def test_constructors(self, data, closed, name):
left, right = data[:-1], data[1:]
ivs = [Interval(l, r, closed=closed) for l, r in lzip(left, right)]
expected = IntervalIndex._simple_new(
left=left, right=right, closed=closed, name=name)
# validate expected
assert expected.closed == closed
assert expected.name == name
assert expected.dtype.subtype == data.dtype
tm.assert_index_equal(expected.left, data[:-1])
tm.assert_index_equal(expected.right, data[1:])
# validated constructors
result = IntervalIndex(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_breaks(data, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_arrays(
left, right, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
lzip(left, right), closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = Index(ivs, name=name)
assert isinstance(result, IntervalIndex)
tm.assert_index_equal(result, expected)
# idempotent
tm.assert_index_equal(Index(expected), expected)
tm.assert_index_equal(IntervalIndex(expected), expected)
result = IntervalIndex.from_intervals(expected)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(
expected.values, name=expected.name)
tm.assert_index_equal(result, expected)
left, right = expected.left, expected.right
result = IntervalIndex.from_arrays(
left, right, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(
expected.to_tuples(), closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
breaks = expected.left.tolist() + [expected.right[-1]]
result = IntervalIndex.from_breaks(
breaks, closed=expected.closed, name=expected.name)
tm.assert_index_equal(result, expected)
def test_constructors_errors_string(self, data):
# GH 19016
left, right = data[:-1], data[1:]
tuples = lzip(left, right)
ivs = [Interval(l, r) for l, r in tuples] or data
msg = ('category, object, and string subtypes are not supported '
'for IntervalIndex')
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex(ivs)
with tm.assert_raises_regex(TypeError, msg):
Index(ivs)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_intervals(ivs)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_breaks(data)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_arrays(left, right)
with tm.assert_raises_regex(TypeError, msg):
IntervalIndex.from_tuples(tuples)
def test_is_():
mi = MultiIndex.from_tuples(lzip(range(10), range(10)))
assert mi.is_(mi)
assert mi.is_(mi.view())
assert mi.is_(mi.view().view().view().view())
mi2 = mi.view()
# names are metadata, they don't change id
mi2.names = ["A", "B"]
assert mi2.is_(mi)
assert mi.is_(mi2)
assert mi.is_(mi.set_names(["C", "D"]))
mi2 = mi.view()
mi2.set_names(["E", "F"], inplace=True)
assert mi.is_(mi2)
# levels are inherent properties, they change identity
mi3 = mi2.set_levels([lrange(10), lrange(10)])
assert not mi3.is_(mi2)
# shouldn't change
assert mi2.is_(mi)
mi4 = mi3.view()
# GH 17464 - Remove duplicate MultiIndex levels
mi4.set_levels([lrange(10), lrange(10)], inplace=True)
assert not mi4.is_(mi3)
mi5 = mi.view()
mi5.set_levels(mi5.levels, inplace=True)
assert not mi5.is_(mi)
def get_schema(frame, name, flavor, keys=None):
"Return a CREATE TABLE statement to suit the contents of a DataFrame."
lookup_type = lambda dtype: get_sqltype(dtype.type, flavor)
# Replace spaces in DataFrame column names with _.
# Also force lowercase, postgresql can be case sensitive
safe_columns = [s.replace(' ', '_').strip().lower() for s in frame.dtypes.index]
column_types = lzip(safe_columns, map(lookup_type, frame.dtypes))
if flavor == 'sqlite':
columns = ',\n '.join('[%s] %s' % x for x in column_types)
elif flavor == 'postgresql':
columns = ',\n '.join('"%s" %s' % x for x in column_types)
else:
columns = ',\n '.join('`%s` %s' % x for x in column_types)
keystr = ''
if keys is not None:
if isinstance(keys, compat.string_types):
keys = (keys,)
keystr = ', PRIMARY KEY (%s)' % ','.join(keys)
template = """CREATE TABLE %(name)s (
%(columns)s
%(keystr)s
);"""
create_statement = template % {'name': name, 'columns': columns,
'keystr': keystr}
return create_statement
def test_drop(self):
simple = DataFrame({"A": [1, 2, 3, 4], "B": [0, 1, 2, 3]})
assert_frame_equal(simple.drop("A", axis=1), simple[["B"]])
assert_frame_equal(simple.drop(["A", "B"], axis="columns"), simple[[]])
assert_frame_equal(simple.drop([0, 1, 3], axis=0), simple.ix[[2], :])
assert_frame_equal(simple.drop([0, 3], axis="index"), simple.ix[[1, 2], :])
self.assertRaises(ValueError, simple.drop, 5)
self.assertRaises(ValueError, simple.drop, "C", 1)
self.assertRaises(ValueError, simple.drop, [1, 5])
self.assertRaises(ValueError, simple.drop, ["A", "C"], 1)
# errors = 'ignore'
assert_frame_equal(simple.drop(5, errors="ignore"), simple)
assert_frame_equal(simple.drop([0, 5], errors="ignore"), simple.ix[[1, 2, 3], :])
assert_frame_equal(simple.drop("C", axis=1, errors="ignore"), simple)
assert_frame_equal(simple.drop(["A", "C"], axis=1, errors="ignore"), simple[["B"]])
# non-unique - wheee!
nu_df = DataFrame(lzip(range(3), range(-3, 1), list("abc")), columns=["a", "a", "b"])
assert_frame_equal(nu_df.drop("a", axis=1), nu_df[["b"]])
assert_frame_equal(nu_df.drop("b", axis="columns"), nu_df["a"])
nu_df = nu_df.set_index(pd.Index(["X", "Y", "X"]))
nu_df.columns = list("abc")
assert_frame_equal(nu_df.drop("X", axis="rows"), nu_df.ix[["Y"], :])
assert_frame_equal(nu_df.drop(["X", "Y"], axis=0), nu_df.ix[[], :])
# inplace cache issue
# GH 5628
df = pd.DataFrame(np.random.randn(10, 3), columns=list("abc"))
expected = df[~(df.b > 0)]
df.drop(labels=df[df.b > 0].index, inplace=True)
assert_frame_equal(df, expected)
def test_boxplot_legacy(self):
grouped = self.hist_df.groupby(by='gender')
with warnings.catch_warnings():
warnings.simplefilter('ignore')
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=2, layout=(1, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
grouped = df.groupby(level=1)
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=10, layout=(4, 3))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
grouped = df.unstack(level=1).groupby(level=0, axis=1)
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values()), axes_num=3, layout=(2, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
def groups(self):
""" dict {group name -> group labels} """
if len(self.groupings) == 1:
return self.groupings[0].groups
else:
to_groupby = lzip(*(ping.grouper for ping in self.groupings))
to_groupby = Index(to_groupby)
return self.axis.groupby(to_groupby)
def tquery(self, *args):
cur = self.execute(*args)
result = self._fetchall_as_list(cur)
# This makes into tuples
if result and len(result[0]) == 1:
# python 3 compat
result = list(lzip(*result)[0])
elif result is None: # pragma: no cover
result = []
return result
def tquery(sql, con=None, cur=None, retry=True):
"""
DEPRECATED. Returns list of tuples corresponding to each row in given sql
query.
If only one column selected, then plain list is returned.
To obtain the same result in the future, you can use the following:
>>> execute(sql, con, params).fetchall()
Parameters
----------
sql: string
SQL query to be executed
con: DBAPI2 connection
cur: depreciated, cursor is obtained from connection
Returns
-------
Results Iterable
"""
warnings.warn(
"tquery is depreciated, and will be removed in future versions. "
"You can use ``execute(...).fetchall()`` instead.",
FutureWarning,
)
cur = execute(sql, con, cur=cur)
result = _safe_fetch(cur)
if con is not None:
try:
cur.close()
con.commit()
except Exception as e:
excName = e.__class__.__name__
if excName == "OperationalError": # pragma: no cover
print("Failed to commit, may need to restart interpreter")
else:
raise
traceback.print_exc()
if retry:
return tquery(sql, con=con, retry=False)
if result and len(result[0]) == 1:
# python 3 compat
result = list(lzip(*result)[0])
elif result is None: # pragma: no cover
result = []
return result
def test_boxplot_legacy3(self):
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
grouped = df.unstack(level=1).groupby(level=0, axis=1)
with tm.assert_produces_warning(UserWarning):
axes = _check_plot_works(grouped.boxplot, return_type='axes')
self._check_axes_shape(list(axes.values), axes_num=3, layout=(2, 2))
axes = _check_plot_works(grouped.boxplot, subplots=False,
return_type='axes')
self._check_axes_shape(axes, axes_num=1, layout=(1, 1))
def get_kwargs_from_breaks(self, breaks, closed='right'):
"""
converts intervals in breaks format to a dictionary of kwargs to
specific to the format expected by IntervalIndex.from_tuples
"""
if len(breaks) == 0:
return {'data': breaks}
tuples = lzip(breaks[:-1], breaks[1:])
if isinstance(breaks, (list, tuple)):
return {'data': tuples}
return {'data': com._asarray_tuplesafe(tuples)}
def __init__(self, encoding):
if(encoding is None):
self._encoding = 'cp1252'
else:
self._encoding = encoding
#type code.
#--------------------
#str1 1 = 0x01
#str2 2 = 0x02
#...
#str244 244 = 0xf4
#byte 251 = 0xfb (sic)
#int 252 = 0xfc
#long 253 = 0xfd
#float 254 = 0xfe
#double 255 = 0xff
#--------------------
#NOTE: the byte type seems to be reserved for categorical variables
# with a label, but the underlying variable is -127 to 100
# we're going to drop the label and cast to int
self.DTYPE_MAP = \
dict(
lzip(range(1, 245), ['a' + str(i) for i in range(1, 245)]) +
[
(251, np.int16),
(252, np.int32),
(253, np.int64),
(254, np.float32),
(255, np.float64)
]
)
self.TYPE_MAP = lrange(251) + list('bhlfd')
#NOTE: technically, some of these are wrong. there are more numbers
# that can be represented. it's the 27 ABOVE and BELOW the max listed
# numeric data type in [U] 12.2.2 of the 11.2 manual
self.MISSING_VALUES = \
{
'b': (-127, 100),
'h': (-32767, 32740),
'l': (-2147483647, 2147483620),
'f': (-1.701e+38, +1.701e+38),
'd': (-1.798e+308, +8.988e+307)
}
self.OLD_TYPE_MAPPING = \
{
'i': 252,
'f': 254,
'b': 251
}
def test_indexer_caching(self):
# GH5727
# make sure that indexers are in the _internal_names_set
n = 1000001
arrays = [lrange(n), lrange(n)]
index = MultiIndex.from_tuples(lzip(*arrays))
s = Series(np.zeros(n), index=index)
str(s)
# setitem
expected = Series(np.ones(n), index=index)
s = Series(np.zeros(n), index=index)
s[s == 0] = 1
tm.assert_series_equal(s, expected)
def test_series_getitem_not_sorted(self):
arrays = [['bar', 'bar', 'baz', 'baz', 'qux', 'qux', 'foo', 'foo'],
['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]
tuples = lzip(*arrays)
index = MultiIndex.from_tuples(tuples)
s = Series(randn(8), index=index)
arrays = [np.array(x) for x in zip(*index.values)]
result = s['qux']
result2 = s.loc['qux']
expected = s[arrays[0] == 'qux']
expected.index = expected.index.droplevel(0)
tm.assert_series_equal(result, expected)
tm.assert_series_equal(result2, expected)
def test_boxplot(self):
df = DataFrame(np.random.rand(10, 2), columns=["Col1", "Col2"])
df["X"] = Series(["A", "A", "A", "A", "A", "B", "B", "B", "B", "B"])
grouped = df.groupby(by="X")
_check_plot_works(grouped.boxplot)
_check_plot_works(grouped.boxplot, subplots=False)
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3), index=MultiIndex.from_tuples(tuples))
grouped = df.groupby(level=1)
_check_plot_works(grouped.boxplot)
_check_plot_works(grouped.boxplot, subplots=False)
grouped = df.unstack(level=1).groupby(level=0, axis=1)
_check_plot_works(grouped.boxplot)
_check_plot_works(grouped.boxplot, subplots=False)
def test_constructors_errors_tz(self, tz_left, tz_right):
# GH 18537
left = date_range('2017-01-01', periods=4, tz=tz_left)
right = date_range('2017-01-02', periods=4, tz=tz_right)
# don't need to check IntervalIndex(...) or from_intervals, since
# mixed tz are disallowed at the Interval level
with pytest.raises(ValueError):
IntervalIndex.from_arrays(left, right)
with pytest.raises(ValueError):
IntervalIndex.from_tuples(lzip(left, right))
with pytest.raises(ValueError):
breaks = left.tolist() + [right[-1]]
IntervalIndex.from_breaks(breaks)
def __init__(self, encoding):
