legend-pydataobj 1.6.2__py3-none-any.whl → 1.7.0__py3-none-any.whl

{legend_pydataobj-1.6.2.dist-info → legend_pydataobj-1.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: legend_pydataobj
-Version: 1.6.2
+Version: 1.7.0
 Summary: LEGEND Python Data Objects
 Author: The LEGEND Collaboration
 Maintainer: The LEGEND Collaboration

{legend_pydataobj-1.6.2.dist-info → legend_pydataobj-1.7.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
 lgdo/__init__.py,sha256=nv9kORuX2FCA6rQLbH959E0fuGMfZvHb0H5uyrLr2WI,3046
-lgdo/_version.py,sha256=ay9A4GSmtr3NioHirRgXvWfXtjwRjzXIO_WPuFobCoI,411
-lgdo/cli.py,sha256=hHc0Cz4ZXEOwo55oIukHAhHUkw09ePr4m3sO7eUbWHA,8018
+lgdo/_version.py,sha256=2fEqxujmrV2dsREie2BmOYFLu66FowyHtZT2AoLuIzU,411
+lgdo/cli.py,sha256=vB1Oj6kZ5gWaY9HBPBRRRyiepp72hm3bFvQeUUWeMYg,8214
 lgdo/lgdo_utils.py,sha256=6a2YWEwpyEMXlAyTHZMO01aqxy6SxJzPZkGNWKNWuS0,2567
 lgdo/lh5_store.py,sha256=xHwzbKNueEtFwScxrgfvCo2_bWKS6j7ojrpeF9kQflc,8483
 lgdo/logging.py,sha256=82wIOj7l7xr3WYyeHdpSXbbjzHJsy-uRyKYUYx2vMfQ,1003
@@ -18,8 +18,8 @@ lgdo/lh5/datatype.py,sha256=VhPWeWv3FW8XM6ZOFOdTZOYK3_hRZ3i0fYsBOEOIF5U,1623
 lgdo/lh5/exceptions.py,sha256=QWStQD27Qrm4oYs5Z3UAIoq4y7X-f_Z6QWCBCH0DXwE,1006
 lgdo/lh5/iterator.py,sha256=eqH9a_ZjEhgqJUZbMj36jXK_1Xbx86450DVw7LHNB3Y,12369
 lgdo/lh5/store.py,sha256=sYX1harVGRyP0oq1LGq2qrFhorutkev9MOovwhzEWZ4,6670
-lgdo/lh5/tools.py,sha256=AH0RuaUEJ7Tfzb964KnuVdxCKrGqwNP8XDt2iq4829g,8386
-lgdo/lh5/utils.py,sha256=xSTv0obtsUxO38JpkPKd2FbzENlhuTvYR0aexFU1ZQc,6640
+lgdo/lh5/tools.py,sha256=MqYvyag2Uo3RxO0jLphml6UfScLPI2a2MCz3kjkIwmU,9430
+lgdo/lh5/utils.py,sha256=7QYhKd8MqpeFevLyWuasv63WfzEPx7Fd9wA-l3JjnIQ,6984
 lgdo/lh5/_serializers/__init__.py,sha256=7zvTmBdp-pqS0ium6cKKjEvcqIND-kBC7319G5wMq5Y,1213
 lgdo/lh5/_serializers/read/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lgdo/lh5/_serializers/read/array.py,sha256=DLguBkiVNXZuUk7LdalixA8uISx_SETVPXWk-26HYmk,933
@@ -30,7 +30,7 @@ lgdo/lh5/_serializers/read/scalar.py,sha256=YwvA6kyNUh6H0kh2L7bzfgLkA8Et2dQFjp2n
 lgdo/lh5/_serializers/read/utils.py,sha256=K_HDQ_H-vtbs_gEif1MTtFki4qh6lw-5HE7b-7_s-9Q,417
 lgdo/lh5/_serializers/read/vector_of_vectors.py,sha256=ED4gr2Sw5TZBeww2c2kLbqn9dWYBk1VTgHiR4-5E1Mc,6665
 lgdo/lh5/_serializers/write/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lgdo/lh5/_serializers/write/array.py,sha256=lpz0V7bvy2rWkUuSAgX3aTSUe-HLvLnmnIXZLPX_Ddw,2802
