def _get_axes(N, K, index, columns):
# helper to create the axes as indexes
# return axes or defaults
if index is None:
index = ibase.default_index(N)
else:
index = ensure_index(index)
if columns is None:
columns = ibase.default_index(K)
else:
columns = ensure_index(columns)
return index, columns
def _prep_index(self, data, index, columns):
N, K = data.shape
if index is None:
index = ibase.default_index(N)
if columns is None:
columns = ibase.default_index(K)
if len(columns) != K:
raise ValueError('Column length mismatch: {columns} vs. {K}'
.format(columns=len(columns), K=K))
if len(index) != N:
raise ValueError('Index length mismatch: {index} vs. {N}'
.format(index=len(index), N=N))
return index, columns
def _list_of_series_to_arrays(data, columns, coerce_float=False, dtype=None):
if columns is None:
columns = _get_objs_combined_axis(data, sort=False)
indexer_cache = {}
aligned_values = []
for s in data:
index = getattr(s, 'index', None)
if index is None:
index = ibase.default_index(len(s))
if id(index) in indexer_cache:
indexer = indexer_cache[id(index)]
else:
indexer = indexer_cache[id(index)] = index.get_indexer(columns)
values = com.values_from_object(s)
aligned_values.append(algorithms.take_1d(values, indexer))
values = np.vstack(aligned_values)
if values.dtype == np.object_:
content = list(values.T)
return _convert_object_array(content, columns, dtype=dtype,
coerce_float=coerce_float)
else:
return values.T, columns
def _get_concat_axis(self):
"""
Return index to be used along concatenation axis.
"""
if self._is_series:
if self.axis == 0:
indexes = [x.index for x in self.objs]
elif self.ignore_index:
idx = ibase.default_index(len(self.objs))
return idx
elif self.keys is None:
names = [None] * len(self.objs)
num = 0
has_names = False
for i, x in enumerate(self.objs):
if not isinstance(x, Series):
raise TypeError("Cannot concatenate type 'Series' "
"with object of type {type!r}"
.format(type=type(x).__name__))
if x.name is not None:
names[i] = x.name
has_names = True
else:
names[i] = num
num += 1
if has_names:
return Index(names)
else:
return ibase.default_index(len(self.objs))
else:
return ensure_index(self.keys).set_names(self.names)
else:
indexes = [x._data.axes[self.axis] for x in self.objs]
if self.ignore_index:
idx = ibase.default_index(sum(len(i) for i in indexes))
return idx
if self.keys is None:
concat_axis = _concat_indexes(indexes)
else:
concat_axis = _make_concat_multiindex(indexes, self.keys,
self.levels, self.names)
self._maybe_check_integrity(concat_axis)
return concat_axis
def extract_index(data):
index = None
if len(data) == 0:
index = Index([])
elif len(data) > 0:
raw_lengths = []
indexes = []
have_raw_arrays = False
have_series = False
have_dicts = False
for val in data:
if isinstance(val, ABCSeries):
have_series = True
indexes.append(val.index)
elif isinstance(val, dict):
have_dicts = True
indexes.append(list(val.keys()))
elif is_list_like(val) and getattr(val, 'ndim', 1) == 1:
have_raw_arrays = True
raw_lengths.append(len(val))
if not indexes and not raw_lengths:
raise ValueError('If using all scalar values, you must pass'
' an index')
if have_series or have_dicts:
index = _union_indexes(indexes)
if have_raw_arrays:
lengths = list(set(raw_lengths))
if len(lengths) > 1:
raise ValueError('arrays must all be same length')
if have_dicts:
raise ValueError('Mixing dicts with non-Series may lead to '
'ambiguous ordering.')
