class IndexAppend(object):
goal_time = 0.2
def setup(self):
N = 10000
self.range_idx = RangeIndex(0, 100)
self.int_idx = self.range_idx.astype(int)
self.obj_idx = self.int_idx.astype(str)
self.range_idxs = []
self.int_idxs = []
self.object_idxs = []
for i in range(1, N):
r_idx = RangeIndex(i * 100, (i + 1) * 100)
self.range_idxs.append(r_idx)
i_idx = r_idx.astype(int)
self.int_idxs.append(i_idx)
o_idx = i_idx.astype(str)
self.object_idxs.append(o_idx)
def time_append_range_list(self):
self.range_idx.append(self.range_idxs)
def time_append_int_list(self):
self.int_idx.append(self.int_idxs)
def time_append_obj_list(self):
self.obj_idx.append(self.object_idxs)
def test_copy(self):
i = RangeIndex(5, name='Foo')
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._range == range(0, 5, 1)
assert i_copy.name == 'Foo'
def test_constructor_range(self):
self.assertRaises(TypeError, lambda: RangeIndex(range(1, 5, 2)))
result = RangeIndex.from_range(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
self.assertTrue(result.equals(expected))
result = RangeIndex.from_range(range(5, 6))
expected = RangeIndex(5, 6, 1)
self.assertTrue(result.equals(expected))
# an invalid range
result = RangeIndex.from_range(range(5, 1))
expected = RangeIndex(0, 0, 1)
self.assertTrue(result.equals(expected))
result = RangeIndex.from_range(range(5))
expected = RangeIndex(0, 5, 1)
self.assertTrue(result.equals(expected))
result = Index(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
self.assertTrue(result.equals(expected))
self.assertRaises(TypeError,
lambda: Index(range(1, 5, 2), dtype='float64'))
def test_constructor_range(self):
pytest.raises(TypeError, lambda: RangeIndex(range(1, 5, 2)))
result = RangeIndex.from_range(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5, 6))
expected = RangeIndex(5, 6, 1)
tm.assert_index_equal(result, expected, exact=True)
# an invalid range
result = RangeIndex.from_range(range(5, 1))
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5))
expected = RangeIndex(0, 5, 1)
tm.assert_index_equal(result, expected, exact=True)
result = Index(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
pytest.raises(TypeError,
lambda: Index(range(1, 5, 2), dtype='float64'))
def test_copy(self):
i = RangeIndex(5, name='Foo')
i_copy = i.copy()
self.assertTrue(i_copy is not i)
self.assertTrue(i_copy.identical(i))
self.assertEqual(i_copy._start, 0)
self.assertEqual(i_copy._stop, 5)
self.assertEqual(i_copy._step, 1)
self.assertEqual(i_copy.name, 'Foo')
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
self.assertTrue(i.nbytes < i.astype(int).nbytes / 10)
# constant memory usage
i2 = RangeIndex(0, 10)
self.assertEqual(i.nbytes, i2.nbytes)
def test_copy(self):
i = RangeIndex(5, name='Foo')
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._start == 0
assert i_copy._stop == 5
assert i_copy._step == 1
assert i_copy.name == 'Foo'
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
assert i.nbytes < i.astype(int).nbytes / 10
# constant memory usage
i2 = RangeIndex(0, 10)
assert i.nbytes == i2.nbytes
def test_view(self):
i = RangeIndex(0, name='Foo')
i_view = i.view()
assert i_view.name == 'Foo'
i_view = i.view('i8')
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_view(self):
super(TestRangeIndex, self).test_view()
i = RangeIndex(0, name='Foo')
i_view = i.view()
self.assertEqual(i_view.name, 'Foo')
i_view = i.view('i8')
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_view(self, indices):
super(TestRangeIndex, self).test_view(indices)
i = RangeIndex(0, name='Foo')
i_view = i.view()
assert i_view.name == 'Foo'
i_view = i.view('i8')
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_constructor_corner(self):
arr = np.array([1, 2, 3, 4], dtype=object)
index = RangeIndex(1, 5)
self.assertEqual(index.values.dtype, np.int64)
self.assertTrue(index.equals(arr))
# non-int raise Exception
self.assertRaises(TypeError, RangeIndex, '1', '10', '1')
self.assertRaises(TypeError, RangeIndex, 1.1, 10.2, 1.3)
# invalid passed type
self.assertRaises(TypeError, lambda: RangeIndex(1, 5, dtype='float64'))
def test_constructor_same(self):
# pass thru w and w/o copy
index = RangeIndex(1, 5, 2)
result = RangeIndex(index, copy=False)
assert result.identical(index)
result = RangeIndex(index, copy=True)
tm.assert_index_equal(result, index, exact=True)
result = RangeIndex(index)
tm.assert_index_equal(result, index, exact=True)
pytest.raises(TypeError,
lambda: RangeIndex(index, dtype='float64'))
def test_delete(self):
idx = RangeIndex(5, name='Foo')
expected = idx[1:].astype(int)
result = idx.delete(0)
self.assertTrue(result.equals(expected))
self.assertEqual(result.name, expected.name)
expected = idx[:-1].astype(int)
result = idx.delete(-1)
self.assertTrue(result.equals(expected))
self.assertEqual(result.name, expected.name)
with tm.assertRaises((IndexError, ValueError)):
# either depending on numpy version
result = idx.delete(len(idx))
def setup(self):
N = 10000
self.range_idx = RangeIndex(0, 100)
self.int_idx = self.range_idx.astype(int)
self.obj_idx = self.int_idx.astype(str)
self.range_idxs = []
self.int_idxs = []
self.object_idxs = []
for i in range(1, N):
r_idx = RangeIndex(i * 100, (i + 1) * 100)
self.range_idxs.append(r_idx)
i_idx = r_idx.astype(int)
self.int_idxs.append(i_idx)
o_idx = i_idx.astype(str)
self.object_idxs.append(o_idx)
def test_delete(self):
idx = RangeIndex(5, name='Foo')
expected = idx[1:].astype(int)
result = idx.delete(0)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
expected = idx[:-1].astype(int)
result = idx.delete(-1)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
with pytest.raises((IndexError, ValueError)):
# either depending on numpy version
result = idx.delete(len(idx))
def test_constructor_name(self):
# GH12288
orig = RangeIndex(10)
orig.name = 'original'
copy = RangeIndex(orig)
copy.name = 'copy'
self.assertTrue(orig.name, 'original')
self.assertTrue(copy.name, 'copy')
new = Index(copy)
self.assertTrue(new.name, 'copy')
new.name = 'new'
self.assertTrue(orig.name, 'original')
self.assertTrue(new.name, 'copy')
self.assertTrue(new.name, 'new')
def test_constructor_name(self):
# GH12288
orig = RangeIndex(10)
orig.name = 'original'
copy = RangeIndex(orig)
copy.name = 'copy'
assert orig.name == 'original'
assert copy.name == 'copy'
new = Index(copy)
assert new.name == 'copy'
new.name = 'new'
assert orig.name == 'original'
assert copy.name == 'copy'
assert new.name == 'new'
def to_parquet(df, path, engine='auto', compression='snappy', **kwargs):
"""
Write a DataFrame to the parquet format.
Parameters
----------
df : DataFrame
path : string
File path
engine : {'auto', 'pyarrow', 'fastparquet'}, default 'auto'
Parquet reader library to use. If 'auto', then the option
'io.parquet.engine' is used. If 'auto', then the first
library to be installed is used.
compression : str, optional, default 'snappy'
compression method, includes {'gzip', 'snappy', 'brotli'}
kwargs
Additional keyword arguments passed to the engine
"""
impl = get_engine(engine)
if not isinstance(df, DataFrame):
raise ValueError("to_parquet only support IO with DataFrames")
valid_types = {'string', 'unicode'}
# validate index
# --------------
# validate that we have only a default index
# raise on anything else as we don't serialize the index
if not isinstance(df.index, Int64Index):
raise ValueError("parquet does not support serializing {} "
"for the index; you can .reset_index()"
"to make the index into column(s)".format(
type(df.index)))
if not df.index.equals(RangeIndex.from_range(range(len(df)))):
raise ValueError("parquet does not support serializing a "
"non-default index for the index; you "
"can .reset_index() to make the index "
"into column(s)")
if df.index.name is not None:
raise ValueError("parquet does not serialize index meta-data on a "
"default index")
# validate columns
# ----------------
# must have value column names (strings only)
if df.columns.inferred_type not in valid_types:
raise ValueError("parquet must have string column names")
return impl.write(df, path, compression=compression, **kwargs)
class Range:
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
def time_max(self):
self.idx_inc.max()
def time_max_trivial(self):
self.idx_dec.max()
def time_min(self):
self.idx_dec.min()
def time_min_trivial(self):
self.idx_inc.min()
def to_feather(df, path):
"""
Write a DataFrame to the feather-format
Parameters
----------
df : DataFrame
path : string
File path
"""
path = _stringify_path(path)
if not isinstance(df, DataFrame):
raise ValueError("feather only support IO with DataFrames")
feather = _try_import()
valid_types = {'string', 'unicode'}
# validate index
# --------------
# validate that we have only a default index
# raise on anything else as we don't serialize the index
if not isinstance(df.index, Int64Index):
raise ValueError("feather does not support serializing {} "
"for the index; you can .reset_index()"
"to make the index into column(s)".format(
type(df.index)))
if not df.index.equals(RangeIndex.from_range(range(len(df)))):
raise ValueError("feather does not support serializing a "
"non-default index for the index; you "
"can .reset_index() to make the index "
"into column(s)")
if df.index.name is not None:
raise ValueError("feather does not serialize index meta-data on a "
"default index")
# validate columns
# ----------------
# must have value column names (strings only)
if df.columns.inferred_type not in valid_types:
raise ValueError("feather must have string column names")
feather.write_dataframe(df, path)
def test_intersection(self):
# intersect with Int64Index
other = Index(np.arange(1, 6))
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(self.index)
expected = Index(np.sort(np.asarray(np.intersect1d(self.index.values,
other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = self.index.intersection(other)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def test_max_min(self, start, stop, step):
# GH17607
idx = RangeIndex(start, stop, step)
expected = idx._int64index.max()
result = idx.max()
assert result == expected
expected = idx._int64index.min()
result = idx.min()
assert result == expected
# empty
idx = RangeIndex(start, stop, -step)
assert isna(idx.max())
assert isna(idx.min())
def test_constructor_same(self):
# pass thru w and w/o copy
index = RangeIndex(1, 5, 2)
result = RangeIndex(index, copy=False)
self.assertTrue(result.identical(index))
result = RangeIndex(index, copy=True)
self.assertTrue(result.equals(index))
result = RangeIndex(index)
self.assertTrue(result.equals(index))
self.assertRaises(TypeError,
lambda: RangeIndex(index, dtype='float64'))
def test_max_min_range(self, start, stop, step):
# GH#17607
idx = RangeIndex(start, stop, step)
expected = idx._int64index.max()
result = idx.max()
assert result == expected
# skipna should be irrelevant since RangeIndex should never have NAs
result2 = idx.max(skipna=False)
assert result2 == expected
expected = idx._int64index.min()
result = idx.min()
assert result == expected
# skipna should be irrelevant since RangeIndex should never have NAs
result2 = idx.min(skipna=False)
assert result2 == expected
# empty
idx = RangeIndex(start, stop, -step)
assert isna(idx.max())
assert isna(idx.min())
def create_data():
""" create the pickle data """