+lgdo/lh5/_serializers/write/array.py,sha256=Gosg8rOCH_2dRMj_oNSWyXuoYXDjy0OK--GCYWswR4U,2803
 lgdo/lh5/_serializers/write/composite.py,sha256=f3b4YeOoUr8y1wA7zsKEFT5mIwX8SD0MYQ40unMRyQc,8460
 lgdo/lh5/_serializers/write/scalar.py,sha256=gkcF2WVBR3aQYl0EynbVUocx4y3r8tvPfQYQJjkPvP4,643
 lgdo/lh5/_serializers/write/vector_of_vectors.py,sha256=mZuC7NIb-IkmJ9wgn37TTvFTLLAFR71iivrY4yiSJZM,2912
@@ -41,14 +41,14 @@ lgdo/types/encoded.py,sha256=JW4U5ow7KLMzhKnmhdnxbC3SZJAs4bOEDZWKG4KY1uU,15293
 lgdo/types/fixedsizearray.py,sha256=7Fj4QS9ubaeEf2tM3HwjSs6AuG8hKSYaT6Hy7Y_VHdQ,1525
 lgdo/types/lgdo.py,sha256=UnJDi1emQYVgH_H29Vipfs4LelPopxG5pgZUu1eKOlw,2761
 lgdo/types/scalar.py,sha256=c5Es2vyDqyWTPV6mujzfIzMpC1jNWkEIcvYyWQUxH3Q,1933
-lgdo/types/struct.py,sha256=rLtyPthut2wjwiOqwntPrYjjt3uRQbTLWWjiewfKm20,3979
-lgdo/types/table.py,sha256=-ldEt_sY-Q5GqcqrDjvCKJ5fZ79NDa9hY-gs4mYgNZQ,17153
-lgdo/types/vectorofvectors.py,sha256=9pKtPfvh0vQ-nmg68LUM8cMttoxTl0BG3QH5awQtSxo,24503
+lgdo/types/struct.py,sha256=Q0OWLVd4B0ciLb8t6VsxU3MPbmGLZ7WfQNno1lSQS0Q,4918
+lgdo/types/table.py,sha256=PYxHXRmuNZkz1UK6MzUVWGhEsRFf6t-xXGFFrXUP0EY,17936
+lgdo/types/vectorofvectors.py,sha256=d_n0lK6rut3_DdPcmMro0ObJAIRhMQnYj0cqAEpckPc,24368
 lgdo/types/vovutils.py,sha256=7BWPP0BSj-92ifbCIUBcfqxG5-TS8uxujTyJJuDFI04,10302
 lgdo/types/waveformtable.py,sha256=f2tS4f1OEoYaTM5ldCX9zmw8iSISCT3t3wS1SrPdu_o,9901
-legend_pydataobj-1.6.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-legend_pydataobj-1.6.2.dist-info/METADATA,sha256=XON5L-CQcu1HuiKff1CoE5QqBOQtr1bHXxYvErIYdFg,44353
-legend_pydataobj-1.6.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-legend_pydataobj-1.6.2.dist-info/entry_points.txt,sha256=Uu5MTlppBZxB4QGlLv-oX8FqACWjAZDNii__TBDJwLQ,72
-legend_pydataobj-1.6.2.dist-info/top_level.txt,sha256=KyR-EUloqiXcQ62IWnzBmtInDtvsHl4q2ZJAZgTcLXE,5
-legend_pydataobj-1.6.2.dist-info/RECORD,,
+legend_pydataobj-1.7.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+legend_pydataobj-1.7.0.dist-info/METADATA,sha256=rcfERzQLFd45YcFRMTusx2x7i1LuU7faypmwka_83Ws,44353
+legend_pydataobj-1.7.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+legend_pydataobj-1.7.0.dist-info/entry_points.txt,sha256=Uu5MTlppBZxB4QGlLv-oX8FqACWjAZDNii__TBDJwLQ,72
+legend_pydataobj-1.7.0.dist-info/top_level.txt,sha256=KyR-EUloqiXcQ62IWnzBmtInDtvsHl4q2ZJAZgTcLXE,5
+legend_pydataobj-1.7.0.dist-info/RECORD,,