self._encoding = encoding
# type code.
# --------------------
# str1 1 = 0x01
# str2 2 = 0x02
# ...
# str244 244 = 0xf4
# byte 251 = 0xfb (sic)
# int 252 = 0xfc
# long 253 = 0xfd
# float 254 = 0xfe
# double 255 = 0xff
# --------------------
# NOTE: the byte type seems to be reserved for categorical variables
# with a label, but the underlying variable is -127 to 100
# we're going to drop the label and cast to int
self.DTYPE_MAP = dict(
lzip(range(1, 245), ["a" + str(i) for i in range(1, 245)])
+ [(251, np.int16), (252, np.int32), (253, np.int64), (254, np.float32), (255, np.float64)]
)
self.DTYPE_MAP_XML = dict(
[
(32768, np.string_),
(65526, np.float64),
(65527, np.float32),
(65528, np.int64),
(65529, np.int32),
(65530, np.int16),
]
)
self.TYPE_MAP = lrange(251) + list("bhlfd")
self.TYPE_MAP_XML = dict([(65526, "d"), (65527, "f"), (65528, "l"), (65529, "h"), (65530, "b")])
# NOTE: technically, some of these are wrong. there are more numbers
# that can be represented. it's the 27 ABOVE and BELOW the max listed
# numeric data type in [U] 12.2.2 of the 11.2 manual
self.MISSING_VALUES = {
"b": (-127, 100),
"h": (-32767, 32740),
"l": (-2147483647, 2147483620),
"f": (-1.701e38, +1.701e38),
"d": (-1.798e308, +8.988e307),
}
self.OLD_TYPE_MAPPING = {"i": 252, "f": 254, "b": 251}
def test_drop(self):
simple = DataFrame({"A": [1, 2, 3, 4], "B": [0, 1, 2, 3]})
assert_frame_equal(simple.drop("A", axis=1), simple[['B']])
assert_frame_equal(simple.drop(["A", "B"], axis='columns'),
simple[[]])
assert_frame_equal(simple.drop([0, 1, 3], axis=0), simple.loc[[2], :])
assert_frame_equal(simple.drop(
[0, 3], axis='index'), simple.loc[[1, 2], :])
with pytest.raises(KeyError, match=r"\[5\] not found in axis"):
simple.drop(5)
with pytest.raises(KeyError, match=r"\['C'\] not found in axis"):
simple.drop('C', 1)
with pytest.raises(KeyError, match=r"\[5\] not found in axis"):
simple.drop([1, 5])
with pytest.raises(KeyError, match=r"\['C'\] not found in axis"):
simple.drop(['A', 'C'], 1)
# errors = 'ignore'
assert_frame_equal(simple.drop(5, errors='ignore'), simple)
assert_frame_equal(simple.drop([0, 5], errors='ignore'),
simple.loc[[1, 2, 3], :])
assert_frame_equal(simple.drop('C', axis=1, errors='ignore'), simple)
assert_frame_equal(simple.drop(['A', 'C'], axis=1, errors='ignore'),
simple[['B']])
# non-unique - wheee!
nu_df = DataFrame(lzip(range(3), range(-3, 1), list('abc')),
columns=['a', 'a', 'b'])
assert_frame_equal(nu_df.drop('a', axis=1), nu_df[['b']])
assert_frame_equal(nu_df.drop('b', axis='columns'), nu_df['a'])
assert_frame_equal(nu_df.drop([]), nu_df) # GH 16398
nu_df = nu_df.set_index(pd.Index(['X', 'Y', 'X']))
nu_df.columns = list('abc')
assert_frame_equal(nu_df.drop('X', axis='rows'), nu_df.loc[["Y"], :])
assert_frame_equal(nu_df.drop(['X', 'Y'], axis=0), nu_df.loc[[], :])
# inplace cache issue
# GH 5628
df = pd.DataFrame(np.random.randn(10, 3), columns=list('abc'))
expected = df[~(df.b > 0)]
df.drop(labels=df[df.b > 0].index, inplace=True)
assert_frame_equal(df, expected)
def _get_schema_legacy(frame, name, flavor, keys=None):
"""Old function from 0.13.1. To keep backwards compatibility.
When mysql legacy support is dropped, it should be possible to
remove this code
"""
def get_sqltype(dtype, flavor):
pytype = dtype.type
pytype_name = "text"
if issubclass(pytype, np.floating):
pytype_name = "float"
elif issubclass(pytype, np.integer):
pytype_name = "int"
elif issubclass(pytype, np.datetime64) or pytype is datetime:
# Caution: np.datetime64 is also a subclass of np.number.
pytype_name = "datetime"
elif pytype is datetime.date:
pytype_name = "date"
elif issubclass(pytype, np.bool_):
pytype_name = "bool"
return _SQL_TYPES[pytype_name][flavor]
lookup_type = lambda dtype: get_sqltype(dtype, flavor)
column_types = lzip(frame.dtypes.index, map(lookup_type, frame.dtypes))
if flavor == 'sqlite':
columns = ',\n '.join('[%s] %s' % x for x in column_types)
else:
columns = ',\n '.join('`%s` %s' % x for x in column_types)
keystr = ''
if keys is not None:
if isinstance(keys, string_types):
keys = (keys,)
keystr = ', PRIMARY KEY (%s)' % ','.join(keys)
template = """CREATE TABLE %(name)s (
%(columns)s
%(keystr)s
);"""
create_statement = template % {'name': name, 'columns': columns,
'keystr': keystr}
return create_statement
def tquery(sql, con=None, cur=None, retry=True):
"""
Returns list of tuples corresponding to each row in given sql
query.
If only one column selected, then plain list is returned.
Parameters
----------
sql: string
SQL query to be executed
con: SQLConnection or DB API 2.0-compliant connection
cur: DB API 2.0 cursor
Provide a specific connection or a specific cursor if you are executing a
lot of sequential statements and want to commit outside.
"""
cur = execute(sql, con, cur=cur)
result = _safe_fetch(cur)
if con is not None:
try:
cur.close()
con.commit()
except Exception as e:
excName = e.__class__.__name__
if excName == 'OperationalError': # pragma: no cover
print('Failed to commit, may need to restart interpreter')
else:
raise
traceback.print_exc()
if retry:
return tquery(sql, con=con, retry=False)
if result and len(result[0]) == 1:
# python 3 compat
result = list(lzip(*result)[0])
elif result is None: # pragma: no cover
result = []
return result
def _parse_data(schema, rows):
# see:
# http://pandas.pydata.org/pandas-docs/dev/missing_data.html
# #missing-data-casting-rules-and-indexing
dtype_map = {'FLOAT': np.dtype(float),
'TIMESTAMP': 'M8[ns]'}
fields = schema['fields']
col_types = [field['type'] for field in fields]
col_names = [str(field['name']) for field in fields]
col_dtypes = [dtype_map.get(field['type'], object) for field in fields]
page_array = np.zeros((len(rows),), dtype=lzip(col_names, col_dtypes))
for row_num, raw_row in enumerate(rows):
entries = raw_row.get('f', [])
for col_num, field_type in enumerate(col_types):
field_value = _parse_entry(entries[col_num].get('v', ''),
field_type)
page_array[row_num][col_num] = field_value
return DataFrame(page_array, columns=col_names)
def test_plot(self):
df = tm.makeTimeDataFrame()
_check_plot_works(df.plot, grid=False)
_check_plot_works(df.plot, subplots=True)
_check_plot_works(df.plot, subplots=True, use_index=False)
df = DataFrame({'x': [1, 2], 'y': [3, 4]})
self._check_plot_fails(df.plot, kind='line', blarg=True)
df = DataFrame(np.random.rand(10, 3),
index=list(string.ascii_letters[:10]))
_check_plot_works(df.plot, use_index=True)
_check_plot_works(df.plot, sort_columns=False)
_check_plot_works(df.plot, yticks=[1, 5, 10])
_check_plot_works(df.plot, xticks=[1, 5, 10])
_check_plot_works(df.plot, ylim=(-100, 100), xlim=(-100, 100))
_check_plot_works(df.plot, subplots=True, title='blah')
_check_plot_works(df.plot, title='blah')
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3),
index=MultiIndex.from_tuples(tuples))
_check_plot_works(df.plot, use_index=True)
# unicode
index = MultiIndex.from_tuples([(u('\u03b1'), 0),
(u('\u03b1'), 1),
(u('\u03b2'), 2),
(u('\u03b2'), 3),
(u('\u03b3'), 4),
(u('\u03b3'), 5),
(u('\u03b4'), 6),
(u('\u03b4'), 7)], names=['i0', 'i1'])
columns = MultiIndex.from_tuples([('bar', u('\u0394')),
('bar', u('\u0395'))], names=['c0',
'c1'])
df = DataFrame(np.random.randint(0, 10, (8, 2)),
columns=columns,
index=index)
_check_plot_works(df.plot, title=u('\u03A3'))
def test_plot(self):
df = tm.makeTimeDataFrame()
_check_plot_works(df.plot, grid=False)
_check_plot_works(df.plot, subplots=True)
_check_plot_works(df.plot, subplots=True, use_index=False)
df = DataFrame({"x": [1, 2], "y": [3, 4]})
self._check_plot_fails(df.plot, kind="line", blarg=True)
df = DataFrame(np.random.rand(10, 3), index=list(string.ascii_letters[:10]))
_check_plot_works(df.plot, use_index=True)
_check_plot_works(df.plot, sort_columns=False)
_check_plot_works(df.plot, yticks=[1, 5, 10])
_check_plot_works(df.plot, xticks=[1, 5, 10])
_check_plot_works(df.plot, ylim=(-100, 100), xlim=(-100, 100))
_check_plot_works(df.plot, subplots=True, title="blah")
_check_plot_works(df.plot, title="blah")
tuples = lzip(string.ascii_letters[:10], range(10))
df = DataFrame(np.random.rand(10, 3), index=MultiIndex.from_tuples(tuples))
_check_plot_works(df.plot, use_index=True)
# unicode
index = MultiIndex.from_tuples(
[
(u("\u03b1"), 0),
(u("\u03b1"), 1),
(u("\u03b2"), 2),
(u("\u03b2"), 3),
(u("\u03b3"), 4),
(u("\u03b3"), 5),
(u("\u03b4"), 6),
(u("\u03b4"), 7),
],
names=["i0", "i1"],
)
columns = MultiIndex.from_tuples([("bar", u("\u0394")), ("bar", u("\u0395"))], names=["c0", "c1"])
df = DataFrame(np.random.randint(0, 10, (8, 2)), columns=columns, index=index)
_check_plot_works(df.plot, title=u("\u03A3"))
def __init__(self, encoding):
self._encoding = encoding
#type code.
#--------------------
#str1 1 = 0x01
#str2 2 = 0x02
#...
#str244 244 = 0xf4
#byte 251 = 0xfb (sic)
#int 252 = 0xfc
#long 253 = 0xfd
#float 254 = 0xfe
#double 255 = 0xff
#--------------------
#NOTE: the byte type seems to be reserved for categorical variables
# with a label, but the underlying variable is -127 to 100
# we're going to drop the label and cast to int
self.DTYPE_MAP = \
dict(
lzip(range(1, 245), ['a' + str(i) for i in range(1, 245)]) +
[
(251, np.int16),
(252, np.int32),
(253, np.int64),
(254, np.float32),
(255, np.float64)
]
)
self.DTYPE_MAP_XML = \
dict(
[
(32768, np.string_),
(65526, np.float64),
(65527, np.float32),
(65528, np.int64),
(65529, np.int32),
(65530, np.int16)
]
)
self.TYPE_MAP = lrange(251) + list('bhlfd')
self.TYPE_MAP_XML = \
dict(
[
(65526, 'd'),
(65527, 'f'),
(65528, 'l'),
(65529, 'h'),
(65530, 'b')
]
)
#NOTE: technically, some of these are wrong. there are more numbers
# that can be represented. it's the 27 ABOVE and BELOW the max listed
# numeric data type in [U] 12.2.2 of the 11.2 manual
self.MISSING_VALUES = \
{
'b': (-127, 100),
'h': (-32767, 32740),
'l': (-2147483647, 2147483620),
'f': (-1.701e+38, +1.701e+38),
'd': (-1.798e+308, +8.988e+307)
}
self.OLD_TYPE_MAPPING = \
{
'i': 252,
'f': 254,
'b': 251
}
def __init__(self, encoding):
self._encoding = encoding
#type code.
