lamindb 0.48a3__py3-none-any.whl → 0.48.1__py3-none-any.whl

lamindb/dev/_view_parents.py

@@ -33,9 +33,10 @@ def view_lineage(file: File, with_children: bool = True):
     u = graphviz.Digraph(
         file.id,
         node_attr={
-            "fillcolor": "antiquewhite",
-            "color": "orange",
+            "fillcolor": "honeydew",
+            "color": "seagreen",
             "fontname": "Helvetica",
+            "fontsize": "10",
         },
         edge_attr={"arrowsize": "0.5"},
     )
@@ -50,7 +51,7 @@ def view_lineage(file: File, with_children: bool = True):
         else:
             style = "rounded,filled"
             shape = "box"
-            fillcolor = "antiquewhite"
+            fillcolor = "honeydew"
         u.node(
             node_id,
             label=node_label,
@@ -65,12 +66,12 @@ def view_lineage(file: File, with_children: bool = True):
             add_node(row["target_record"], row["target"], row["target_label"], u)
 
         u.edge(row["source"], row["target"], color="dimgrey")
-    # label the searched file orange
+    # label the searched file mediumseagreen
     u.node(
         file.id,
         label=file_label,
         style="rounded,filled",
-        fillcolor="orange",
+        fillcolor="mediumseagreen",
         shape="box",
     )
 
@@ -93,7 +94,9 @@ def view_parents(
         df_edges = pd.concat(
             [
                 df_edges,
-                _df_edges_from_children(record=record, field=field, distance=distance),
+                _df_edges_from_parents(
+                    record=record, field=field, distance=distance, children=True
+                ),
             ]
         ).drop_duplicates()
 
@@ -102,18 +105,19 @@ def view_parents(
     u = graphviz.Digraph(
         record.id,
         node_attr={
-            "color": "orange",
-            "fillcolor": "antiquewhite",
+            "color": "seagreen",
+            "fillcolor": "honeydew",
             "shape": "box",
             "style": "rounded,filled",
             "fontname": "Helvetica",
+            "fontsize": "10",
         },
         edge_attr={"arrowsize": "0.5"},
     )
     u.node(
         record_label.replace(":", "_"),
         label=record_label,
-        fillcolor="orange",
+        fillcolor="mediumseagreen",
     )
     for _, row in df_edges.iterrows():
         u.node(row["source"], label=row["source_label"])
@@ -122,17 +126,21 @@ def view_parents(
     return u
 
 
-def _get_parents(record: ORM, field: str, distance: int):
+def _get_parents(record: ORM, field: str, distance: int, children: bool = False):
     """Recursively get parent records within a distance."""
+    if children:
+        key = "parents"
+    else:
+        key = "children"
     model = record.__class__
-    condition = f"children__{field}"
+    condition = f"{key}__{field}"
     results = model.select(**{condition: record.__getattribute__(field)}).all()
     if distance < 2:
         return results
 
     d = 2
     while d < distance:
-        condition = "children__" + condition
+        condition = f"{key}__{condition}"
         records = model.select(**{condition: record.__getattribute__(field)}).all()
 
         if len(records) == 0:
@@ -143,59 +151,21 @@ def _get_parents(record: ORM, field: str, distance: int):
     return results
 