lgdo/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.6.2'
-__version_tuple__ = version_tuple = (1, 6, 2)
+__version__ = version = '1.7.0'
+__version_tuple__ = version_tuple = (1, 7, 0)

lgdo/cli.py

@@ -52,6 +52,11 @@ def lh5ls(args=None):
         default=None,
         help="""Maximum tree depth of groups to print""",
     )
+    parser.add_argument(
+        "--detail",
+        action="store_true",
+        help="""Print details about datasets""",
+    )
 
     args = parser.parse_args(args)
 
@@ -66,7 +71,13 @@ def lh5ls(args=None):
         print(__version__)  # noqa: T201
         sys.exit()
 
-    lh5.show(args.lh5_file, args.lh5_group, attrs=args.attributes, depth=args.depth)
+    lh5.show(
+        args.lh5_file,
+        args.lh5_group,
+        attrs=args.attributes,
+        depth=args.depth,
+        detail=args.detail,
+    )
 
 
 def lh5concat(args=None):

lgdo/lh5/_serializers/write/array.py

@@ -10,7 +10,7 @@ from ...exceptions import LH5EncodeError
 
 log = logging.getLogger(__name__)
 
-DEFAULT_HDF5_SETTINGS: dict[str, ...] = {"shuffle": True, "compression": "lzf"}
+DEFAULT_HDF5_SETTINGS: dict[str, ...] = {"shuffle": True, "compression": "gzip"}
 
 
 def _h5_write_array(

lgdo/lh5/tools.py

@@ -87,6 +87,7 @@ def show(
     indent: str = "",
     header: bool = True,
     depth: int | None = None,
+    detail: bool = False,
 ) -> None:
     """Print a tree of LH5 file contents with LGDO datatype.
 
@@ -104,6 +105,8 @@ def show(
         print `lh5_group` at the top of the diagram.
     depth
         maximum tree depth of groups to print
+    detail
+        whether to print additional information about how the data is stored
 
     Examples
     --------
@@ -171,6 +174,26 @@ def show(
 
         print(f"{indent}{char} \033[1m{key}\033[0m · {dtype} {_attrs}")  # noqa: T201
 
+        if detail and isinstance(val, h5py.Dataset):
+            char = "|       "
+            if killme:
+                char = "        "
+            toprint = f"{indent}{char}"
+            try:
+                toprint += f"\033[3mdtype\033[0m={val.dtype}"
+                toprint += f", \033[3mshape\033[0m={val.shape}"
+                toprint += f", \033[3mnbytes\033[0m={utils.fmtbytes(val.nbytes)}"
+                if (chunkshape := val.chunks) is None:
+                    toprint += ", \033[3mnumchunks\033[0m=contiguous"
+                else:
+                    toprint += f", \033[3mnumchunks\033[0m={val.id.get_num_chunks()}"
+                    toprint += f", \033[3mchunkshape\033[0m={chunkshape}"
+                toprint += f", \033[3mcompression\033[0m={val.compression}"
+            except TypeError:
+                toprint += "(scalar)"
+
+            print(toprint)  # noqa: T201
+
         # if it's a group, call this function recursively
         if isinstance(val, h5py.Group):
             show(
@@ -179,6 +202,7 @@ def show(
                 header=False,
                 attrs=attrs,
                 depth=depth - 1 if depth else None,
+                detail=detail,
             )
 
         # break or move to next key

lgdo/lh5/utils.py

@@ -221,3 +221,13 @@ def expand_path(
         return paths[0]
 
     return paths
+
+
+# https://stackoverflow.com/a/1094933
+def fmtbytes(num, suffix="B"):
+    """Returns formatted f-string for printing human-readable number of bytes."""
+    for unit in ("", "k", "M", "G", "T", "P", "E", "Z"):
+        if abs(num) < 1024.0:
+            return f"{num:3.1f} {unit}{suffix}"
+        num /= 1024.0
+    return f"{num:.1f} Y{suffix}"

lgdo/types/struct.py

@@ -6,6 +6,7 @@ utilities.
 from __future__ import annotations
 
 import logging
+from collections.abc import Mapping
 from typing import Any
 
 import numpy as np
@@ -24,8 +25,8 @@ class Struct(LGDO, dict):
 
     def __init__(
         self,
-        obj_dict: dict[str, LGDO] | None = None,
-        attrs: dict[str, Any] | None = None,
+        obj_dict: Mapping[str, LGDO] | None = None,
+        attrs: Mapping[str, Any] | None = None,
     ) -> None:
         """
         Parameters
@@ -37,8 +38,25 @@ class Struct(LGDO, dict):
             a set of user attributes to be carried along with this LGDO.
         """
         if obj_dict is not None:
-            self.update(obj_dict)
-
+            for k, v in obj_dict.items():
+                # check if value is another mapping-like object
+                # initialize another struct (or derived class) in such a case
+                if not isinstance(v, LGDO) and isinstance(v, Mapping):
+                    # NOTE: calling self.__new__() and then self.__init__() allows for polymorphism
+                    # but is there a better way?
+                    nested = self.__new__(type(self), v)
+                    nested.__init__(v)
+                    super().update({k: nested})
+                else:
+                    # otherwise object must be an LGDO
+                    if not isinstance(v, LGDO):
+                        msg = f"value of '{k}' ({v!r}) is not an LGDO or a dictionary"
+                        raise ValueError(msg)
+
+                    # assign
+                    super().update({k: v})
+
+        # call LGDO constructor to setup attributes
         super().__init__(attrs)
 