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
}
scalars = dict(timestamp=Timestamp("20130101"), period=Period("2012", "M"))
index = dict(
int=Index(np.arange(10)),
date=date_range("20130101", periods=10),
period=period_range("2013-01-01", freq="M", periods=10),
float=Index(np.arange(10, dtype=np.float64)),
uint=Index(np.arange(10, dtype=np.uint64)),
timedelta=timedelta_range("00:00:00", freq="30T", periods=10),
)
index["range"] = RangeIndex(10)
if _loose_version >= LooseVersion("0.21"):
from pandas import interval_range
index["interval"] = interval_range(0, periods=10)
mi = dict(
reg2=MultiIndex.from_tuples(
tuple(
zip(
*[
["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
["one", "two", "one", "two", "one", "two", "one", "two"],
]
)
),
names=["first", "second"],
)
)
series = dict(
float=Series(data["A"]),
int=Series(data["B"]),
mixed=Series(data["E"]),
ts=Series(
np.arange(10).astype(np.int64), index=date_range("20130101", periods=10)
),
mi=Series(
np.arange(5).astype(np.float64),
index=MultiIndex.from_tuples(
tuple(zip(*[[1, 1, 2, 2, 2], [3, 4, 3, 4, 5]])), names=["one", "two"]
),
),
dup=Series(np.arange(5).astype(np.float64), index=["A", "B", "C", "D", "A"]),
cat=Series(Categorical(["foo", "bar", "baz"])),
dt=Series(date_range("20130101", periods=5)),
dt_tz=Series(date_range("20130101", periods=5, tz="US/Eastern")),
period=Series([Period("2000Q1")] * 5),
)
mixed_dup_df = DataFrame(data)
mixed_dup_df.columns = list("ABCDA")
frame = dict(
float=DataFrame({"A": series["float"], "B": series["float"] + 1}),
int=DataFrame({"A": series["int"], "B": series["int"] + 1}),
mixed=DataFrame({k: data[k] for k in ["A", "B", "C", "D"]}),
mi=DataFrame(
{"A": np.arange(5).astype(np.float64), "B": np.arange(5).astype(np.int64)},
index=MultiIndex.from_tuples(
tuple(
zip(
*[
["bar", "bar", "baz", "baz", "baz"],
["one", "two", "one", "two", "three"],
]
)
),
names=["first", "second"],
),
),
dup=DataFrame(
np.arange(15).reshape(5, 3).astype(np.float64), columns=["A", "B", "A"]
),
cat_onecol=DataFrame({"A": Categorical(["foo", "bar"])}),
cat_and_float=DataFrame(
{
"A": Categorical(["foo", "bar", "baz"]),
"B": np.arange(3).astype(np.int64),
}
),
mixed_dup=mixed_dup_df,
dt_mixed_tzs=DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
},
index=range(5),
),
dt_mixed2_tzs=DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
"C": Timestamp("20130603", tz="UTC"),
},
index=range(5),
),
)
cat = dict(
int8=Categorical(list("abcdefg")),
int16=Categorical(np.arange(1000)),
int32=Categorical(np.arange(10000)),
)
timestamp = dict(
normal=Timestamp("2011-01-01"),
nat=NaT,
tz=Timestamp("2011-01-01", tz="US/Eastern"),
)
timestamp["freq"] = Timestamp("2011-01-01", freq="D")
timestamp["both"] = Timestamp("2011-01-01", tz="Asia/Tokyo", freq="M")
off = {
"DateOffset": DateOffset(years=1),
"DateOffset_h_ns": DateOffset(hour=6, nanoseconds=5824),
"BusinessDay": BusinessDay(offset=timedelta(seconds=9)),
"BusinessHour": BusinessHour(normalize=True, n=6, end="15:14"),
"CustomBusinessDay": CustomBusinessDay(weekmask="Mon Fri"),
"SemiMonthBegin": SemiMonthBegin(day_of_month=9),
"SemiMonthEnd": SemiMonthEnd(day_of_month=24),
"MonthBegin": MonthBegin(1),
"MonthEnd": MonthEnd(1),
"QuarterBegin": QuarterBegin(1),
"QuarterEnd": QuarterEnd(1),
"Day": Day(1),
"YearBegin": YearBegin(1),
"YearEnd": YearEnd(1),
"Week": Week(1),
"Week_Tues": Week(2, normalize=False, weekday=1),
"WeekOfMonth": WeekOfMonth(week=3, weekday=4),
"LastWeekOfMonth": LastWeekOfMonth(n=1, weekday=3),
"FY5253": FY5253(n=2, weekday=6, startingMonth=7, variation="last"),
"Easter": Easter(),
"Hour": Hour(1),
"Minute": Minute(1),
}
return dict(
series=series,
frame=frame,
index=index,
scalars=scalars,
mi=mi,
sp_series=dict(float=_create_sp_series(), ts=_create_sp_tsseries()),
sp_frame=dict(float=_create_sp_frame()),
cat=cat,
timestamp=timestamp,
offsets=off,
)
def test_from_records_sequencelike(self):
df = DataFrame(
{
"A": np.array(np.random.randn(6), dtype=np.float64),
"A1": np.array(np.random.randn(6), dtype=np.float64),
"B": np.array(np.arange(6), dtype=np.int64),
"C": ["foo"] * 6,
"D": np.array([True, False] * 3, dtype=bool),
"E": np.array(np.random.randn(6), dtype=np.float32),
"E1": np.array(np.random.randn(6), dtype=np.float32),
"F": np.array(np.arange(6), dtype=np.int32),
}
)
# this is actually tricky to create the recordlike arrays and
# have the dtypes be intact
blocks = df._to_dict_of_blocks()
tuples = []
columns = []
dtypes = []
for dtype, b in blocks.items():
columns.extend(b.columns)
dtypes.extend([(c, np.dtype(dtype).descr[0][1]) for c in b.columns])
for i in range(len(df.index)):
tup = []
for _, b in blocks.items():
tup.extend(b.iloc[i].values)
tuples.append(tuple(tup))
recarray = np.array(tuples, dtype=dtypes).view(np.recarray)
recarray2 = df.to_records()
lists = [list(x) for x in tuples]
# tuples (lose the dtype info)
result = DataFrame.from_records(tuples, columns=columns).reindex(
columns=df.columns
)
# created recarray and with to_records recarray (have dtype info)
result2 = DataFrame.from_records(recarray, columns=columns).reindex(
columns=df.columns
)
result3 = DataFrame.from_records(recarray2, columns=columns).reindex(
columns=df.columns
)
# list of tupels (no dtype info)
result4 = DataFrame.from_records(lists, columns=columns).reindex(
columns=df.columns
)
tm.assert_frame_equal(result, df, check_dtype=False)
tm.assert_frame_equal(result2, df)
tm.assert_frame_equal(result3, df)
tm.assert_frame_equal(result4, df, check_dtype=False)
# tuples is in the order of the columns
result = DataFrame.from_records(tuples)
tm.assert_index_equal(result.columns, RangeIndex(8))
# test exclude parameter & we are casting the results here (as we don't
# have dtype info to recover)
columns_to_test = [columns.index("C"), columns.index("E1")]
exclude = list(set(range(8)) - set(columns_to_test))
result = DataFrame.from_records(tuples, exclude=exclude)
result.columns = [columns[i] for i in sorted(columns_to_test)]
tm.assert_series_equal(result["C"], df["C"])
tm.assert_series_equal(result["E1"], df["E1"].astype("float64"))
def create_data():
"""create the pickle data"""
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
}
scalars = {
"timestamp": Timestamp("20130101"),
"period": Period("2012", "M")
}
index = {
"int": Index(np.arange(10)),
"date": date_range("20130101", periods=10),
"period": period_range("2013-01-01", freq="M", periods=10),
"float": Index(np.arange(10, dtype=np.float64)),
"uint": Index(np.arange(10, dtype=np.uint64)),
"timedelta": timedelta_range("00:00:00", freq="30T", periods=10),
}
index["range"] = RangeIndex(10)
index["interval"] = interval_range(0, periods=10)
mi = {
"reg2":
MultiIndex.from_tuples(
tuple(
zip(*[
["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
["one", "two", "one", "two", "one", "two", "one", "two"],
])),
names=["first", "second"],
)
}
series = {
"float":
Series(data["A"]),
"int":
Series(data["B"]),
"mixed":
Series(data["E"]),
"ts":
Series(np.arange(10).astype(np.int64),
index=date_range("20130101", periods=10)),
"mi":
Series(
np.arange(5).astype(np.float64),
index=MultiIndex.from_tuples(tuple(
zip(*[[1, 1, 2, 2, 2], [3, 4, 3, 4, 5]])),
names=["one", "two"]),
),
"dup":
Series(np.arange(5).astype(np.float64),
index=["A", "B", "C", "D", "A"]),
"cat":
Series(Categorical(["foo", "bar", "baz"])),
"dt":
Series(date_range("20130101", periods=5)),
"dt_tz":
Series(date_range("20130101", periods=5, tz="US/Eastern")),
"period":
Series([Period("2000Q1")] * 5),
}
mixed_dup_df = DataFrame(data)
mixed_dup_df.columns = list("ABCDA")
frame = {
"float":
DataFrame({
"A": series["float"],
"B": series["float"] + 1
}),
"int":
DataFrame({
"A": series["int"],
"B": series["int"] + 1
}),
"mixed":
DataFrame({k: data[k]
for k in ["A", "B", "C", "D"]}),
"mi":
DataFrame(
{
"A": np.arange(5).astype(np.float64),
"B": np.arange(5).astype(np.int64)
},
index=MultiIndex.from_tuples(
tuple(
zip(*[
["bar", "bar", "baz", "baz", "baz"],
["one", "two", "one", "two", "three"],
])),
names=["first", "second"],
),
),
"dup":
DataFrame(np.arange(15).reshape(5, 3).astype(np.float64),
columns=["A", "B", "A"]),
"cat_onecol":
DataFrame({"A": Categorical(["foo", "bar"])}),
"cat_and_float":
DataFrame({
"A": Categorical(["foo", "bar", "baz"]),
"B": np.arange(3).astype(np.int64),
}),
"mixed_dup":
mixed_dup_df,
"dt_mixed_tzs":
DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
},
index=range(5),
),
"dt_mixed2_tzs":
DataFrame(
{
"A": Timestamp("20130102", tz="US/Eastern"),
"B": Timestamp("20130603", tz="CET"),
"C": Timestamp("20130603", tz="UTC"),
},
index=range(5),
),
}
cat = {
"int8": Categorical(list("abcdefg")),
"int16": Categorical(np.arange(1000)),
"int32": Categorical(np.arange(10000)),
}
timestamp = {
"normal": Timestamp("2011-01-01"),
"nat": NaT,
"tz": Timestamp("2011-01-01", tz="US/Eastern"),
}
timestamp["freq"] = Timestamp("2011-01-01", freq="D")
timestamp["both"] = Timestamp("2011-01-01", tz="Asia/Tokyo", freq="M")
off = {
"DateOffset": DateOffset(years=1),
"DateOffset_h_ns": DateOffset(hour=6, nanoseconds=5824),
"BusinessDay": BusinessDay(offset=timedelta(seconds=9)),
"BusinessHour": BusinessHour(normalize=True, n=6, end="15:14"),
"CustomBusinessDay": CustomBusinessDay(weekmask="Mon Fri"),
"SemiMonthBegin": SemiMonthBegin(day_of_month=9),
"SemiMonthEnd": SemiMonthEnd(day_of_month=24),
"MonthBegin": MonthBegin(1),
"MonthEnd": MonthEnd(1),
"QuarterBegin": QuarterBegin(1),
"QuarterEnd": QuarterEnd(1),
"Day": Day(1),
"YearBegin": YearBegin(1),
"YearEnd": YearEnd(1),
"Week": Week(1),
"Week_Tues": Week(2, normalize=False, weekday=1),
"WeekOfMonth": WeekOfMonth(week=3, weekday=4),
"LastWeekOfMonth": LastWeekOfMonth(n=1, weekday=3),
"FY5253": FY5253(n=2, weekday=6, startingMonth=7, variation="last"),
"Easter": Easter(),
"Hour": Hour(1),
"Minute": Minute(1),
}
return {
"series": series,
"frame": frame,
"index": index,
"scalars": scalars,
"mi": mi,
"sp_series": {
"float": _create_sp_series(),
"ts": _create_sp_tsseries()
},
"sp_frame": {
"float": _create_sp_frame()
},
"cat": cat,
"timestamp": timestamp,
"offsets": off,
}
def test_intersection(self, sort):
# intersect with Int64Index
other = Index(np.arange(1, 6))
result = self.index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(self.index, sort=sort)
expected = Index(np.sort(np.asarray(np.intersect1d(self.index.values,
other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = self.index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = self.index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(self.index.values,
other.values)))
tm.assert_index_equal(result, expected)
# reversed (GH 17296)
result = other.intersection(self.index, sort=sort)
tm.assert_index_equal(result, expected)
# GH 17296: intersect two decreasing RangeIndexes
first = RangeIndex(10, -2, -2)
other = RangeIndex(5, -4, -1)
expected = first.astype(int).intersection(other.astype(int), sort=sort)
result = first.intersection(other, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
# reversed
result = other.intersection(first, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def test_constructor_invalid_args_wrong_type(self, args):
msg = f"Wrong type {type(args)} for value {args}"
with pytest.raises(TypeError, match=msg):
RangeIndex(args)
def test_numeric_compat2(self):