#--------------------
#str1 1 = 0x01
#str2 2 = 0x02
#...
#str244 244 = 0xf4
#byte 251 = 0xfb (sic)
#int 252 = 0xfc
#long 253 = 0xfd
#float 254 = 0xfe
#double 255 = 0xff
#--------------------
#NOTE: the byte type seems to be reserved for categorical variables
# with a label, but the underlying variable is -127 to 100
# we're going to drop the label and cast to int
self.DTYPE_MAP = \
dict(
lzip(range(1, 245), ['a' + str(i) for i in range(1, 245)]) +
[
(251, np.int8),
(252, np.int16),
(253, np.int32),
(254, np.float32),
(255, np.float64)
]
)
self.DTYPE_MAP_XML = \
dict(
[
(32768, np.string_),
(65526, np.float64),
(65527, np.float32),
(65528, np.int32),
(65529, np.int16),
(65530, np.int8)
]
)
self.TYPE_MAP = lrange(251) + list('bhlfd')
self.TYPE_MAP_XML = \
dict(
[
(65526, 'd'),
(65527, 'f'),
(65528, 'l'),
(65529, 'h'),
(65530, 'b')
]
)
#NOTE: technically, some of these are wrong. there are more numbers
# that can be represented. it's the 27 ABOVE and BELOW the max listed
# numeric data type in [U] 12.2.2 of the 11.2 manual
float32_min = b'\xff\xff\xff\xfe'
float32_max = b'\xff\xff\xff\x7e'
float64_min = b'\xff\xff\xff\xff\xff\xff\xef\xff'
float64_max = b'\xff\xff\xff\xff\xff\xff\xdf\x7f'
self.VALID_RANGE = \
{
'b': (-127, 100),
'h': (-32767, 32740),
'l': (-2147483647, 2147483620),
'f': (np.float32(struct.unpack('<f', float32_min)[0]),
np.float32(struct.unpack('<f', float32_max)[0])),
'd': (np.float64(struct.unpack('<d', float64_min)[0]),
np.float64(struct.unpack('<d', float64_max)[0]))
}
self.OLD_TYPE_MAPPING = \
{
'i': 252,
'f': 254,
'b': 251
}
# These missing values are the generic '.' in Stata, and are used
# to replace nans
self.MISSING_VALUES = \
{
'b': 101,
'h': 32741,
'l': 2147483621,
'f': np.float32(struct.unpack('<f', b'\x00\x00\x00\x7f')[0]),
'd': np.float64(struct.unpack('<d', b'\x00\x00\x00\x00\x00\x00\xe0\x7f')[0])
}
def makeCustomIndex(nentries, nlevels, prefix='#', names=False, ndupe_l=None,
idx_type=None):
"""Create an index/multindex with given dimensions, levels, names, etc'
nentries - number of entries in index
nlevels - number of levels (> 1 produces multindex)
prefix - a string prefix for labels
names - (Optional), bool or list of strings. if True will use default names,
if false will use no names, if a list is given, the name of each level
in the index will be taken from the list.
ndupe_l - (Optional), list of ints, the number of rows for which the
label will repeated at the corresponding level, you can specify just
the first few, the rest will use the default ndupe_l of 1.
len(ndupe_l) <= nlevels.
idx_type - "i"/"f"/"s"/"u"/"dt/"p".
If idx_type is not None, `idx_nlevels` must be 1.
"i"/"f" creates an integer/float index,
"s"/"u" creates a string/unicode index
"dt" create a datetime index.
if unspecified, string labels will be generated.
"""
if ndupe_l is None:
ndupe_l = [1] * nlevels
assert (_is_sequence(ndupe_l) and len(ndupe_l) <= nlevels)
assert (names is None or names is False
or names is True or len(names) is nlevels)
assert idx_type is None or \
(idx_type in ('i', 'f', 's', 'u', 'dt', 'p') and nlevels == 1)
if names is True:
# build default names
names = [prefix + str(i) for i in range(nlevels)]
if names is False:
# pass None to index constructor for no name
names = None
# make singelton case uniform
if isinstance(names, compat.string_types) and nlevels == 1:
names = [names]
# specific 1D index type requested?
idx_func = dict(i=makeIntIndex, f=makeFloatIndex, s=makeStringIndex,
u=makeUnicodeIndex, dt=makeDateIndex, p=makePeriodIndex).get(idx_type)
if idx_func:
idx = idx_func(nentries)
# but we need to fill in the name
if names:
idx.name = names[0]
return idx
elif idx_type is not None:
raise ValueError('"%s" is not a legal value for `idx_type`, use '
'"i"/"f"/"s"/"u"/"dt/"p".' % idx_type)
if len(ndupe_l) < nlevels:
ndupe_l.extend([1] * (nlevels - len(ndupe_l)))
assert len(ndupe_l) == nlevels
assert all([x > 0 for x in ndupe_l])
tuples = []
for i in range(nlevels):
def keyfunc(x):
import re
numeric_tuple = re.sub("[^\d_]_?", "", x).split("_")
return lmap(int, numeric_tuple)
# build a list of lists to create the index from
div_factor = nentries // ndupe_l[i] + 1
cnt = Counter()
for j in range(div_factor):
label = prefix + '_l%d_g' % i + str(j)
cnt[label] = ndupe_l[i]
# cute Counter trick
result = list(sorted(cnt.elements(), key=keyfunc))[:nentries]
tuples.append(result)
tuples = lzip(*tuples)
# convert tuples to index
if nentries == 1:
index = Index(tuples[0], name=names[0])
else:
index = MultiIndex.from_tuples(tuples, names=names)
return index
def _write_hierarchical_rows(self, fmt_values, indent):
template = 'rowspan="{span}" valign="top"'
truncate_h = self.fmt.truncate_h
truncate_v = self.fmt.truncate_v
frame = self.fmt.tr_frame
ncols = len(frame.columns)
nrows = len(frame)
row_levels = self.frame.index.nlevels
idx_values = frame.index.format(sparsify=False, adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
levels = frame.index.format(sparsify=sentinel, adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
if truncate_v:
# Insert ... row and adjust idx_values and
# level_lengths to take this into account.
ins_row = self.fmt.tr_row_num
inserted = False
for lnum, records in enumerate(level_lengths):
rec_new = {}
for tag, span in list(records.items()):
if tag >= ins_row:
rec_new[tag + 1] = span
elif tag + span > ins_row:
rec_new[tag] = span + 1
# GH 14882 - Make sure insertion done once
if not inserted:
dot_row = list(idx_values[ins_row - 1])
dot_row[-1] = u('...')
idx_values.insert(ins_row, tuple(dot_row))
inserted = True
else:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
else:
rec_new[tag] = span
# If ins_row lies between tags, all cols idx cols
# receive ...
if tag + span == ins_row:
rec_new[ins_row] = 1
if lnum == 0:
idx_values.insert(ins_row, tuple(
[u('...')] * len(level_lengths)))
# GH 14882 - Place ... in correct level
elif inserted:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
level_lengths[lnum] = rec_new
level_lengths[inner_lvl][ins_row] = 1
for ix_col in range(len(fmt_values)):
fmt_values[ix_col].insert(ins_row, '...')
nrows += 1
for i in range(nrows):
row = []
tags = {}
sparse_offset = 0
j = 0
for records, v in zip(level_lengths, idx_values[i]):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
sparse_offset += 1
continue
j += 1
row.append(v)
row.extend(fmt_values[j][i] for j in range(ncols))
if truncate_h:
row.insert(row_levels - sparse_offset +
self.fmt.tr_col_num, '...')
self.write_tr(row, indent, self.indent_delta, tags=tags,
nindex_levels=len(levels) - sparse_offset)
else:
for i in range(len(frame)):
idx_values = list(zip(*frame.index.format(
sparsify=False, adjoin=False, names=False)))
row = []
row.extend(idx_values[i])
row.extend(fmt_values[j][i] for j in range(ncols))
if truncate_h:
row.insert(row_levels + self.fmt.tr_col_num, '...')
self.write_tr(row, indent, self.indent_delta, tags=None,
nindex_levels=frame.index.nlevels)
def makeCustomIndex(nentries, nlevels, prefix='#', names=False, ndupe_l=None,
idx_type=None):
"""Create an index/multindex with given dimensions, levels, names, etc'
nentries - number of entries in index
nlevels - number of levels (> 1 produces multindex)
prefix - a string prefix for labels
names - (Optional), bool or list of strings. if True will use default names,
if false will use no names, if a list is given, the name of each level
in the index will be taken from the list.
ndupe_l - (Optional), list of ints, the number of rows for which the
label will repeated at the corresponding level, you can specify just
the first few, the rest will use the default ndupe_l of 1.
len(ndupe_l) <= nlevels.
idx_type - "i"/"f"/"s"/"u"/"dt/"p".
If idx_type is not None, `idx_nlevels` must be 1.
"i"/"f" creates an integer/float index,
"s"/"u" creates a string/unicode index
"dt" create a datetime index.
if unspecified, string labels will be generated.
"""
if ndupe_l is None:
ndupe_l = [1] * nlevels
assert (_is_sequence(ndupe_l) and len(ndupe_l) <= nlevels)
assert (names is None or names is False
or names is True or len(names) is nlevels)
assert idx_type is None or \
(idx_type in ('i', 'f', 's', 'u', 'dt', 'p') and nlevels == 1)
if names is True:
# build default names
names = [prefix + str(i) for i in range(nlevels)]
if names is False:
# pass None to index constructor for no name
names = None
# make singelton case uniform
if isinstance(names, compat.string_types) and nlevels == 1:
names = [names]
# specific 1D index type requested?
idx_func = dict(i=makeIntIndex, f=makeFloatIndex, s=makeStringIndex,
u=makeUnicodeIndex, dt=makeDateIndex, p=makePeriodIndex).get(idx_type)
if idx_func:
idx = idx_func(nentries)
# but we need to fill in the name
if names:
idx.name = names[0]
return idx
elif idx_type is not None:
raise ValueError('"%s" is not a legal value for `idx_type`, use '
'"i"/"f"/"s"/"u"/"dt/"p".' % idx_type)
if len(ndupe_l) < nlevels:
ndupe_l.extend([1] * (nlevels - len(ndupe_l)))
assert len(ndupe_l) == nlevels
assert all([x > 0 for x in ndupe_l])
tuples = []
for i in range(nlevels):
def keyfunc(x):
import re
numeric_tuple = re.sub("[^\d_]_?", "", x).split("_")
return lmap(int, numeric_tuple)
# build a list of lists to create the index from
div_factor = nentries // ndupe_l[i] + 1
cnt = Counter()
for j in range(div_factor):
label = prefix + '_l%d_g' % i + str(j)
cnt[label] = ndupe_l[i]
# cute Counter trick
result = list(sorted(cnt.elements(), key=keyfunc))[:nentries]
tuples.append(result)
tuples = lzip(*tuples)
# convert tuples to index
if nentries == 1:
index = Index(tuples[0], name=names[0])
else:
index = MultiIndex.from_tuples(tuples, names=names)
return index
def _write_hierarchical_rows(self, fmt_values, indent):
template = 'rowspan="{span}" valign="top"'
truncate_h = self.fmt.truncate_h
truncate_v = self.fmt.truncate_v
frame = self.fmt.tr_frame
nrows = len(frame)
# TODO: after gh-22887 fixed, refactor to use class property
# in place of row_levels
row_levels = self.frame.index.nlevels
idx_values = frame.index.format(sparsify=False,
adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if self.fmt.sparsify:
# GH3547
sentinel = com.sentinel_factory()
levels = frame.index.format(sparsify=sentinel,
adjoin=False,
names=False)
level_lengths = get_level_lengths(levels, sentinel)
inner_lvl = len(level_lengths) - 1
if truncate_v:
# Insert ... row and adjust idx_values and
# level_lengths to take this into account.
ins_row = self.fmt.tr_row_num
inserted = False
for lnum, records in enumerate(level_lengths):
rec_new = {}
for tag, span in list(records.items()):
if tag >= ins_row:
rec_new[tag + 1] = span
elif tag + span > ins_row:
rec_new[tag] = span + 1
# GH 14882 - Make sure insertion done once
if not inserted:
dot_row = list(idx_values[ins_row - 1])
dot_row[-1] = u('...')
idx_values.insert(ins_row, tuple(dot_row))
inserted = True
else:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
else:
rec_new[tag] = span
# If ins_row lies between tags, all cols idx cols
# receive ...
if tag + span == ins_row:
rec_new[ins_row] = 1
if lnum == 0:
idx_values.insert(
ins_row,
tuple([u('...')] * len(level_lengths)))
# GH 14882 - Place ... in correct level
elif inserted:
dot_row = list(idx_values[ins_row])
dot_row[inner_lvl - lnum] = u('...')