if have_series:
if lengths[0] != len(index):
msg = ('array length {length} does not match index '
'length {idx_len}'
.format(length=lengths[0], idx_len=len(index)))
raise ValueError(msg)
else:
index = ibase.default_index(lengths[0])
return ensure_index(index)
def _get_names_from_index(data) -> Index:
has_some_name = any(getattr(s, "name", None) is not None for s in data)
if not has_some_name:
return ibase.default_index(len(data))
index: list[Hashable] = list(range(len(data)))
count = 0
for i, s in enumerate(data):
n = getattr(s, "name", None)
if n is not None:
index[i] = n
else:
index[i] = f"Unnamed {count}"
count += 1
return Index(index)
def get_names_from_index(data):
has_some_name = any(getattr(s, "name", None) is not None for s in data)
if not has_some_name:
return ibase.default_index(len(data))
index = list(range(len(data)))
count = 0
for i, s in enumerate(data):
n = getattr(s, "name", None)
if n is not None:
index[i] = n
else:
index[i] = "Unnamed {count}".format(count=count)
count += 1
return index
def get_names_from_index(data):
has_some_name = any(getattr(s, 'name', None) is not None for s in data)
if not has_some_name:
return ibase.default_index(len(data))
index = lrange(len(data))
count = 0
for i, s in enumerate(data):
n = getattr(s, 'name', None)
if n is not None:
index[i] = n
else:
index[i] = 'Unnamed {count}'.format(count=count)
count += 1
return index
def to_arrays(data, columns, dtype: Optional[DtypeObj] = None):
"""
Return list of arrays, columns.
"""
if isinstance(data, ABCDataFrame):
if columns is not None:
arrays = [
data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns
]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
columns = data.dtype.names
if columns is not None:
return [[]] * len(columns), columns
return [], [] # columns if columns is not None else []
elif isinstance(data[0], Categorical):
if columns is None:
columns = ibase.default_index(len(data))
return data, columns
elif isinstance(data, np.ndarray) and data.dtype.names is not None:
# e.g. recarray
columns = list(data.dtype.names)
arrays = [data[k] for k in columns]
return arrays, columns
if isinstance(data[0], (list, tuple)):
content, columns = _list_to_arrays(data, columns)
elif isinstance(data[0], abc.Mapping):
content, columns = _list_of_dict_to_arrays(data, columns)
elif isinstance(data[0], ABCSeries):
content, columns = _list_of_series_to_arrays(data, columns)
else:
# last ditch effort
data = [tuple(x) for x in data]
content, columns = _list_to_arrays(data, columns)
content, columns = _finalize_columns_and_data(content, columns, dtype)
return content, columns
def to_arrays(data, columns, coerce_float=False, dtype=None):
"""
Return list of arrays, columns.
"""
if isinstance(data, ABCDataFrame):
if columns is not None:
arrays = [data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
columns = data.dtype.names
if columns is not None:
return [[]] * len(columns), columns
return [], [] # columns if columns is not None else []
if isinstance(data[0], (list, tuple)):
return _list_to_arrays(data, columns, coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], compat.Mapping):
return _list_of_dict_to_arrays(data, columns,
coerce_float=coerce_float, dtype=dtype)
elif isinstance(data[0], ABCSeries):
return _list_of_series_to_arrays(data, columns,
coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], Categorical):
if columns is None:
columns = ibase.default_index(len(data))
return data, columns
elif (isinstance(data, (np.ndarray, ABCSeries, Index)) and
data.dtype.names is not None):
columns = list(data.dtype.names)
arrays = [data[k] for k in columns]
return arrays, columns
else:
# last ditch effort
data = lmap(tuple, data)
return _list_to_arrays(data, columns, coerce_float=coerce_float,
dtype=dtype)
def to_arrays(data, columns, coerce_float=False, dtype=None):
"""
Return list of arrays, columns.
"""
if isinstance(data, ABCDataFrame):
if columns is not None:
arrays = [data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
columns = data.dtype.names
if columns is not None:
return [[]] * len(columns), columns
return [], [] # columns if columns is not None else []
if isinstance(data[0], (list, tuple)):
return _list_to_arrays(data, columns, coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], compat.Mapping):
return _list_of_dict_to_arrays(data, columns,
coerce_float=coerce_float, dtype=dtype)
elif isinstance(data[0], ABCSeries):
return _list_of_series_to_arrays(data, columns,
coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], Categorical):
if columns is None:
columns = ibase.default_index(len(data))
return data, columns
elif (isinstance(data, (np.ndarray, ABCSeries, Index)) and
data.dtype.names is not None):
columns = list(data.dtype.names)
arrays = [data[k] for k in columns]
return arrays, columns
else:
# last ditch effort
data = lmap(tuple, data)
return _list_to_arrays(data, columns, coerce_float=coerce_float,
dtype=dtype)
def _convert_object_array(content, columns, coerce_float=False, dtype=None):
if columns is None:
columns = ibase.default_index(len(content))
else:
if len(columns) != len(content): # pragma: no cover
# caller's responsibility to check for this...
raise AssertionError('{col:d} columns passed, passed data had '
'{con} columns'.format(col=len(columns),
con=len(content)))
# provide soft conversion of object dtypes
def convert(arr):
if dtype != object and dtype != np.object:
arr = lib.maybe_convert_objects(arr, try_float=coerce_float)
arr = maybe_cast_to_datetime(arr, dtype)
return arr
arrays = [convert(arr) for arr in content]
return arrays, columns
def _convert_object_array(content, columns, coerce_float=False, dtype=None):
if columns is None:
columns = ibase.default_index(len(content))
else:
if len(columns) != len(content): # pragma: no cover
# caller's responsibility to check for this...
raise AssertionError('{col:d} columns passed, passed data had '
'{con} columns'.format(col=len(columns),
con=len(content)))
# provide soft conversion of object dtypes
def convert(arr):
if dtype != object and dtype != np.object:
arr = lib.maybe_convert_objects(arr, try_float=coerce_float)
arr = maybe_cast_to_datetime(arr, dtype)
return arr
arrays = [convert(arr) for arr in content]
return arrays, columns
def masked_rec_array_to_mgr(data, index, columns, dtype, copy):
"""
Extract from a masked rec array and create the manager.
"""
# essentially process a record array then fill it
fill_value = data.fill_value
fdata = ma.getdata(data)
if index is None:
index = get_names_from_index(fdata)
if index is None:
index = ibase.default_index(len(data))
index = ensure_index(index)
if columns is not None:
columns = ensure_index(columns)
arrays, arr_columns = to_arrays(fdata, columns)
# fill if needed
new_arrays = []
for fv, arr, col in zip(fill_value, arrays, arr_columns):
# TODO: numpy docs suggest fv must be scalar, but could it be
# non-scalar for object dtype?
assert lib.is_scalar(fv), fv
mask = ma.getmaskarray(data[col])
if mask.any():
arr, fv = maybe_upcast(arr, fill_value=fv, copy=True)
arr[mask] = fv
new_arrays.append(arr)
# create the manager
arrays, arr_columns = reorder_arrays(new_arrays, arr_columns, columns)
if columns is None:
columns = arr_columns
mgr = arrays_to_mgr(arrays, arr_columns, index, columns, dtype)
if copy:
mgr = mgr.copy()
return mgr
def masked_rec_array_to_mgr(
data: "MaskedRecords", index, columns, dtype: Optional[DtypeObj], copy: bool
):
"""
Extract from a masked rec array and create the manager.
"""
# essentially process a record array then fill it
fdata = ma.getdata(data)
if index is None:
index = _get_names_from_index(fdata)
if index is None:
index = ibase.default_index(len(data))
index = ensure_index(index)
if columns is not None:
columns = ensure_index(columns)
arrays, arr_columns = to_arrays(fdata, columns)
# fill if needed
new_arrays = []
for col in arr_columns:
arr = data[col]
fv = arr.fill_value
mask = ma.getmaskarray(arr)
if mask.any():
arr, fv = maybe_upcast(arr, fill_value=fv, copy=True)
arr[mask] = fv
new_arrays.append(arr)
# create the manager
arrays, arr_columns = reorder_arrays(new_arrays, arr_columns, columns)
if columns is None:
columns = arr_columns
mgr = arrays_to_mgr(arrays, arr_columns, index, columns, dtype)
if copy:
mgr = mgr.copy()
return mgr
def _list_of_series_to_arrays(
data: List,
columns: Union[Index, List],
coerce_float: bool = False,
dtype: Optional[DtypeObj] = None,
) -> Tuple[List[Scalar], Union[Index, List[Axis]]]:
if columns is None:
# We know pass_data is non-empty because data[0] is a Series
pass_data = [
x for x in data if isinstance(x, (ABCSeries, ABCDataFrame))
]
columns = get_objs_combined_axis(pass_data, sort=False)
indexer_cache: Dict[int, Scalar] = {}
aligned_values = []
for s in data:
index = getattr(s, "index", None)
if index is None:
index = ibase.default_index(len(s))
if id(index) in indexer_cache:
indexer = indexer_cache[id(index)]
else:
indexer = indexer_cache[id(index)] = index.get_indexer(columns)
values = extract_array(s, extract_numpy=True)
aligned_values.append(algorithms.take_1d(values, indexer))
values = np.vstack(aligned_values)
if values.dtype == np.object_:
content = list(values.T)
columns = _validate_or_indexify_columns(content, columns)
content = _convert_object_array(content,
dtype=dtype,
coerce_float=coerce_float)
return content, columns
else:
return values.T, columns
def rec_array_to_mgr(
data: Union[MaskedRecords, np.recarray, np.ndarray],
index,
columns,
dtype: Optional[DtypeObj],
copy: bool,
typ: str,
):
"""
Extract from a masked rec array and create the manager.