 
-def _get_children(record: ORM, field: str, distance: int):
-    """Recursively get parent records within a distance."""
-    model = record.__class__
-    condition = f"parents__{field}"
-    results = model.select(**{condition: record.__getattribute__(field)}).all()
-    if distance < 2:
-        return results
-
-    d = 2
-    while d < distance:
-        condition = "parents__" + condition
-        records = model.select(**{condition: record.__getattribute__(field)}).all()
-
-        if len(records) == 0:
-            return results
-
-        results = results | records
-        d += 1
-    return results
-
-
-def _df_edges_from_parents(record: ORM, field: str, distance: int):
+def _df_edges_from_parents(
+    record: ORM, field: str, distance: int, children: bool = False
+):
     """Construct a DataFrame of edges as the input of graphviz.Digraph."""
-    parents = _get_parents(record=record, field=field, distance=distance)
-    records = parents | record.__class__.objects.filter(id=record.id)
-    df = records.distinct().df(include=[f"parents__{field}"])
-    df_edges = df[[f"parents__{field}", field]]
-    df_edges = df_edges.explode(f"parents__{field}")
-    df_edges.dropna(axis=0, inplace=True)
-    df_edges.rename(
-        columns={f"parents__{field}": "source", field: "target"}, inplace=True
+    key = "children" if children else "parents"
+    parents = _get_parents(
+        record=record, field=field, distance=distance, children=children
     )
-    df_edges = df_edges.drop_duplicates()
-
-    # colons messes with the node formatting:
-    # https://graphviz.readthedocs.io/en/stable/node_ports.html
-    df_edges["source_label"] = df_edges["source"]
-    df_edges["target_label"] = df_edges["target"]
-    df_edges["source"] = df_edges["source"].str.replace(":", "_")
-    df_edges["target"] = df_edges["target"].str.replace(":", "_")
-    return df_edges
-
-
-def _df_edges_from_children(record: ORM, field: str, distance: int):
-    """Construct a DataFrame of edges as the input of graphviz.Digraph."""
-    children = _get_children(record=record, field=field, distance=distance)
-    records = children | record.__class__.objects.filter(id=record.id)
-    df = records.distinct().df(include=[f"children__{field}"])
-    df_edges = df[[f"children__{field}", field]]
-    df_edges = df_edges.explode(f"children__{field}")
+    records = parents | record.__class__.objects.filter(id=record.id)
+    df = records.distinct().df(include=[f"{key}__{field}"])
+    df_edges = df[[f"{key}__{field}", field]]
+    df_edges = df_edges.explode(f"{key}__{field}")
     df_edges.dropna(axis=0, inplace=True)
     df_edges.rename(
-        columns={f"children__{field}": "source", field: "target"}, inplace=True
+        columns={f"{key}__{field}": "source", field: "target"}, inplace=True
     )
     df_edges = df_edges.drop_duplicates()
 
@@ -244,12 +214,13 @@ def _label_file_run(record: Union[File, Run]):
             name = record.key
         else:
             name = record.description.replace("&", "&amp;")
+
         return (
-            rf'<{name}   <BR/><FONT COLOR="GREY" POINT-SIZE="10"'
+            rf'<{name}<BR/><FONT COLOR="GREY" POINT-SIZE="10"'
             rf' FACE="Monospace">id={record.id}<BR/>suffix={record.suffix}</FONT>>'
         )
     elif isinstance(record, Run):
-        name = f'{record.transform.name.replace("&", "&amp;")}   '
+        name = f'{record.transform.name.replace("&", "&amp;")}'
         return (
             rf'<{name}<BR/><FONT COLOR="GREY" POINT-SIZE="10"'
             rf' FACE="Monospace">id={record.id}<BR/>type={record.transform.type},'

lamindb/dev/datasets/__init__.py

@@ -4,7 +4,9 @@
    :toctree: .
 
    file_fcs
+   file_fcs_alpert19
    file_jpg_paradisi05
+   file_tiff_suo22
    file_fastq
    file_bam
    file_mini_csv
@@ -19,6 +21,8 @@
    anndata_pbmc68k_reduced
    anndata_pbmc3k_processed
    anndata_with_obs
+   anndata_suo22_Visium10X
+   mudata_papalexi21_subset
    schmidt22_crispra_gws_IFNG
    schmidt22_perturbseq
    fake_bio_notebook_titles
@@ -29,6 +33,7 @@ from ._core import (
     anndata_mouse_sc_lymph_node,
     anndata_pbmc3k_processed,
     anndata_pbmc68k_reduced,
+    anndata_suo22_Visium10X,
     anndata_with_obs,
     df_iris,
     df_iris_in_meter,
@@ -38,9 +43,12 @@ from ._core import (
     file_bam,
     file_fastq,
     file_fcs,
+    file_fcs_alpert19,
     file_jpg_paradisi05,
     file_mini_csv,
+    file_tiff_suo22,
     generate_cell_ranger_files,
+    mudata_papalexi21_subset,
     schmidt22_crispra_gws_IFNG,
     schmidt22_perturbseq,
 )

lamindb/dev/datasets/_core.py

@@ -11,13 +11,22 @@ from .._settings import settings
 
 
 def file_fcs() -> Path:
-    """Return fcs file example."""
+    """Example FCS file."""
     filepath, _ = urlretrieve(
         "https://lamindb-test.s3.amazonaws.com/example.fcs", "example.fcs"
     )
     return Path(filepath)
 