idx_values[ins_row] = tuple(dot_row)
level_lengths[lnum] = rec_new
level_lengths[inner_lvl][ins_row] = 1
for ix_col in range(len(fmt_values)):
fmt_values[ix_col].insert(ins_row, '...')
nrows += 1
for i in range(nrows):
row = []
tags = {}
sparse_offset = 0
j = 0
for records, v in zip(level_lengths, idx_values[i]):
if i in records:
if records[i] > 1:
tags[j] = template.format(span=records[i])
else:
sparse_offset += 1
continue
j += 1
row.append(v)
row.extend(fmt_values[j][i] for j in range(self.ncols))
if truncate_h:
row.insert(
row_levels - sparse_offset + self.fmt.tr_col_num,
'...')
self.write_tr(row,
indent,
self.indent_delta,
tags=tags,
nindex_levels=len(levels) - sparse_offset)
else:
for i in range(len(frame)):
idx_values = list(
zip(*frame.index.format(
sparsify=False, adjoin=False, names=False)))
row = []
row.extend(idx_values[i])
row.extend(fmt_values[j][i] for j in range(self.ncols))
if truncate_h:
row.insert(row_levels + self.fmt.tr_col_num, '...')
self.write_tr(row,
indent,
self.indent_delta,
tags=None,
nindex_levels=frame.index.nlevels)
def _translate(self):
"""
Convert the DataFrame in `self.data` and the attrs from `_build_styles`
into a dictionary of {head, body, uuid, cellstyle}
"""
table_styles = self.table_styles or []
caption = self.caption
ctx = self.ctx
precision = self.precision
uuid = self.uuid or str(uuid1()).replace("-", "_")
ROW_HEADING_CLASS = "row_heading"
COL_HEADING_CLASS = "col_heading"
DATA_CLASS = "data"
BLANK_CLASS = "blank"
BLANK_VALUE = ""
cell_context = dict()
n_rlvls = self.data.index.nlevels
n_clvls = self.data.columns.nlevels
rlabels = self.data.index.tolist()
clabels = self.data.columns.tolist()
idx_values = self.data.index.format(sparsify=False, adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if n_rlvls == 1:
rlabels = [[x] for x in rlabels]
if n_clvls == 1:
clabels = [[x] for x in clabels]
clabels = list(zip(*clabels))
cellstyle = []
head = []
for r in range(n_clvls):
row_es = [{"type": "th",
"value": BLANK_VALUE,
"class": " ".join([BLANK_CLASS])}] * n_rlvls
for c in range(len(clabels[0])):
cs = [COL_HEADING_CLASS, "level%s" % r, "col%s" % c]
cs.extend(cell_context.get(
"col_headings", {}).get(r, {}).get(c, []))
value = clabels[r][c]
row_es.append({"type": "th",
"value": value,
"display_value": value,
"class": " ".join(cs)})
head.append(row_es)
if self.data.index.names and self.data.index.names != [None]:
index_header_row = []
for c, name in enumerate(self.data.index.names):
cs = [COL_HEADING_CLASS,
"level%s" % (n_clvls + 1),
"col%s" % c]
index_header_row.append({"type": "th", "value": name,
"class": " ".join(cs)})
index_header_row.extend(
[{"type": "th",
"value": BLANK_VALUE,
"class": " ".join([BLANK_CLASS])
}] * len(clabels[0]))
head.append(index_header_row)
body = []
for r, idx in enumerate(self.data.index):
cs = [ROW_HEADING_CLASS, "level%s" % c, "row%s" % r]
cs.extend(
cell_context.get("row_headings", {}).get(r, {}).get(c, []))
row_es = [{"type": "th",
"value": rlabels[r][c],
"class": " ".join(cs),
"display_value": rlabels[r][c]}
for c in range(len(rlabels[r]))]
for c, col in enumerate(self.data.columns):
cs = [DATA_CLASS, "row%s" % r, "col%s" % c]
cs.extend(cell_context.get("data", {}).get(r, {}).get(c, []))
formatter = self._display_funcs[(r, c)]
value = self.data.iloc[r, c]
row_es.append({
"type": "td",
"value": value,
"class": " ".join(cs),
"id": "_".join(cs[1:]),
"display_value": formatter(value)
})
props = []
for x in ctx[r, c]:
# have to handle empty styles like ['']
if x.count(":"):
props.append(x.split(":"))
else:
props.append(['', ''])
cellstyle.append({'props': props,
'selector': "row%s_col%s" % (r, c)})
body.append(row_es)
return dict(head=head, cellstyle=cellstyle, body=body, uuid=uuid,
precision=precision, table_styles=table_styles,
caption=caption, table_attributes=self.table_attributes)
def test_constructors(self, data, closed, name):
left, right = data[:-1], data[1:]
ivs = [Interval(l, r, closed=closed) for l, r in lzip(left, right)]
expected = IntervalIndex._simple_new(left=left,
right=right,
closed=closed,
name=name)
# validate expected
assert expected.closed == closed
assert expected.name == name
assert expected.dtype.subtype == data.dtype
tm.assert_index_equal(expected.left, data[:-1])
tm.assert_index_equal(expected.right, data[1:])
# validated constructors
result = IntervalIndex(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(ivs, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_breaks(data, closed=closed, name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_arrays(left,
right,
closed=closed,
name=name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(lzip(left, right),
closed=closed,
name=name)
tm.assert_index_equal(result, expected)
result = Index(ivs, name=name)
assert isinstance(result, IntervalIndex)
tm.assert_index_equal(result, expected)
# idempotent
tm.assert_index_equal(Index(expected), expected)
tm.assert_index_equal(IntervalIndex(expected), expected)
result = IntervalIndex.from_intervals(expected)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_intervals(expected.values,
name=expected.name)
tm.assert_index_equal(result, expected)
left, right = expected.left, expected.right
result = IntervalIndex.from_arrays(left,
right,
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
result = IntervalIndex.from_tuples(expected.to_tuples(),
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
breaks = expected.left.tolist() + [expected.right[-1]]
result = IntervalIndex.from_breaks(breaks,
closed=expected.closed,
name=expected.name)
tm.assert_index_equal(result, expected)
def __init__(self, encoding):
self._encoding = encoding
#type code.
#--------------------
#str1 1 = 0x01
#str2 2 = 0x02
#...
#str244 244 = 0xf4
#byte 251 = 0xfb (sic)
#int 252 = 0xfc
#long 253 = 0xfd
#float 254 = 0xfe
#double 255 = 0xff
#--------------------
#NOTE: the byte type seems to be reserved for categorical variables
# with a label, but the underlying variable is -127 to 100
# we're going to drop the label and cast to int
self.DTYPE_MAP = \
dict(
lzip(range(1, 245), ['a' + str(i) for i in range(1, 245)]) +
[
(251, np.int8),
(252, np.int16),
(253, np.int32),
(254, np.float32),
(255, np.float64)
]
)
self.DTYPE_MAP_XML = \
dict(
[
(32768, np.string_),
(65526, np.float64),
(65527, np.float32),
(65528, np.int32),
(65529, np.int16),
(65530, np.int8)
]
)
self.TYPE_MAP = lrange(251) + list('bhlfd')
self.TYPE_MAP_XML = \
dict(
[
(65526, 'd'),
(65527, 'f'),
(65528, 'l'),
(65529, 'h'),
(65530, 'b')
]
)
#NOTE: technically, some of these are wrong. there are more numbers
# that can be represented. it's the 27 ABOVE and BELOW the max listed
# numeric data type in [U] 12.2.2 of the 11.2 manual
float32_min = b'\xff\xff\xff\xfe'
float32_max = b'\xff\xff\xff\x7e'
float64_min = b'\xff\xff\xff\xff\xff\xff\xef\xff'
float64_max = b'\xff\xff\xff\xff\xff\xff\xdf\x7f'
self.VALID_RANGE = \
{
'b': (-127, 100),
'h': (-32767, 32740),
'l': (-2147483647, 2147483620),
'f': (np.float32(struct.unpack('<f', float32_min)[0]),
np.float32(struct.unpack('<f', float32_max)[0])),
'd': (np.float64(struct.unpack('<d', float64_min)[0]),
np.float64(struct.unpack('<d', float64_max)[0]))
}
self.OLD_TYPE_MAPPING = \
{
'i': 252,
'f': 254,
'b': 251
}
# These missing values are the generic '.' in Stata, and are used
# to replace nans
self.MISSING_VALUES = \
{
'b': 101,
'h': 32741,
'l': 2147483621,
'f': np.float32(struct.unpack('<f', b'\x00\x00\x00\x7f')[0]),
'd': np.float64(struct.unpack('<d', b'\x00\x00\x00\x00\x00\x00\xe0\x7f')[0])
}
# Reserved words cannot be used as variable names
self.RESERVED_WORDS = ('aggregate', 'array', 'boolean', 'break',
'byte', 'case', 'catch', 'class', 'colvector',
'complex', 'const', 'continue', 'default',
'delegate', 'delete', 'do', 'double', 'else',
'eltypedef', 'end', 'enum', 'explicit',
'export', 'external', 'float', 'for', 'friend',
'function', 'global', 'goto', 'if', 'inline',
'int', 'local', 'long', 'NULL', 'pragma',
'protected', 'quad', 'rowvector', 'short',
'typedef', 'typename', 'virtual')
from pandas.core.indexes.api import Index, MultiIndex
@pytest.fixture(params=[
tm.makeUnicodeIndex(100),
tm.makeStringIndex(100),
tm.makeDateIndex(100),
tm.makePeriodIndex(100),
tm.makeTimedeltaIndex(100),
tm.makeIntIndex(100),
tm.makeUIntIndex(100),
tm.makeFloatIndex(100),
Index([True, False]),
tm.makeCategoricalIndex(100),
Index([]),
MultiIndex.from_tuples(lzip(['foo', 'bar', 'baz'], [1, 2, 3])),
Index([0, 0, 1, 1, 2, 2])
],
ids=lambda x: type(x).__name__)
def indices(request):
return request.param
@pytest.fixture(params=[1, np.array(1, dtype=np.int64)])
def one(request):
# zero-dim integer array behaves like an integer
return request.param
zeros = [
box([0] * 5, dtype=dtype) for box in [pd.Index, np.array]
def _make_concat_multiindex(indexes, keys, levels=None, names=None):
if ((levels is None and isinstance(keys[0], tuple)) or
(levels is not None and len(levels) > 1)):
zipped = lzip(*keys)
if names is None:
names = [None] * len(zipped)
if levels is None:
levels = [Categorical.from_array(zp).levels for zp in zipped]
else:
levels = [_ensure_index(x) for x in levels]
else:
zipped = [keys]
if names is None:
names = [None]
if levels is None:
levels = [_ensure_index(keys)]
else:
levels = [_ensure_index(x) for x in levels]
if not _all_indexes_same(indexes):
label_list = []
# things are potentially different sizes, so compute the exact labels
# for each level and pass those to MultiIndex.from_arrays
for hlevel, level in zip(zipped, levels):
to_concat = []
for key, index in zip(hlevel, indexes):
try:
i = level.get_loc(key)
except KeyError:
raise ValueError('Key %s not in level %s'
% (str(key), str(level)))
to_concat.append(np.repeat(i, len(index)))
label_list.append(np.concatenate(to_concat))
concat_index = _concat_indexes(indexes)
# these go at the end
if isinstance(concat_index, MultiIndex):
levels.extend(concat_index.levels)
label_list.extend(concat_index.labels)
else:
factor = Categorical.from_array(concat_index)
levels.append(factor.levels)
label_list.append(factor.codes)
if len(names) == len(levels):
names = list(names)
else:
# make sure that all of the passed indices have the same nlevels
if not len(set([ i.nlevels for i in indexes ])) == 1:
raise AssertionError("Cannot concat indices that do"
" not have the same number of levels")
# also copies
names = names + _get_consensus_names(indexes)
return MultiIndex(levels=levels, labels=label_list, names=names,
verify_integrity=False)
new_index = indexes[0]
n = len(new_index)
kpieces = len(indexes)
# also copies
new_names = list(names)
new_levels = list(levels)
# construct labels
new_labels = []
# do something a bit more speedy
for hlevel, level in zip(zipped, levels):
hlevel = _ensure_index(hlevel)
mapped = level.get_indexer(hlevel)
mask = mapped == -1
if mask.any():
raise ValueError('Values not found in passed level: %s'
% str(hlevel[mask]))
new_labels.append(np.repeat(mapped, n))
if isinstance(new_index, MultiIndex):
new_levels.extend(new_index.levels)
new_labels.extend([np.tile(lab, kpieces) for lab in new_index.labels])
else:
new_levels.append(new_index)
new_labels.append(np.tile(np.arange(n), kpieces))
if len(new_names) < len(new_levels):
new_names.extend(new_index.names)
return MultiIndex(levels=new_levels, labels=new_labels, names=new_names,
verify_integrity=False)
def _zip2(*args):
return lib.list_to_object_array(lzip(*args))
class TestIntervalIndex(Base):
_holder = IntervalIndex
def setup_method(self, method):
self.index = IntervalIndex.from_arrays([0, 1], [1, 2])
self.index_with_nan = IntervalIndex.from_tuples([(0, 1), np.nan,
(1, 2)])
self.indices = dict(intervalIndex=tm.makeIntervalIndex(10))
def create_index(self, closed='right'):
return IntervalIndex.from_breaks(range(11), closed=closed)
def create_index_with_nan(self, closed='right'):
mask = [True, False] + [True] * 8
return IntervalIndex.from_arrays(np.where(mask, np.arange(10), np.nan),
np.where(mask, np.arange(1, 11),
np.nan),
closed=closed)
def test_properties(self, closed):
index = self.create_index(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
tm.assert_index_equal(index.left, Index(np.arange(10)))
tm.assert_index_equal(index.right, Index(np.arange(1, 11)))
tm.assert_index_equal(index.mid, Index(np.arange(0.5, 10.5)))
assert index.closed == closed
ivs = [Interval(l, r, closed) for l, r in zip(range(10), range(1, 11))]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
tm.assert_numpy_array_equal(index.values, expected)
# with nans
index = self.create_index_with_nan(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
expected_left = Index([0, np.nan, 2, 3, 4, 5, 6, 7, 8, 9])
expected_right = expected_left + 1
expected_mid = expected_left + 0.5
tm.assert_index_equal(index.left, expected_left)
tm.assert_index_equal(index.right, expected_right)
tm.assert_index_equal(index.mid, expected_mid)
assert index.closed == closed
ivs = [
Interval(l, r, closed) if notna(l) else np.nan
for l, r in zip(expected_left, expected_right)
]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
tm.assert_numpy_array_equal(index.values, expected)