     def datatype_name(self) -> str:

lgdo/types/table.py

@@ -42,9 +42,9 @@ class Table(Struct):
 
     def __init__(
         self,
+        col_dict: Mapping[str, LGDO] | pd.DataFrame | ak.Array | None = None,
         size: int | None = None,
-        col_dict: dict[str, LGDO] | None = None,
-        attrs: dict[str, Any] | None = None,
+        attrs: Mapping[str, Any] | None = None,
     ) -> None:
         r"""
         Parameters
@@ -56,11 +56,14 @@ class Table(Struct):
             determined from the length of the first array in `col_dict`. If
             neither is provided, a default length of 1024 is used.
         col_dict
-            instantiate this table using the supplied named array-like LGDO's.
-            Note 1: no copy is performed, the objects are used directly.
-            Note 2: if `size` is not ``None``, all arrays will be resized to
-            match it.  Note 3: if the arrays have different lengths, all will
-            be resized to match the length of the first array.
+            instantiate this table using the supplied mapping of column names
+            and array-like objects. Supported input types are: mapping of
+            strings to LGDOs, :class:`pd.DataFrame` and :class:`ak.Array`.
+            Note 1: no copy is performed, the objects are used directly (unless
+            :class:`ak.Array` is provided).  Note 2: if `size` is not ``None``,
+            all arrays will be resized to match it.  Note 3: if the arrays have
+            different lengths, all will be resized to match the length of the
+            first array.
         attrs
             A set of user attributes to be carried along with this LGDO.
 
@@ -68,14 +71,20 @@ class Table(Struct):
         -----
         the :attr:`loc` attribute is initialized to 0.
         """
+        if isinstance(col_dict, pd.DataFrame):
+            col_dict = {k: Array(v) for k, v in col_dict.items()}
+
+        if isinstance(col_dict, ak.Array):
+            col_dict = _ak_to_lgdo_or_col_dict(col_dict)
+
+        # call Struct constructor
         super().__init__(obj_dict=col_dict, attrs=attrs)
 
         # if col_dict is not empty, set size according to it
         # if size is also supplied, resize all fields to match it
         # otherwise, warn if the supplied fields have varying size
         if col_dict is not None and len(col_dict) > 0:
-            do_warn = size is None
-            self.resize(new_size=size, do_warn=do_warn)
+            self.resize(new_size=size, do_warn=(size is None))
 
         # if no col_dict, just set the size (default to 1024)
         else:
@@ -479,3 +488,11 @@ class Table(Struct):
 
         msg = f"{library!r} is not a supported third-party format."
         raise TypeError(msg)
+
+
+def _ak_to_lgdo_or_col_dict(array: ak.Array):
+    if isinstance(array.type.content, ak.types.RecordType):
+        return {field: _ak_to_lgdo_or_col_dict(array[field]) for field in array.fields}
+    if isinstance(array.type.content, ak.types.NumpyType):
+        return Array(ak.to_numpy(array))
+    return VectorOfVectors(array)

lgdo/types/vectorofvectors.py

@@ -302,26 +302,23 @@ class VectorOfVectors(LGDO):
          [3],
         ]
         """
-        if self.ndim == 2:
-            vidx = self.cumulative_length
-            old_s = len(self)
-            dlen = new_size - old_s
-            csum = vidx[-1] if len(self) > 0 else 0
-
-            # first resize the cumulative length
-            self.cumulative_length.resize(new_size)
-
-            # if new_size > size, new elements are filled with zeros, let's fix
-            # that
-            if dlen > 0:
-                self.cumulative_length[old_s:] = csum
-
-            # then resize the data array
-            # if dlen > 0 this has no effect
-            if len(self.cumulative_length) > 0:
-                self.flattened_data.resize(self.cumulative_length[-1])
-        else:
-            raise NotImplementedError
+        vidx = self.cumulative_length
+        old_s = len(self)
+        dlen = new_size - old_s
+        csum = vidx[-1] if len(self) > 0 else 0
+
+        # first resize the cumulative length
+        self.cumulative_length.resize(new_size)
+
+        # if new_size > size, new elements are filled with zeros, let's fix
+        # that
+        if dlen > 0:
+            self.cumulative_length[old_s:] = csum
+
+        # then resize the data array
+        # if dlen > 0 this has no effect
+        if len(self.cumulative_length) > 0:
+            self.flattened_data.resize(self.cumulative_length[-1])
 
     def append(self, new: NDArray) -> None:
         """Append a 1D vector `new` at the end.