# validate that we are handling the RangeIndex overrides to numeric ops
# and returning RangeIndex where possible
idx = RangeIndex(0, 10, 2)
result = idx * 2
expected = RangeIndex(0, 20, 4)
tm.assert_index_equal(result, expected, exact=True)
result = idx + 2
expected = RangeIndex(2, 12, 2)
tm.assert_index_equal(result, expected, exact=True)
result = idx - 2
expected = RangeIndex(-2, 8, 2)
tm.assert_index_equal(result, expected, exact=True)
result = idx / 2
expected = RangeIndex(0, 5, 1).astype("float64")
tm.assert_index_equal(result, expected, exact=True)
result = idx / 4
expected = RangeIndex(0, 10, 2) / 4
tm.assert_index_equal(result, expected, exact=True)
result = idx // 1
expected = idx
tm.assert_index_equal(result, expected, exact=True)
# __mul__
result = idx * idx
expected = Index(idx.values * idx.values)
tm.assert_index_equal(result, expected, exact=True)
# __pow__
idx = RangeIndex(0, 1000, 2)
result = idx ** 2
expected = idx._int64index ** 2
tm.assert_index_equal(Index(result.values), expected, exact=True)
# __floordiv__
cases_exact = [
(RangeIndex(0, 1000, 2), 2, RangeIndex(0, 500, 1)),
(RangeIndex(-99, -201, -3), -3, RangeIndex(33, 67, 1)),
(RangeIndex(0, 1000, 1), 2, RangeIndex(0, 1000, 1)._int64index // 2),
(
RangeIndex(0, 100, 1),
2.0,
RangeIndex(0, 100, 1)._int64index // 2.0,
),
(RangeIndex(0), 50, RangeIndex(0)),
(RangeIndex(2, 4, 2), 3, RangeIndex(0, 1, 1)),
(RangeIndex(-5, -10, -6), 4, RangeIndex(-2, -1, 1)),
(RangeIndex(-100, -200, 3), 2, RangeIndex(0)),
]
for idx, div, expected in cases_exact:
tm.assert_index_equal(idx // div, expected, exact=True)
def makeRangeIndex(k=10, name=None, **kwargs):
return RangeIndex(0, k, 1, name=name, **kwargs)
def ichimoku(high, low, close, tenkan=None, kijun=None, senkou=None, offset=None, **kwargs):
"""Indicator: Ichimoku Kinkō Hyō (Ichimoku)"""
high = verify_series(high)
low = verify_series(low)
close = verify_series(close)
tenkan = int(tenkan) if tenkan and tenkan > 0 else 9
kijun = int(kijun) if kijun and kijun > 0 else 26
senkou = int(senkou) if senkou and senkou > 0 else 52
offset = get_offset(offset)
# Calculate Result
tenkan_sen = midprice(high=high, low=low, length=tenkan)
kijun_sen = midprice(high=high, low=low, length=kijun)
span_a = 0.5 * (tenkan_sen + kijun_sen)
span_b = midprice(high=high, low=low, length=senkou)
# Copy Span A and B values before their shift
_span_a = span_a[-kijun:].copy()
_span_b = span_b[-kijun:].copy()
span_a = span_a.shift(kijun)
span_b = span_b.shift(kijun)
chikou_span = close.shift(-kijun)
# Offset
if offset != 0:
tenkan_sen = tenkan_sen.shift(offset)
kijun_sen = kijun_sen.shift(offset)
span_a = span_a.shift(offset)
span_b = span_b.shift(offset)
chikou_span = chikou_span.shift(offset)
# Handle fills
if 'fillna' in kwargs:
span_a.fillna(kwargs['fillna'], inplace=True)
span_b.fillna(kwargs['fillna'], inplace=True)
chikou_span.fillna(kwargs['fillna'], inplace=True)
if 'fill_method' in kwargs:
span_a.fillna(method=kwargs['fill_method'], inplace=True)
span_b.fillna(method=kwargs['fill_method'], inplace=True)
chikou_span.fillna(method=kwargs['fill_method'], inplace=True)
# Name and Categorize it
span_a.name = f"ISA_{tenkan}"
span_b.name = f"ISB_{kijun}"
tenkan_sen.name = f"ITS_{tenkan}"
kijun_sen.name = f"IKS_{kijun}"
chikou_span.name = f"ICS_{kijun}"
chikou_span.category = kijun_sen.category = tenkan_sen.category = 'trend'
span_b.category = span_a.category = chikou_span
# Prepare Ichimoku DataFrame
data = {span_a.name: span_a, span_b.name: span_b, tenkan_sen.name: tenkan_sen, kijun_sen.name: kijun_sen, chikou_span.name: chikou_span}
ichimokudf = DataFrame(data)
ichimokudf.name = f"ICHIMOKU_{tenkan}_{kijun}_{senkou}"
ichimokudf.category = 'overlap'
# Prepare Span DataFrame
last = close.index[-1]
if close.index.dtype == 'int64':
ext_index = RangeIndex(start=last + 1, stop=last + kijun + 1)
spandf = DataFrame(index=ext_index, columns=[span_a.name, span_b.name])
_span_a.index = _span_b.index = ext_index
else:
df_freq = close.index.value_counts().mode()[0]
tdelta = Timedelta(df_freq, unit='d')
new_dt = date_range(start=last + tdelta, periods=kijun, freq='B')
spandf = DataFrame(index=new_dt, columns=[span_a.name, span_b.name])
_span_a.index = _span_b.index = new_dt
spandf[span_a.name] = _span_a
spandf[span_b.name] = _span_b
spandf.name = f"ICHISPAN_{tenkan}_{kijun}"
spandf.category = 'overlap'
return ichimokudf, spandf
def test_slice_integer(self):
# same as above, but for Integer based indexes
# these coerce to a like integer
# oob indicates if we are out of bounds
# of positional indexing
for index, oob in [
(Int64Index(range(5)), False),
(RangeIndex(5), False),
(Int64Index(range(5)) + 10, True),
]:
# s is an in-range index
s = Series(range(5), index=index)
# getitem
for l in [slice(3.0, 4), slice(3, 4.0), slice(3.0, 4.0)]:
for idxr in [lambda x: x.loc]:
result = idxr(s)[l]
# these are all label indexing
# except getitem which is positional
# empty
if oob:
indexer = slice(0, 0)
else:
indexer = slice(3, 5)
self.check(result, s, indexer, False)
# positional indexing
msg = (
"cannot do slice indexing "
fr"on {type(index).__name__} with these indexers \[(3|4)\.0\] of "
"type float"
)
with pytest.raises(TypeError, match=msg):
s[l]
# getitem out-of-bounds
for l in [slice(-6, 6), slice(-6.0, 6.0)]:
for idxr in [lambda x: x.loc]:
result = idxr(s)[l]
# these are all label indexing
# except getitem which is positional
# empty
if oob:
indexer = slice(0, 0)
else:
indexer = slice(-6, 6)
self.check(result, s, indexer, False)
# positional indexing
msg = (
"cannot do slice indexing "
fr"on {type(index).__name__} with these indexers \[-6\.0\] of "
"type float"
)
with pytest.raises(TypeError, match=msg):
s[slice(-6.0, 6.0)]
# getitem odd floats
for l, res1 in [
(slice(2.5, 4), slice(3, 5)),
(slice(2, 3.5), slice(2, 4)),
(slice(2.5, 3.5), slice(3, 4)),
]:
for idxr in [lambda x: x.loc]:
result = idxr(s)[l]
if oob:
res = slice(0, 0)
else:
res = res1
self.check(result, s, res, False)
# positional indexing
msg = (
"cannot do slice indexing "
fr"on {type(index).__name__} with these indexers \[(2|3)\.5\] of "
"type float"
)
with pytest.raises(TypeError, match=msg):
s[l]
# setitem
for l in [slice(3.0, 4), slice(3, 4.0), slice(3.0, 4.0)]:
for idxr in [lambda x: x.loc]:
sc = s.copy()
idxr(sc)[l] = 0
result = idxr(sc)[l].values.ravel()
assert (result == 0).all()
# positional indexing
msg = (
"cannot do slice indexing "
fr"on {type(index).__name__} with these indexers \[(3|4)\.0\] of "
"type float"
)
with pytest.raises(TypeError, match=msg):
s[l] = 0
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name="asdf")
assert idx.name == idx[1:].name
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name="foo")
taken = index.take([3, 0, 1])
assert index.name == taken.name
def create_index(self):
return RangeIndex(start=0, stop=20, step=2)
def test_get_indexer_pad(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='pad')
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_decreasing(self, stop):
# GH 28678
index = RangeIndex(7, stop, -3)
result = index.get_indexer(range(9))
expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
class TestRangeIndex(Numeric):
_holder = RangeIndex
_compat_props = ['shape', 'ndim', 'size']
def setup_method(self, method):
self.indices = dict(index=RangeIndex(0, 20, 2, name='foo'),
index_dec=RangeIndex(18, -1, -2, name='bar'))
self.setup_indices()
def create_index(self):
return RangeIndex(5)
def test_can_hold_identifiers(self):
idx = self.create_index()
key = idx[0]
assert idx._can_hold_identifiers_and_holds_name(key) is False
def test_too_many_names(self):
with pytest.raises(ValueError, match="^Length"):
self.index.names = ["roger", "harold"]
@pytest.mark.parametrize('name', [None, 'foo'])
@pytest.mark.parametrize('args, kwargs, start, stop, step',
[((5, ), dict(), 0, 5, 1),
((1, 5), dict(), 1, 5, 1),
((1, 5, 2), dict(), 1, 5, 2),
((0, ), dict(), 0, 0, 1),
((0, 0), dict(), 0, 0, 1),
(tuple(), dict(start=0), 0, 0, 1),
(tuple(), dict(stop=0), 0, 0, 1)])
def test_constructor(self, args, kwargs, start, stop, step, name):
result = RangeIndex(*args, name=name, **kwargs)
expected = Index(np.arange(start, stop, step, dtype=np.int64),
name=name)
assert isinstance(result, RangeIndex)
assert result._start == start
assert result._stop == stop
assert result._step == step
assert result.name is name
tm.assert_index_equal(result, expected)
def test_constructor_invalid_args(self):
msg = "RangeIndex\\(\\.\\.\\.\\) must be called with integers"
with pytest.raises(TypeError, match=msg):
RangeIndex()
with pytest.raises(TypeError, match=msg):
RangeIndex(name='Foo')
# invalid args
for i in [
Index(['a', 'b']),
Series(['a', 'b']),
np.array(['a', 'b']), [], 'foo',
datetime(2000, 1, 1, 0, 0),
np.arange(0, 10),
np.array([1]), [1]
]:
with pytest.raises(TypeError):
RangeIndex(i)
# we don't allow on a bare Index
msg = (r'Index\(\.\.\.\) must be called with a collection of some '
r'kind, 0 was passed')
with pytest.raises(TypeError, match=msg):
Index(0, 1000)
def test_constructor_same(self):
# pass thru w and w/o copy
index = RangeIndex(1, 5, 2)
result = RangeIndex(index, copy=False)
assert result.identical(index)
result = RangeIndex(index, copy=True)
tm.assert_index_equal(result, index, exact=True)
result = RangeIndex(index)
tm.assert_index_equal(result, index, exact=True)
with pytest.raises(TypeError):
RangeIndex(index, dtype='float64')
def test_constructor_range(self):
with pytest.raises(TypeError):
RangeIndex(range(1, 5, 2))
result = RangeIndex.from_range(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5, 6))
expected = RangeIndex(5, 6, 1)
tm.assert_index_equal(result, expected, exact=True)
# an invalid range
result = RangeIndex.from_range(range(5, 1))
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5))
expected = RangeIndex(0, 5, 1)
tm.assert_index_equal(result, expected, exact=True)
result = Index(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
with pytest.raises(TypeError):
Index(range(1, 5, 2), dtype='float64')
def test_constructor_name(self):
# GH12288
orig = RangeIndex(10)
orig.name = 'original'
copy = RangeIndex(orig)
copy.name = 'copy'
assert orig.name == 'original'
assert copy.name == 'copy'
new = Index(copy)
assert new.name == 'copy'
new.name = 'new'
assert orig.name == 'original'
assert copy.name == 'copy'
assert new.name == 'new'
def test_constructor_corner(self):
arr = np.array([1, 2, 3, 4], dtype=object)
index = RangeIndex(1, 5)
assert index.values.dtype == np.int64
tm.assert_index_equal(index, Index(arr))
# non-int raise Exception
with pytest.raises(TypeError):
RangeIndex('1', '10', '1')
with pytest.raises(TypeError):
RangeIndex(1.1, 10.2, 1.3)
# invalid passed type
with pytest.raises(TypeError):
RangeIndex(1, 5, dtype='float64')
@pytest.mark.parametrize('index, start, stop, step',
[(RangeIndex(5), 0, 5, 1),
(RangeIndex(0, 5), 0, 5, 1),
(RangeIndex(5, step=2), 0, 5, 2),
(RangeIndex(1, 5, 2), 1, 5, 2)])
def test_start_stop_step_attrs(self, index, start, stop, step):
# GH 25710
assert index.start == start
assert index.stop == stop
assert index.step == step
def test_copy(self):
i = RangeIndex(5, name='Foo')
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._start == 0
assert i_copy._stop == 5
assert i_copy._step == 1
assert i_copy.name == 'Foo'
def test_repr(self):