@pytest.mark.parametrize(
'breaks',
[[1, 1, 2, 5, 15, 53, 217, 1014, 5335, 31240, 201608],
[-np.inf, -100, -10, 0.5, 1, 1.5, 3.8, 101, 202, np.inf],
pd.to_datetime(['20170101', '20170202', '20170303', '20170404']),
pd.to_timedelta(['1ns', '2ms', '3s', '4M', '5H', '6D'])])
def test_length(self, closed, breaks):
# GH 18789
index = IntervalIndex.from_breaks(breaks, closed=closed)
result = index.length
expected = Index(iv.length for iv in index)
tm.assert_index_equal(result, expected)
# with NA
index = index.insert(1, np.nan)
result = index.length
expected = Index(iv.length if notna(iv) else iv for iv in index)
tm.assert_index_equal(result, expected)
def test_with_nans(self, closed):
index = self.create_index(closed=closed)
assert not index.hasnans
result = index.isna()
expected = np.repeat(False, len(index))
tm.assert_numpy_array_equal(result, expected)
result = index.notna()
expected = np.repeat(True, len(index))
tm.assert_numpy_array_equal(result, expected)
index = self.create_index_with_nan(closed=closed)
assert index.hasnans
result = index.isna()
expected = np.array([False, True] + [False] * (len(index) - 2))
tm.assert_numpy_array_equal(result, expected)
result = index.notna()
expected = np.array([True, False] + [True] * (len(index) - 2))
tm.assert_numpy_array_equal(result, expected)
def test_copy(self, closed):
expected = self.create_index(closed=closed)
result = expected.copy()
assert result.equals(expected)
result = expected.copy(deep=True)
assert result.equals(expected)
assert result.left is not expected.left
def test_ensure_copied_data(self, closed):
# exercise the copy flag in the constructor
# not copying
index = self.create_index(closed=closed)
result = IntervalIndex(index, copy=False)
tm.assert_numpy_array_equal(index.left.values,
result.left.values,
check_same='same')
tm.assert_numpy_array_equal(index.right.values,
result.right.values,
check_same='same')
# by-definition make a copy
result = IntervalIndex(index.values, copy=False)
tm.assert_numpy_array_equal(index.left.values,
result.left.values,
check_same='copy')
tm.assert_numpy_array_equal(index.right.values,
result.right.values,
check_same='copy')
def test_equals(self, closed):
expected = IntervalIndex.from_breaks(np.arange(5), closed=closed)
assert expected.equals(expected)
assert expected.equals(expected.copy())
assert not expected.equals(expected.astype(object))
assert not expected.equals(np.array(expected))
assert not expected.equals(list(expected))
assert not expected.equals([1, 2])
assert not expected.equals(np.array([1, 2]))
assert not expected.equals(pd.date_range('20130101', periods=2))
expected_name1 = IntervalIndex.from_breaks(np.arange(5),
closed=closed,
name='foo')
expected_name2 = IntervalIndex.from_breaks(np.arange(5),
closed=closed,
name='bar')
assert expected.equals(expected_name1)
assert expected_name1.equals(expected_name2)
for other_closed in {'left', 'right', 'both', 'neither'} - {closed}:
expected_other_closed = IntervalIndex.from_breaks(
np.arange(5), closed=other_closed)
assert not expected.equals(expected_other_closed)
@pytest.mark.parametrize('klass', [list, tuple, np.array, pd.Series])
def test_where(self, closed, klass):
idx = self.create_index(closed=closed)
cond = [True] * len(idx)
expected = idx
result = expected.where(klass(cond))
tm.assert_index_equal(result, expected)
cond = [False] + [True] * len(idx[1:])
expected = IntervalIndex([np.nan] + idx[1:].tolist())
result = idx.where(klass(cond))
tm.assert_index_equal(result, expected)
def test_delete(self, closed):
expected = IntervalIndex.from_breaks(np.arange(1, 11), closed=closed)
result = self.create_index(closed=closed).delete(0)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('data', [
interval_range(0, periods=10, closed='neither'),
interval_range(1.7, periods=8, freq=2.5, closed='both'),
interval_range(Timestamp('20170101'), periods=12, closed='left'),
interval_range(Timedelta('1 day'), periods=6, closed='right')
])
def test_insert(self, data):
item = data[0]
idx_item = IntervalIndex([item])
# start
expected = idx_item.append(data)
result = data.insert(0, item)
tm.assert_index_equal(result, expected)
# end
expected = data.append(idx_item)
result = data.insert(len(data), item)
tm.assert_index_equal(result, expected)
# mid
expected = data[:3].append(idx_item).append(data[3:])
result = data.insert(3, item)
tm.assert_index_equal(result, expected)
# invalid type
msg = 'can only insert Interval objects and NA into an IntervalIndex'
with tm.assert_raises_regex(ValueError, msg):
data.insert(1, 'foo')
# invalid closed
msg = 'inserted item must be closed on the same side as the index'
for closed in {'left', 'right', 'both', 'neither'} - {item.closed}:
with tm.assert_raises_regex(ValueError, msg):
bad_item = Interval(item.left, item.right, closed=closed)
data.insert(1, bad_item)
# GH 18295 (test missing)
na_idx = IntervalIndex([np.nan], closed=data.closed)
for na in (np.nan, pd.NaT, None):
expected = data[:1].append(na_idx).append(data[1:])
result = data.insert(1, na)
tm.assert_index_equal(result, expected)
def test_take(self, closed):
index = self.create_index(closed=closed)
result = index.take(range(10))
tm.assert_index_equal(result, index)
result = index.take([0, 0, 1])
expected = IntervalIndex.from_arrays([0, 0, 1], [1, 1, 2],
closed=closed)
tm.assert_index_equal(result, expected)
def test_unique(self, closed):
# unique non-overlapping
idx = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)],
closed=closed)
assert idx.is_unique
# unique overlapping - distinct endpoints
idx = IntervalIndex.from_tuples([(0, 1), (0.5, 1.5)], closed=closed)
assert idx.is_unique
# unique overlapping - shared endpoints
idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)],
closed=closed)
assert idx.is_unique
# unique nested
idx = IntervalIndex.from_tuples([(-1, 1), (-2, 2)], closed=closed)
assert idx.is_unique
# duplicate
idx = IntervalIndex.from_tuples([(0, 1), (0, 1), (2, 3)],
closed=closed)
assert not idx.is_unique
# empty
idx = IntervalIndex([], closed=closed)
assert idx.is_unique
def test_monotonic(self, closed):
# increasing non-overlapping
idx = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)],
closed=closed)
assert idx.is_monotonic
assert idx._is_strictly_monotonic_increasing
assert not idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# decreasing non-overlapping
idx = IntervalIndex.from_tuples([(4, 5), (2, 3), (1, 2)],
closed=closed)
assert not idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert idx.is_monotonic_decreasing
assert idx._is_strictly_monotonic_decreasing
# unordered non-overlapping
idx = IntervalIndex.from_tuples([(0, 1), (4, 5), (2, 3)],
closed=closed)
assert not idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert not idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# increasing overlapping
idx = IntervalIndex.from_tuples([(0, 2), (0.5, 2.5), (1, 3)],
closed=closed)
assert idx.is_monotonic
assert idx._is_strictly_monotonic_increasing
assert not idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# decreasing overlapping
idx = IntervalIndex.from_tuples([(1, 3), (0.5, 2.5), (0, 2)],
closed=closed)
assert not idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert idx.is_monotonic_decreasing
assert idx._is_strictly_monotonic_decreasing
# unordered overlapping
idx = IntervalIndex.from_tuples([(0.5, 2.5), (0, 2), (1, 3)],
closed=closed)
assert not idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert not idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# increasing overlapping shared endpoints
idx = pd.IntervalIndex.from_tuples([(1, 2), (1, 3), (2, 3)],
closed=closed)
assert idx.is_monotonic
assert idx._is_strictly_monotonic_increasing
assert not idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# decreasing overlapping shared endpoints
idx = pd.IntervalIndex.from_tuples([(2, 3), (1, 3), (1, 2)],
closed=closed)
assert not idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert idx.is_monotonic_decreasing
assert idx._is_strictly_monotonic_decreasing
# stationary
idx = IntervalIndex.from_tuples([(0, 1), (0, 1)], closed=closed)
assert idx.is_monotonic
assert not idx._is_strictly_monotonic_increasing
assert idx.is_monotonic_decreasing
assert not idx._is_strictly_monotonic_decreasing
# empty
idx = IntervalIndex([], closed=closed)
assert idx.is_monotonic
assert idx._is_strictly_monotonic_increasing
assert idx.is_monotonic_decreasing
assert idx._is_strictly_monotonic_decreasing
@pytest.mark.skip(reason='not a valid repr as we use interval notation')
def test_repr(self):
i = IntervalIndex.from_tuples([(0, 1), (1, 2)], closed='right')
expected = ("IntervalIndex(left=[0, 1],"
"\n right=[1, 2],"
"\n closed='right',"
"\n dtype='interval[int64]')")
assert repr(i) == expected
i = IntervalIndex.from_tuples(
(Timestamp('20130101'), Timestamp('20130102')),
(Timestamp('20130102'), Timestamp('20130103')),
closed='right')
expected = ("IntervalIndex(left=['2013-01-01', '2013-01-02'],"
"\n right=['2013-01-02', '2013-01-03'],"
"\n closed='right',"
"\n dtype='interval[datetime64[ns]]')")
assert repr(i) == expected
@pytest.mark.skip(reason='not a valid repr as we use interval notation')
def test_repr_max_seq_item_setting(self):
super(TestIntervalIndex, self).test_repr_max_seq_item_setting()
@pytest.mark.skip(reason='not a valid repr as we use interval notation')
def test_repr_roundtrip(self):
super(TestIntervalIndex, self).test_repr_roundtrip()
# TODO: check this behavior is consistent with test_interval_new.py
def test_get_item(self, closed):
i = IntervalIndex.from_arrays((0, 1, np.nan), (1, 2, np.nan),
closed=closed)
assert i[0] == Interval(0.0, 1.0, closed=closed)
assert i[1] == Interval(1.0, 2.0, closed=closed)
assert isna(i[2])
result = i[0:1]
expected = IntervalIndex.from_arrays((0., ), (1., ), closed=closed)
tm.assert_index_equal(result, expected)
result = i[0:2]
expected = IntervalIndex.from_arrays((0., 1), (1., 2.), closed=closed)
tm.assert_index_equal(result, expected)
result = i[1:3]
expected = IntervalIndex.from_arrays((1., np.nan), (2., np.nan),
closed=closed)
tm.assert_index_equal(result, expected)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_get_loc_value(self):
pytest.raises(KeyError, self.index.get_loc, 0)
assert self.index.get_loc(0.5) == 0
assert self.index.get_loc(1) == 0
assert self.index.get_loc(1.5) == 1
assert self.index.get_loc(2) == 1
pytest.raises(KeyError, self.index.get_loc, -1)
pytest.raises(KeyError, self.index.get_loc, 3)
idx = IntervalIndex.from_tuples([(0, 2), (1, 3)])
assert idx.get_loc(0.5) == 0
assert idx.get_loc(1) == 0
tm.assert_numpy_array_equal(idx.get_loc(1.5),
np.array([0, 1], dtype='int64'))
tm.assert_numpy_array_equal(np.sort(idx.get_loc(2)),
np.array([0, 1], dtype='int64'))
assert idx.get_loc(3) == 1
pytest.raises(KeyError, idx.get_loc, 3.5)
idx = IntervalIndex.from_arrays([0, 2], [1, 3])
pytest.raises(KeyError, idx.get_loc, 1.5)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def slice_locs_cases(self, breaks):
# TODO: same tests for more index types
index = IntervalIndex.from_breaks([0, 1, 2], closed='right')
assert index.slice_locs() == (0, 2)
assert index.slice_locs(0, 1) == (0, 1)
assert index.slice_locs(1, 1) == (0, 1)
assert index.slice_locs(0, 2) == (0, 2)
assert index.slice_locs(0.5, 1.5) == (0, 2)
assert index.slice_locs(0, 0.5) == (0, 1)
assert index.slice_locs(start=1) == (0, 2)
assert index.slice_locs(start=1.2) == (1, 2)
assert index.slice_locs(end=1) == (0, 1)
assert index.slice_locs(end=1.1) == (0, 2)
assert index.slice_locs(end=1.0) == (0, 1)
assert index.slice_locs(-1, -1) == (0, 0)
index = IntervalIndex.from_breaks([0, 1, 2], closed='neither')
assert index.slice_locs(0, 1) == (0, 1)
assert index.slice_locs(0, 2) == (0, 2)
assert index.slice_locs(0.5, 1.5) == (0, 2)
assert index.slice_locs(1, 1) == (1, 1)
assert index.slice_locs(1, 2) == (1, 2)
index = IntervalIndex.from_tuples([(0, 1), (2, 3), (4, 5)],
closed='both')
assert index.slice_locs(1, 1) == (0, 1)
assert index.slice_locs(1, 2) == (0, 2)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_slice_locs_int64(self):
self.slice_locs_cases([0, 1, 2])
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_slice_locs_float64(self):
self.slice_locs_cases([0.0, 1.0, 2.0])
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def slice_locs_decreasing_cases(self, tuples):
index = IntervalIndex.from_tuples(tuples)
assert index.slice_locs(1.5, 0.5) == (1, 3)
assert index.slice_locs(2, 0) == (1, 3)
assert index.slice_locs(2, 1) == (1, 3)
assert index.slice_locs(3, 1.1) == (0, 3)
assert index.slice_locs(3, 3) == (0, 2)
assert index.slice_locs(3.5, 3.3) == (0, 1)
assert index.slice_locs(1, -3) == (2, 3)
slice_locs = index.slice_locs(-1, -1)
assert slice_locs[0] == slice_locs[1]
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_slice_locs_decreasing_int64(self):
self.slice_locs_cases([(2, 4), (1, 3), (0, 2)])
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_slice_locs_decreasing_float64(self):
self.slice_locs_cases([(2., 4.), (1., 3.), (0., 2.)])
