def test_cached_data(self):
# GH 26565
# Calling RangeIndex._data caches an int64 array of the same length at
# self._cached_data. This tests 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
df = pd.DataFrame({'a': range(10)}, index=idx)
df.loc[50]
assert idx._cached_data is None
with pytest.raises(KeyError):
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 data._data
assert isinstance(idx._data, np.ndarray)
assert isinstance(idx._cached_data, np.ndarray)
def test_cache(self):
# GH 26565, GH26617, GH35432
# This test checks whether _cache has been set.
# Calling RangeIndex._cache["_data"] creates an int64 array of the same length
# as the RangeIndex and stores it in _cache.
idx = RangeIndex(0, 100, 10)
assert idx._cache == {}
repr(idx)
assert idx._cache == {}
str(idx)
assert idx._cache == {}
idx.get_loc(20)
assert idx._cache == {}
90 in idx # True
assert idx._cache == {}
91 in idx # False
assert idx._cache == {}
idx.all()
assert idx._cache == {}
idx.any()
assert idx._cache == {}
for _ in idx:
pass
assert idx._cache == {}
df = pd.DataFrame({"a": range(10)}, index=idx)
df.loc[50]
assert idx._cache == {}
with pytest.raises(KeyError, match="51"):
df.loc[51]
assert idx._cache == {}
df.loc[10:50]
assert idx._cache == {}
df.iloc[5:10]
assert idx._cache == {}
# idx._cache should contain a _data entry after call to idx._data
idx._data
assert isinstance(idx._data, np.ndarray)
assert idx._data is idx._data # check cached value is reused
assert len(idx._cache) == 4
expected = np.arange(0, 100, 10, dtype="int64")
tm.assert_numpy_array_equal(idx._cache["_data"], expected)
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
with tm.assert_produces_warning(FutureWarning):
idx.contains(90)
assert idx._cached_data is None
with tm.assert_produces_warning(FutureWarning):
idx.contains(91)
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):
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_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.contains(90)
assert idx._cached_data is None
idx.contains(91)
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):
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_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
idx.format()
assert idx._cache == {}
df = pd.DataFrame({"a": range(10)}, index=idx)
str(df)
assert idx._cache == {}
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_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):
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):
assert idx.get_loc('a') == -1
assert '_engine' in idx._cache
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
# Different types of scalars can be excluded immediately, no need to
# use the _engine
with pytest.raises(KeyError, match="'a'"):
idx.get_loc("a")
assert "_engine" not in idx._cache
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 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)
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, freq=base_index.freq)
# 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)
# To avoid possible inconsistencies with `get_loc` below,
# set the key directly equal to the last index location
key = index[-1]
# 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 - 1
else:
end = loc
return loc, index[:end + 1], index_was_expanded
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
def _get_index_loc(self, key, base_index=None):
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:
# 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, 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:
# 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, 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_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