 
+def file_fcs_alpert19() -> Path:
+    """FCS file from Alpert19."""
+    filepath, _ = urlretrieve(
+        "https://lamindb-test.s3.amazonaws.com/Alpert19-070314-Mike-Study+15-2013-plate+1-15-004-1-13_cells_found.fcs",  # noqa
+        "Alpert19.fcs",
+    )
+    return Path(filepath)
+
+
 def file_jpg_paradisi05() -> Path:
     """Return jpg file example.
 
@@ -30,26 +39,45 @@ def file_jpg_paradisi05() -> Path:
     return Path(filepath)
 
 
-def file_fastq() -> Path:
+def file_fastq(in_storage_root=False) -> Path:
     """Mini mock fastq file."""
-    with open("./input.fastq.gz", "w") as f:
+    basedir = Path(".") if not in_storage_root else settings.storage
+    filepath = basedir / "input.fastq.gz"
+    with open(filepath, "w") as f:
         f.write("Mock fastq file.")
-    return Path("./input.fastq.gz")
+    return filepath
 
 
-def file_bam() -> Path:
+def file_bam(in_storage_root=False) -> Path:
     """Mini mock bam file."""
-    with open("./output.bam", "w") as f:
+    basedir = Path(".") if not in_storage_root else settings.storage
+    filepath = basedir / "output.bam"
+    with open(filepath, "w") as f:
         f.write("Mock bam file.")
-    return Path("./output.bam")
+    return filepath
 
 
-def file_mini_csv() -> Path:
+def file_mini_csv(in_storage_root=False) -> Path:
     """Mini csv file."""
-    filename = Path("./mini.csv")
+    basedir = Path(".") if not in_storage_root else settings.storage
+    filepath = basedir / "mini.csv"
     df = pd.DataFrame([1, 2, 3], columns=["test"])
-    df.to_csv(filename, index=False)
-    return filename
+    df.to_csv(filepath, index=False)
+    return filepath
+
+
+def file_tiff_suo22():
+    """Image file from Suo22.
+
+    Pair with anndata_suo22_Visium10X
+    """
+    filepath, _ = urlretrieve(
+        "https://lamindb-test.s3.amazonaws.com/F121_LP1_4LIV.tiff",
+        "F121_LP1_4LIV.tiff",
+    )
+    Path("suo22/").mkdir(exist_ok=True)
+    filepath = Path(filepath).rename("suo22/F121_LP1_4LIV.tiff")
+    return Path(filepath)
 
 
 def dir_scrnaseq_cellranger(in_storage_root=False) -> Path:
@@ -59,12 +87,12 @@ def dir_scrnaseq_cellranger(in_storage_root=False) -> Path:
     )
     from zipfile import ZipFile
 
-    path = Path(".") if not in_storage_root else settings.storage
+    basedir = Path(".") if not in_storage_root else settings.storage
     with ZipFile(filepath, "r") as zipObj:
         # Extract all the contents of zip file in current directory
-        zipObj.extractall(path=path)
+        zipObj.extractall(path=basedir)
 
-    return path / "cellranger_run_001"
+    return basedir / "cellranger_run_001"
 
 
 def anndata_mouse_sc_lymph_node() -> ad.AnnData:
@@ -133,7 +161,10 @@ def anndata_human_immune_cells() -> ad.AnnData:
         adata.write('human_immune.h5ad')
     """
     filepath, _ = urlretrieve("https://lamindb-test.s3.amazonaws.com/human_immune.h5ad")
-    return ad.read(filepath)
+    adata = ad.read(filepath)
+    del adata.raw
+    adata.var.drop(columns=["gene_symbols", "feature_name"], inplace=True)
+    return adata
 
 
 def anndata_with_obs() -> ad.AnnData:
@@ -163,6 +194,40 @@ def anndata_with_obs() -> ad.AnnData:
     return adata
 