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_slice_locs_fails(self):
index = IntervalIndex.from_tuples([(1, 2), (0, 1), (2, 3)])
with pytest.raises(KeyError):
index.slice_locs(1, 2)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_get_loc_interval(self):
assert self.index.get_loc(Interval(0, 1)) == 0
assert self.index.get_loc(Interval(0, 0.5)) == 0
assert self.index.get_loc(Interval(0, 1, 'left')) == 0
pytest.raises(KeyError, self.index.get_loc, Interval(2, 3))
pytest.raises(KeyError, self.index.get_loc, Interval(-1, 0, 'left'))
# Make consistent with test_interval_new.py (see #16316, #16386)
@pytest.mark.parametrize('item', [3, Interval(1, 4)])
def test_get_loc_length_one(self, item, closed):
# GH 20921
index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
result = index.get_loc(item)
assert result == 0
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_get_indexer(self):
actual = self.index.get_indexer([-1, 0, 0.5, 1, 1.5, 2, 3])
expected = np.array([-1, -1, 0, 0, 1, 1, -1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
actual = self.index.get_indexer(self.index)
expected = np.array([0, 1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
index = IntervalIndex.from_breaks([0, 1, 2], closed='left')
actual = index.get_indexer([-1, 0, 0.5, 1, 1.5, 2, 3])
expected = np.array([-1, 0, 0, 1, 1, -1, -1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
actual = self.index.get_indexer(index[:1])
expected = np.array([0], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
actual = self.index.get_indexer(index)
expected = np.array([-1, 1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_get_indexer_subintervals(self):
# TODO: is this right?
# return indexers for wholly contained subintervals
target = IntervalIndex.from_breaks(np.linspace(0, 2, 5))
actual = self.index.get_indexer(target)
expected = np.array([0, 0, 1, 1], dtype='p')
tm.assert_numpy_array_equal(actual, expected)
target = IntervalIndex.from_breaks([0, 0.67, 1.33, 2])
actual = self.index.get_indexer(target)
expected = np.array([0, 0, 1, 1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
actual = self.index.get_indexer(target[[0, -1]])
expected = np.array([0, 1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
target = IntervalIndex.from_breaks([0, 0.33, 0.67, 1], closed='left')
actual = self.index.get_indexer(target)
expected = np.array([0, 0, 0], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
# Make consistent with test_interval_new.py (see #16316, #16386)
@pytest.mark.parametrize(
'item',
[[3], np.arange(1, 5), [Interval(1, 4)],
interval_range(1, 4)])
def test_get_indexer_length_one(self, item, closed):
# GH 17284
index = IntervalIndex.from_tuples([(0, 5)], closed=closed)
result = index.get_indexer(item)
expected = np.array([0] * len(item), dtype='intp')
tm.assert_numpy_array_equal(result, expected)
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def test_contains(self):
# Only endpoints are valid.
i = IntervalIndex.from_arrays([0, 1], [1, 2])
# Invalid
assert 0 not in i
assert 1 not in i
assert 2 not in i
# Valid
assert Interval(0, 1) in i
assert Interval(0, 2) in i
assert Interval(0, 0.5) in i
assert Interval(3, 5) not in i
assert Interval(-1, 0, closed='left') not in i
# To be removed, replaced by test_interval_new.py (see #16316, #16386)
def testcontains(self):
# can select values that are IN the range of a value
i = IntervalIndex.from_arrays([0, 1], [1, 2])
assert i.contains(0.1)
assert i.contains(0.5)
assert i.contains(1)
assert i.contains(Interval(0, 1))
assert i.contains(Interval(0, 2))
# these overlaps completely
assert i.contains(Interval(0, 3))
assert i.contains(Interval(1, 3))
assert not i.contains(20)
assert not i.contains(-20)
def test_dropna(self, closed):
expected = IntervalIndex.from_tuples([(0.0, 1.0), (1.0, 2.0)],
closed=closed)
ii = IntervalIndex.from_tuples([(0, 1), (1, 2), np.nan], closed=closed)
result = ii.dropna()
tm.assert_index_equal(result, expected)
ii = IntervalIndex.from_arrays([0, 1, np.nan], [1, 2, np.nan],
closed=closed)
result = ii.dropna()
tm.assert_index_equal(result, expected)
# TODO: check this behavior is consistent with test_interval_new.py
def test_non_contiguous(self, closed):
index = IntervalIndex.from_tuples([(0, 1), (2, 3)], closed=closed)
target = [0.5, 1.5, 2.5]
actual = index.get_indexer(target)
expected = np.array([0, -1, 1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
assert 1.5 not in index
def test_union(self, closed):
index = self.create_index(closed=closed)
other = IntervalIndex.from_breaks(range(5, 13), closed=closed)
expected = IntervalIndex.from_breaks(range(13), closed=closed)
result = index.union(other)
tm.assert_index_equal(result, expected)
result = other.union(index)
tm.assert_index_equal(result, expected)
tm.assert_index_equal(index.union(index), index)
tm.assert_index_equal(index.union(index[:1]), index)
# GH 19101: empty result, same dtype
index = IntervalIndex(np.array([], dtype='int64'), closed=closed)
result = index.union(index)
tm.assert_index_equal(result, index)
# GH 19101: empty result, different dtypes
other = IntervalIndex(np.array([], dtype='float64'), closed=closed)
result = index.union(other)
tm.assert_index_equal(result, index)
def test_intersection(self, closed):
index = self.create_index(closed=closed)
other = IntervalIndex.from_breaks(range(5, 13), closed=closed)
expected = IntervalIndex.from_breaks(range(5, 11), closed=closed)
result = index.intersection(other)
tm.assert_index_equal(result, expected)
result = other.intersection(index)
tm.assert_index_equal(result, expected)
tm.assert_index_equal(index.intersection(index), index)
# GH 19101: empty result, same dtype
other = IntervalIndex.from_breaks(range(300, 314), closed=closed)
expected = IntervalIndex(np.array([], dtype='int64'), closed=closed)
result = index.intersection(other)
tm.assert_index_equal(result, expected)
# GH 19101: empty result, different dtypes
breaks = np.arange(300, 314, dtype='float64')
other = IntervalIndex.from_breaks(breaks, closed=closed)
result = index.intersection(other)
tm.assert_index_equal(result, expected)
def test_difference(self, closed):
index = self.create_index(closed=closed)
tm.assert_index_equal(index.difference(index[:1]), index[1:])
# GH 19101: empty result, same dtype
result = index.difference(index)
expected = IntervalIndex(np.array([], dtype='int64'), closed=closed)
tm.assert_index_equal(result, expected)
# GH 19101: empty result, different dtypes
other = IntervalIndex.from_arrays(index.left.astype('float64'),
index.right,
closed=closed)
result = index.difference(other)
tm.assert_index_equal(result, expected)
def test_symmetric_difference(self, closed):
index = self.create_index(closed=closed)
result = index[1:].symmetric_difference(index[:-1])
expected = IntervalIndex([index[0], index[-1]])
tm.assert_index_equal(result, expected)
# GH 19101: empty result, same dtype
result = index.symmetric_difference(index)
expected = IntervalIndex(np.array([], dtype='int64'), closed=closed)
tm.assert_index_equal(result, expected)
# GH 19101: empty result, different dtypes
other = IntervalIndex.from_arrays(index.left.astype('float64'),
index.right,
closed=closed)
result = index.symmetric_difference(other)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize(
'op_name',
['union', 'intersection', 'difference', 'symmetric_difference'])
def test_set_operation_errors(self, closed, op_name):
index = self.create_index(closed=closed)
set_op = getattr(index, op_name)
# non-IntervalIndex
msg = ('the other index needs to be an IntervalIndex too, but '
'was type Int64Index')
with tm.assert_raises_regex(TypeError, msg):
set_op(Index([1, 2, 3]))
# mixed closed
msg = ('can only do set operations between two IntervalIndex objects '
'that are closed on the same side')
for other_closed in {'right', 'left', 'both', 'neither'} - {closed}:
other = self.create_index(closed=other_closed)
with tm.assert_raises_regex(ValueError, msg):
set_op(other)
# GH 19016: incompatible dtypes
other = interval_range(Timestamp('20180101'), periods=9, closed=closed)
msg = ('can only do {op} between two IntervalIndex objects that have '
'compatible dtypes').format(op=op_name)
with tm.assert_raises_regex(TypeError, msg):
set_op(other)
def test_isin(self, closed):
index = self.create_index(closed=closed)
expected = np.array([True] + [False] * (len(index) - 1))
result = index.isin(index[:1])
tm.assert_numpy_array_equal(result, expected)
result = index.isin([index[0]])
tm.assert_numpy_array_equal(result, expected)
other = IntervalIndex.from_breaks(np.arange(-2, 10), closed=closed)
expected = np.array([True] * (len(index) - 1) + [False])
result = index.isin(other)
tm.assert_numpy_array_equal(result, expected)
result = index.isin(other.tolist())
tm.assert_numpy_array_equal(result, expected)
for other_closed in {'right', 'left', 'both', 'neither'}:
other = self.create_index(closed=other_closed)
expected = np.repeat(closed == other_closed, len(index))
result = index.isin(other)
tm.assert_numpy_array_equal(result, expected)
result = index.isin(other.tolist())
tm.assert_numpy_array_equal(result, expected)
def test_comparison(self):
actual = Interval(0, 1) < self.index
expected = np.array([False, True])
tm.assert_numpy_array_equal(actual, expected)
actual = Interval(0.5, 1.5) < self.index
expected = np.array([False, True])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index > Interval(0.5, 1.5)
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == self.index
expected = np.array([True, True])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index <= self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index >= self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index < self.index
expected = np.array([False, False])
tm.assert_numpy_array_equal(actual, expected)
actual = self.index > self.index
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == IntervalIndex.from_breaks([0, 1, 2], 'left')
tm.assert_numpy_array_equal(actual, expected)
actual = self.index == self.index.values
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index.values == self.index
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index <= self.index.values
tm.assert_numpy_array_equal(actual, np.array([True, True]))
actual = self.index != self.index.values
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index > self.index.values
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index.values > self.index
tm.assert_numpy_array_equal(actual, np.array([False, False]))
# invalid comparisons
actual = self.index == 0