i = RangeIndex(5, name='Foo')
result = repr(i)
expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
i = RangeIndex(5, 0, -1)
result = repr(i)
expected = "RangeIndex(start=5, stop=0, step=-1)"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
def test_insert(self):
idx = RangeIndex(5, name='Foo')
result = idx[1:4]
# test 0th element
tm.assert_index_equal(idx[0:4], result.insert(0, idx[0]))
# GH 18295 (test missing)
expected = Float64Index([0, np.nan, 1, 2, 3, 4])
for na in (np.nan, pd.NaT, None):
result = RangeIndex(5).insert(1, na)
tm.assert_index_equal(result, expected)
def test_delete(self):
idx = RangeIndex(5, name='Foo')
expected = idx[1:].astype(int)
result = idx.delete(0)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
expected = idx[:-1].astype(int)
result = idx.delete(-1)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
with pytest.raises((IndexError, ValueError)):
# either depending on numpy version
result = idx.delete(len(idx))
def test_view(self):
i = RangeIndex(0, name='Foo')
i_view = i.view()
assert i_view.name == 'Foo'
i_view = i.view('i8')
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_dtype(self):
assert self.index.dtype == np.int64
def test_is_monotonic(self):
assert self.index.is_monotonic is True
assert self.index.is_monotonic_increasing is True
assert self.index.is_monotonic_decreasing is False
assert self.index._is_strictly_monotonic_increasing is True
assert self.index._is_strictly_monotonic_decreasing is False
index = RangeIndex(4, 0, -1)
assert index.is_monotonic is False
assert index._is_strictly_monotonic_increasing is False
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(2, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
def test_equals_range(self):
equiv_pairs = [(RangeIndex(0, 9, 2), RangeIndex(0, 10, 2)),
(RangeIndex(0), RangeIndex(1, -1, 3)),
(RangeIndex(1, 2, 3), RangeIndex(1, 3, 4)),
(RangeIndex(0, -9, -2), RangeIndex(0, -10, -2))]
for left, right in equiv_pairs:
assert left.equals(right)
assert right.equals(left)
def test_logical_compat(self):
idx = self.create_index()
assert idx.all() == idx.values.all()
assert idx.any() == idx.values.any()
def test_identical(self):
i = Index(self.index.copy())
assert i.identical(self.index)
# we don't allow object dtype for RangeIndex
if isinstance(self.index, RangeIndex):
return
same_values_different_type = Index(i, dtype=object)
assert not i.identical(same_values_different_type)
i = self.index.copy(dtype=object)
i = i.rename('foo')
same_values = Index(i, dtype=object)
assert same_values.identical(self.index.copy(dtype=object))
assert not i.identical(self.index)
assert Index(same_values, name='foo', dtype=object).identical(i)
assert not self.index.copy(dtype=object).identical(
self.index.copy(dtype='int64'))
def test_get_indexer(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_pad(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='pad')
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_backfill(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='backfill')
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_join_outer(self):
# join with Int64Index
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = self.index.join(other,
how='outer',
return_indexers=True)
noidx_res = self.index.join(other, how='outer')
tm.assert_index_equal(res, noidx_res)
eres = Int64Index([
0, 2, 4, 6, 8, 10, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
25
])
elidx = np.array(
[0, 1, 2, 3, 4, 5, 6, 7, -1, 8, -1, 9, -1, -1, -1, -1, -1, -1, -1],
dtype=np.intp)
eridx = np.array(
[-1, -1, -1, -1, -1, -1, -1, -1, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0],
dtype=np.intp)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# join with RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = self.index.join(other,
how='outer',
return_indexers=True)
noidx_res = self.index.join(other, how='outer')
tm.assert_index_equal(res, noidx_res)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_inner(self):
# Join with non-RangeIndex
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = self.index.join(other,
how='inner',
return_indexers=True)
# no guarantee of sortedness, so sort for comparison purposes
ind = res.argsort()
res = res.take(ind)
lidx = lidx.take(ind)
ridx = ridx.take(ind)
eres = Int64Index([16, 18])
elidx = np.array([8, 9], dtype=np.intp)
eridx = np.array([9, 7], dtype=np.intp)
assert isinstance(res, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# Join two RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = self.index.join(other,
how='inner',
return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_left(self):
# Join with Int64Index
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = self.index.join(other,
how='left',
return_indexers=True)
eres = self.index
eridx = np.array([-1, -1, -1, -1, -1, -1, -1, -1, 9, 7], dtype=np.intp)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
# Join withRangeIndex
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = self.index.join(other,
how='left',
return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_right(self):
# Join with Int64Index
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = self.index.join(other,
how='right',
return_indexers=True)
eres = other
elidx = np.array([-1, -1, -1, -1, -1, -1, -1, 9, -1, 8, -1],
dtype=np.intp)
assert isinstance(other, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
# Join withRangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = self.index.join(other,
how='right',
return_indexers=True)
eres = other
assert isinstance(other, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
def test_join_non_int_index(self):
other = Index([3, 6, 7, 8, 10], dtype=object)
outer = self.index.join(other, how='outer')
outer2 = other.join(self.index, how='outer')
expected = Index([0, 2, 3, 4, 6, 7, 8, 10, 12, 14, 16, 18])
tm.assert_index_equal(outer, outer2)
tm.assert_index_equal(outer, expected)
inner = self.index.join(other, how='inner')
inner2 = other.join(self.index, how='inner')
expected = Index([6, 8, 10])
tm.assert_index_equal(inner, inner2)
tm.assert_index_equal(inner, expected)
left = self.index.join(other, how='left')
tm.assert_index_equal(left, self.index.astype(object))
left2 = other.join(self.index, how='left')
tm.assert_index_equal(left2, other)
right = self.index.join(other, how='right')
tm.assert_index_equal(right, other)
right2 = other.join(self.index, how='right')
tm.assert_index_equal(right2, self.index.astype(object))
def test_join_non_unique(self):
other = Index([4, 4, 3, 3])
res, lidx, ridx = self.index.join(other, return_indexers=True)
eres = Int64Index([0, 2, 4, 4, 6, 8, 10, 12, 14, 16, 18])
elidx = np.array([0, 1, 2, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.intp)
eridx = np.array([-1, -1, 0, 1, -1, -1, -1, -1, -1, -1, -1],
dtype=np.intp)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_self(self):
kinds = 'outer', 'inner', 'left', 'right'
for kind in kinds:
joined = self.index.join(self.index, how=kind)
assert self.index is joined
@pytest.mark.parametrize("sort", [None, False])
def test_intersection(self, sort):
# intersect with Int64Index
other = Index(np.arange(1, 6))
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(self.index, sort=sort)
expected = Index(
np.sort(np.asarray(np.intersect1d(self.index.values,
other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = self.index.intersection(other, sort=sort)
expected = Index(
np.sort(np.intersect1d(self.index.values, other.values)))
tm.assert_index_equal(result, expected)
# reversed (GH 17296)
result = other.intersection(self.index, sort=sort)
tm.assert_index_equal(result, expected)
# GH 17296: intersect two decreasing RangeIndexes
first = RangeIndex(10, -2, -2)
other = RangeIndex(5, -4, -1)
expected = first.astype(int).intersection(other.astype(int), sort=sort)
result = first.intersection(other, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
# reversed
result = other.intersection(first, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def test_union_noncomparable(self):
from datetime import datetime, timedelta
# corner case, non-Int64Index
now = datetime.now()
other = Index([now + timedelta(i) for i in range(4)], dtype=object)
result = self.index.union(other)
expected = Index(np.concatenate((self.index, other)))
tm.assert_index_equal(result, expected)
result = other.union(self.index)
expected = Index(np.concatenate((other, self.index)))
tm.assert_index_equal(result, expected)
def test_union(self):
RI = RangeIndex
I64 = Int64Index
cases = [(RI(0, 10, 1), RI(0, 10, 1), RI(0, 10, 1)),
(RI(0, 10, 1), RI(5, 20, 1), RI(0, 20, 1)),
(RI(0, 10, 1), RI(10, 20, 1), RI(0, 20, 1)),
(RI(0, -10, -1), RI(0, -10, -1), RI(0, -10, -1)),
(RI(0, -10, -1), RI(-10, -20, -1), RI(-19, 1, 1)),
(RI(0, 10, 2), RI(1, 10, 2), RI(0, 10, 1)),
(RI(0, 11, 2), RI(1, 12, 2), RI(0, 12, 1)),
(RI(0, 21, 4), RI(-2, 24, 4), RI(-2, 24, 2)),
(RI(0, -20, -2), RI(-1, -21, -2), RI(-19, 1, 1)),
(RI(0, 100, 5), RI(0, 100, 20), RI(0, 100, 5)),
(RI(0, -100, -5), RI(5, -100, -20), RI(-95, 10, 5)),
(RI(0, -11, -1), RI(1, -12, -4), RI(-11, 2, 1)),
(RI(0), RI(0), RI(0)), (RI(0, -10, -2), RI(0), RI(0, -10,
-2)),
(RI(0, 100, 2), RI(100, 150, 200), RI(0, 102, 2)),
(RI(0, -100, -2), RI(-100, 50, 102), RI(-100, 4, 2)),
(RI(0, -100, -1), RI(0, -50, -3), RI(-99, 1, 1)),
(RI(0, 1, 1), RI(5, 6, 10), RI(0, 6, 5)),
(RI(0, 10, 5), RI(-5, -6, -20), RI(-5, 10, 5)),
(RI(0, 3, 1), RI(4, 5, 1), I64([0, 1, 2, 4])),
(RI(0, 10, 1), I64([]), RI(0, 10, 1)),
(RI(0), I64([1, 5, 6]), I64([1, 5, 6]))]
for idx1, idx2, expected in cases:
res1 = idx1.union(idx2)
res2 = idx2.union(idx1)
res3 = idx1._int64index.union(idx2)
tm.assert_index_equal(res1, expected, exact=True)
tm.assert_index_equal(res2, expected, exact=True)
tm.assert_index_equal(res3, expected)
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
assert i.nbytes < i._int64index.nbytes / 10
# constant memory usage
i2 = RangeIndex(0, 10)
assert i.nbytes == i2.nbytes
def test_cant_or_shouldnt_cast(self):
# can't
with pytest.raises(TypeError):
RangeIndex('foo', 'bar', 'baz')
# shouldn't
with pytest.raises(TypeError):
RangeIndex('0', '1', '2')
def test_view_Index(self):
self.index.view(Index)
def test_prevent_casting(self):
result = self.index.astype('O')
assert result.dtype == np.object_
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name='foo')
taken = index.take([3, 0, 1])
assert index.name == taken.name
def test_take_fill_value(self):
# GH 12631
idx = pd.RangeIndex(1, 4, name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = pd.Int64Index([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
# fill_value
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -1]), fill_value=True)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = pd.Int64Index([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
idx.take(np.array([1, -5]))
def test_print_unicode_columns(self):
df = pd.DataFrame({
u("\u05d0"): [1, 2, 3],
"\u05d1": [4, 5, 6],
"c": [7, 8, 9]
})
repr(df.columns) # should not raise UnicodeDecodeError
def test_repr_roundtrip(self):
tm.assert_index_equal(eval(repr(self.index)), self.index)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name='asdf')
assert idx.name == idx[1:].name
def test_explicit_conversions(self):
