lamindb 0.70.1__py3-none-any.whl → 0.70.2__py3-none-any.whl

lamindb/__init__.py

@@ -40,7 +40,7 @@ Modules & settings:
 
 """
 
-__version__ = "0.70.1"  # denote a release candidate for 0.1.0 with 0.1rc1
+__version__ = "0.70.2"  # denote a release candidate for 0.1.0 with 0.1rc1
 
 import os as _os
 

lamindb/_annotate.py

@@ -351,7 +351,7 @@ class AnnDataAnnotator(DataFrameAnnotator):
         self,
         adata: ad.AnnData,
         var_index: FieldAttr,
-        categoricals: dict[str, FieldAttr],
+        categoricals: dict[str, FieldAttr] | None = None,
         using: str = "default",
         verbosity: str = "hint",
         organism: str | None = None,
@@ -494,7 +494,7 @@ class MuDataAnnotator:
         self,
         mdata: MuData,
         var_index: dict[str, dict[str, FieldAttr]],
-        categoricals: dict[str, FieldAttr],
+        categoricals: dict[str, FieldAttr] | None = None,
         using: str = "default",
         verbosity: str = "hint",
         organism: str | None = None,
@@ -751,7 +751,7 @@ class Annotate:
         cls,
         adata: ad.AnnData,
         var_index: FieldAttr,
-        categoricals: dict[str, FieldAttr],
+        categoricals: dict[str, FieldAttr] | None = None,
         using: str = "default",
         verbosity: str = "hint",
         organism: str | None = None,
@@ -772,7 +772,7 @@ class Annotate:
         cls,
         mdata: MuData,
         var_index: dict[str, dict[str, FieldAttr]],
-        categoricals: dict[str, dict[str, FieldAttr]],
+        categoricals: dict[str, FieldAttr] | None = None,
         using: str = "default",
         verbosity: str = "hint",
         organism: str | None = None,

lamindb/_finish.py

@@ -20,37 +20,40 @@ if TYPE_CHECKING:
     from ._query_set import QuerySet
 
 
-class CallFinishInLastCell(SystemExit):
+class TrackNotCalled(SystemExit):
     pass
 
 
-def finish(i_saved_the_notebook: bool = False):
-    """Mark a tracked run as finished.
+class NotebookNotSaved(SystemExit):
+    pass
 
-    When run in notebooks, save the run report to your default storage location.
 
-    Args:
-        i_saved_the_notebook: Indicate that you saved the notebook in your
-            editor (JupyterLab, VSCode, etc.).
-    """
-    if is_run_from_ipython:
-        # notebooks
-        from nbproject.dev import read_notebook
-        from nbproject.dev._check_last_cell import check_last_cell
+def get_seconds_since_modified(filepath) -> float:
+    return datetime.now().timestamp() - filepath.stat().st_mtime
 
-        if not i_saved_the_notebook and not ln_setup._TESTING:
-            logger.error(
-                "Please pass `i_saved_the_notebook=True` to `ln.finish()`, save the notebook, and re-run this cell."
+
+def finish():
+    """Mark a tracked run as finished.
+
+    If run in a notebook, it saves the run report & source code to your default storage location.
+    """
+    if run_context.path is None:
+        raise TrackNotCalled("Please run `ln.track()` before `ln.finish()`")
+    if is_run_from_ipython:  # notebooks
+        if (
+            get_seconds_since_modified(run_context.path) > 3
+            and os.getenv("LAMIN_TESTING") is None
+        ):
+            raise NotebookNotSaved(
+                "Please save the notebook in your editor right before running `ln.finish()`"
             )
-            return None
         save_run_context_core(
             run=run_context.run,
             transform=run_context.transform,
             filepath=run_context.path,
             finished_at=True,
         )
-    else:
-        # scripts
+    else:  # scripts
         # save_run_context_core was already called during ln.track()
         run_context.run.finished_at = datetime.now(timezone.utc)  # update run time
         run_context.run.save()
@@ -98,7 +101,7 @@ def save_run_context_core(
         # log_level is set to 40 to silence the nbconvert logging
         subprocess.run(
             "jupyter nbconvert --to html"
-            f" {filepath.as_posix()} --Application.log_level=40",
+            f" '{filepath.as_posix()}' --Application.log_level=40",
             shell=True,
             check=True,
         )
@@ -118,7 +121,7 @@ def save_run_context_core(
         # first, copy the notebook file to a temporary file in the cache
         source_code_path = ln_setup.settings.storage.cache_dir / filepath.name
         shutil.copy2(filepath, source_code_path)  # copy
-        subprocess.run(f"nbstripout {source_code_path}", shell=True, check=True)
+        subprocess.run(f"nbstripout '{source_code_path}'", shell=True, check=True)
     # find initial versions of source codes and html reports
     prev_report = None
     prev_source = None
@@ -139,9 +142,8 @@ def save_run_context_core(
             if os.getenv("LAMIN_TESTING") is None:
                 # in test, auto-confirm overwrite
                 response = input(
-                    "You try to save a new notebook source code with the same version"
-                    f" '{transform.version}'; do you want to replace the content of the"
-                    f" existing source code {transform.source_code}? (y/n)"
+                    f"You are about to overwrite existing source code (hash {transform.source_code.hash}) for transform version"
+                    f" '{transform.version}'. Proceed? (y/n)"
                 )
             else:
                 response = "y"
@@ -149,10 +151,7 @@ def save_run_context_core(
                 transform.source_code.replace(source_code_path)
                 transform.source_code.save()
             else:
-                logger.warning(
-                    "Please create a new version of the notebook via `lamin track"
-                    " <filepath>` and re-run the notebook"
-                )
+                logger.warning("Please re-run `ln.track()` to make a new version")
                 return "rerun-the-notebook"
     else:
         source_code = ln.Artifact(
@@ -207,8 +206,11 @@ def save_run_context_core(
     transform.save()
     if transform.type == TransformType.notebook:
         logger.success(f"saved transform.latest_report: {transform.latest_report}")
-    identifier = ln_setup.settings.instance.slug
-    logger.success(f"go to: https://lamin.ai/{identifier}/transform/{transform.uid}")
+    if ln_setup.settings.instance.is_remote:
+        identifier = ln_setup.settings.instance.slug
+        logger.success(
+            f"go to: https://lamin.ai/{identifier}/transform/{transform.uid}"
+        )
     # because run & transform changed, update the global run_context
     run_context.run = run
     run_context.transform = transform