tm.assert_numpy_array_equal(actual, np.array([False, False]))
actual = self.index == self.index.left
tm.assert_numpy_array_equal(actual, np.array([False, False]))
with tm.assert_raises_regex(TypeError, 'unorderable types'):
self.index > 0
with tm.assert_raises_regex(TypeError, 'unorderable types'):
self.index <= 0
with pytest.raises(TypeError):
self.index > np.arange(2)
with pytest.raises(ValueError):
self.index > np.arange(3)
def test_missing_values(self, closed):
idx = Index([
np.nan,
Interval(0, 1, closed=closed),
Interval(1, 2, closed=closed)
])
idx2 = IntervalIndex.from_arrays([np.nan, 0, 1], [np.nan, 1, 2],
closed=closed)
assert idx.equals(idx2)
with pytest.raises(ValueError):
IntervalIndex.from_arrays([np.nan, 0, 1],
np.array([0, 1, 2]),
closed=closed)
tm.assert_numpy_array_equal(isna(idx), np.array([True, False, False]))
def test_sort_values(self, closed):
index = self.create_index(closed=closed)
result = index.sort_values()
tm.assert_index_equal(result, index)
result = index.sort_values(ascending=False)
tm.assert_index_equal(result, index[::-1])
# with nan
index = IntervalIndex([Interval(1, 2), np.nan, Interval(0, 1)])
result = index.sort_values()
expected = IntervalIndex([Interval(0, 1), Interval(1, 2), np.nan])
tm.assert_index_equal(result, expected)
result = index.sort_values(ascending=False)
expected = IntervalIndex([np.nan, Interval(1, 2), Interval(0, 1)])
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('tz', [None, 'US/Eastern'])
def test_datetime(self, tz):
start = Timestamp('2000-01-01', tz=tz)
dates = date_range(start=start, periods=10)
index = IntervalIndex.from_breaks(dates)
# test mid
start = Timestamp('2000-01-01T12:00', tz=tz)
expected = date_range(start=start, periods=9)
tm.assert_index_equal(index.mid, expected)
# __contains__ doesn't check individual points
assert Timestamp('2000-01-01', tz=tz) not in index
assert Timestamp('2000-01-01T12', tz=tz) not in index
assert Timestamp('2000-01-02', tz=tz) not in index
iv_true = Interval(Timestamp('2000-01-01T08', tz=tz),
Timestamp('2000-01-01T18', tz=tz))
iv_false = Interval(Timestamp('1999-12-31', tz=tz),
Timestamp('2000-01-01', tz=tz))
assert iv_true in index
assert iv_false not in index
# .contains does check individual points
assert not index.contains(Timestamp('2000-01-01', tz=tz))
assert index.contains(Timestamp('2000-01-01T12', tz=tz))
assert index.contains(Timestamp('2000-01-02', tz=tz))
assert index.contains(iv_true)
assert not index.contains(iv_false)
# test get_indexer
start = Timestamp('1999-12-31T12:00', tz=tz)
target = date_range(start=start, periods=7, freq='12H')
actual = index.get_indexer(target)
expected = np.array([-1, -1, 0, 0, 1, 1, 2], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
start = Timestamp('2000-01-08T18:00', tz=tz)
target = date_range(start=start, periods=7, freq='6H')
actual = index.get_indexer(target)
expected = np.array([7, 7, 8, 8, 8, 8, -1], dtype='intp')
tm.assert_numpy_array_equal(actual, expected)
def test_append(self, closed):
index1 = IntervalIndex.from_arrays([0, 1], [1, 2], closed=closed)
index2 = IntervalIndex.from_arrays([1, 2], [2, 3], closed=closed)
result = index1.append(index2)
expected = IntervalIndex.from_arrays([0, 1, 1, 2], [1, 2, 2, 3],
closed=closed)
tm.assert_index_equal(result, expected)
result = index1.append([index1, index2])
expected = IntervalIndex.from_arrays([0, 1, 0, 1, 1, 2],
[1, 2, 1, 2, 2, 3],
closed=closed)
tm.assert_index_equal(result, expected)
msg = ('can only append two IntervalIndex objects that are closed '
'on the same side')
for other_closed in {'left', 'right', 'both', 'neither'} - {closed}:
index_other_closed = IntervalIndex.from_arrays([0, 1], [1, 2],
closed=other_closed)
with tm.assert_raises_regex(ValueError, msg):
index1.append(index_other_closed)
def test_is_non_overlapping_monotonic(self, closed):
# Should be True in all cases
tpls = [(0, 1), (2, 3), (4, 5), (6, 7)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is True
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is True
# Should be False in all cases (overlapping)
tpls = [(0, 2), (1, 3), (4, 5), (6, 7)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is False
# Should be False in all cases (non-monotonic)
tpls = [(0, 1), (2, 3), (6, 7), (4, 5)]
idx = IntervalIndex.from_tuples(tpls, closed=closed)
assert idx.is_non_overlapping_monotonic is False
idx = IntervalIndex.from_tuples(tpls[::-1], closed=closed)
assert idx.is_non_overlapping_monotonic is False
# Should be False for closed='both', otherwise True (GH16560)
if closed == 'both':
idx = IntervalIndex.from_breaks(range(4), closed=closed)
assert idx.is_non_overlapping_monotonic is False
else:
idx = IntervalIndex.from_breaks(range(4), closed=closed)
assert idx.is_non_overlapping_monotonic is True
@pytest.mark.parametrize('tuples', [
lzip(range(10), range(1, 11)),
lzip(date_range('20170101', periods=10),
date_range('20170101', periods=10)),
lzip(timedelta_range('0 days', periods=10),
timedelta_range('1 day', periods=10))
])
def test_to_tuples(self, tuples):
# GH 18756
idx = IntervalIndex.from_tuples(tuples)
result = idx.to_tuples()
expected = Index(com._asarray_tuplesafe(tuples))
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('tuples', [
lzip(range(10), range(1, 11)) + [np.nan],
lzip(date_range('20170101', periods=10),
date_range('20170101', periods=10)) + [np.nan],
lzip(timedelta_range('0 days', periods=10),
timedelta_range('1 day', periods=10)) + [np.nan]
])
@pytest.mark.parametrize('na_tuple', [True, False])
def test_to_tuples_na(self, tuples, na_tuple):
# GH 18756
idx = IntervalIndex.from_tuples(tuples)
result = idx.to_tuples(na_tuple=na_tuple)
# check the non-NA portion
expected_notna = Index(com._asarray_tuplesafe(tuples[:-1]))
result_notna = result[:-1]
tm.assert_index_equal(result_notna, expected_notna)
# check the NA portion
result_na = result[-1]
if na_tuple:
assert isinstance(result_na, tuple)
assert len(result_na) == 2
assert all(isna(x) for x in result_na)
else:
assert isna(result_na)
@pytest.mark.parametrize('new_closed',
['left', 'right', 'both', 'neither'])
def test_set_closed(self, name, closed, new_closed):
# GH 21670
index = interval_range(0, 5, closed=closed, name=name)
result = index.set_closed(new_closed)
expected = interval_range(0, 5, closed=new_closed, name=name)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize('bad_closed', ['foo', 10, 'LEFT', True, False])
def test_set_closed_errors(self, bad_closed):
# GH 21670
index = interval_range(0, 5)
msg = "invalid option for 'closed': {closed}".format(closed=bad_closed)
with tm.assert_raises_regex(ValueError, msg):
index.set_closed(bad_closed)
import pandas.util.testing as tm
@pytest.fixture(params=[tm.makeUnicodeIndex(100),
tm.makeStringIndex(100),
tm.makeDateIndex(100),
tm.makePeriodIndex(100),
tm.makeTimedeltaIndex(100),
tm.makeIntIndex(100),
tm.makeUIntIndex(100),
tm.makeRangeIndex(100),
tm.makeFloatIndex(100),
Index([True, False]),
tm.makeCategoricalIndex(100),
Index([]),
MultiIndex.from_tuples(lzip(
['foo', 'bar', 'baz'], [1, 2, 3])),
Index([0, 0, 1, 1, 2, 2])],
ids=lambda x: type(x).__name__)
def indices(request):
return request.param
@pytest.fixture(params=[1, np.array(1, dtype=np.int64)])
def one(request):
# zero-dim integer array behaves like an integer
return request.param
zeros = [box([0] * 5, dtype=dtype)
for box in [pd.Index, np.array]
for dtype in [np.int64, np.uint64, np.float64]]
def _make_concat_multiindex(indexes, keys, levels=None, names=None):
if ((levels is None and isinstance(keys[0], tuple)) or
(levels is not None and len(levels) > 1)):
zipped = lzip(*keys)
if names is None:
names = [None] * len(zipped)
if levels is None:
levels = [Categorical.from_array(
zp, ordered=True).categories for zp in zipped]
else:
levels = [_ensure_index(x) for x in levels]
else:
zipped = [keys]
if names is None:
names = [None]
if levels is None:
levels = [_ensure_index(keys)]
else:
levels = [_ensure_index(x) for x in levels]
if not _all_indexes_same(indexes):
label_list = []
# things are potentially different sizes, so compute the exact labels
# for each level and pass those to MultiIndex.from_arrays
for hlevel, level in zip(zipped, levels):
to_concat = []
for key, index in zip(hlevel, indexes):
try:
i = level.get_loc(key)
except KeyError:
raise ValueError('Key %s not in level %s'
% (str(key), str(level)))
to_concat.append(np.repeat(i, len(index)))
label_list.append(np.concatenate(to_concat))
concat_index = _concat_indexes(indexes)
# these go at the end
if isinstance(concat_index, MultiIndex):
levels.extend(concat_index.levels)
label_list.extend(concat_index.labels)
else:
factor = Categorical.from_array(concat_index, ordered=True)
levels.append(factor.categories)
label_list.append(factor.codes)
if len(names) == len(levels):
names = list(names)
else:
# make sure that all of the passed indices have the same nlevels
if not len(set([idx.nlevels for idx in indexes])) == 1:
raise AssertionError("Cannot concat indices that do"
" not have the same number of levels")
# also copies
names = names + _get_consensus_names(indexes)
return MultiIndex(levels=levels, labels=label_list, names=names,
verify_integrity=False)
new_index = indexes[0]
n = len(new_index)
kpieces = len(indexes)
# also copies
new_names = list(names)
new_levels = list(levels)
# construct labels
new_labels = []
# do something a bit more speedy
for hlevel, level in zip(zipped, levels):
hlevel = _ensure_index(hlevel)
mapped = level.get_indexer(hlevel)
mask = mapped == -1
if mask.any():
raise ValueError('Values not found in passed level: %s'
% str(hlevel[mask]))
new_labels.append(np.repeat(mapped, n))
if isinstance(new_index, MultiIndex):
new_levels.extend(new_index.levels)
new_labels.extend([np.tile(lab, kpieces) for lab in new_index.labels])
else:
new_levels.append(new_index)
new_labels.append(np.tile(np.arange(n), kpieces))
if len(new_names) < len(new_levels):
new_names.extend(new_index.names)
return MultiIndex(levels=new_levels, labels=new_labels, names=new_names,
verify_integrity=False)
class TestSeriesMisc(TestData, SharedWithSparse):
series_klass = Series
# SharedWithSparse tests use generic, series_klass-agnostic assertion
_assert_series_equal = staticmethod(tm.assert_series_equal)
def test_tab_completion(self):
# GH 9910
s = Series(list('abcd'))
# Series of str values should have .str but not .dt/.cat in __dir__
assert 'str' in dir(s)
assert 'dt' not in dir(s)
assert 'cat' not in dir(s)
# similarly for .dt
s = Series(date_range('1/1/2015', periods=5))
assert 'dt' in dir(s)
assert 'str' not in dir(s)
assert 'cat' not in dir(s)