"""
# essentially process a record array then fill it
fdata = ma.getdata(data)
if index is None:
index = _get_names_from_index(fdata)
if index is None:
index = ibase.default_index(len(data))
index = ensure_index(index)
if columns is not None:
columns = ensure_index(columns)
arrays, arr_columns = to_arrays(fdata, columns)
# fill if needed
if isinstance(data, np.ma.MaskedArray):
new_arrays = fill_masked_arrays(data, arr_columns)
else:
new_arrays = arrays
# create the manager
arrays, arr_columns = reorder_arrays(new_arrays, arr_columns, columns)
if columns is None:
columns = arr_columns
mgr = arrays_to_mgr(arrays, arr_columns, index, columns, dtype, typ=typ)
if copy:
mgr = mgr.copy()
return mgr
def masked_rec_array_to_mgr(data, index, columns, dtype, copy):
"""
Extract from a masked rec array and create the manager.
"""
# essentially process a record array then fill it
fill_value = data.fill_value
fdata = ma.getdata(data)
if index is None:
index = get_names_from_index(fdata)
if index is None:
index = ibase.default_index(len(data))
index = ensure_index(index)
if columns is not None:
columns = ensure_index(columns)
arrays, arr_columns = to_arrays(fdata, columns)
# fill if needed
new_arrays = []
for fv, arr, col in zip(fill_value, arrays, arr_columns):
mask = ma.getmaskarray(data[col])
if mask.any():
arr, fv = maybe_upcast(arr, fill_value=fv, copy=True)
arr[mask] = fv
new_arrays.append(arr)
# create the manager
arrays, arr_columns = reorder_arrays(new_arrays, arr_columns, columns)
if columns is None:
columns = arr_columns
mgr = arrays_to_mgr(arrays, arr_columns, index, columns, dtype)
if copy:
mgr = mgr.copy()
return mgr
def _list_of_series_to_arrays(
data: List,
columns: Optional[Index],
) -> Tuple[np.ndarray, Index]:
# returned np.ndarray has ndim == 2
if columns is None:
# We know pass_data is non-empty because data[0] is a Series
pass_data = [
x for x in data if isinstance(x, (ABCSeries, ABCDataFrame))
]
columns = get_objs_combined_axis(pass_data, sort=False)
indexer_cache: Dict[int, np.ndarray] = {}
aligned_values = []
for s in data:
index = getattr(s, "index", None)
if index is None:
index = ibase.default_index(len(s))
if id(index) in indexer_cache:
indexer = indexer_cache[id(index)]
else:
indexer = indexer_cache[id(index)] = index.get_indexer(columns)
values = extract_array(s, extract_numpy=True)
aligned_values.append(algorithms.take_nd(values, indexer))
# error: Argument 1 to "vstack" has incompatible type "List[ExtensionArray]";
# expected "Sequence[Union[Union[int, float, complex, str, bytes, generic],
# Sequence[Union[int, float, complex, str, bytes, generic]],
# Sequence[Sequence[Any]], _SupportsArray]]"
content = np.vstack(aligned_values) # type: ignore[arg-type]
return content, columns
def to_arrays(
data,
columns: Optional[Index],
dtype: Optional[DtypeObj] = None) -> Tuple[List[ArrayLike], Index]:
"""
Return list of arrays, columns.
