def dict_to_pydf(data: dict[str, Sequence[Any]],
columns: ColumnsType | None = None) -> PyDataFrame:
"""
Construct a PyDataFrame from a dictionary of sequences.
"""
if columns is not None:
# the columns arg may also set the dtype of the series
columns, dtypes = _unpack_columns(columns, lookup_names=data.keys())
if not data and dtypes:
data_series = [
pli.Series(name, [], dtypes.get(name)).inner()
for name in columns
]
else:
data_series = [
pli.Series(name, values, dtypes.get(name)).inner()
for name, values in data.items()
]
data_series = _handle_columns_arg(data_series, columns=columns)
return PyDataFrame(data_series)
if _NUMPY_AVAILABLE:
all_numpy = True
for val in data.values():
# only start a thread pool from a reasonable size.
all_numpy = all_numpy and isinstance(
val, np.ndarray) and len(val) > 1000
if not all_numpy:
break
if all_numpy:
# yes, multi-threading was easier in python here
# we cannot run multiple threads that run python code
# and release the gil in pyo3
# it will deadlock.
# dummy is threaded
import multiprocessing.dummy
pool_size = threadpool_size()
pool = multiprocessing.dummy.Pool(pool_size)
data_series = pool.map(
lambda t: pli.Series(t[0], t[1]).inner(),
[(k, v) for k, v in data.items()],
)
return PyDataFrame(data_series)
# fast path
return PyDataFrame.read_dict(data)
def dict_to_pydf(
data: Dict[str, Sequence[Any]],
columns: Optional[ColumnsType] = None,
) -> "PyDataFrame":
"""
Construct a PyDataFrame from a dictionary of sequences.
"""
if columns is not None:
# the columns arg may also set the dtype of the series
columns, dtypes = _unpack_columns(columns, lookup_names=data.keys())
if not data and dtypes:
data_series = [
pli.Series(name, [], dtypes.get(name)).inner() for name in columns
]
else:
data_series = [
pli.Series(name, values, dtypes.get(name)).inner()
for name, values in data.items()
]
data_series = _handle_columns_arg(data_series, columns=columns)
return PyDataFrame(data_series)
# fast path
return PyDataFrame.read_dict(data)