# GH 8608
# add/sub are overridden explicitly for Float/Int Index
idx = RangeIndex(5)
# float conversions
arr = np.arange(5, dtype='int64') * 3.2
expected = Float64Index(arr)
fidx = idx * 3.2
tm.assert_index_equal(fidx, expected)
fidx = 3.2 * idx
tm.assert_index_equal(fidx, expected)
# interops with numpy arrays
expected = Float64Index(arr)
a = np.zeros(5, dtype='float64')
result = fidx - a
tm.assert_index_equal(result, expected)
expected = Float64Index(-arr)
a = np.zeros(5, dtype='float64')
result = a - fidx
tm.assert_index_equal(result, expected)
def test_has_duplicates(self):
for ind in self.indices:
if not len(ind):
continue
idx = self.indices[ind]
assert idx.is_unique
assert not idx.has_duplicates
def test_extended_gcd(self):
result = self.index._extended_gcd(6, 10)
assert result[0] == result[1] * 6 + result[2] * 10
assert 2 == result[0]
result = self.index._extended_gcd(10, 6)
assert 2 == result[1] * 10 + result[2] * 6
assert 2 == result[0]
def test_min_fitting_element(self):
result = RangeIndex(0, 20, 2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(1, 6)._min_fitting_element(1)
assert 1 == result
result = RangeIndex(18, -2, -2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(5, 0, -1)._min_fitting_element(1)
assert 1 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._min_fitting_element(big_num)
assert big_num == result
def test_max_fitting_element(self):
result = RangeIndex(0, 20, 2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(1, 6)._max_fitting_element(4)
assert 4 == result
result = RangeIndex(18, -2, -2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(5, 0, -1)._max_fitting_element(4)
assert 4 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._max_fitting_element(big_num)
assert big_num == result
def test_pickle_compat_construction(self):
# RangeIndex() is a valid constructor
pass
def test_slice_specialised(self):
# scalar indexing
res = self.index[1]
expected = 2
assert res == expected
res = self.index[-1]
expected = 18
assert res == expected
# slicing
# slice value completion
index = self.index[:]
expected = self.index
tm.assert_index_equal(index, expected)
# positive slice values
index = self.index[7:10:2]
expected = Index(np.array([14, 18]), name='foo')
tm.assert_index_equal(index, expected)
# negative slice values
index = self.index[-1:-5:-2]
expected = Index(np.array([18, 14]), name='foo')
tm.assert_index_equal(index, expected)
# stop overshoot
index = self.index[2:100:4]
expected = Index(np.array([4, 12]), name='foo')
tm.assert_index_equal(index, expected)
# reverse
index = self.index[::-1]
expected = Index(self.index.values[::-1], name='foo')
tm.assert_index_equal(index, expected)
index = self.index[-8::-1]
expected = Index(np.array([4, 2, 0]), name='foo')
tm.assert_index_equal(index, expected)
index = self.index[-40::-1]
expected = Index(np.array([], dtype=np.int64), name='foo')
tm.assert_index_equal(index, expected)
index = self.index[40::-1]
expected = Index(self.index.values[40::-1], name='foo')
tm.assert_index_equal(index, expected)
index = self.index[10::-1]
expected = Index(self.index.values[::-1], name='foo')
tm.assert_index_equal(index, expected)
def test_len_specialised(self):
# make sure that our len is the same as
# np.arange calc
for step in np.arange(1, 6, 1):
arr = np.arange(0, 5, step)
i = RangeIndex(0, 5, step)
assert len(i) == len(arr)
i = RangeIndex(5, 0, step)
assert len(i) == 0
for step in np.arange(-6, -1, 1):
arr = np.arange(5, 0, step)
i = RangeIndex(5, 0, step)
assert len(i) == len(arr)
i = RangeIndex(0, 5, step)
assert len(i) == 0
def test_append(self):
# GH16212
RI = RangeIndex
I64 = Int64Index
F64 = Float64Index
OI = Index
cases = [([RI(1, 12, 5)], RI(1, 12, 5)), ([RI(0, 6, 4)], RI(0, 6, 4)),
([RI(1, 3), RI(3, 7)], RI(1, 7)),
([RI(1, 5, 2), RI(5, 6)], RI(1, 6, 2)),
([RI(1, 3, 2), RI(4, 7, 3)], RI(1, 7, 3)),
([RI(-4, 3, 2), RI(4, 7, 2)], RI(-4, 7, 2)),
([RI(-4, -8), RI(-8, -12)], RI(0, 0)),
([RI(-4, -8), RI(3, -4)], RI(0, 0)),
([RI(-4, -8), RI(3, 5)], RI(3, 5)),
([RI(-4, -2), RI(3, 5)], I64([-4, -3, 3, 4])),
([RI(-2, ), RI(3, 5)], RI(3, 5)),
([RI(2, ), RI(2)], I64([0, 1, 0, 1])),
([RI(2, ), RI(2, 5), RI(5, 8, 4)], RI(0, 6)),
([RI(2, ), RI(3, 5), RI(5, 8, 4)], I64([0, 1, 3, 4, 5])),
([RI(-2, 2), RI(2, 5), RI(5, 8, 4)], RI(-2, 6)),
([RI(3, ), I64([-1, 3, 15])], I64([0, 1, 2, -1, 3, 15])),
([RI(3, ), F64([-1, 3.1, 15.])], F64([0, 1, 2, -1, 3.1,
15.])),
([RI(3, ), OI(['a', None, 14])], OI([0, 1, 2, 'a', None,
14])),
([RI(3, 1), OI(['a', None, 14])], OI(['a', None, 14]))]
for indices, expected in cases:
result = indices[0].append(indices[1:])
tm.assert_index_equal(result, expected, exact=True)
if len(indices) == 2:
# Append single item rather than list
result2 = indices[0].append(indices[1])
tm.assert_index_equal(result2, expected, exact=True)
def test_constructor_additional_invalid_args(self, args):
msg = f"Value needs to be a scalar value, was type {type(args).__name__}"
with pytest.raises(TypeError, match=msg):
RangeIndex(args)
def setup_method(self, method):
self.indices = dict(index=RangeIndex(0, 20, 2, name='foo'),
index_dec=RangeIndex(18, -1, -2, name='bar'))
self.setup_indices()
def test_constructor_range(self):
result = RangeIndex.from_range(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5, 6))
expected = RangeIndex(5, 6, 1)
tm.assert_index_equal(result, expected, exact=True)
# an invalid range
result = RangeIndex.from_range(range(5, 1))
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected, exact=True)
result = RangeIndex.from_range(range(5))
expected = RangeIndex(0, 5, 1)
tm.assert_index_equal(result, expected, exact=True)
result = Index(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
msg = (
r"(RangeIndex.)?from_range\(\) got an unexpected keyword argument( 'copy')?"
)
with pytest.raises(TypeError, match=msg):
RangeIndex.from_range(range(10), copy=True)
def create_index(self):
return RangeIndex(5)
def _get_index_loc(self, key, base_index=None):
"""
Get the location of a specific key in an index
Parameters
----------
key : label
The key for which to find the location if the underlying index is
a DateIndex or a location if the underlying index is a RangeIndex
or an Int64Index.
base_index : pd.Index, optional
Optionally the base index to search. If None, the model's index is
searched.
Returns
-------
loc : int
The location of the key
index : pd.Index
The index including the key; this is a copy of the original index
unless the index had to be expanded to accommodate `key`.
index_was_expanded : bool
Whether or not the index was expanded to accommodate `key`.
Notes
-----
If `key` is past the end of of the given index, and the index is either
an Int64Index or a date index, this function extends the index up to
and including key, and then returns the location in the new index.
"""
if base_index is None:
base_index = self._index
index = base_index
date_index = isinstance(base_index, (PeriodIndex, DatetimeIndex))
int_index = isinstance(base_index, Int64Index)
range_index = isinstance(base_index, RangeIndex)
index_class = type(base_index)
nobs = len(index)
# Special handling for RangeIndex
if range_index and isinstance(key, (int, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > nobs - 1:
# See gh5835. Remove the except after pandas 0.25 required.
try:
base_index_start = base_index.start
base_index_step = base_index.step
except AttributeError:
base_index_start = base_index._start
base_index_step = base_index._step
stop = base_index_start + (key + 1) * base_index_step
index = RangeIndex(start=base_index_start,
stop=stop,
step=base_index_step)
# Special handling for Int64Index
if (not range_index and int_index and not date_index and
isinstance(key, (int, np.integer))):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > base_index[-1]:
index = Int64Index(np.arange(base_index[0], int(key + 1)))
# Special handling for date indexes
if date_index:
# Use index type to choose creation function
if index_class is DatetimeIndex:
index_fn = date_range
else:
index_fn = period_range
# Integer key (i.e. already given a location)
if isinstance(key, (int, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key < nobs:
key = index[nobs + key]
# Out-of-sample (note that we include key itself in the new
# index)
elif key > len(base_index) - 1:
index = index_fn(start=base_index[0],
periods=int(key + 1),
freq=base_index.freq)
key = index[-1]
else:
key = index[key]
# Other key types (i.e. string date or some datetime-like object)
else:
# Covert the key to the appropriate date-like object
if index_class is PeriodIndex:
date_key = Period(key, freq=base_index.freq)
else:
date_key = Timestamp(key)
# Out-of-sample
if date_key > base_index[-1]:
# First create an index that may not always include `key`
index = index_fn(start=base_index[0], end=date_key,
freq=base_index.freq)
# Now make sure we include `key`
if not index[-1] == date_key:
index = index_fn(start=base_index[0],
periods=len(index) + 1,
freq=base_index.freq)
# Get the location
if date_index:
# (note that get_loc will throw a KeyError if key is invalid)
loc = index.get_loc(key)
elif int_index or range_index:
# For Int64Index and RangeIndex, key is assumed to be the location
# and not an index value (this assumption is required to support
# RangeIndex)
try:
index[key]
# We want to raise a KeyError in this case, to keep the exception
# consistent across index types.
# - Attempting to index with an out-of-bound location (e.g.
# index[10] on an index of length 9) will raise an IndexError
# (as of Pandas 0.22)
# - Attemtping to index with a type that cannot be cast to integer
# (e.g. a non-numeric string) will raise a ValueError if the
# index is RangeIndex (otherwise will raise an IndexError)
# (as of Pandas 0.22)
except (IndexError, ValueError) as e:
raise KeyError(str(e))
loc = key
else:
loc = index.get_loc(key)
# Check if we now have a modified index
index_was_expanded = index is not base_index
# Return the index through the end of the loc / slice
if isinstance(loc, slice):
end = loc.stop
else:
end = loc
return loc, index[:end + 1], index_was_expanded
def test_get_indexer(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name='foo')
taken = index.take([3, 0, 1])
self.assertEqual(index.name, taken.name)
def test_intersection(self, sort):
# intersect with Int64Index
index = RangeIndex(start=0, stop=20, step=2)
other = Index(np.arange(1, 6))
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
expected = Index(
np.sort(np.asarray(np.intersect1d(index.values, other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
# reversed (GH 17296)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# GH 17296: intersect two decreasing RangeIndexes
first = RangeIndex(10, -2, -2)
other = RangeIndex(5, -4, -1)
expected = first.astype(int).intersection(other.astype(int), sort=sort)
result = first.intersection(other, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
# reversed
result = other.intersection(first, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
def setup(self):
idx_large_fast = RangeIndex(100000)
idx_small_slow = date_range(start="1/1/2012", periods=1)
self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
self.idx_non_object = RangeIndex(1)
def decode(obj):
"""
Decoder for deserializing numpy data types.