"""
if isinstance(data, ABCDataFrame):
if columns is not None:
arrays = [
data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns
]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
# error: Incompatible types in assignment (expression has type
# "Optional[Tuple[str, ...]]", variable has type "Optional[Index]")
columns = data.dtype.names # type: ignore[assignment]
if columns is not None:
# i.e. numpy structured array
arrays = [data[name] for name in columns]
return arrays, ensure_index(columns)
return [], ensure_index([])
elif isinstance(data[0], Categorical):
if columns is None:
columns = ibase.default_index(len(data))
return data, columns
elif isinstance(data, np.ndarray) and data.dtype.names is not None:
# e.g. recarray
columns = Index(list(data.dtype.names))
arrays = [data[k] for k in columns]
return arrays, columns
if isinstance(data[0], (list, tuple)):
content = _list_to_arrays(data)
elif isinstance(data[0], abc.Mapping):
content, columns = _list_of_dict_to_arrays(data, columns)
elif isinstance(data[0], ABCSeries):
content, columns = _list_of_series_to_arrays(data, columns)
else:
# last ditch effort
data = [tuple(x) for x in data]
content = _list_to_arrays(data)
# error: Incompatible types in assignment (expression has type "List[ndarray]",
# variable has type "List[Union[Union[str, int, float, bool], Union[Any, Any, Any,
# Any]]]")
content, columns = _finalize_columns_and_data( # type: ignore[assignment]
content, columns, dtype)
# error: Incompatible return value type (got "Tuple[ndarray, Index]", expected
# "Tuple[List[ExtensionArray], Index]")
# error: Incompatible return value type (got "Tuple[ndarray, Index]", expected
# "Tuple[List[ndarray], Index]")
return content, columns # type: ignore[return-value]
def __init__(self, data=None, index=None, sparse_index=None, kind='block',
fill_value=None, name=None, dtype=None, copy=False,
fastpath=False):
# we are called internally, so short-circuit
if fastpath:
# data is an ndarray, index is defined
if not isinstance(data, SingleBlockManager):
data = SingleBlockManager(data, index, fastpath=True)
if copy:
data = data.copy()
else:
if data is None:
data = []
if isinstance(data, Series) and name is None:
name = data.name
if isinstance(data, SparseArray):
if index is not None:
assert (len(index) == len(data))
sparse_index = data.sp_index
if fill_value is None:
fill_value = data.fill_value
data = np.asarray(data)
elif isinstance(data, SparseSeries):
if index is None:
index = data.index.view()
if fill_value is None:
fill_value = data.fill_value
# extract the SingleBlockManager
data = data._data
elif isinstance(data, (Series, dict)):
data = Series(data, index=index)
index = data.index.view()
res = make_sparse(data, kind=kind, fill_value=fill_value)
data, sparse_index, fill_value = res
elif isinstance(data, (tuple, list, np.ndarray)):
# array-like
if sparse_index is None:
res = make_sparse(data, kind=kind, fill_value=fill_value)
data, sparse_index, fill_value = res
else:
assert (len(data) == sparse_index.npoints)
elif isinstance(data, SingleBlockManager):
if dtype is not None:
data = data.astype(dtype)
if index is None:
index = data.index.view()
elif not data.index.equals(index) or copy: # pragma: no cover
# GH#19275 SingleBlockManager input should only be called
# internally
raise AssertionError('Cannot pass both SingleBlockManager '
'`data` argument and a different '
'`index` argument. `copy` must '
'be False.')
else:
length = len(index)
if data == fill_value or (isna(data) and isna(fill_value)):
if kind == 'block':
sparse_index = BlockIndex(length, [], [])
else:
sparse_index = IntIndex(length, [])
data = np.array([])
else:
if kind == 'block':
locs, lens = ([0], [length]) if length else ([], [])
sparse_index = BlockIndex(length, locs, lens)
else:
sparse_index = IntIndex(length, index)
v = data
data = np.empty(length)
data.fill(v)
if index is None:
index = ibase.default_index(sparse_index.length)
index = ensure_index(index)
# create/copy the manager
if isinstance(data, SingleBlockManager):
if copy:
data = data.copy()
else:
# create a sparse array
if not isinstance(data, SparseArray):
data = SparseArray(data, sparse_index=sparse_index,
fill_value=fill_value, dtype=dtype,
copy=copy)
data = SingleBlockManager(data, index)
generic.NDFrame.__init__(self, data)
self.index = index
self.name = name
def to_arrays(data,
columns: Index | None,
dtype: DtypeObj | None = None) -> tuple[list[ArrayLike], Index]:
"""
Return list of arrays, columns.
