def array_to_series(array):
if isinstance(array, pa.ChunkedArray):
return Series._concat(
[array_to_series(chunk) for chunk in array.chunks]
)
if isinstance(array, pa.Column):
return Series._concat(
[array_to_series(chunk) for chunk in array.data.chunks]
)
array_len = len(array)
null_count = array.null_count
buffers = make_device_arrays(array)
mask, data = buffers[0], buffers[1]
dtype = arrow_to_pandas_dtype(array.type)
if pa.types.is_dictionary(array.type):
from cudf.dataframe import CategoricalColumn
codes = array_to_series(array.indices)
categories = array_to_series(array.dictionary)
data = CategoricalColumn(
data=codes.data,
mask=mask,
null_count=null_count,
categories=categories,
ordered=array.type.ordered,
)
elif pa.types.is_string(array.type):
import nvstrings
offs, data = buffers[1], buffers[2]
offs = offs[array.offset : array.offset + array_len + 1]
data = None if data is None else data.device_ctypes_pointer.value
mask = None if mask is None else mask.device_ctypes_pointer.value
data = nvstrings.from_offsets(
data,
offs.device_ctypes_pointer.value,
array_len,
mask,
null_count,
True,
)
elif data is not None:
data = data[array.offset : array.offset + len(array)]
series = Series(data, dtype=dtype)
if null_count > 0 and mask is not None and not series.has_null_mask:
return series.set_mask(mask, null_count)
return series
def make_series(self):
"""Make a Series object out of this node
"""
if self.is_dictionary:
sr = self._make_dictionary_series()
else:
sr = Series(self.data)
# set nullmask
if self.null_count:
sr = sr.set_mask(self.null, null_count=self.null_count)
return sr
