def concatenate_block_managers(mgrs_indexers, axes, concat_axis: int,
copy: bool) -> BlockManager:
"""
Concatenate block managers into one.
Parameters
----------
mgrs_indexers : list of (BlockManager, {axis: indexer,...}) tuples
axes : list of Index
concat_axis : int
copy : bool
Returns
-------
BlockManager
"""
concat_plans = [
_get_mgr_concatenation_plan(mgr, indexers)
for mgr, indexers in mgrs_indexers
]
concat_plan = _combine_concat_plans(concat_plans, concat_axis)
blocks = []
for placement, join_units in concat_plan:
if len(join_units) == 1 and not join_units[0].indexers:
b = join_units[0].block
values = b.values
if copy:
values = values.copy()
else:
values = values.view()
b = b.make_block_same_class(values, placement=placement)
elif _is_uniform_join_units(join_units):
blk = join_units[0].block
vals = [ju.block.values for ju in join_units]
if not blk.is_extension:
values = concat_compat(vals, axis=blk.ndim - 1)
else:
# TODO(EA2D): special-casing not needed with 2D EAs
values = concat_compat(vals)
if not isinstance(values, ExtensionArray):
values = values.reshape(1, len(values))
b = make_block(values, placement=placement, ndim=blk.ndim)
else:
b = make_block(
_concatenate_join_units(join_units, concat_axis, copy=copy),
placement=placement,
ndim=len(axes),
)
blocks.append(b)
return BlockManager(blocks, axes)
def concatenate_block_managers(mgrs_indexers, axes, concat_axis: int,
copy: bool) -> BlockManager:
"""
Concatenate block managers into one.
Parameters
----------
mgrs_indexers : list of (BlockManager, {axis: indexer,...}) tuples
axes : list of Index
concat_axis : int
copy : bool
Returns
-------
BlockManager
"""
concat_plans = [
_get_mgr_concatenation_plan(mgr, indexers)
for mgr, indexers in mgrs_indexers
]
concat_plan = _combine_concat_plans(concat_plans, concat_axis)
blocks = []
for placement, join_units in concat_plan:
if len(join_units) == 1 and not join_units[0].indexers:
b = join_units[0].block
values = b.values
if copy:
values = values.copy()
else:
values = values.view()
b = b.make_block_same_class(values, placement=placement)
elif _is_uniform_join_units(join_units):
blk = join_units[0].block
vals = [ju.block.values for ju in join_units]
if not blk.is_extension or blk.is_datetimetz or blk.is_categorical:
# datetimetz and categorical can have the same type but multiple
# dtypes, concatting does not necessarily preserve dtype
values = concat_compat(vals, axis=blk.ndim - 1)
else:
# TODO(EA2D): special-casing not needed with 2D EAs
values = concat_compat(vals)
b = make_block(values, placement=placement, ndim=blk.ndim)
else:
b = make_block(
_concatenate_join_units(join_units, concat_axis, copy=copy),
placement=placement,
)
blocks.append(b)
return BlockManager(blocks, axes)
def apply_with_block(self: T, f, align_keys=None, **kwargs) -> T:
align_keys = align_keys or []
aligned_args = {k: kwargs[k] for k in align_keys}
result_arrays = []
for i, arr in enumerate(self.arrays):
if aligned_args:
for k, obj in aligned_args.items():
if isinstance(obj, (ABCSeries, ABCDataFrame)):
# The caller is responsible for ensuring that
# obj.axes[-1].equals(self.items)
if obj.ndim == 1:
if self.ndim == 2:
kwargs[k] = obj.iloc[slice(i, i + 1)]._values
else:
kwargs[k] = obj.iloc[:]._values
else:
kwargs[k] = obj.iloc[:, [i]]._values
else:
# otherwise we have an ndarray
if obj.ndim == 2:
kwargs[k] = obj[[i]]
if hasattr(arr,
"tz") and arr.tz is None: # type: ignore[union-attr]
# DatetimeArray needs to be converted to ndarray for DatetimeBlock
arr = arr._data # type: ignore[union-attr]
elif arr.dtype.kind == "m" and not isinstance(arr, np.ndarray):
# TimedeltaArray needs to be converted to ndarray for TimedeltaBlock
arr = arr._data # type: ignore[union-attr]
if self.ndim == 2:
if isinstance(arr, np.ndarray):
arr = np.atleast_2d(arr)
block = make_block(arr, placement=slice(0, 1, 1), ndim=2)
else:
block = make_block(arr,
placement=slice(0, len(self), 1),
ndim=1)
applied = getattr(block, f)(**kwargs)
if isinstance(applied, list):
applied = applied[0]
arr = applied.values
if self.ndim == 2:
if isinstance(arr, np.ndarray):
arr = arr[0, :]
result_arrays.append(arr)
return type(self)(result_arrays, self._axes)
def iget(self, i: int) -> SingleBlockManager:
"""
Return the data as a SingleBlockManager.
