def _format_labels(bins,
precision: int,
right: bool = True,
include_lowest: bool = False,
dtype=None):
""" based on the dtype, return our labels """
closed = "right" if right else "left"
if is_datetime64tz_dtype(dtype):
formatter = lambda x: Timestamp(x, tz=dtype.tz)
adjust = lambda x: x - Timedelta("1ns")
elif is_datetime64_dtype(dtype):
formatter = Timestamp
adjust = lambda x: x - Timedelta("1ns")
elif is_timedelta64_dtype(dtype):
formatter = Timedelta
adjust = lambda x: x - Timedelta("1ns")
else:
precision = _infer_precision(precision, bins)
formatter = lambda x: _round_frac(x, precision)
adjust = lambda x: x - 10**(-precision)
breaks = [formatter(b) for b in bins]
labels = IntervalIndex.from_breaks(breaks, closed=closed)
if right and include_lowest:
# we will adjust the left hand side by precision to
# account that we are all right closed
v = adjust(labels[0].left)
i = IntervalIndex([Interval(v, labels[0].right, closed="right")])
labels = i.append(labels[1:])
return labels
def get_loc(self, key, method=None):
self._check_method(method)
original_key = key
key = self._maybe_cast_indexed(key)
if self.is_non_overlapping_monotonic:
if isinstance(key, Interval):
left = self._maybe_cast_slice_bound(key.left, 'left', None)
right = self._maybe_cast_slice_bound(key.right, 'right', None)
key = Interval(left, right, key.closed)
else:
key = self._maybe_cast_slice_bound(key, 'left', None)
start, stop = self._find_non_overlapping_monotonic_bounds(key)
if start is None or stop is None:
return slice(start, stop)
elif start + 1 == stop:
return start
elif start < stop:
return slice(start, stop)
else:
raise KeyError(original_key)
else:
# use the interval tree
if isinstance(key, Interval):
left, right = _get_interval_closed_bounds(key)
return self._engine.get_loc_interval(left, right)
else:
return self._engine.get_loc(key)
def __getitem__(self, value):
left = self.left[value]
right = self.right[value]
# scalar
if not isinstance(left, ABCIndexClass):
if isna(left):
return self._fill_value
return Interval(left, right, self.closed)
return self._shallow_copy(left, right)
def __getitem__(self, value):
mask = self._isnan[value]
if is_scalar(mask) and mask:
return self._na_value
left = self.left[value]
right = self.right[value]
# scalar
if not isinstance(left, Index):
return Interval(left, right, self.closed)
return self._shallow_copy(left, right)
def _ndarray_values(self):
left = self.left
right = self.right
mask = self._isnan
closed = self.closed
result = np.empty(len(left), dtype=object)
for i in range(len(left)):
if mask[i]:
result[i] = np.nan
else:
result[i] = Interval(left[i], right[i], closed)
return result
def __getitem__(self, key):
key = check_array_indexer(self, key)
left = self._left[key]
right = self._right[key]
if not isinstance(left, (np.ndarray, ExtensionArray)):
# scalar
if is_scalar(left) and isna(left):
return self._fill_value
return Interval(left, right, self.closed)
if np.ndim(left) > 1:
# GH#30588 multi-dimensional indexer disallowed
raise ValueError("multi-dimensional indexing not allowed")
return self._shallow_copy(left, right)
def __getitem__(self, value):
left = self.left[value]
right = self.right[value]
# scalar
if not isinstance(left, ABCIndexClass):
if is_scalar(left) and isna(left):
return self._fill_value
if np.ndim(left) > 1:
# GH#30588 multi-dimensional indexer disallowed
raise ValueError("multi-dimensional indexing not allowed")
return Interval(left, right, self.closed)
return self._shallow_copy(left, right)
def __getitem__(self, key):
key = check_array_indexer(self, key)
result = self._combined[key]
if is_integer(key):
left, right = result[0], result[1]
if isna(left):
return self._fill_value
return Interval(left, right, self.closed)
# TODO: need to watch out for incorrectly-reducing getitem
if np.ndim(result) > 2:
# GH#30588 multi-dimensional indexer disallowed
raise ValueError("multi-dimensional indexing not allowed")
return type(self)._simple_new(result, closed=self.closed)
def values(self):
"""
Returns the IntervalIndex's data as a numpy array of Interval
objects (with dtype='object')
"""
left = self.left
right = self.right
mask = self._isnan
closed = self._closed
result = np.empty(len(left), dtype=object)
for i in range(len(left)):
if mask[i]:
result[i] = np.nan
else:
result[i] = Interval(left[i], right[i], closed)
return result
def __array__(self, dtype=None) -> np.ndarray:
"""
Return the IntervalArray's data as a numpy array of Interval
objects (with dtype='object')
"""
left = self.left
right = self.right
mask = self.isna()
closed = self._closed
result = np.empty(len(left), dtype=object)
for i in range(len(left)):
if mask[i]:
result[i] = np.nan
else:
result[i] = Interval(left[i], right[i], closed)
return result
def test__one_hot_encoded_targets(self):
"""given"""
df = pd.DataFrame({"a": [-0.1, 0, 0.1], "b": [0, 1, 2]})
encoder = OneHotEncodedTargets(
"a", np.linspace(-0.1, 0.1, 4, endpoint=True))
"""when"""
encoded = encoder.encode(df)
decoded = encoder.decode(encoded)
"""then"""
np.testing.assert_array_almost_equal(
encoded.values, np.array([[1., 0., 0.], [0., 1., 0.], [0., 0.,
1.]]))
self.assertEqual(
decoded[1],
Interval(-0.03333333333333334,
0.033333333333333326,
closed='right'))
def get_loc(self, key, method=None):
"""Get integer location, slice or boolean mask for requested label.
Parameters
----------
key : label
method : {None}, optional
* default: matches where the label is within an interval only.
Returns
-------
loc : int if unique index, slice if monotonic index, else mask
Examples
---------
>>> i1, i2 = pd.Interval(0, 1), pd.Interval(1, 2)
>>> index = pd.IntervalIndex.from_intervals([i1, i2])
>>> index.get_loc(1)
0
You can also supply an interval or an location for a point inside an
interval.
>>> index.get_loc(pd.Interval(0, 2))
array([0, 1], dtype=int64)
>>> index.get_loc(1.5)
1
If a label is in several intervals, you get the locations of all the
relevant intervals.
>>> i3 = pd.Interval(0, 2)
>>> overlapping_index = pd.IntervalIndex.from_intervals([i2, i3])
>>> overlapping_index.get_loc(1.5)
array([0, 1], dtype=int64)
"""
self._check_method(method)
original_key = key
key = self._maybe_cast_indexed(key)
if self.is_non_overlapping_monotonic:
if isinstance(key, Interval):
left = self._maybe_cast_slice_bound(key.left, 'left', None)
right = self._maybe_cast_slice_bound(key.right, 'right', None)
key = Interval(left, right, key.closed)
else:
key = self._maybe_cast_slice_bound(key, 'left', None)
start, stop = self._find_non_overlapping_monotonic_bounds(key)
if start is None or stop is None:
return slice(start, stop)
elif start + 1 == stop:
return start
elif start < stop:
return slice(start, stop)
else:
raise KeyError(original_key)
else:
# use the interval tree
if isinstance(key, Interval):
left, right = _get_interval_closed_bounds(key)
return self._engine.get_loc_interval(left, right)
else:
return self._engine.get_loc(key)