lamindb/core/storage/__init__.py

@@ -10,5 +10,6 @@ from lamindb_setup.core.upath import LocalPathClasses, UPath, infer_filesystem
 
 from ._anndata_sizes import size_adata
 from ._backed_access import AnnDataAccessor, BackedAccessor
+from ._valid_suffixes import VALID_SUFFIXES
 from .objects import infer_suffix, write_to_file
 from .paths import delete_storage, load_to_memory

lamindb/core/storage/_backed_access.py

@@ -733,7 +733,7 @@ class BackedAccessor:
 
 
 def backed_access(
-    artifact_or_filepath: Artifact | Path, using_key: str | None
+    artifact_or_filepath: Artifact | Path, using_key: str | None = None
 ) -> AnnDataAccessor | BackedAccessor:
     if isinstance(artifact_or_filepath, Artifact):
         filepath = filepath_from_artifact(artifact_or_filepath, using_key=using_key)
@@ -747,11 +747,11 @@ def backed_access(
         conn, storage = registry.open("zarr", filepath)
     else:
         raise ValueError(
-            "file should have .h5, .hdf5, .h5ad, .zarr suffix, not"
+            "object should have .h5, .hdf5, .h5ad, .zarr suffix, not"
             f" {filepath.suffix}."
         )
 
-    if filepath.suffix in (".h5ad", ".zarr"):
+    if filepath.suffix == ".h5ad":
         return AnnDataAccessor(conn, storage, name)
     else:
         if get_spec(storage).encoding_type == "anndata":

lamindb/core/storage/_valid_suffixes.py

@@ -0,0 +1,3 @@
+from lamindb_setup.core.upath import VALID_SUFFIXES
+
+VALID_SUFFIXES.update({".vitessce.json", ".anndata.zarr", ".spatialdata.zarr"})

lamindb/integrations/_vitessce.py

@@ -8,6 +8,8 @@ import lamindb_setup as ln_setup
 from lamin_utils import logger
 
 from lamindb._artifact import Artifact
+from lamindb._run import Run
+from lamindb._transform import Transform
 
 if TYPE_CHECKING:
     from vitessce import VitessceConfig
@@ -15,36 +17,54 @@ if TYPE_CHECKING:
 
 # tested & context in https://github.com/laminlabs/lamin-spatial
 def save_vitessce_config(vitessce_config: VitessceConfig, description: str) -> Artifact:
-    """Takes a ``VitessceConfig`` object and saves it as an artifact.
+    """Validates and saves a ``VitessceConfig`` object.
+
+    Example: :doc:`docs:vitessce`.
 
