def __getitem__(self, arg):
if isinstance(arg, Number):
arg = int(arg)
return self.element_indexing(arg)
elif isinstance(arg, slice):
# compute mask slice
start, stop = utils.normalize_slice(arg, len(self))
if self.null_count > 0:
if arg.step is not None and arg.step != 1:
raise NotImplementedError(arg)
# slicing data
subdata = self.data[arg]
# slicing mask
bytemask = cudautils.expand_mask_bits(
self.data.size,
self.mask.to_gpu_array(),
)
submask = Buffer(cudautils.compact_mask_bytes(bytemask[arg]))
col = self.replace(data=subdata, mask=submask)
return col
else:
newbuffer = self.data[arg]
return self.replace(data=newbuffer)
else:
raise NotImplementedError(type(arg))
def to_pandas(self):
arr = self.data_array_view
sr = pd.Series(arr.copy_to_host())
if self.nullable:
mask_bytes = (cudautils.expand_mask_bits(
len(self), self.mask_array_view).copy_to_host().astype(bool))
sr[~mask_bytes] = None
return sr
def to_arrow(self):
mask = None
if self.has_null_mask:
# Necessary because PyArrow doesn't support from_buffers for
# DictionaryArray yet
mask = pa.array(
# Why does expand_mask_bits return as int32?
cudautils.expand_mask_bits(
len(self),
self.nullmask.mem).copy_to_host().astype('int8'))
indices = pa.array(self.cat().codes.data.mem.copy_to_host())
ordered = self.cat()._ordered
dictionary = pa.array(self.cat().categories)
return pa.DictionaryArray.from_arrays(indices=indices,
dictionary=dictionary,
mask=mask,
from_pandas=True,
ordered=ordered)
def __getitem__(self, arg):
from cudf.dataframe import columnops
if isinstance(arg, Number):
arg = int(arg)
return self.element_indexing(arg)
elif isinstance(arg, slice):
# compute mask slice
if self.null_count > 0:
if arg.step is not None and arg.step != 1:
raise NotImplementedError(arg)
# slicing data
subdata = self.data[arg]
# slicing mask
if self.dtype == "object":
data_size = self.data.size()
else:
data_size = self.data.size
bytemask = cudautils.expand_mask_bits(data_size,
self.mask.to_gpu_array())
submask = Buffer(cudautils.compact_mask_bytes(bytemask[arg]))
col = self.replace(data=subdata, mask=submask)
return col
else:
newbuffer = self.data[arg]
return self.replace(data=newbuffer)
else:
arg = columnops.as_column(arg)
if len(arg) == 0:
arg = columnops.as_column([], dtype="int32")
if pd.api.types.is_integer_dtype(arg.dtype):
return self.take(arg.data.mem)
if pd.api.types.is_bool_dtype(arg.dtype):
return self.apply_boolean_mask(arg)
raise NotImplementedError(type(arg))
def __getitem__(self, arg):
from cudf.core.column import column
if isinstance(arg, Number):
arg = int(arg)
return self.element_indexing(arg)
elif isinstance(arg, slice):
if is_categorical_dtype(self):
codes = self.codes[arg]
return build_column(
data=None,
dtype=self.dtype,
mask=codes.mask,
children=(codes,),
)
start, stop, stride = arg.indices(len(self))
if start == stop:
return column_empty(0, self.dtype, masked=True)
# compute mask slice
if self.has_nulls:
if arg.step is not None and arg.step != 1:
raise NotImplementedError(arg)
# slicing data
slice_data = self.data_array_view[arg]
# slicing mask
data_size = self.size
bytemask = cudautils.expand_mask_bits(
data_size, self.mask_array_view
)
slice_mask = cudautils.compact_mask_bytes(bytemask[arg])
else:
slice_data = self.data_array_view[arg]
slice_mask = None
if self.dtype == "object":
return as_column(slice_data)
else:
if arg.step is not None and arg.step != 1:
slice_data = cudautils.as_contiguous(slice_data)
slice_data = Buffer(slice_data)
else:
# data Buffer lifetime is tied to self:
slice_data = Buffer(
data=slice_data.device_ctypes_pointer.value,
size=slice_data.nbytes,
owner=self,
)
# mask Buffer lifetime is not:
if slice_mask is not None:
slice_mask = Buffer(slice_mask)
return build_column(slice_data, self.dtype, mask=slice_mask)
else:
arg = column.as_column(arg)
if len(arg) == 0:
arg = column.as_column([], dtype="int32")
if pd.api.types.is_integer_dtype(arg.dtype):
return self.take(arg)
if pd.api.types.is_bool_dtype(arg.dtype):
return self.apply_boolean_mask(arg)
raise NotImplementedError(type(arg))
