def test_basic(self):
self.assertTrue(is_categorical_dtype(self.dtype))
factor = Categorical(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
s = Series(factor, name='A')
# dtypes
self.assertTrue(is_categorical_dtype(s.dtype))
self.assertTrue(is_categorical_dtype(s))
self.assertFalse(is_categorical_dtype(np.dtype('float64')))
self.assertTrue(is_categorical(s.dtype))
self.assertTrue(is_categorical(s))
self.assertFalse(is_categorical(np.dtype('float64')))
self.assertFalse(is_categorical(1.0))
def test_basic(self):
self.assertTrue(is_categorical_dtype(self.dtype))
factor = Categorical(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
s = Series(factor, name='A')
# dtypes
self.assertTrue(is_categorical_dtype(s.dtype))
self.assertTrue(is_categorical_dtype(s))
self.assertFalse(is_categorical_dtype(np.dtype('float64')))
self.assertTrue(is_categorical(s.dtype))
self.assertTrue(is_categorical(s))
self.assertFalse(is_categorical(np.dtype('float64')))
self.assertFalse(is_categorical(1.0))
def take_nd(arr,
indexer,
axis=0,
out=None,
fill_value=np.nan,
mask_info=None,
allow_fill=True):
"""
Specialized Cython take which sets NaN values in one pass
Parameters
----------
arr : ndarray
Input array
indexer : ndarray
1-D array of indices to take, subarrays corresponding to -1 value
indicies are filed with fill_value
axis : int, default 0
Axis to take from
out : ndarray or None, default None
Optional output array, must be appropriate type to hold input and
fill_value together, if indexer has any -1 value entries; call
_maybe_promote to determine this type for any fill_value
fill_value : any, default np.nan
Fill value to replace -1 values with
mask_info : tuple of (ndarray, boolean)
If provided, value should correspond to:
(indexer != -1, (indexer != -1).any())
If not provided, it will be computed internally if necessary
allow_fill : boolean, default True
If False, indexer is assumed to contain no -1 values so no filling
will be done. This short-circuits computation of a mask. Result is
undefined if allow_fill == False and -1 is present in indexer.
"""
# dispatch to internal type takes
if is_categorical(arr):
return arr.take_nd(indexer,
fill_value=fill_value,
allow_fill=allow_fill)
elif is_datetimetz(arr):
return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
if indexer is None:
indexer = np.arange(arr.shape[axis], dtype=np.int64)
dtype, fill_value = arr.dtype, arr.dtype.type()
else:
indexer = _ensure_int64(indexer)
if not allow_fill:
dtype, fill_value = arr.dtype, arr.dtype.type()
mask_info = None, False
else:
# check for promotion based on types only (do this first because
# it's faster than computing a mask)
dtype, fill_value = _maybe_promote(arr.dtype, fill_value)
if dtype != arr.dtype and (out is None or out.dtype != dtype):
# check if promotion is actually required based on indexer
if mask_info is not None:
mask, needs_masking = mask_info
else:
mask = indexer == -1
needs_masking = mask.any()
mask_info = mask, needs_masking
if needs_masking:
if out is not None and out.dtype != dtype:
raise TypeError('Incompatible type for fill_value')
else:
# if not, then depromote, set fill_value to dummy
# (it won't be used but we don't want the cython code
# to crash when trying to cast it to dtype)
dtype, fill_value = arr.dtype, arr.dtype.type()
flip_order = False
if arr.ndim == 2:
if arr.flags.f_contiguous:
flip_order = True
if flip_order:
arr = arr.T
axis = arr.ndim - axis - 1
if out is not None:
out = out.T
# at this point, it's guaranteed that dtype can hold both the arr values
# and the fill_value
if out is None:
out_shape = list(arr.shape)
out_shape[axis] = len(indexer)
out_shape = tuple(out_shape)
if arr.flags.f_contiguous and axis == arr.ndim - 1:
# minor tweak that can make an order-of-magnitude difference
# for dataframes initialized directly from 2-d ndarrays
# (s.t. df.values is c-contiguous and df._data.blocks[0] is its
# f-contiguous transpose)
out = np.empty(out_shape, dtype=dtype, order='F')
else:
out = np.empty(out_shape, dtype=dtype)
func = _get_take_nd_function(arr.ndim,
arr.dtype,
out.dtype,
axis=axis,
mask_info=mask_info)
indexer = _ensure_int64(indexer)
func(arr, indexer, out, fill_value)
if flip_order:
out = out.T
return out
def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan, mask_info=None,
allow_fill=True):
"""
Specialized Cython take which sets NaN values in one pass
Parameters
----------
arr : ndarray
Input array
indexer : ndarray
1-D array of indices to take, subarrays corresponding to -1 value
indicies are filed with fill_value
axis : int, default 0
Axis to take from
out : ndarray or None, default None
Optional output array, must be appropriate type to hold input and
fill_value together, if indexer has any -1 value entries; call
_maybe_promote to determine this type for any fill_value
fill_value : any, default np.nan
Fill value to replace -1 values with
mask_info : tuple of (ndarray, boolean)
If provided, value should correspond to:
(indexer != -1, (indexer != -1).any())
If not provided, it will be computed internally if necessary
allow_fill : boolean, default True
If False, indexer is assumed to contain no -1 values so no filling
will be done. This short-circuits computation of a mask. Result is
undefined if allow_fill == False and -1 is present in indexer.
"""
# dispatch to internal type takes
if is_categorical(arr):
return arr.take_nd(indexer, fill_value=fill_value,
allow_fill=allow_fill)
elif is_datetimetz(arr):
return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
if indexer is None:
indexer = np.arange(arr.shape[axis], dtype=np.int64)
dtype, fill_value = arr.dtype, arr.dtype.type()
else:
indexer = _ensure_int64(indexer)
if not allow_fill:
dtype, fill_value = arr.dtype, arr.dtype.type()
mask_info = None, False
else:
# check for promotion based on types only (do this first because
# it's faster than computing a mask)
dtype, fill_value = _maybe_promote(arr.dtype, fill_value)
if dtype != arr.dtype and (out is None or out.dtype != dtype):
# check if promotion is actually required based on indexer
if mask_info is not None:
mask, needs_masking = mask_info
else:
mask = indexer == -1
needs_masking = mask.any()
mask_info = mask, needs_masking
if needs_masking:
if out is not None and out.dtype != dtype:
raise TypeError('Incompatible type for fill_value')
else:
# if not, then depromote, set fill_value to dummy
# (it won't be used but we don't want the cython code
# to crash when trying to cast it to dtype)
dtype, fill_value = arr.dtype, arr.dtype.type()
flip_order = False
if arr.ndim == 2:
if arr.flags.f_contiguous:
flip_order = True
if flip_order:
arr = arr.T
axis = arr.ndim - axis - 1
if out is not None:
out = out.T
# at this point, it's guaranteed that dtype can hold both the arr values
# and the fill_value
if out is None:
out_shape = list(arr.shape)
out_shape[axis] = len(indexer)
out_shape = tuple(out_shape)
if arr.flags.f_contiguous and axis == arr.ndim - 1:
# minor tweak that can make an order-of-magnitude difference
# for dataframes initialized directly from 2-d ndarrays
# (s.t. df.values is c-contiguous and df._data.blocks[0] is its
# f-contiguous transpose)
out = np.empty(out_shape, dtype=dtype, order='F')
else:
out = np.empty(out_shape, dtype=dtype)
func = _get_take_nd_function(arr.ndim, arr.dtype, out.dtype, axis=axis,
mask_info=mask_info)
indexer = _ensure_int64(indexer)
func(arr, indexer, out, fill_value)
if flip_order:
out = out.T
return out