"""
typ = obj.get('typ')
if typ is None:
return obj
elif typ == 'timestamp':
freq = obj['freq'] if 'freq' in obj else obj['offset']
return Timestamp(obj['value'], tz=obj['tz'], freq=freq)
elif typ == 'nat':
return NaT
elif typ == 'period':
return Period(ordinal=obj['ordinal'], freq=obj['freq'])
elif typ == 'index':
dtype = dtype_for(obj['dtype'])
data = unconvert(obj['data'], dtype, obj.get('compress'))
return Index(data, dtype=dtype, name=obj['name'])
elif typ == 'range_index':
return RangeIndex(obj['start'],
obj['stop'],
obj['step'],
name=obj['name'])
elif typ == 'multi_index':
dtype = dtype_for(obj['dtype'])
data = unconvert(obj['data'], dtype, obj.get('compress'))
data = [tuple(x) for x in data]
return MultiIndex.from_tuples(data, names=obj['names'])
elif typ == 'period_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'])
freq = d.pop('freq', None)
return PeriodIndex(PeriodArray(data, freq), **d)
elif typ == 'datetime_index':
data = unconvert(obj['data'], np.int64, obj.get('compress'))
d = dict(name=obj['name'], freq=obj['freq'])
result = DatetimeIndex(data, **d)
tz = obj['tz']
# reverse tz conversion
if tz is not None:
result = result.tz_localize('UTC').tz_convert(tz)
return result
elif typ in ('interval_index', 'interval_array'):
return globals()[obj['klass']].from_arrays(obj['left'],
obj['right'],
obj['closed'],
name=obj['name'])
elif typ == 'category':
from_codes = globals()[obj['klass']].from_codes
return from_codes(codes=obj['codes'],
categories=obj['categories'],
ordered=obj['ordered'])
elif typ == 'interval':
return Interval(obj['left'], obj['right'], obj['closed'])
elif typ == 'series':
dtype = dtype_for(obj['dtype'])
pd_dtype = pandas_dtype(dtype)
index = obj['index']
result = Series(unconvert(obj['data'], dtype, obj['compress']),
index=index,
dtype=pd_dtype,
name=obj['name'])
return result
elif typ == 'block_manager':
axes = obj['axes']
def create_block(b):
values = _safe_reshape(
unconvert(b['values'], dtype_for(b['dtype']), b['compress']),
b['shape'])
# locs handles duplicate column names, and should be used instead
# of items; see GH 9618
if 'locs' in b:
placement = b['locs']
else:
placement = axes[0].get_indexer(b['items'])
if is_datetime64tz_dtype(b['dtype']):
assert isinstance(values, np.ndarray), type(values)
assert values.dtype == 'M8[ns]', values.dtype
values = DatetimeArray(values, dtype=b['dtype'])
return make_block(values=values,
klass=getattr(internals, b['klass']),
placement=placement,
dtype=b['dtype'])
blocks = [create_block(b) for b in obj['blocks']]
return globals()[obj['klass']](BlockManager(blocks, axes))
elif typ == 'datetime':
return parse(obj['data'])
elif typ == 'datetime64':
return np.datetime64(parse(obj['data']))
elif typ == 'date':
return parse(obj['data']).date()
elif typ == 'timedelta':
return timedelta(*obj['data'])
elif typ == 'timedelta64':
return np.timedelta64(int(obj['data']))
# elif typ == 'sparse_series':
# dtype = dtype_for(obj['dtype'])
# return SparseSeries(
# unconvert(obj['sp_values'], dtype, obj['compress']),
# sparse_index=obj['sp_index'], index=obj['index'],
# fill_value=obj['fill_value'], kind=obj['kind'], name=obj['name'])
# elif typ == 'sparse_dataframe':
# return SparseDataFrame(
# obj['data'], columns=obj['columns'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind']
# )
# elif typ == 'sparse_panel':
# return SparsePanel(
# obj['data'], items=obj['items'],
# default_fill_value=obj['default_fill_value'],
# default_kind=obj['default_kind'])
elif typ == 'block_index':
return globals()[obj['klass']](obj['length'], obj['blocs'],
obj['blengths'])
elif typ == 'int_index':
return globals()[obj['klass']](obj['length'], obj['indices'])
elif typ == 'ndarray':
return unconvert(obj['data'], np.typeDict[obj['dtype']],
obj.get('compress')).reshape(obj['shape'])
elif typ == 'np_scalar':
if obj.get('sub_typ') == 'np_complex':
return c2f(obj['real'], obj['imag'], obj['dtype'])
else:
dtype = dtype_for(obj['dtype'])
try:
return dtype(obj['data'])
except (ValueError, TypeError):
return dtype.type(obj['data'])
elif typ == 'np_complex':
return complex(obj['real'] + '+' + obj['imag'] + 'j')
elif isinstance(obj, (dict, list, set)):
return obj
else:
return obj
def test_constructor(self):
index = RangeIndex(5)
expected = np.arange(5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 5
assert index._step == 1
assert index.name is None
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5)
expected = np.arange(1, 5, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 1
tm.assert_index_equal(Index(expected), index)
index = RangeIndex(1, 5, 2)
expected = np.arange(1, 5, 2, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._step == 2
tm.assert_index_equal(Index(expected), index)
for index in [
RangeIndex(0),
RangeIndex(start=0),
RangeIndex(stop=0),
RangeIndex(0, 0)
]:
expected = np.empty(0, dtype=np.int64)
assert isinstance(index, RangeIndex)
assert index._start == 0
assert index._stop == 0
assert index._step == 1
tm.assert_index_equal(Index(expected), index)
for index in [
RangeIndex(0, name='Foo'),
RangeIndex(start=0, name='Foo'),
RangeIndex(stop=0, name='Foo'),
RangeIndex(0, 0, name='Foo')
]:
assert isinstance(index, RangeIndex)
assert index.name == 'Foo'
# we don't allow on a bare Index
with pytest.raises(TypeError):
Index(0, 1000)
def _get_index_loc(self, key, base_index=None):
"""
Get the location of a specific key in an index
Parameters
----------
key : label
The key for which to find the location if the underlying index is
a DateIndex or a location if the underlying index is a RangeIndex
or an Int64Index.
base_index : pd.Index, optional
Optionally the base index to search. If None, the model's index is
searched.
Returns
-------
loc : int
The location of the key
index : pd.Index
The index including the key; this is a copy of the original index
unless the index had to be expanded to accomodate `key`.
index_was_expanded : bool
Whether or not the index was expanded to accomodate `key`.
Notes
-----
If `key` is past the end of of the given index, and the index is either
an Int64Index or a date index, this function extends the index up to
and including key, and then returns the location in the new index.
"""
if base_index is None:
base_index = self._index
index = base_index
date_index = isinstance(base_index, (PeriodIndex, DatetimeIndex))
int_index = isinstance(base_index, Int64Index)
range_index = isinstance(base_index, RangeIndex)
index_class = type(base_index)
nobs = len(index)
# Special handling for RangeIndex
if range_index and isinstance(key, (int, long, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > nobs - 1:
stop = base_index._start + (key + 1) * base_index._step
index = RangeIndex(start=base_index._start,
stop=stop,
step=base_index._step)
# Special handling for Int64Index
if (not range_index and int_index and not date_index and
isinstance(key, (int, long, np.integer))):
# Negative indices (that lie in the Index)
if key < 0 and -key <= nobs:
key = nobs + key
# Out-of-sample (note that we include key itself in the new index)
elif key > base_index[-1]:
index = Int64Index(np.arange(base_index[0], int(key + 1)))
# Special handling for date indexes
if date_index:
# Integer key (i.e. already given a location)
if isinstance(key, (int, long, np.integer)):
# Negative indices (that lie in the Index)
if key < 0 and -key < nobs:
key = index[nobs + key]
# Out-of-sample (note that we include key itself in the new
# index)
elif key > len(base_index) - 1:
index = index_class(start=base_index[0],
periods=int(key + 1),
freq=base_index.freq)
key = index[-1]
else:
key = index[key]
# Other key types (i.e. string date or some datetime-like object)
else:
# Covert the key to the appropriate date-like object
if index_class is PeriodIndex:
date_key = Period(key, freq=base_index.freq)
else:
date_key = Timestamp(key)
# Out-of-sample
if date_key > base_index[-1]:
# First create an index that may not always include `key`
index = index_class(start=base_index[0], end=date_key,
freq=base_index.freq)
# Now make sure we include `key`
if not index[-1] == date_key:
index = index_class(start=base_index[0],
periods=len(index) + 1,
freq=base_index.freq)
# Get the location
if date_index:
# (note that get_loc will throw a KeyError if key is invalid)
loc = index.get_loc(key)
elif int_index or range_index:
# For Int64Index and RangeIndex, key is assumed to be the location
# and not an index value (this assumption is required to support
# RangeIndex)
try:
index[key]