"""
from pandas.core.internals.managers import SingleBlockManager
values = self.arrays[i]
block = make_block(values, placement=slice(0, len(values)), ndim=1)
return SingleBlockManager(block, self._axes[0])
def init_ndarray(values, index, columns, dtype=None, copy=False):
# input must be a ndarray, list, Series, index
if isinstance(values, ABCSeries):
if columns is None:
if values.name is not None:
columns = [values.name]
if index is None:
index = values.index
else:
values = values.reindex(index)
# zero len case (GH #2234)
if not len(values) and columns is not None and len(columns):
values = np.empty((0, 1), dtype=object)
# we could have a categorical type passed or coerced to 'category'
# recast this to an arrays_to_mgr
if is_categorical_dtype(getattr(values, "dtype",
None)) or is_categorical_dtype(dtype):
if not hasattr(values, "dtype"):
values = prep_ndarray(values, copy=copy)
values = values.ravel()
elif copy:
values = values.copy()
index, columns = _get_axes(len(values), 1, index, columns)
return arrays_to_mgr([values], columns, index, columns, dtype=dtype)
elif is_extension_array_dtype(values):
# GH#19157
if columns is None:
columns = [0]
return arrays_to_mgr([values], columns, index, columns, dtype=dtype)
# by definition an array here
# the dtypes will be coerced to a single dtype
values = prep_ndarray(values, copy=copy)
if dtype is not None:
if not is_dtype_equal(values.dtype, dtype):
try:
values = values.astype(dtype)
except Exception as orig:
# e.g. ValueError when trying to cast object dtype to float64
raise ValueError("failed to cast to '{dtype}' (Exception "
"was: {orig})".format(dtype=dtype,
orig=orig)) from orig
index, columns = _get_axes(*values.shape, index=index, columns=columns)
values = values.T
# if we don't have a dtype specified, then try to convert objects
# on the entire block; this is to convert if we have datetimelike's
# embedded in an object type
if dtype is None and is_object_dtype(values):
if values.ndim == 2 and values.shape[0] != 1:
# transpose and separate blocks
dvals_list = [maybe_infer_to_datetimelike(row) for row in values]
for n in range(len(dvals_list)):
if isinstance(dvals_list[n], np.ndarray):
dvals_list[n] = dvals_list[n].reshape(1, -1)
from pandas.core.internals.blocks import make_block
# TODO: What about re-joining object columns?
block_values = [
make_block(dvals_list[n], placement=[n])
for n in range(len(dvals_list))
]
else:
datelike_vals = maybe_infer_to_datetimelike(values)
block_values = [datelike_vals]
else:
block_values = [values]
return create_block_manager_from_blocks(block_values, [columns, index])
def init_ndarray(values, index, columns, dtype: Optional[DtypeObj], copy: bool):
# input must be a ndarray, list, Series, index
if isinstance(values, ABCSeries):
if columns is None:
if values.name is not None:
columns = [values.name]
if index is None:
index = values.index
else:
values = values.reindex(index)
# zero len case (GH #2234)
if not len(values) and columns is not None and len(columns):
values = np.empty((0, 1), dtype=object)
if is_extension_array_dtype(values) or is_extension_array_dtype(dtype):
# GH#19157
if isinstance(values, np.ndarray) and values.ndim > 1:
# GH#12513 a EA dtype passed with a 2D array, split into
# multiple EAs that view the values
values = [values[:, n] for n in range(values.shape[1])]
else:
values = [values]
if columns is None:
columns = Index(range(len(values)))
return arrays_to_mgr(values, columns, index, columns, dtype=dtype)
# by definition an array here
# the dtypes will be coerced to a single dtype
values = _prep_ndarray(values, copy=copy)
if dtype is not None and not is_dtype_equal(values.dtype, dtype):
try:
values = construct_1d_ndarray_preserving_na(
values.ravel(), dtype=dtype, copy=False
).reshape(values.shape)
except Exception as orig:
# e.g. ValueError when trying to cast object dtype to float64
raise ValueError(
f"failed to cast to '{dtype}' (Exception was: {orig})"
) from orig
# _prep_ndarray ensures that values.ndim == 2 at this point
index, columns = _get_axes(
values.shape[0], values.shape[1], index=index, columns=columns
)
values = values.T
# if we don't have a dtype specified, then try to convert objects
# on the entire block; this is to convert if we have datetimelike's
# embedded in an object type
if dtype is None and is_object_dtype(values.dtype):
if values.ndim == 2 and values.shape[0] != 1:
# transpose and separate blocks
dvals_list = [maybe_infer_to_datetimelike(row) for row in values]
for n in range(len(dvals_list)):
if isinstance(dvals_list[n], np.ndarray):
dvals_list[n] = dvals_list[n].reshape(1, -1)