"""
if isinstance(data, ABCDataFrame):
if columns is not None:
arrays = [
data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns
]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
if data.dtype.names is not None:
# i.e. numpy structured array
columns = ensure_index(data.dtype.names)
arrays = [data[name] for name in columns]
return arrays, columns
return [], ensure_index([])
elif isinstance(data[0], Categorical):
# GH#38845 deprecate special case
warnings.warn(
"The behavior of DataFrame([categorical, ...]) is deprecated and "
"in a future version will be changed to match the behavior of "
"DataFrame([any_listlike, ...]). "
"To retain the old behavior, pass as a dictionary "
"DataFrame({col: categorical, ..})",
FutureWarning,
stacklevel=4,
)
if columns is None:
columns = ibase.default_index(len(data))
return data, columns
elif isinstance(data, np.ndarray) and data.dtype.names is not None:
# e.g. recarray
columns = Index(list(data.dtype.names))
arrays = [data[k] for k in columns]
return arrays, columns
if isinstance(data[0], (list, tuple)):
arr = _list_to_arrays(data)
elif isinstance(data[0], abc.Mapping):
arr, columns = _list_of_dict_to_arrays(data, columns)
elif isinstance(data[0], ABCSeries):
arr, columns = _list_of_series_to_arrays(data, columns)
else:
# last ditch effort
data = [tuple(x) for x in data]
arr = _list_to_arrays(data)
content, columns = _finalize_columns_and_data(arr, columns, dtype)
return content, columns
def _extract_index(data) -> Index:
"""
Try to infer an Index from the passed data, raise ValueError on failure.
"""
index = None
if len(data) == 0:
index = Index([])
elif len(data) > 0:
raw_lengths = []
indexes: list[list[Hashable] | Index] = []
have_raw_arrays = False
have_series = False
have_dicts = False
for val in data:
if isinstance(val, ABCSeries):
have_series = True
indexes.append(val.index)
elif isinstance(val, dict):
have_dicts = True
indexes.append(list(val.keys()))
elif is_list_like(val) and getattr(val, "ndim", 1) == 1:
have_raw_arrays = True
raw_lengths.append(len(val))
elif isinstance(val, np.ndarray) and val.ndim > 1:
raise ValueError(
"Per-column arrays must each be 1-dimensional")
if not indexes and not raw_lengths:
raise ValueError(
"If using all scalar values, you must pass an index")
if have_series:
index = union_indexes(indexes)
elif have_dicts:
index = union_indexes(indexes, sort=False)
if have_raw_arrays:
lengths = list(set(raw_lengths))
if len(lengths) > 1:
raise ValueError("All arrays must be of the same length")
if have_dicts:
raise ValueError(
"Mixing dicts with non-Series may lead to ambiguous ordering."
)
if have_series:
assert index is not None # for mypy
if lengths[0] != len(index):
msg = (f"array length {lengths[0]} does not match index "
f"length {len(index)}")
raise ValueError(msg)
else:
index = ibase.default_index(lengths[0])
# error: Argument 1 to "ensure_index" has incompatible type "Optional[Index]";
# expected "Union[Union[Union[ExtensionArray, ndarray], Index, Series],
# Sequence[Any]]"
return ensure_index(index) # type: ignore[arg-type]
def __init__(self,
data=None,
index=None,
sparse_index=None,
kind='block',
fill_value=None,
name=None,
dtype=None,
copy=False,
fastpath=False):
# we are called internally, so short-circuit
if fastpath:
# data is an ndarray, index is defined
if not isinstance(data, SingleBlockManager):
data = SingleBlockManager(data, index, fastpath=True)
if copy:
data = data.copy()
else:
if data is None:
data = []
if isinstance(data, Series) and name is None:
name = data.name
if isinstance(data, SparseArray):
if index is not None:
assert (len(index) == len(data))
sparse_index = data.sp_index
if fill_value is None:
fill_value = data.fill_value
data = np.asarray(data)
elif isinstance(data, SparseSeries):
if index is None:
index = data.index.view()
if fill_value is None:
fill_value = data.fill_value
# extract the SingleBlockManager
data = data._data
elif isinstance(data, (Series, dict)):
data = Series(data, index=index)
index = data.index.view()
res = make_sparse(data, kind=kind, fill_value=fill_value)
data, sparse_index, fill_value = res
elif isinstance(data, (tuple, list, np.ndarray)):
# array-like
if sparse_index is None:
res = make_sparse(data, kind=kind, fill_value=fill_value)
data, sparse_index, fill_value = res
else:
assert (len(data) == sparse_index.npoints)
elif isinstance(data, SingleBlockManager):
if dtype is not None:
data = data.astype(dtype)
if index is None:
index = data.index.view()
elif not data.index.equals(index) or copy: # pragma: no cover
# GH#19275 SingleBlockManager input should only be called
# internally
raise AssertionError('Cannot pass both SingleBlockManager '
'`data` argument and a different '
'`index` argument. `copy` must '
'be False.')