# We want to raise a KeyError in this case, to keep the exception
# consistent across index types.
# - Attempting to index with an out-of-bound location (e.g.
# index[10] on an index of length 9) will raise an IndexError
# (as of Pandas 0.22)
# - Attemtping to index with a type that cannot be cast to integer
# (e.g. a non-numeric string) will raise a ValueError if the
# index is RangeIndex (otherwise will raise an IndexError)
# (as of Pandas 0.22)
except (IndexError, ValueError) as e:
raise KeyError(str(e))
loc = key
else:
loc = index.get_loc(key)
# Check if we now have a modified index
index_was_expanded = index is not base_index
# Return the index through the end of the loc / slice
if isinstance(loc, slice):
end = loc.stop
else:
end = loc
return loc, index[:end + 1], index_was_expanded
class TestRangeIndex(Numeric):
_holder = RangeIndex
_compat_props = ["shape", "ndim", "size"]
@pytest.fixture(
params=[
RangeIndex(start=0, stop=20, step=2, name="foo"),
RangeIndex(start=18, stop=-1, step=-2, name="bar"),
],
ids=["index_inc", "index_dec"],
)
def indices(self, request):
return request.param
def create_index(self):
return RangeIndex(start=0, stop=20, step=2)
def test_can_hold_identifiers(self):
idx = self.create_index()
key = idx[0]
assert idx._can_hold_identifiers_and_holds_name(key) is False
def test_too_many_names(self):
index = self.create_index()
with pytest.raises(ValueError, match="^Length"):
index.names = ["roger", "harold"]
@pytest.mark.parametrize(
"index, start, stop, step",
[
(RangeIndex(5), 0, 5, 1),
(RangeIndex(0, 5), 0, 5, 1),
(RangeIndex(5, step=2), 0, 5, 2),
(RangeIndex(1, 5, 2), 1, 5, 2),
],
)
def test_start_stop_step_attrs(self, index, start, stop, step):
# GH 25710
assert index.start == start
assert index.stop == stop
assert index.step == step
@pytest.mark.parametrize("attr_name", ["_start", "_stop", "_step"])
def test_deprecated_start_stop_step_attrs(self, attr_name):
# GH 26581
idx = self.create_index()
with tm.assert_produces_warning(FutureWarning):
getattr(idx, attr_name)
def test_copy(self):
i = RangeIndex(5, name="Foo")
i_copy = i.copy()
assert i_copy is not i
assert i_copy.identical(i)
assert i_copy._range == range(0, 5, 1)
assert i_copy.name == "Foo"
def test_repr(self):
i = RangeIndex(5, name="Foo")
result = repr(i)
expected = "RangeIndex(start=0, stop=5, step=1, name='Foo')"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
i = RangeIndex(5, 0, -1)
result = repr(i)
expected = "RangeIndex(start=5, stop=0, step=-1)"
assert result == expected
result = eval(result)
tm.assert_index_equal(result, i, exact=True)
def test_insert(self):
idx = RangeIndex(5, name="Foo")
result = idx[1:4]
# test 0th element
tm.assert_index_equal(idx[0:4], result.insert(0, idx[0]))
# GH 18295 (test missing)
expected = Float64Index([0, np.nan, 1, 2, 3, 4])
for na in (np.nan, pd.NaT, None):
result = RangeIndex(5).insert(1, na)
tm.assert_index_equal(result, expected)
def test_delete(self):
idx = RangeIndex(5, name="Foo")
expected = idx[1:].astype(int)
result = idx.delete(0)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
expected = idx[:-1].astype(int)
result = idx.delete(-1)
tm.assert_index_equal(result, expected)
assert result.name == expected.name
with pytest.raises((IndexError, ValueError)):
# either depending on numpy version
result = idx.delete(len(idx))
def test_view(self):
i = RangeIndex(0, name="Foo")
i_view = i.view()
assert i_view.name == "Foo"
i_view = i.view("i8")
tm.assert_numpy_array_equal(i.values, i_view)
i_view = i.view(RangeIndex)
tm.assert_index_equal(i, i_view)
def test_dtype(self):
index = self.create_index()
assert index.dtype == np.int64
def test_cached_data(self):
# GH 26565, GH26617
# Calling RangeIndex._data caches an int64 array of the same length at
# self._cached_data. This test checks whether _cached_data has been set
idx = RangeIndex(0, 100, 10)
assert idx._cached_data is None
repr(idx)
assert idx._cached_data is None
str(idx)
assert idx._cached_data is None
idx.get_loc(20)
assert idx._cached_data is None
90 in idx
assert idx._cached_data is None
91 in idx
assert idx._cached_data is None
idx.all()
assert idx._cached_data is None
idx.any()
assert idx._cached_data is None
df = pd.DataFrame({"a": range(10)}, index=idx)
df.loc[50]
assert idx._cached_data is None
with pytest.raises(KeyError, match="51"):
df.loc[51]
assert idx._cached_data is None
df.loc[10:50]
assert idx._cached_data is None
df.iloc[5:10]
assert idx._cached_data is None
# actually calling idx._data
assert isinstance(idx._data, np.ndarray)
assert isinstance(idx._cached_data, np.ndarray)
def test_is_monotonic(self):
index = RangeIndex(0, 20, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is False
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is False
index = RangeIndex(4, 0, -1)
assert index.is_monotonic is False
assert index._is_strictly_monotonic_increasing is False
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 2)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(2, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
index = RangeIndex(1, 1)
assert index.is_monotonic is True
assert index.is_monotonic_increasing is True
assert index.is_monotonic_decreasing is True
assert index._is_strictly_monotonic_increasing is True
assert index._is_strictly_monotonic_decreasing is True
def test_equals_range(self):
equiv_pairs = [
(RangeIndex(0, 9, 2), RangeIndex(0, 10, 2)),
(RangeIndex(0), RangeIndex(1, -1, 3)),
(RangeIndex(1, 2, 3), RangeIndex(1, 3, 4)),
(RangeIndex(0, -9, -2), RangeIndex(0, -10, -2)),
]
for left, right in equiv_pairs:
assert left.equals(right)
assert right.equals(left)
def test_logical_compat(self):
idx = self.create_index()
assert idx.all() == idx.values.all()
assert idx.any() == idx.values.any()
def test_identical(self):
index = self.create_index()
i = Index(index.copy())
assert i.identical(index)
# we don't allow object dtype for RangeIndex
if isinstance(index, RangeIndex):
return
same_values_different_type = Index(i, dtype=object)
assert not i.identical(same_values_different_type)
i = index.copy(dtype=object)
i = i.rename("foo")
same_values = Index(i, dtype=object)
assert same_values.identical(index.copy(dtype=object))
assert not i.identical(index)
assert Index(same_values, name="foo", dtype=object).identical(i)
assert not index.copy(dtype=object).identical(index.copy(dtype="int64"))
def test_get_indexer(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_pad(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="pad")
expected = np.array([0, 0, 1, 1, 2, 2, 3, 3, 4, 4], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_backfill(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="backfill")
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer_limit(self):
# GH 28631
idx = RangeIndex(4)
target = RangeIndex(6)
result = idx.get_indexer(target, method="pad", limit=1)
expected = np.array([0, 1, 2, 3, 3, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
@pytest.mark.parametrize("stop", [0, -1, -2])
def test_get_indexer_decreasing(self, stop):
# GH 28678
index = RangeIndex(7, stop, -3)
result = index.get_indexer(range(9))
expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp)
tm.assert_numpy_array_equal(result, expected)
def test_join_outer(self):
# join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="outer", return_indexers=True)
noidx_res = index.join(other, how="outer")
tm.assert_index_equal(res, noidx_res)
eres = Int64Index(
[0, 2, 4, 6, 8, 10, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25]
)
elidx = np.array(
[0, 1, 2, 3, 4, 5, 6, 7, -1, 8, -1, 9, -1, -1, -1, -1, -1, -1, -1],
dtype=np.intp,
)
eridx = np.array(
[-1, -1, -1, -1, -1, -1, -1, -1, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0],
dtype=np.intp,
)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# join with RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="outer", return_indexers=True)
noidx_res = index.join(other, how="outer")
tm.assert_index_equal(res, noidx_res)
assert isinstance(res, Int64Index)
assert not isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_inner(self):
# Join with non-RangeIndex
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="inner", return_indexers=True)
# no guarantee of sortedness, so sort for comparison purposes
ind = res.argsort()
res = res.take(ind)
lidx = lidx.take(ind)
ridx = ridx.take(ind)
eres = Int64Index([16, 18])
elidx = np.array([8, 9], dtype=np.intp)
eridx = np.array([9, 7], dtype=np.intp)
assert isinstance(res, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
# Join two RangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="inner", return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_left(self):
# Join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="left", return_indexers=True)
eres = index
eridx = np.array([-1, -1, -1, -1, -1, -1, -1, -1, 9, 7], dtype=np.intp)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
# Join withRangeIndex
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="left", return_indexers=True)
assert isinstance(res, RangeIndex)
tm.assert_index_equal(res, eres)
assert lidx is None
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_right(self):
# Join with Int64Index
index = self.create_index()
other = Int64Index(np.arange(25, 14, -1))
res, lidx, ridx = index.join(other, how="right", return_indexers=True)
eres = other
elidx = np.array([-1, -1, -1, -1, -1, -1, -1, 9, -1, 8, -1], dtype=np.intp)
assert isinstance(other, Int64Index)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
# Join withRangeIndex
other = RangeIndex(25, 14, -1)
res, lidx, ridx = index.join(other, how="right", return_indexers=True)
eres = other
assert isinstance(other, RangeIndex)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
assert ridx is None
def test_join_non_int_index(self):
index = self.create_index()
other = Index([3, 6, 7, 8, 10], dtype=object)
outer = index.join(other, how="outer")
outer2 = other.join(index, how="outer")
expected = Index([0, 2, 3, 4, 6, 7, 8, 10, 12, 14, 16, 18])
tm.assert_index_equal(outer, outer2)
tm.assert_index_equal(outer, expected)
inner = index.join(other, how="inner")
inner2 = other.join(index, how="inner")
expected = Index([6, 8, 10])
tm.assert_index_equal(inner, inner2)
tm.assert_index_equal(inner, expected)
left = index.join(other, how="left")
tm.assert_index_equal(left, index.astype(object))
left2 = other.join(index, how="left")
tm.assert_index_equal(left2, other)
right = index.join(other, how="right")
tm.assert_index_equal(right, other)
right2 = other.join(index, how="right")
tm.assert_index_equal(right2, index.astype(object))
def test_join_non_unique(self):
index = self.create_index()
other = Index([4, 4, 3, 3])
res, lidx, ridx = index.join(other, return_indexers=True)
eres = Int64Index([0, 2, 4, 4, 6, 8, 10, 12, 14, 16, 18])
elidx = np.array([0, 1, 2, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.intp)
eridx = np.array([-1, -1, 0, 1, -1, -1, -1, -1, -1, -1, -1], dtype=np.intp)
tm.assert_index_equal(res, eres)
tm.assert_numpy_array_equal(lidx, elidx)
tm.assert_numpy_array_equal(ridx, eridx)
def test_join_self(self, join_type):
index = self.create_index()
joined = index.join(index, how=join_type)
assert index is joined
def test_nbytes(self):
# memory savings vs int index
i = RangeIndex(0, 1000)
assert i.nbytes < i._int64index.nbytes / 10
# constant memory usage
i2 = RangeIndex(0, 10)
assert i.nbytes == i2.nbytes
def test_cant_or_shouldnt_cast(self):
# can't
with pytest.raises(TypeError):
RangeIndex("foo", "bar", "baz")
# shouldn't
with pytest.raises(TypeError):
RangeIndex("0", "1", "2")
def test_view_index(self):
index = self.create_index()
index.view(Index)
def test_prevent_casting(self):
index = self.create_index()
result = index.astype("O")
assert result.dtype == np.object_
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name="foo")
taken = index.take([3, 0, 1])
assert index.name == taken.name
def test_take_fill_value(self):
# GH 12631
idx = pd.RangeIndex(1, 4, name="xxx")
result = idx.take(np.array([1, 0, -1]))
expected = pd.Int64Index([2, 1, 3], name="xxx")
tm.assert_index_equal(result, expected)
# fill_value
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -1]), fill_value=True)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False, fill_value=True)