from pandas.core.internals.blocks import make_block
# TODO: What about re-joining object columns?
block_values = [
make_block(dvals_list[n], placement=[n], ndim=2)
for n in range(len(dvals_list))
]
else:
datelike_vals = maybe_infer_to_datetimelike(values)
block_values = [datelike_vals]
else:
block_values = [values]
return create_block_manager_from_blocks(block_values, [columns, index])
def concatenate_managers(mgrs_indexers, axes: List[Index], concat_axis: int,
copy: bool) -> Manager:
"""
Concatenate block managers into one.
Parameters
----------
mgrs_indexers : list of (BlockManager, {axis: indexer,...}) tuples
axes : list of Index
concat_axis : int
copy : bool
Returns
-------
BlockManager
"""
# TODO(ArrayManager) this assumes that all managers are of the same type
if isinstance(mgrs_indexers[0][0], ArrayManager):
return concatenate_array_managers(mgrs_indexers, axes, concat_axis,
copy)
concat_plans = [
_get_mgr_concatenation_plan(mgr, indexers)
for mgr, indexers in mgrs_indexers
]
concat_plan = _combine_concat_plans(concat_plans, concat_axis)
blocks = []
for placement, join_units in concat_plan:
if len(join_units) == 1 and not join_units[0].indexers:
b = join_units[0].block
values = b.values
if copy:
values = values.copy()
else:
values = values.view()
b = b.make_block_same_class(values, placement=placement)
elif _is_uniform_join_units(join_units):
blk = join_units[0].block
vals = [ju.block.values for ju in join_units]
if not blk.is_extension:
# _is_uniform_join_units ensures a single dtype, so
# we can use np.concatenate, which is more performant
# than concat_compat
values = np.concatenate(vals, axis=blk.ndim - 1)
else:
# TODO(EA2D): special-casing not needed with 2D EAs
values = concat_compat(vals)
if not isinstance(values, ExtensionArray):
values = values.reshape(1, len(values))
if blk.values.dtype == values.dtype:
# Fast-path
b = blk.make_block_same_class(values, placement=placement)
else:
b = make_block(values, placement=placement, ndim=blk.ndim)
else:
new_values = _concatenate_join_units(join_units,
concat_axis,
copy=copy)
b = make_block(new_values, placement=placement, ndim=len(axes))
blocks.append(b)
return BlockManager(blocks, axes)
def ndarray_to_mgr(values, index, columns, dtype: Optional[DtypeObj],
copy: bool, typ: str) -> Manager:
# used in DataFrame.__init__
# input must be a ndarray, list, Series, Index, ExtensionArray
if isinstance(values, ABCSeries):
if columns is None:
if values.name is not None:
columns = Index([values.name])
if index is None:
index = values.index
else:
values = values.reindex(index)
# zero len case (GH #2234)
if not len(values) and columns is not None and len(columns):
values = np.empty((0, 1), dtype=object)
if is_extension_array_dtype(values) or is_extension_array_dtype(dtype):
# GH#19157
if isinstance(values, np.ndarray) and values.ndim > 1:
# GH#12513 a EA dtype passed with a 2D array, split into
# multiple EAs that view the values
values = [values[:, n] for n in range(values.shape[1])]
else:
values = [values]
if columns is None:
columns = Index(range(len(values)))
return arrays_to_mgr(values,
columns,
index,
columns,
dtype=dtype,
typ=typ)
# by definition an array here
# the dtypes will be coerced to a single dtype
values = _prep_ndarray(values, copy=copy)
if dtype is not None and not is_dtype_equal(values.dtype, dtype):
shape = values.shape
flat = values.ravel()
if not is_integer_dtype(dtype):
# TODO: skipping integer_dtype is needed to keep the tests passing,
# not clear it is correct
# Note: we really only need _try_cast, but keeping to exposed funcs
values = sanitize_array(flat,