 
+def anndata_suo22_Visium10X():
+    """AnnData from Suo22 generated by 10x Visium."""
+    import anndata as ad
+
+    filepath, _ = urlretrieve(
+        "https://lamindb-test.s3.amazonaws.com/suo22_Visium10X_data_LI_subset.h5ad",
+        "Visium10X_data_LI_subset.h5ad",
+    )
+    Path("suo22/").mkdir(exist_ok=True)
+    filepath = Path(filepath).rename("suo22/Visium10X_data_LI_subset.h5ad")
+    return ad.read(filepath)
+
+
+def mudata_papalexi21_subset():
+    """A subsetted mudata from papalexi21.
+
+    To reproduce the subsetting:
+    >>> !wget https://figshare.com/ndownloader/files/36509460
+    >>> import mudata as md
+    >>> import scanpy as sc
+    >>> mdata = md.read_h5mu("36509460")
+    >>> mdata = sc.pp.subsample(mdata, n_obs=200, copy=True)[0]
+    >>> mdata[:, -300:].copy().write("papalexi21_subset_200x300_lamindb_demo_2023-07-25.h5mu")  # noqa
+    """
+    import mudata as md
+
+    filepath, _ = urlretrieve(
+        "https://lamindb-test.s3.amazonaws.com/papalexi21_subset_200x300_lamindb_demo_2023-07-25.h5mu",  # noqa
+        "papalexi21_subset.h5mu",
+    )
+
+    return md.read_h5mu(filepath)
+
+
 def df_iris() -> pd.DataFrame:
     """The iris dataset as in sklearn.
 

{lamindb-0.48a3.dist-info → lamindb-0.48.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.48a3
+Version: 0.48.1
 Summary: LaminDB: Manage R&D data & analyses.
 Author-email: Lamin Labs <laminlabs@gmail.com>
 Requires-Python: >=3.8
@@ -8,9 +8,9 @@ Description-Content-Type: text/markdown
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
-Requires-Dist: lnschema_core==0.40.1
-Requires-Dist: lamindb_setup==0.49.0
-Requires-Dist: lamin_utils==0.9.1
+Requires-Dist: lnschema_core==0.42.2
+Requires-Dist: lamindb_setup==0.49.1
+Requires-Dist: lamin_utils==0.9.3
 Requires-Dist: erdiagram>=0.1.2
 Requires-Dist: rapidfuzz
 Requires-Dist: pydantic[dotenv]
@@ -25,7 +25,7 @@ Requires-Dist: botocore==1.29.76 ; extra == "aws"
 Requires-Dist: urllib3<2 ; extra == "aws"
 Requires-Dist: boto3==1.26.76 ; extra == "aws"
 Requires-Dist: fsspec[s3]==2023.5.0 ; extra == "aws"
-Requires-Dist: lnschema_bionty==0.27.4 ; extra == "bionty"
+Requires-Dist: lnschema_bionty==0.28.2 ; extra == "bionty"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"
 Requires-Dist: laminci>=0.3 ; extra == "dev"
@@ -257,7 +257,7 @@ pip install lamindb  # basic data management
 You can configure the installation using `extras`, e.g.,
 
 ```shell
-pip install lamindb[jupyter,bionty,fcs,aws]
+pip install 'lamindb[jupyter,bionty,fcs,aws]'
 ```
 
 Supported `extras` are:

{lamindb-0.48a3.dist-info → lamindb-0.48.1.dist-info}/RECORD

@@ -1,28 +1,29 @@
-lamindb/__init__.py,sha256=Jw_GabBpHKGMeq0sKzxB0aDwCB2-3OaLVjYbtxMFJ5g,2709
-lamindb/_context.py,sha256=J8YzSVFsnAvPBrQl0xlSei3d1-l01rp736RStIingqQ,17847
-lamindb/_dataset.py,sha256=J4kmPfS9cSPr9qJ5Rn7L0Zv2FnVA6FrUBvwEgGBMUDQ,5438
+lamindb/__init__.py,sha256=2z4YI7b6UvGZHwooeAkDKiCVDpQ5TkxRK62EDLT9iMA,2647
+lamindb/_context.py,sha256=lRGju9hB_rqaSAtIFY28kIciPSxy9yG86frdIBI1bBc,17875
+lamindb/_dataset.py,sha256=nR1cGJZmNEoiATECFEBMKskk5ynP46ODejvSoOLH_hA,5546
 lamindb/_delete.py,sha256=Jzb0sTlpdNDMa90ORMFiPbX0d-GhZsjmobQFc1miuJ8,1877
-lamindb/_feature.py,sha256=d043ps_Lw73_9-7sAG70mocUnN2TkAIMBnJrCax15zg,3755
-lamindb/_feature_set.py,sha256=36CuOUCpZiAh4mrwlNoCIXydy1edlBOv9_Ct4rev_F0,6582
-lamindb/_file.py,sha256=-0RhjTTE5TBzvIq50AFp8j2_cHo3EabMTcnwyAuEPRM,31754
-lamindb/_from_values.py,sha256=cmZdLV8ttq5cmYXT-R8fDDcTPLqlmKPf5eF3qH9xR1Y,10262
-lamindb/_label.py,sha256=ky9t_-dTA1u2iLeZn6Hj4IUfzyw9JY-2fDb64fCyYL0,1322
+lamindb/_feature.py,sha256=CNSZpnMX25JX5C11ie6GPAvwPiKzd7EYhLZ9Uk1HEWk,4043
+lamindb/_feature_manager.py,sha256=EaIUaFa67VyIJZ1u6ncPfiCzJkGNKmt2RZ9P3b_tzUA,6713
+lamindb/_feature_set.py,sha256=zkhCuH33PgTc3-zsWT7XlJcxIf7fBv7OI4n8R8cS_8I,6747
+lamindb/_file.py,sha256=sKCkAg0IMm0M4f0FwZhBKmgRUZPVN97vvwakicAp6oM,32815
+lamindb/_from_values.py,sha256=bbahbzm18yLam3LC_rguX7wFaBX8KYG3So6BrPcvJzI,12106
+lamindb/_label.py,sha256=taBj95rOrj56xQhjKN04E4FA1qWtsKZbCzC5OGLcIPA,2771
 lamindb/_logger.py,sha256=Q9ugUnZE4EwH0N6qFMG2HlILmu-SArnEEy-nafTPjRg,47
-lamindb/_manager.py,sha256=xOj2anF_z9hg2wrMncEpMqYHml5SehRbGxlNkeiIqzM,1877
-lamindb/_orm.py,sha256=tVskEYgvSWn2_y47btCzdxg0YQ_OlTrBfYjlGmbbCpk,19242
-lamindb/_queryset.py,sha256=WCM67hB3JwmN4GVVGs8AiIxxQjQ_rFH9kA7uEqpmHr0,9666
-lamindb/_save.py,sha256=iBrONuU-6cMtapouTACqcFDiZlNiipe7o9yLnMNmPoM,8539
+lamindb/_manager.py,sha256=x6-rRsFlPHL1VAN_mipfNKInY_E6E-M28Q8xn4fphUo,1895
+lamindb/_orm.py,sha256=AHia6AzRKLldg6n1emm02e9BOFGTbTv1qy-tdMJjWdY,23727
+lamindb/_queryset.py,sha256=hhToC5NcKS2PF59jxpdbsA16VBg1oVqVeMzWEFQXQRE,9713
+lamindb/_save.py,sha256=ZgV5qXBKLf84U0ssCS8z19bkIsh9SgjcJe38-laKlY8,9004
 lamindb/_select.py,sha256=w-a_vOLBm-HFIfDhtLJd9ieeU-V8vn16EQ2QlgU0jyA,325
 lamindb/_transform.py,sha256=K-Y37UqQPu06lsA3Jfnkyt5dssRpuMnpCDDHDbT40Z4,1251