expected = pd.Int64Index([2, 1, 3], name="xxx")
tm.assert_index_equal(result, expected)
msg = "Unable to fill values because RangeIndex cannot contain NA"
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with pytest.raises(ValueError, match=msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
idx.take(np.array([1, -5]))
def test_print_unicode_columns(self):
df = pd.DataFrame({"\u05d0": [1, 2, 3], "\u05d1": [4, 5, 6], "c": [7, 8, 9]})
repr(df.columns) # should not raise UnicodeDecodeError
def test_repr_roundtrip(self):
index = self.create_index()
tm.assert_index_equal(eval(repr(index)), index)
def test_slice_keep_name(self):
idx = RangeIndex(1, 2, name="asdf")
assert idx.name == idx[1:].name
def test_explicit_conversions(self):
# GH 8608
# add/sub are overridden explicitly for Float/Int Index
idx = RangeIndex(5)
# float conversions
arr = np.arange(5, dtype="int64") * 3.2
expected = Float64Index(arr)
fidx = idx * 3.2
tm.assert_index_equal(fidx, expected)
fidx = 3.2 * idx
tm.assert_index_equal(fidx, expected)
# interops with numpy arrays
expected = Float64Index(arr)
a = np.zeros(5, dtype="float64")
result = fidx - a
tm.assert_index_equal(result, expected)
expected = Float64Index(-arr)
a = np.zeros(5, dtype="float64")
result = a - fidx
tm.assert_index_equal(result, expected)
def test_has_duplicates(self, indices):
assert indices.is_unique
assert not indices.has_duplicates
def test_extended_gcd(self):
index = self.create_index()
result = index._extended_gcd(6, 10)
assert result[0] == result[1] * 6 + result[2] * 10
assert 2 == result[0]
result = index._extended_gcd(10, 6)
assert 2 == result[1] * 10 + result[2] * 6
assert 2 == result[0]
def test_min_fitting_element(self):
result = RangeIndex(0, 20, 2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(1, 6)._min_fitting_element(1)
assert 1 == result
result = RangeIndex(18, -2, -2)._min_fitting_element(1)
assert 2 == result
result = RangeIndex(5, 0, -1)._min_fitting_element(1)
assert 1 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._min_fitting_element(big_num)
assert big_num == result
def test_max_fitting_element(self):
result = RangeIndex(0, 20, 2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(1, 6)._max_fitting_element(4)
assert 4 == result
result = RangeIndex(18, -2, -2)._max_fitting_element(17)
assert 16 == result
result = RangeIndex(5, 0, -1)._max_fitting_element(4)
assert 4 == result
big_num = 500000000000000000000000
result = RangeIndex(5, big_num * 2, 1)._max_fitting_element(big_num)
assert big_num == result
def test_pickle_compat_construction(self):
# RangeIndex() is a valid constructor
pass
def test_slice_specialised(self):
index = self.create_index()
index.name = "foo"
# scalar indexing
res = index[1]
expected = 2
assert res == expected
res = index[-1]
expected = 18
assert res == expected
# slicing
# slice value completion
index_slice = index[:]
expected = index
tm.assert_index_equal(index_slice, expected)
# positive slice values
index_slice = index[7:10:2]
expected = Index(np.array([14, 18]), name="foo")
tm.assert_index_equal(index_slice, expected)
# negative slice values
index_slice = index[-1:-5:-2]
expected = Index(np.array([18, 14]), name="foo")
tm.assert_index_equal(index_slice, expected)
# stop overshoot
index_slice = index[2:100:4]
expected = Index(np.array([4, 12]), name="foo")
tm.assert_index_equal(index_slice, expected)
# reverse
index_slice = index[::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-8::-1]
expected = Index(np.array([4, 2, 0]), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[-40::-1]
expected = Index(np.array([], dtype=np.int64), name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[40::-1]
expected = Index(index.values[40::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
index_slice = index[10::-1]
expected = Index(index.values[::-1], name="foo")
tm.assert_index_equal(index_slice, expected)
@pytest.mark.parametrize("step", set(range(-5, 6)) - {0})
def test_len_specialised(self, step):
# make sure that our len is the same as np.arange calc
start, stop = (0, 5) if step > 0 else (5, 0)
arr = np.arange(start, stop, step)
index = RangeIndex(start, stop, step)
assert len(index) == len(arr)
index = RangeIndex(stop, start, step)
assert len(index) == 0
@pytest.fixture(
params=[
([RI(1, 12, 5)], RI(1, 12, 5)),
([RI(0, 6, 4)], RI(0, 6, 4)),
([RI(1, 3), RI(3, 7)], RI(1, 7)),
([RI(1, 5, 2), RI(5, 6)], RI(1, 6, 2)),
([RI(1, 3, 2), RI(4, 7, 3)], RI(1, 7, 3)),
([RI(-4, 3, 2), RI(4, 7, 2)], RI(-4, 7, 2)),
([RI(-4, -8), RI(-8, -12)], RI(0, 0)),
([RI(-4, -8), RI(3, -4)], RI(0, 0)),
([RI(-4, -8), RI(3, 5)], RI(3, 5)),
([RI(-4, -2), RI(3, 5)], I64([-4, -3, 3, 4])),
([RI(-2), RI(3, 5)], RI(3, 5)),
([RI(2), RI(2)], I64([0, 1, 0, 1])),
([RI(2), RI(2, 5), RI(5, 8, 4)], RI(0, 6)),
([RI(2), RI(3, 5), RI(5, 8, 4)], I64([0, 1, 3, 4, 5])),
([RI(-2, 2), RI(2, 5), RI(5, 8, 4)], RI(-2, 6)),
([RI(3), I64([-1, 3, 15])], I64([0, 1, 2, -1, 3, 15])),
([RI(3), F64([-1, 3.1, 15.0])], F64([0, 1, 2, -1, 3.1, 15.0])),
([RI(3), OI(["a", None, 14])], OI([0, 1, 2, "a", None, 14])),
([RI(3, 1), OI(["a", None, 14])], OI(["a", None, 14])),
]
)
def appends(self, request):
"""Inputs and expected outputs for RangeIndex.append test"""
return request.param
def test_append(self, appends):
# GH16212
indices, expected = appends
result = indices[0].append(indices[1:])
tm.assert_index_equal(result, expected, exact=True)
if len(indices) == 2:
# Append single item rather than list
result2 = indices[0].append(indices[1])
tm.assert_index_equal(result2, expected, exact=True)
def test_engineless_lookup(self):
# GH 16685
# Standard lookup on RangeIndex should not require the engine to be
# created
idx = RangeIndex(2, 10, 3)
assert idx.get_loc(5) == 1
tm.assert_numpy_array_equal(
idx.get_indexer([2, 8]), ensure_platform_int(np.array([0, 2]))
)
with pytest.raises(KeyError, match="3"):
idx.get_loc(3)
assert "_engine" not in idx._cache
# The engine is still required for lookup of a different dtype scalar:
with pytest.raises(KeyError, match="'a'"):
assert idx.get_loc("a") == -1
assert "_engine" in idx._cache
def test_get_indexer_backfill(self):
index = self.create_index()
target = RangeIndex(10)
indexer = index.get_indexer(target, method="backfill")
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_take_preserve_name(self):
index = RangeIndex(1, 5, name='foo')
taken = index.take([3, 0, 1])
assert index.name == taken.name
def test_constructor_range_object(self):
result = RangeIndex(range(1, 5, 2))
expected = RangeIndex(1, 5, 2)
tm.assert_index_equal(result, expected, exact=True)
class Range:
def setup(self):
self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
def time_max(self):
self.idx_inc.max()
def time_max_trivial(self):
self.idx_dec.max()
def time_min(self):
self.idx_dec.min()
def time_min_trivial(self):
self.idx_inc.min()
def time_get_loc_inc(self):
self.idx_inc.get_loc(900000)
def time_get_loc_dec(self):
self.idx_dec.get_loc(100000)
class TestRangeIndexSetOps:
@pytest.mark.parametrize("sort", [None, False])
def test_intersection(self, sort):
# intersect with Int64Index
index = RangeIndex(start=0, stop=20, step=2)
other = Index(np.arange(1, 6))
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
expected = Index(
np.sort(np.asarray(np.intersect1d(index.values, other.values))))
tm.assert_index_equal(result, expected)
# intersect with increasing RangeIndex
other = RangeIndex(1, 6)
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
# intersect with decreasing RangeIndex
other = RangeIndex(5, 0, -1)
result = index.intersection(other, sort=sort)
expected = Index(np.sort(np.intersect1d(index.values, other.values)))
tm.assert_index_equal(result, expected)
# reversed (GH 17296)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# GH 17296: intersect two decreasing RangeIndexes
first = RangeIndex(10, -2, -2)
other = RangeIndex(5, -4, -1)
expected = first.astype(int).intersection(other.astype(int), sort=sort)
result = first.intersection(other, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
# reversed
result = other.intersection(first, sort=sort).astype(int)
tm.assert_index_equal(result, expected)
index = RangeIndex(5)
# intersect of non-overlapping indices
other = RangeIndex(5, 10, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
other = RangeIndex(-1, -5, -1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
# intersection of empty indices
other = RangeIndex(0, 0, 1)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
result = other.intersection(index, sort=sort)
tm.assert_index_equal(result, expected)
# intersection of non-overlapping values based on start value and gcd
index = RangeIndex(1, 10, 2)
other = RangeIndex(0, 10, 4)
result = index.intersection(other, sort=sort)
expected = RangeIndex(0, 0, 1)
tm.assert_index_equal(result, expected)
@pytest.mark.parametrize("sort", [False, None])
def test_union_noncomparable(self, sort):
# corner case, non-Int64Index
index = RangeIndex(start=0, stop=20, step=2)
other = Index([datetime.now() + timedelta(i) for i in range(4)],
dtype=object)
result = index.union(other, sort=sort)
expected = Index(np.concatenate((index, other)))
tm.assert_index_equal(result, expected)
result = other.union(index, sort=sort)
expected = Index(np.concatenate((other, index)))
tm.assert_index_equal(result, expected)
@pytest.fixture(params=[
(
RangeIndex(0, 10, 1),
RangeIndex(0, 10, 1),
RangeIndex(0, 10, 1),
RangeIndex(0, 10, 1),
),
(
RangeIndex(0, 10, 1),
RangeIndex(5, 20, 1),
RangeIndex(0, 20, 1),
Int64Index(range(20)),
),
(
RangeIndex(0, 10, 1),
RangeIndex(10, 20, 1),
RangeIndex(0, 20, 1),
Int64Index(range(20)),
),
(
RangeIndex(0, -10, -1),
RangeIndex(0, -10, -1),
RangeIndex(0, -10, -1),
RangeIndex(0, -10, -1),
),
(
RangeIndex(0, -10, -1),
RangeIndex(-10, -20, -1),
RangeIndex(-19, 1, 1),
Int64Index(range(0, -20, -1)),
),
(
RangeIndex(0, 10, 2),
RangeIndex(1, 10, 2),
RangeIndex(0, 10, 1),
Int64Index(list(range(0, 10, 2)) + list(range(1, 10, 2))),
),
(
RangeIndex(0, 11, 2),
RangeIndex(1, 12, 2),
RangeIndex(0, 12, 1),
Int64Index(list(range(0, 11, 2)) + list(range(1, 12, 2))),
),
(
RangeIndex(0, 21, 4),
RangeIndex(-2, 24, 4),
RangeIndex(-2, 24, 2),
Int64Index(list(range(0, 21, 4)) + list(range(-2, 24, 4))),
),
(
RangeIndex(0, -20, -2),
RangeIndex(-1, -21, -2),
RangeIndex(-19, 1, 1),
Int64Index(list(range(0, -20, -2)) + list(range(-1, -21, -2))),
),
(
RangeIndex(0, 100, 5),
RangeIndex(0, 100, 20),
RangeIndex(0, 100, 5),
Int64Index(range(0, 100, 5)),
),
(
RangeIndex(0, -100, -5),
RangeIndex(5, -100, -20),
RangeIndex(-95, 10, 5),
Int64Index(list(range(0, -100, -5)) + [5]),
),
(
RangeIndex(0, -11, -1),
RangeIndex(1, -12, -4),
RangeIndex(-11, 2, 1),
Int64Index(list(range(0, -11, -1)) + [1, -11]),
),
(RangeIndex(0), RangeIndex(0), RangeIndex(0), RangeIndex(0)),
(
RangeIndex(0, -10, -2),
RangeIndex(0),
RangeIndex(0, -10, -2),
RangeIndex(0, -10, -2),
),
(
RangeIndex(0, 100, 2),
RangeIndex(100, 150, 200),
RangeIndex(0, 102, 2),
Int64Index(range(0, 102, 2)),
),
(
RangeIndex(0, -100, -2),
RangeIndex(-100, 50, 102),
RangeIndex(-100, 4, 2),
Int64Index(list(range(0, -100, -2)) + [-100, 2]),
),
(
RangeIndex(0, -100, -1),
RangeIndex(0, -50, -3),
RangeIndex(-99, 1, 1),
Int64Index(list(range(0, -100, -1))),
),
(
RangeIndex(0, 1, 1),
RangeIndex(5, 6, 10),
RangeIndex(0, 6, 5),
Int64Index([0, 5]),
),
(
RangeIndex(0, 10, 5),
RangeIndex(-5, -6, -20),
RangeIndex(-5, 10, 5),
Int64Index([0, 5, -5]),
),
(
RangeIndex(0, 3, 1),
RangeIndex(4, 5, 1),
Int64Index([0, 1, 2, 4]),
Int64Index([0, 1, 2, 4]),
),
(
RangeIndex(0, 10, 1),
Int64Index([]),
RangeIndex(0, 10, 1),
RangeIndex(0, 10, 1),
),
(
RangeIndex(0),
Int64Index([1, 5, 6]),
Int64Index([1, 5, 6]),
Int64Index([1, 5, 6]),
),
])
def unions(self, request):
"""Inputs and expected outputs for RangeIndex.union tests"""
return request.param
def test_union_sorted(self, unions):
idx1, idx2, expected_sorted, expected_notsorted = unions
res1 = idx1.union(idx2, sort=None)
tm.assert_index_equal(res1, expected_sorted, exact=True)
res1 = idx1.union(idx2, sort=False)
tm.assert_index_equal(res1, expected_notsorted, exact=True)
res2 = idx2.union(idx1, sort=None)
res3 = idx1._int64index.union(idx2, sort=None)
tm.assert_index_equal(res2, expected_sorted, exact=True)
tm.assert_index_equal(res3, expected_sorted)