repr(df))
def test_to_string_utf8_columns(self):
n = u"\u05d0".encode('utf-8')
with option_context('display.max_rows', 1):
df = pd.DataFrame([1, 2], columns=[n])
repr(df)
def test_repr_no_backslash(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(np.random.randn(10, 4))
self.assertTrue('\\' not in repr(df))
def test_to_string_utf8_columns(self):
n = u"\u05d0".encode('utf-8')
with option_context('display.max_rows', 1):
df = pd.DataFrame([1, 2], columns=[n])
repr(df)
def test_wide_repr_wide_columns(self):
with option_context('mode.sim_interactive', True):
df = DataFrame(randn(5, 3), columns=['a' * 90, 'b' * 90, 'c' * 90])
rep_str = repr(df)
self.assert_(len(rep_str.splitlines()) == 20)
def test_string_categorical_index_repr(self):
# short
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'])
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc'], categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc'], categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# multiple lines
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 10)
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb',
'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
categories=['a', 'bb', 'ccc'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',
u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc',
u'a', u'bb', u'ccc', u'a', u'bb', u'ccc'],
categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# truncated
idx = pd.CategoricalIndex(['a', 'bb', 'ccc'] * 100)
if PY3:
expected = u"""CategoricalIndex(['a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a',
...
'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc', 'a', 'bb', 'ccc'],
categories=['a', 'bb', 'ccc'], ordered=False, dtype='category', length=300)""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a', u'bb',
u'ccc', u'a',
...
u'ccc', u'a', u'bb', u'ccc', u'a', u'bb', u'ccc', u'a',
u'bb', u'ccc'],
categories=[u'a', u'bb', u'ccc'], ordered=False, dtype='category', length=300)""" # noqa
assert unicode(idx) == expected
# larger categories
idx = pd.CategoricalIndex(list('abcdefghijklmmo'))
if PY3:
expected = u"""CategoricalIndex(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l',
'm', 'm', 'o'],
categories=['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', ...], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'a', u'b', u'c', u'd', u'e', u'f', u'g', u'h', u'i', u'j',
u'k', u'l', u'm', u'm', u'o'],
categories=[u'a', u'b', u'c', u'd', u'e', u'f', u'g', u'h', ...], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# short
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'])
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう'], categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう'], categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# multiple lines
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 10)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう',
u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# truncated
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
...
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ',
...
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)""" # noqa
assert unicode(idx) == expected
# larger categories
idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
if PY3:
expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ', 'し',
'す', 'せ', 'そ'],
categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', u'け', u'こ',
u'さ', u'し', u'す', u'せ', u'そ'],
categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# Emable Unicode option -----------------------------------------
with cf.option_context('display.unicode.east_asian_width', True):
# short
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'])
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう'], categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう'], categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# multiple lines
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 10)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
# truncated
idx = pd.CategoricalIndex([u'あ', u'いい', u'ううう'] * 100)
if PY3:
expected = u"""CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
'ううう', 'あ',
...
'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
'あ', 'いい', 'ううう'],
categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'いい', u'ううう', u'あ', u'いい', u'ううう', u'あ',
u'いい', u'ううう', u'あ',
...
u'ううう', u'あ', u'いい', u'ううう', u'あ', u'いい',
u'ううう', u'あ', u'いい', u'ううう'],
categories=[u'あ', u'いい', u'ううう'], ordered=False, dtype='category', length=300)""" # noqa
assert unicode(idx) == expected
# larger categories
idx = pd.CategoricalIndex(list(u'あいうえおかきくけこさしすせそ'))
if PY3:
expected = u"""CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ',
'さ', 'し', 'す', 'せ', 'そ'],
categories=['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', ...], ordered=False, dtype='category')""" # noqa
assert repr(idx) == expected
else:
expected = u"""CategoricalIndex([u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く',
u'け', u'こ', u'さ', u'し', u'す', u'せ', u'そ'],
categories=[u'あ', u'い', u'う', u'え', u'お', u'か', u'き', u'く', ...], ordered=False, dtype='category')""" # noqa
assert unicode(idx) == expected
def test_repr_summary(self):
with cf.option_context('display.max_seq_items', 10):
r = repr(pd.Index(np.arange(1000)))
self.assertTrue(len(r) < 200)
self.assertTrue("..." in r)