     Args:
         vitessce_config (``VitessceConfig``): A VitessceConfig object.
         description: A description for the artifact.
-    """
-    # can't assume vitessce is installed
-    from vitessce import VitessceConfig
 
-    # create a local _data export_ in a folder
-    timestamp = datetime.now(timezone.utc).isoformat().split(".")[0]
-    vitesse_export_folder = f"./vitessce_export_{timestamp}.vitessce"
-    vitessce_config.export(to="files", base_url="", out_dir=vitesse_export_folder)
-    logger.important(f"local export: {vitesse_export_folder}")
-    # create an artifact and store the local export in th cloud
-    artifact = Artifact(vitesse_export_folder, description=description)
-    artifact.save()
-    # create a JSON export that points to the data in the cloud
-    config_dict = vitessce_config.to_dict(base_url=artifact.path.to_url())
-    logger.important(f"base url: {artifact.path.to_url()}")
-    # manually place that JSON export into the local data export folder
-    config_filename = "vitessce_config.json"
-    config_file_local_path = f"{vitesse_export_folder}/{config_filename}"
+    .. versionchanged:: 0.70.2
+        This function no longer saves the dataset. It only saves the VitessceConfig object.
+    """
+    vc_dict = vitessce_config.to_dict()
+    # validate
+    datasets = vc_dict["datasets"]
+    input_artifacts = []
+    for dataset in datasets:
+        if "files" not in dataset:
+            raise ValueError("Each dataset must have a 'files' key.")
+        for file in dataset["files"]:
+            if "url" not in file:
+                raise ValueError("Each file must have a 'url' key.")
+            filename = file["url"].split("/")[-1]
+            assert filename.endswith((".anndata.zarr", ".spatialdata.zarr", ".zarr"))
+            filestem = (
+                filename.replace(".anndata.zarr", "")
+                .replace(".spatialdata.zarr", "")
+                .replace(".zarr", "")
+            )
+            artifact = Artifact.filter(uid__startswith=filestem).one_or_none()
+            if artifact is None:
+                logger.warning(f"could not find dataset in lamindb: {dataset}")
+            else:
+                input_artifacts.append(artifact)
+    # link inputs
+    with logger.mute():
+        transform = Transform(name="save_vitessce_config", type="function", version="1")
+        transform.save()
+    run = Run(transform=transform)
+    run.save()
+    run.input_artifacts.set(input_artifacts)
+    # create a JSON export
+    config_file_local_path = (
+        ln_setup.settings.storage.cache_dir / "config.vitessce.json"
+    )
     with open(config_file_local_path, "w") as file:
-        json.dump(config_dict, file)
-    # manually place that JSON export into the previously registered artifact folder
-    config_file_path = artifact.path / config_filename
-    config_file_path.upload_from(config_file_local_path)
-    # log the the URLs
-    logger.important(f"config url: {config_file_path.to_url()}")
+        json.dump(vc_dict, file)
+    artifact = Artifact(config_file_local_path, description=description, run=run)
+    artifact.save()
     slug = ln_setup.settings.instance.slug
     logger.important(f"go to: https://lamin.ai/{slug}/artifact/{artifact.uid}")
     return artifact

{lamindb-0.70.1.dist-info → lamindb-0.70.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.70.1
+Version: 0.70.2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.8
@@ -10,8 +10,8 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Requires-Dist: lnschema_core==0.65.1
-Requires-Dist: lamindb_setup==0.69.2
-Requires-Dist: lamin_utils==0.13.1
+Requires-Dist: lamindb_setup==0.69.4
+Requires-Dist: lamin_utils==0.13.2
 Requires-Dist: lamin_cli==0.12.3
 Requires-Dist: rapidfuzz
 Requires-Dist: pyarrow