None,
dtype=dtype,
copy=copy,
raise_cast_failure=True)
else:
try:
values = construct_1d_ndarray_preserving_na(flat,
dtype=dtype,
copy=False)
except Exception as err:
# e.g. ValueError when trying to cast object dtype to float64
msg = f"failed to cast to '{dtype}' (Exception was: {err})"
raise ValueError(msg) from err
values = values.reshape(shape)
# _prep_ndarray ensures that values.ndim == 2 at this point
index, columns = _get_axes(values.shape[0],
values.shape[1],
index=index,
columns=columns)
values = values.T
# if we don't have a dtype specified, then try to convert objects
# on the entire block; this is to convert if we have datetimelike's
# embedded in an object type
if dtype is None and is_object_dtype(values.dtype):
if values.ndim == 2 and values.shape[0] != 1:
# transpose and separate blocks
dvals_list = [maybe_infer_to_datetimelike(row) for row in values]
dvals_list = [ensure_block_shape(dval, 2) for dval in dvals_list]
# TODO: What about re-joining object columns?
dvals_list = [maybe_squeeze_dt64tz(x) for x in dvals_list]
block_values = [
make_block(dvals_list[n], placement=[n], ndim=2)
for n in range(len(dvals_list))
]
else:
datelike_vals = maybe_infer_to_datetimelike(values)
datelike_vals = maybe_squeeze_dt64tz(datelike_vals)
block_values = [datelike_vals]
else:
block_values = [maybe_squeeze_dt64tz(values)]
return create_block_manager_from_blocks(block_values, [columns, index])
def concatenate_block_managers(mgrs_indexers, axes: List[Index],
concat_axis: int, copy: bool) -> Manager:
"""
Concatenate block managers into one.
Parameters
----------
mgrs_indexers : list of (BlockManager, {axis: indexer,...}) tuples
axes : list of Index
concat_axis : int
copy : bool
Returns
-------
BlockManager
"""
if isinstance(mgrs_indexers[0][0], ArrayManager):
if concat_axis == 1:
# TODO for now only fastpath without indexers
mgrs = [t[0] for t in mgrs_indexers]
arrays = [
concat_compat([mgrs[i].arrays[j] for i in range(len(mgrs))],
axis=0) for j in range(len(mgrs[0].arrays))
]
return ArrayManager(arrays, [axes[1], axes[0]])
elif concat_axis == 0:
mgrs = [t[0] for t in mgrs_indexers]
arrays = list(
itertools.chain.from_iterable([mgr.arrays for mgr in mgrs]))
return ArrayManager(arrays, [axes[1], axes[0]])
concat_plans = [
_get_mgr_concatenation_plan(mgr, indexers)
for mgr, indexers in mgrs_indexers
]
concat_plan = _combine_concat_plans(concat_plans, concat_axis)
blocks = []
for placement, join_units in concat_plan:
if len(join_units) == 1 and not join_units[0].indexers:
b = join_units[0].block
values = b.values
if copy:
values = values.copy()
else:
values = values.view()
b = b.make_block_same_class(values, placement=placement)
elif _is_uniform_join_units(join_units):
blk = join_units[0].block
vals = [ju.block.values for ju in join_units]
if not blk.is_extension:
# _is_uniform_join_units ensures a single dtype, so
# we can use np.concatenate, which is more performant
# than concat_compat
values = np.concatenate(vals, axis=blk.ndim - 1)
else:
# TODO(EA2D): special-casing not needed with 2D EAs
values = concat_compat(vals)
if not isinstance(values, ExtensionArray):
values = values.reshape(1, len(values))
if blk.values.dtype == values.dtype:
# Fast-path
b = blk.make_block_same_class(values, placement=placement)
else:
b = make_block(values, placement=placement, ndim=blk.ndim)
else:
b = make_block(
_concatenate_join_units(join_units, concat_axis, copy=copy),
placement=placement,
ndim=len(axes),
)
blocks.append(b)
return BlockManager(blocks, axes)