 lamindb/_view.py,sha256=V5zatnXT40UmcRQx1ZBxyRJUnIqTv_iEelv4Tli3WyI,2074
 lamindb/types.py,sha256=svg5S_aynuGfbEOsbmqkR_gF9d9YMzfOkcvGN37Rzvg,232
-lamindb/dev/__init__.py,sha256=Dw-JxVxRW6UzZTf5ENiaGmeB5VPXqmu0x44R5v8BOLE,311
+lamindb/dev/__init__.py,sha256=JYmmgCbPdYNGL6J4aXxWd988su__uFAScRppvLsOzLo,431
 lamindb/dev/_settings.py,sha256=2mV4K29PZaf1FVM5XbMZD85_1wSvHc3iF20VSBRsFKY,2842
-lamindb/dev/_view_parents.py,sha256=nSO-FE-xMZRmV7cpU1poRKQWgXkGDqgBKWf6Yn7oVT8,9139
+lamindb/dev/_view_parents.py,sha256=IgW2fSwgViSJPIZhloW76pWvvljJ07Ev7Y1xl3ixF1E,7844
 lamindb/dev/hashing.py,sha256=oYHDSEjINsmDYgCLasnhh_VHbB1dLag27ufVUwDgLyQ,1385
 lamindb/dev/utils.py,sha256=LGdiW4k3GClLz65vKAVRkL6Tw-Gkx9DWAdez1jyA5bE,428
-lamindb/dev/datasets/__init__.py,sha256=EiDuUQzFGEyXu_ynf8i5VZv6himLBt1pbmYf8gWqJcg,1017
-lamindb/dev/datasets/_core.py,sha256=VxM0Xo_E2-UTjCV6l30HDHlw3RKYGZaCapvHlOgbLS0,9585
+lamindb/dev/datasets/__init__.py,sha256=ZVnWS5LhUjzrIe_v81hlqoCzgi_gDiV-W9T_rnqTuXo,1215
+lamindb/dev/datasets/_core.py,sha256=NAjisahI6C7GaZfIvmaIl_MTgvin-1NJAjxSG-EZbUA,11767
 lamindb/dev/datasets/_fake.py,sha256=S8mNho-oSh1M9x9oOSsUBLLHmBAegsOLlFk6LnF81EA,942
 lamindb/dev/storage/__init__.py,sha256=zFr8mpH1c3fzaQMYMwoLU9-zIMQ7laiPn5YDHDdFL5Y,424
 lamindb/dev/storage/_anndata_sizes.py,sha256=0XVzA6AQeVGPaGPrhGusKyxFgFjeo3qSN29hxb8D5E8,993
@@ -34,8 +35,8 @@ lamindb/schema/__init__.py,sha256=PznznlFvbeNSZKpn1RS6Gv0JMXFkLmU2_ej_1hVLSTs,79
 lamindb/schema/_core.py,sha256=nWR3X_rNd1AbWw3naMiBi8ppAEpqIDyEYqM54feRB_s,766
 lamindb/setup/__init__.py,sha256=8-0F2C4Glx23-b8-D_1CBGgRBM5PppVhazhoXZYOLsg,275
 lamindb/setup/dev/__init__.py,sha256=iD0f2lx_Hgp-udkiPGal7si5waJSOgvnG6Id-g1mMOY,213
-lamindb-0.48a3.dist-info/entry_points.txt,sha256=MioM8vSpKwXxY3geNBwjo1wnwy1l15WjJYlI3lpKuZI,53
-lamindb-0.48a3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-0.48a3.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-lamindb-0.48a3.dist-info/METADATA,sha256=QAEsZrkONc75rFcy3SI5NjJ1152gHG_tkUV-2RTWAmg,10841
-lamindb-0.48a3.dist-info/RECORD,,
+lamindb-0.48.1.dist-info/entry_points.txt,sha256=MioM8vSpKwXxY3geNBwjo1wnwy1l15WjJYlI3lpKuZI,53
+lamindb-0.48.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-0.48.1.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lamindb-0.48.1.dist-info/METADATA,sha256=hV5390-kWv89OW9gmlWPCNQ3-t2ynnezhp18bhh3klM,10843
+lamindb-0.48.1.dist-info/RECORD,,