else:
length = len(index)
if data == fill_value or (isna(data) and isna(fill_value)):
if kind == 'block':
sparse_index = BlockIndex(length, [], [])
else:
sparse_index = IntIndex(length, [])
data = np.array([])
else:
if kind == 'block':
locs, lens = ([0], [length]) if length else ([], [])
sparse_index = BlockIndex(length, locs, lens)
else:
sparse_index = IntIndex(length, index)
v = data
data = np.empty(length)
data.fill(v)
if index is None:
index = ibase.default_index(sparse_index.length)
index = ensure_index(index)
# create/copy the manager
if isinstance(data, SingleBlockManager):
if copy:
data = data.copy()
else:
# create a sparse array
if not isinstance(data, SparseArray):
data = SparseArray(data,
sparse_index=sparse_index,
fill_value=fill_value,
dtype=dtype,
copy=copy)
data = SingleBlockManager(data, index)
generic.NDFrame.__init__(self, data)
self.index = index
self.name = name
def to_arrays(data,
columns: Index | None,
dtype: DtypeObj | None = None) -> tuple[list[ArrayLike], Index]:
"""
Return list of arrays, columns.
Returns
-------
list[ArrayLike]
These will become columns in a DataFrame.
Index
This will become frame.columns.
Notes
-----
Ensures that len(result_arrays) == len(result_index).
"""
if isinstance(data, ABCDataFrame):
# see test_from_records_with_index_data, test_from_records_bad_index_column
if columns is not None:
arrays = [
data._ixs(i, axis=1).values
for i, col in enumerate(data.columns) if col in columns
]
else:
columns = data.columns
arrays = [data._ixs(i, axis=1).values for i in range(len(columns))]
return arrays, columns
if not len(data):
if isinstance(data, np.ndarray):
if data.dtype.names is not None:
# i.e. numpy structured array
columns = ensure_index(data.dtype.names)
arrays = [data[name] for name in columns]
if len(data) == 0:
# GH#42456 the indexing above results in list of 2D ndarrays
# TODO: is that an issue with numpy?
for i, arr in enumerate(arrays):
if arr.ndim == 2:
arrays[i] = arr[:, 0]
return arrays, columns
return [], ensure_index([])
elif isinstance(data[0], Categorical):
# GH#38845 deprecate special case
warnings.warn(
"The behavior of DataFrame([categorical, ...]) is deprecated and "
"in a future version will be changed to match the behavior of "
"DataFrame([any_listlike, ...]). "
"To retain the old behavior, pass as a dictionary "
"DataFrame({col: categorical, ..})",
FutureWarning,
stacklevel=4,
)
if columns is None:
columns = ibase.default_index(len(data))
elif len(columns) > len(data):
raise ValueError("len(columns) > len(data)")
elif len(columns) < len(data):
# doing this here is akin to a pre-emptive reindex
data = data[:len(columns)]
return data, columns
elif isinstance(data, np.ndarray) and data.dtype.names is not None:
# e.g. recarray
columns = Index(list(data.dtype.names))
arrays = [data[k] for k in columns]
return arrays, columns
if isinstance(data[0], (list, tuple)):
arr = _list_to_arrays(data)
elif isinstance(data[0], abc.Mapping):
arr, columns = _list_of_dict_to_arrays(data, columns)
elif isinstance(data[0], ABCSeries):
arr, columns = _list_of_series_to_arrays(data, columns)
else:
# last ditch effort
data = [tuple(x) for x in data]
arr = _list_to_arrays(data)
content, columns = _finalize_columns_and_data(arr, columns, dtype)
return content, columns