lamindb 1.3.0__tar.gz → 1.3.2__tar.gz

{lamindb-1.3.0 → lamindb-1.3.2}/CONTRIBUTING.md

@@ -15,10 +15,14 @@ For installation from GitHub, call:
 ```bash
 git clone --recursive https://github.com/laminlabs/lamindb
 pip install laminci
+python -m venv .venv
+source .venv/bin/activate
 nox -s install
 ```
 
-This will install a few dependencies from the git submodules linked [here](https://github.com/laminlabs/lamindb/tree/main/sub).
+This will install a few dependencies from the git submodules linked [here](https://github.com/laminlabs/lamindb/tree/main/sub), as well as packages
+like `pytest` and `pre-commit` that you'll need when developing.
+
 lamindb depends on several other packages that may require modifications for pull requests to successfully pass the continuous integration build.
 We suggest the following workflow if commits to any of the submodules are essential for the current modifications in lamindb:
 
@@ -78,6 +82,8 @@ and enabled for the repository via:
 gitmoji -i
 ```
 
+If you don't have `sudo` in your working environment, follow [these instructions](https://github.com/sindresorhus/guides/blob/main/npm-global-without-sudo.md).
+
 ## Documentation
 
 We build our documentation with an internal tool called `lndocs`.

{lamindb-1.3.0 → lamindb-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: lamindb
-Version: 1.3.0
+Version: 1.3.2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.10,<3.14
@@ -11,7 +11,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: lamin_utils==0.13.11
 Requires-Dist: lamin_cli==1.2.0
-Requires-Dist: lamindb_setup[aws]==1.3.2
+Requires-Dist: lamindb_setup[aws]==1.4.1
 Requires-Dist: pyyaml
 Requires-Dist: pyarrow
 Requires-Dist: pandera
@@ -23,7 +23,7 @@ Requires-Dist: anndata>=0.8.0,<=0.11.3
 Requires-Dist: fsspec
 Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
-Requires-Dist: bionty ; extra == "bionty"
+Requires-Dist: bionty>=1.2.1 ; extra == "bionty"
 Requires-Dist: cellregistry ; extra == "cellregistry"
 Requires-Dist: clinicore ; extra == "clinicore"
 Requires-Dist: tomlkit ; extra == "dev"

{lamindb-1.3.0 → lamindb-1.3.2}/docs/curate.ipynb

@@ -97,7 +97,7 @@
     "        ln.Feature(name=\"assay_oid\", dtype=bt.ExperimentalFactor.ontology_id).save(),\n",
     "        ln.Feature(name=\"donor\", dtype=str, nullable=True).save(),\n",
     "        ln.Feature(name=\"concentration\", dtype=str).save(),\n",
-    "        ln.Feature(name=\"treatment_time_h\", dtype=float, coerce_dtype=True).save(),\n",
+    "        ln.Feature(name=\"treatment_time_h\", dtype=\"num\", coerce_dtype=True).save(),\n",
     "    ],\n",
     ").save()\n",
     "# display the associated features as a dataframe\n",

{lamindb-1.3.0 → lamindb-1.3.2}/docs/faq.md

@@ -10,7 +10,6 @@ faq/setup
 faq/curate-any
 faq/import-modules
 faq/reference-field
-faq/key
 faq/visibility
 faq/delete
 faq/keep-artifacts-local

{lamindb-1.3.0 → lamindb-1.3.2}/lamindb/__init__.py

@@ -72,7 +72,7 @@ Backward compatibility.
 
 # ruff: noqa: I001
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.3.0"
+__version__ = "1.3.2"
 
 import warnings
 

{lamindb-1.3.0 → lamindb-1.3.2}/lamindb/_view.py

@@ -11,7 +11,7 @@ from lamindb_setup._init_instance import get_schema_module_name
 
 from lamindb.models import Feature, FeatureValue, ParamValue, Record
 
-from .models.feature import convert_pandas_dtype_to_lamin_dtype
+from .models.feature import serialize_pandas_dtype
 
 if TYPE_CHECKING:
     import pandas as pd
@@ -114,7 +114,7 @@ def view(
     """
     if df is not None:
         descriptions = {
-            col_name: convert_pandas_dtype_to_lamin_dtype(dtype)
+            col_name: serialize_pandas_dtype(dtype)
             for col_name, dtype in df.dtypes.to_dict().items()
         }
         feature_dtypes = dict(Feature.objects.values_list("name", "dtype"))

lamindb-1.3.2/lamindb/base/types.py

@@ -0,0 +1,90 @@
+"""Types.
+
+Central object types.
+
+.. autosummary::
+   :toctree: .
+
+   ArtifactKind
+   TransformType
+   Dtype
+
+Basic types.
+
+.. autosummary::
+   :toctree: .
+
+   UPathStr
+   StrField
+   ListLike
+   FieldAttr
+"""
+
+from __future__ import annotations
+
+from typing import Literal, Union
+
+import numpy as np
+import pandas as pd
+from django.db.models.query_utils import DeferredAttribute as FieldAttr
+from lamindb_setup.core.types import UPathStr  # noqa: F401
+
+# need to use Union because __future__.annotations doesn't do the job here <3.10
+# typing.TypeAlias, >3.10 on but already deprecated
+ListLike = Union[list[str], pd.Series, np.array]
+StrField = Union[str, FieldAttr]  # typing.TypeAlias
+
+TransformType = Literal[
+    "pipeline", "notebook", "upload", "script", "function", "linker"
+]
+ArtifactKind = Literal["dataset", "model"]
+
+# below is used for Feature.dtype and Param.dtype
+Dtype = Literal[
+    "cat",  # categoricals
+    "num",  # numericals
+    "str",  # string
+    "int",  # integer / numpy.integer
+    "float",  # float
+    "bool",  # boolean
+    "date",  # date
+    "datetime",  # datetime
+    "object",  # this is a pandas input dtype, we're only using it for complicated types, not for strings
+]
+"""Data type.
+
+Data types in lamindb are a string-serialized abstraction of common data types.
+
+Overview
+========
+
+============  ============  =================================================
+description   lamindb       pandas
+============  ============  =================================================
+categorical   `"cat"`       `category`
+numerical     `"num"`       `int | float`
+integer       `"int"`       `int64 | int32 | int16 | int8 | uint | ...`
+float         `"float"`     `float64 | float32 | float16 | float8 | ...`
+string        `"str"`       `object`
+datetime      `"datetime"`  `datetime`
+date          `"date"`      `date`
+============  ============  =================================================
+
+Categoricals
+============
+
+Beyond indicating that a feature is a categorical, `lamindb` allows you to define the registry to which values are restricted.
+
+For example, `'cat[ULabel]'` or `'cat[bionty.CellType]'` indicate that permissible values are from the `ULabel` or `CellType` registry, respectively.
+
+You can also reference multiple registries, e.g., `'cat[ULabel|bionty.CellType]'` indicates that values can be from either registry.
+
+You can also restrict to sub-types defined in registries via the `type` column, e.g., `'cat[ULabel[CellMedium]]'` indicates that values must be of type `CellMedium` within the `ULabel` registry.
+
+Literal
+=======
+
+A `Dtype` object in `lamindb` is a `Literal` up to further specification of `"cat"`.
+
+"""
+FeatureDtype = Dtype  # backward compat

{lamindb-1.3.0 → lamindb-1.3.2}/lamindb/core/types.py

@@ -6,7 +6,7 @@ from anndata import AnnData
 from lamindb_setup.core.types import UPathStr
 
 from lamindb.base.types import (
-    FeatureDtype,
+    Dtype,
     FieldAttr,
     ListLike,
     StrField,