def dataframe_to_serialized_dict(frame):
block_manager = frame._data
blocks = []
axes = [ax for ax in block_manager.axes]
for block in block_manager.blocks:
values = block.values
block_data = {}
if _pandas_api.is_datetimetz(values.dtype):
block_data['timezone'] = pa.lib.tzinfo_to_string(values.tz)
if hasattr(values, 'values'):
values = values.values
elif _pandas_api.is_categorical(values):
block_data.update(dictionary=values.categories,
ordered=values.ordered)
values = values.codes
block_data.update(
placement=block.mgr_locs.as_array,
block=values
)
# If we are dealing with an object array, pickle it instead.
if values.dtype == np.dtype(object):
block_data['object'] = None
block_data['block'] = builtin_pickle.dumps(
values, protocol=builtin_pickle.HIGHEST_PROTOCOL)
blocks.append(block_data)
return {
'blocks': blocks,
'axes': axes
}
def dataframe_to_serialized_dict(frame):
import pandas.core.internals as _int
block_manager = frame._data
blocks = []
axes = [ax for ax in block_manager.axes]
for block in block_manager.blocks:
values = block.values
block_data = {}
if isinstance(block, _int.DatetimeTZBlock):
block_data['timezone'] = pa.lib.tzinfo_to_string(values.tz)
if hasattr(values, 'values'):
values = values.values
elif isinstance(block, _int.CategoricalBlock):
block_data.update(dictionary=values.categories,
ordered=values.ordered)
values = values.codes
block_data.update(placement=block.mgr_locs.as_array, block=values)
# If we are dealing with an object array, pickle it instead. Note that
# we do not use isinstance here because _int.CategoricalBlock is a
# subclass of _int.ObjectBlock.
if type(block) == _int.ObjectBlock:
block_data['object'] = None
block_data['block'] = builtin_pickle.dumps(
values, protocol=builtin_pickle.HIGHEST_PROTOCOL)
blocks.append(block_data)
return {'blocks': blocks, 'axes': axes}
def _pickle_to_buffer(x):
pickled = builtin_pickle.dumps(x, protocol=builtin_pickle.HIGHEST_PROTOCOL)
return py_buffer(pickled)