# Similarly for .cat, but with the twist that str and dt should be
# there if the categories are of that type first cat and str.
s = Series(list('abbcd'), dtype="category")
assert 'cat' in dir(s)
assert 'str' in dir(s) # as it is a string categorical
assert 'dt' not in dir(s)
# similar to cat and str
s = Series(date_range('1/1/2015', periods=5)).astype("category")
assert 'cat' in dir(s)
assert 'str' not in dir(s)
assert 'dt' in dir(s) # as it is a datetime categorical
def test_tab_completion_with_categorical(self):
# test the tab completion display
ok_for_cat = [
'name', 'index', 'categorical', 'categories', 'codes', 'ordered',
'set_categories', 'add_categories', 'remove_categories',
'rename_categories', 'reorder_categories',
'remove_unused_categories', 'as_ordered', 'as_unordered'
]
def get_dir(s):
results = [r for r in s.cat.__dir__() if not r.startswith('_')]
return list(sorted(set(results)))
s = Series(list('aabbcde')).astype('category')
results = get_dir(s)
tm.assert_almost_equal(results, list(sorted(set(ok_for_cat))))
@pytest.mark.parametrize("index", [
tm.makeUnicodeIndex(10),
tm.makeStringIndex(10),
tm.makeCategoricalIndex(10),
Index(['foo', 'bar', 'baz'] * 2),
tm.makeDateIndex(10),
tm.makePeriodIndex(10),
tm.makeTimedeltaIndex(10),
tm.makeIntIndex(10),
tm.makeUIntIndex(10),
tm.makeIntIndex(10),
tm.makeFloatIndex(10),
Index([True, False]),
Index(['a{}'.format(i) for i in range(101)]),
pd.MultiIndex.from_tuples(lzip('ABCD', 'EFGH')),
pd.MultiIndex.from_tuples(lzip([0, 1, 2, 3], 'EFGH')),
])
def test_index_tab_completion(self, index):
# dir contains string-like values of the Index.
s = pd.Series(index=index)
dir_s = dir(s)
for i, x in enumerate(s.index.unique(level=0)):
if i < 100:
assert (not isinstance(x, str) or not x.isidentifier()
or x in dir_s)
else:
assert x not in dir_s
def test_not_hashable(self):
s_empty = Series()
s = Series([1])
msg = "'Series' objects are mutable, thus they cannot be hashed"
with pytest.raises(TypeError, match=msg):
hash(s_empty)
with pytest.raises(TypeError, match=msg):
hash(s)
def test_contains(self):
tm.assert_contains_all(self.ts.index, self.ts)
def test_iter(self):
for i, val in enumerate(self.series):
assert val == self.series[i]
for i, val in enumerate(self.ts):
assert val == self.ts[i]
def test_keys(self):
# HACK: By doing this in two stages, we avoid 2to3 wrapping the call
# to .keys() in a list()
getkeys = self.ts.keys
assert getkeys() is self.ts.index
def test_values(self):
tm.assert_almost_equal(self.ts.values, self.ts, check_dtype=False)
def test_iteritems(self):
for idx, val in self.series.items():
assert val == self.series[idx]
for idx, val in self.ts.items():
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.iteritems(), 'reverse')
def test_items(self):
for idx, val in self.series.items():
assert val == self.series[idx]
for idx, val in self.ts.items():
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.items(), 'reverse')
def test_raise_on_info(self):
s = Series(np.random.randn(10))
msg = "'Series' object has no attribute 'info'"
with pytest.raises(AttributeError, match=msg):
s.info()
def test_copy(self):
for deep in [None, False, True]:
s = Series(np.arange(10), dtype='float64')
# default deep is True
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[::2] = np.NaN
if deep is None or deep is True:
# Did not modify original Series
assert np.isnan(s2[0])
assert not np.isnan(s[0])
else:
# we DID modify the original Series
assert np.isnan(s2[0])
assert np.isnan(s[0])
# GH 11794
# copy of tz-aware
expected = Series([Timestamp('2012/01/01', tz='UTC')])
expected2 = Series([Timestamp('1999/01/01', tz='UTC')])
for deep in [None, False, True]:
s = Series([Timestamp('2012/01/01', tz='UTC')])
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[0] = pd.Timestamp('1999/01/01', tz='UTC')
# default deep is True
if deep is None or deep is True:
# Did not modify original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected)
else:
# we DID modify the original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected2)
def test_axis_alias(self):
s = Series([1, 2, np.nan])
assert_series_equal(s.dropna(axis='rows'), s.dropna(axis='index'))
assert s.dropna().sum('rows') == 3
assert s._get_axis_number('rows') == 0
assert s._get_axis_name('rows') == 'index'
def test_class_axis(self):
# https://github.com/pandas-dev/pandas/issues/18147
# no exception and no empty docstring
assert pydoc.getdoc(Series.index)
def test_numpy_unique(self):
# it works!
np.unique(self.ts)
def test_ndarray_compat(self):
# test numpy compat with Series as sub-class of NDFrame
tsdf = DataFrame(np.random.randn(1000, 3),
columns=['A', 'B', 'C'],
index=date_range('1/1/2000', periods=1000))
def f(x):
return x[x.idxmax()]
result = tsdf.apply(f)
expected = tsdf.max()
tm.assert_series_equal(result, expected)
# .item()
s = Series([1])
result = s.item()
assert result == 1
assert s.item() == s.iloc[0]
# using an ndarray like function
s = Series(np.random.randn(10))
result = Series(np.ones_like(s))
expected = Series(1, index=range(10), dtype='float64')
tm.assert_series_equal(result, expected)
# ravel
s = Series(np.random.randn(10))
tm.assert_almost_equal(s.ravel(order='F'), s.values.ravel(order='F'))
# compress
# GH 6658
s = Series([0, 1., -1], index=list('abc'))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.], index=['b']))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Index(dtype=object) as the same as original
exp = Series([], dtype='float64', index=Index([], dtype='object'))
tm.assert_series_equal(result, exp)
s = Series([0, 1., -1], index=[.1, .2, .3])
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.], index=[.2]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Float64Index as the same as original
exp = Series([], dtype='float64', index=Index([], dtype='float64'))
tm.assert_series_equal(result, exp)
def test_str_accessor_updates_on_inplace(self):
s = pd.Series(list('abc'))
s.drop([0], inplace=True)
assert len(s.str.lower()) == 2
def test_str_attribute(self):
# GH9068
methods = ['strip', 'rstrip', 'lstrip']
s = Series([' jack', 'jill ', ' jesse ', 'frank'])
for method in methods:
expected = Series([getattr(str, method)(x) for x in s.values])
assert_series_equal(getattr(Series.str, method)(s.str), expected)
# str accessor only valid with string values
s = Series(range(5))
with pytest.raises(AttributeError, match='only use .str accessor'):
s.str.repeat(2)
def test_empty_method(self):
s_empty = pd.Series()
assert s_empty.empty
for full_series in [pd.Series([1]), pd.Series(index=[1])]:
assert not full_series.empty
def test_tab_complete_warning(self, ip):
# https://github.com/pandas-dev/pandas/issues/16409
pytest.importorskip('IPython', minversion="6.0.0")
from IPython.core.completer import provisionalcompleter
code = "import pandas as pd; s = pd.Series()"
ip.run_code(code)
with tm.assert_produces_warning(None):
with provisionalcompleter('ignore'):
list(ip.Completer.completions('s.', 1))
def test_integer_series_size(self):
# GH 25580
s = Series(range(9))
assert s.size == 9
s = Series(range(9), dtype="Int64")
assert s.size == 9
def test_zip(self):
lst = [builtins.range(10), builtins.range(10), builtins.range(10)]
actual = [zip(*lst), lzip(*lst)],
expected = list(builtins.zip(*lst)),
lengths = 10,
self.check_result(actual, expected, lengths)
def test_zip(self):
lst = [builtins.range(10), builtins.range(10), builtins.range(10)]
actual = [zip(*lst), lzip(*lst)],
expected = list(builtins.zip(*lst)),
lengths = 10,
self.check_result(actual, expected, lengths)
def _translate(self):
"""
Convert the DataFrame in `self.data` and the attrs from `_build_styles`
into a dictionary of {head, body, uuid, cellstyle}
"""
table_styles = self.table_styles or []
caption = self.caption
ctx = self.ctx
precision = self.precision
uuid = self.uuid or str(uuid1()).replace("-", "_")
ROW_HEADING_CLASS = "row_heading"
COL_HEADING_CLASS = "col_heading"
DATA_CLASS = "data"
BLANK_CLASS = "blank"
BLANK_VALUE = ""
cell_context = dict()
n_rlvls = self.data.index.nlevels
n_clvls = self.data.columns.nlevels
rlabels = self.data.index.tolist()
clabels = self.data.columns.tolist()
idx_values = self.data.index.format(sparsify=False,
adjoin=False,
names=False)
idx_values = lzip(*idx_values)
if n_rlvls == 1:
rlabels = [[x] for x in rlabels]
if n_clvls == 1:
clabels = [[x] for x in clabels]
clabels = list(zip(*clabels))
cellstyle = []
head = []
for r in range(n_clvls):
row_es = [{
"type": "th",
"value": BLANK_VALUE,
"class": " ".join([BLANK_CLASS])
}] * n_rlvls
for c in range(len(clabels[0])):
cs = [COL_HEADING_CLASS, "level%s" % r, "col%s" % c]
cs.extend(
cell_context.get("col_headings", {}).get(r, {}).get(c, []))
row_es.append({
"type": "th",
"value": clabels[r][c],
"class": " ".join(cs)
})
head.append(row_es)
if self.data.index.names:
index_header_row = []
for c, name in enumerate(self.data.index.names):
cs = [
COL_HEADING_CLASS,
"level%s" % (n_clvls + 1),
"col%s" % c
]
index_header_row.append({
"type": "th",
"value": name,
"class": " ".join(cs)
})
index_header_row.extend([{
"type": "th",
"value": BLANK_VALUE,
"class": " ".join([BLANK_CLASS])
}] * len(clabels[0]))
head.append(index_header_row)
body = []
for r, idx in enumerate(self.data.index):
cs = [ROW_HEADING_CLASS, "level%s" % c, "row%s" % r]
cs.extend(
cell_context.get("row_headings", {}).get(r, {}).get(c, []))
row_es = [{
"type": "th",
"value": rlabels[r][c],
"class": " ".join(cs)
} for c in range(len(rlabels[r]))]
for c, col in enumerate(self.data.columns):
cs = [DATA_CLASS, "row%s" % r, "col%s" % c]
cs.extend(cell_context.get("data", {}).get(r, {}).get(c, []))
row_es.append({
"type": "td",
"value": self.data.iloc[r][c],
"class": " ".join(cs),
"id": "_".join(cs[1:])
})
props = []
for x in ctx[r, c]:
# have to handle empty styles like ['']
if x.count(":"):
props.append(x.split(":"))
else:
props.append(['', ''])
cellstyle.append({
'props': props,
'selector': "row%s_col%s" % (r, c)
})
body.append(row_es)
return dict(head=head,
cellstyle=cellstyle,
body=body,
uuid=uuid,
precision=precision,
table_styles=table_styles,
caption=caption,
table_attributes=self.table_attributes)
def _zip2(*args):
return lib.list_to_object_array(lzip(*args))
def _zip(*args):
arr = np.empty(N, dtype=object)
arr[:] = lzip(*args)
return arr
from pandas import *
import numpy as np
from pandas.compat import zip, range, lzip
from pandas.util.testing import rands
import pandas.lib as lib
N = 100000
key1 = [rands(10) for _ in range(N)]
key2 = [rands(10) for _ in range(N)]
zipped = lzip(key1, key2)
def _zip(*args):
arr = np.empty(N, dtype=object)
arr[:] = lzip(*args)
return arr
def _zip2(*args):
return lib.list_to_object_array(lzip(*args))
index = MultiIndex.from_arrays([key1, key2])
to_join = DataFrame({'j1': np.random.randn(100000)}, index=index)
data = DataFrame({
'A': np.random.randn(500000),
'key1': np.repeat(key1, 5),
def test_lzip(self):
lst = [builtins.range(10), builtins.range(10), builtins.range(10)]
results = lzip(*lst),
expecteds = list(builtins.zip(*lst)),
lengths = 10,
self.check_results(results, expecteds, lengths)