Fix issue saving data frame lists; add tests

CHANGELOG.md

@@ -1,8 +1,9 @@
 # Changelog
 
-## Version 0.4.0
+## Version 0.4.0 - 0.4.1
 
 - Support for compressed lists.
+- Fix the copy paste issue for Compressed data frame lists.
 
 ## Version 0.3.0
 

setup.cfg

@@ -52,7 +52,7 @@ install_requires =
     dolomite-base>=0.4.2
     genomicranges>=0.8.2
     biocframe>=0.7.2
-    compressed-lists>=0.4.4
+    compressed-lists>=0.4.5
     h5py
 
 

src/dolomite_ranges/__init__.py

@@ -16,7 +16,9 @@
     del version, PackageNotFoundError
 
 from .save_sequence_information import save_sequence_information
-from .read_sequence_information import read_sequence_information 
+from .read_sequence_information import read_sequence_information
+from .read_frame_list import read_data_frame_list
+from .save_frame_list import save_data_frame_list 
 from .save_genomic_ranges  import save_genomic_ranges
 from .read_genomic_ranges import read_genomic_ranges 
 from .save_genomic_ranges_list import save_compressed_genomic_ranges_list

src/dolomite_ranges/read_atomic_vector_list.py

@@ -21,9 +21,7 @@ def read_atomic_vector_list(path: str, metadata: Optional[dict], **kwargs):
 
         kwargs:
             Further arguments, ignored.
-
-
-    """
+   """
     return _read_compressed_list(path, metadata, "atomic_vector_list", **kwargs)
 
 

src/dolomite_ranges/save_frame_list.py

@@ -6,7 +6,7 @@
 
 @dl.save_object.register
 @dl.validate_saves
-def save_compressed_genomic_ranges_list(x: CompressedSplitBiocFrameList, path: str, **kwargs):
+def save_data_frame_list(x: CompressedSplitBiocFrameList, path: str, **kwargs):
     """Method for saving :py:class:`~compressed_lists.biocframe_list.CompressedSplitBiocFrameList`
     objects to their corresponding file representations, see
     :py:meth:`~dolomite_base.save_object.save_object` for details.
@@ -28,4 +28,4 @@ def save_compressed_genomic_ranges_list(x: CompressedSplitBiocFrameList, path: s
     Returns:
         `x` is saved to `path`.
     """
-    return _save_compressed_list(x, path=path, name="genomic_ranges_list", **kwargs)
+    return _save_compressed_list(x, path=path, name="data_frame_list", **kwargs)

tests/test_frame_list.py

@@ -0,0 +1,48 @@
+import os
+from tempfile import mkdtemp
+
+from biocframe import BiocFrame
+from dolomite_base import read_object, save_object
+from compressed_lists import CompressedSplitBiocFrameList
+import numpy as np
+import dolomite_ranges
+
+
+def test_dataframe_list():
+    a = BiocFrame({
+        "seqnames":["chr1", "chr2", "chr1", "chr3"],
+        "strand":["-", "+", "*", "+"],
+        "mcols":BiocFrame({"score": [1, 2, 3, 4]})
+    })
+
+    b = BiocFrame({
+        "seqnames":["chr2", "chr4", "chr5"],
+        "strand":["-", "+", "*"],
+        "mcols":BiocFrame({"score": [2, 3, 4]})
+    })
+
+    gdf = CompressedSplitBiocFrameList.from_list(lst=[a, b], names=["a", "b"])
+
+    dir = os.path.join(mkdtemp(), "dframe")
+    save_object(gdf, dir)
+
+    roundtrip = read_object(dir)
+    assert isinstance(roundtrip, CompressedSplitBiocFrameList)
+    assert roundtrip.get_names() == gdf.get_names()
+    assert len(roundtrip.get_unlist_data()) == len(gdf.get_unlist_data())
+    assert list(roundtrip[0].get_column("seqnames")) == gdf[0].get_column("seqnames")
+    assert list(roundtrip[0].get_column("strand")) ==gdf[0].get_column("strand")
+
+
+def test_dframe_empty():
+    gdf = CompressedSplitBiocFrameList.empty(n=100)
+
+    print(gdf)
+
+    dir = os.path.join(mkdtemp(), "dframe_empty")
+    save_object(gdf, dir)
+
+    roundtrip = read_object(dir)
+    assert roundtrip.get_names() == gdf.get_names()
+    assert len(roundtrip.get_unlist_data()) == len(gdf.get_unlist_data())
+    assert np.allclose(roundtrip.get_element_lengths(), gdf.get_element_lengths())