{lamindb-0.70.1.dist-info → lamindb-0.70.2.dist-info}/RECORD

@@ -1,12 +1,12 @@
-lamindb/__init__.py,sha256=z8Z1Bsb9A_xPvukQCyt7I2d5w_FsWd27bMZlULQJ7JU,2163
-lamindb/_annotate.py,sha256=BXYWFATifbfRVmLFIgE4cZ4Fls4lkH2WXAEL2o7v-XM,43035
+lamindb/__init__.py,sha256=JHrhBHkihUcLRbreh9xyafsWang75NJxz9CVIWx6Bc0,2163
+lamindb/_annotate.py,sha256=B0KSvo5S2kJPeMMqy2SSFkqRJCS2QRC4NtI0_vWEZMs,43080
 lamindb/_artifact.py,sha256=BUl_3WYwrZ28P93Pb9AiwriVFBSLvBUEQjYEyYCrkZ0,37307
 lamindb/_can_validate.py,sha256=nvoZG-35n3HofkY4Xc6hBv9AV54_RDan7Hzp5TuqY9I,14709
 lamindb/_collection.py,sha256=wf7ClfiD3vsetts_iSUk4UihWsHq0IdOF8LdIIHS7JU,14536
 lamindb/_feature.py,sha256=srAKchY7gqD-h-cWlEiAWuHlpFKFwv0PWIA-JX0Go8c,6758
 lamindb/_feature_set.py,sha256=AzjOcHzQajpeikPOAic-aj0z_C5b7VpHVegg3ThRSLw,9045
 lamindb/_filter.py,sha256=xnjJzjF3Zj4dK_Kfymvhgczk27MhhXz5ZYc7XINbgHY,1331
-lamindb/_finish.py,sha256=SIPIIMAXM2d00L6VHMf2qFiOHuTyAlLy-5qRJ-BYaIQ,8107
+lamindb/_finish.py,sha256=oR7oe6By3vEhF0twDBqSdT1EF28MPhyiS_cfZP0CcCw,8040
 lamindb/_from_values.py,sha256=DVXjnQ2wwNw-2bFzy0uXLdVlqoprrn95hTnrXwn-KqM,12638
 lamindb/_is_versioned.py,sha256=0PgRCmxEmYDcAjllLSOYZm132B1lW6QgmBBERhRyFt0,1341
 lamindb/_parents.py,sha256=N9T8jbd3eaoHDLE9TD1y1QgGcO81E6Brapy8LILzRCQ,14790
@@ -38,17 +38,18 @@ lamindb/core/versioning.py,sha256=DsEHpCueNwhRiIaRH5-O8H_1fJVNtWslCRx30YiIS5o,30
 lamindb/core/datasets/__init__.py,sha256=zRP98oqUAaXhqWyKMiH0s_ImVIuNeziQQ2kQ_t0f-DI,1353
 lamindb/core/datasets/_core.py,sha256=36vUOYFkX_4hBAnM_BujV5BRARMI5b9iI_SM9qS7wGc,20191
 lamindb/core/datasets/_fake.py,sha256=BZF9R_1iF0HDnvtZNqL2FtsjSMuqDIfuFxnw_LJYIh4,953
-lamindb/core/storage/__init__.py,sha256=zsVbIseNLJfObDl7cuCbULr6rnux_R_N8EVV843XmIU,371
+lamindb/core/storage/__init__.py,sha256=6jnbFj-eBV3xZt04qP-kTsMWoP8YwpM50wlnnxDYsZU,415
 lamindb/core/storage/_anndata_sizes.py,sha256=aXO3OB--tF5MChenSsigW6Q-RuE8YJJOUTVukkLrv9A,1029
-lamindb/core/storage/_backed_access.py,sha256=DweJdYP8tKEOZbfJ1UKFQgAIzQjsJqdqj8U9y7T0oXo,24538
+lamindb/core/storage/_backed_access.py,sha256=eManrLsu3pSSQAyAKy47FDBm-iHgjaNfHA-zLy59uDs,24536
+lamindb/core/storage/_valid_suffixes.py,sha256=sewRRU3I6fJ-Jd5ACNcco_o3hic9zmqTs8BuZui-450,133
 lamindb/core/storage/_zarr.py,sha256=0i9-cJPjieIsp5UpK-IyRPkHAF-iKkWgpkWviSni2MM,2900
 lamindb/core/storage/objects.py,sha256=5LbBeZVKuOOB8DceSE-PN8elKY0N9OhFXZPQJE4lK48,1538
 lamindb/core/storage/paths.py,sha256=XWfSHK5b3_TFiK-IMvH-srvxO0bZStzA_rwjNaTxQU4,7725
 lamindb/integrations/__init__.py,sha256=aH2PmO2m4-vwIifMYTB0Fyyr_gZWtVnV71jT0tVWSw0,123
-lamindb/integrations/_vitessce.py,sha256=l3GPkzQXcwnMypbm8vDkITjognELjX8ucLaiqy99Jgg,2131
+lamindb/integrations/_vitessce.py,sha256=Ii2YhGwXH_tNDS9MXzxNekthWoDmDGpgGxAOVcTIbB4,2550
 lamindb/setup/__init__.py,sha256=OwZpZzPDv5lPPGXZP7-zK6UdO4FHvvuBh439yZvIp3A,410
 lamindb/setup/core/__init__.py,sha256=SevlVrc2AZWL3uALbE5sopxBnIZPWZ1IB0NBDudiAL8,167
-lamindb-0.70.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-0.70.1.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-lamindb-0.70.1.dist-info/METADATA,sha256=qbHYrCM8tdhGUBT-70lupGW7AQ5RVNA7gg9yRTvihwA,2835
-lamindb-0.70.1.dist-info/RECORD,,
+lamindb-0.70.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-0.70.2.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+lamindb-0.70.2.dist-info/METADATA,sha256=KqXBjKMhKMBbx7VYeaWWfP0Xot_OyRRjpFO9vZotb7c,2835
+lamindb-0.70.2.dist-info/RECORD,,