lamindb 0.71.3__tar.gz → 0.72.0__tar.gz

{lamindb-0.71.3 → lamindb-0.72.0}/.github/workflows/build.yml

@@ -50,10 +50,10 @@ jobs:
           path: ~/postgres.tar
           key: cache-postgres-0
       - name: cache postgres miss
-        if: ${{ steps.cache-postgres.outputs.cache-hit != 'true' && matrix.group == 'faq' || matrix.group == 'unit' }}
+        if: ${{ steps.cache-postgres.outputs.cache-hit != 'true' }}
         run: docker pull postgres:latest && docker image save postgres:latest --output ~/postgres.tar
       - name: cache postgres use
-        if: ${{ steps.cache-postgres.outputs.cache-hit == 'true' && matrix.group == 'faq' || matrix.group == 'unit' }}
+        if: ${{ steps.cache-postgres.outputs.cache-hit == 'true' }}
         run: docker image load --input ~/postgres.tar
       - run: pip install -U laminci
       - name: install postgres

{lamindb-0.71.3 → lamindb-0.72.0}/.gitmodules

@@ -13,3 +13,6 @@
 [submodule "sub/bionty"]
 	path = sub/bionty
 	url = https://github.com/laminlabs/bionty
+[submodule "sub/wetlab"]
+	path = sub/wetlab
+	url = https://github.com/laminlabs/wetlab

{lamindb-0.71.3 → lamindb-0.72.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.71.3
+Version: 0.72.0
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.8
@@ -9,8 +9,8 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Dist: lnschema_core==0.66.5
-Requires-Dist: lamindb_setup==0.71.4
+Requires-Dist: lnschema_core==0.67.1
+Requires-Dist: lamindb_setup==0.72.1
 Requires-Dist: lamin_utils==0.13.2
 Requires-Dist: lamin_cli==0.13.2
 Requires-Dist: rapidfuzz
@@ -25,7 +25,7 @@ Requires-Dist: graphviz
 Requires-Dist: psycopg2-binary
 Requires-Dist: psutil
 Requires-Dist: lamindb_setup[aws] ; extra == "aws"
-Requires-Dist: bionty==0.42.11 ; extra == "bionty"
+Requires-Dist: bionty==0.43.0 ; extra == "bionty"
 Requires-Dist: pandas<2 ; extra == "dev"
 Requires-Dist: pre-commit ; extra == "dev"
 Requires-Dist: nox ; extra == "dev"

{lamindb-0.71.3 → lamindb-0.72.0}/docs/annotate-for-developers.ipynb

@@ -259,7 +259,7 @@
    "source": [
     "# external metadata features\n",
     "external_meta_features = [\n",
-    "    ln.Feature(name=name, type=\"category\") for name in external_meta.keys()\n",
+    "    ln.Feature(name=name, dtype=\"cat\") for name in external_meta.keys()\n",
     "]\n",
     "ln.save(external_meta_features)\n",
     "external_meta_features"

{lamindb-0.71.3 → lamindb-0.72.0}/docs/changelog.md

@@ -12,6 +12,26 @@ LaminDB implements "migration-based versioning". When upgrading your LaminDB ins
 .. role:: small
 ```
 
+## 0.72
+
+### 0.72.0 {small}`2024-05-19`
+
+- ✨ Extend managed access for AWS S3 to arbitrary paths [PR](https://github.com/laminlabs/lamindb/pull/1668) [@Koncopd](https://github.com/Koncopd) [@fredericenard](https://github.com/fredericenard)
+- ✨ Extended data lineage tracking [PR](https://github.com/laminlabs/lamindb/pull/1667) [@falexwolf](https://github.com/falexwolf)
+    - Now store all _creating_ runs and all _updating_ runs for any entity, not just for `Artifact` & `Collection`, e.g., runs can now have `CellType` record outputs
+    - Code is simpler through inheritance from two new base classes: `TracksRun` and `TracksUpdates`
+- ♻️ Briefer and richer syntax for denoting feature types, renamed `Feature.type` to `Feature.dtype`, e.g., for categorical features, a valid type can be: `cat[ULabel|bionty.Drug]` [PR](https://github.com/laminlabs/lamindb/pull/1663) [@falexwolf](https://github.com/falexwolf)
+- ✨ Support non-categorical metadata [PR](https://github.com/laminlabs/lnschema-core/pull/379) [@falexwolf](https://github.com/falexwolf)
+    - Track non-categorical features: `int`, `float`, `bool`, `datetime`, lists & dictionaries stored in a `FeatureValue` registry
+    - Track arbitrary typed parameters for runs through a `Param` registry analogous to the `Feature` registry: this replaces the hard-to-validate, hard-to-migrate, and hard-to-query `json` field of `Run`
+- 🏗️ Refactor link models [PR](https://github.com/laminlabs/lamindb/pull/1666) [PR](https://github.com/laminlabs/lamindb/pull/1661) [@falexwolf](https://github.com/falexwolf)
+    - All annotation-related links are now stratified by `Feature`: what held for `ULabel` now also holds `CellType` and all other `Bionty` registries
+    - Indicate whether semantic keys were used during validation to enable warnings upon renames
+    - Protect artifact annotations rather than cascade delete them
+    - More consistent naming of link models, e.g., `ulabels.artifact_links` instead of `ulabels.artifactulabel_set`
+    - Dropped linking `Bionty` entities directly against `Collection`
+    - Pruned & squashed migrations for faster instance creation
+
 ## 0.71
 
 ### 0.71.3 {small}`2024-05-14`

{lamindb-0.71.3 → lamindb-0.72.0}/docs/faq/idempotency.ipynb

@@ -130,7 +130,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "label = ln.ULabel(name=\"My project 2\")"
+    "label = ln.ULabel(name=\"My project 1a\")"
    ]
   },
   {
@@ -197,7 +197,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "label = ln.ULabel(name=\"My project 3\")"
+    "label = ln.ULabel(name=\"My project 1b\")"
    ]
   },
   {
@@ -226,7 +226,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "label = ln.ULabel(name=\"My project 3\")"
+    "label = ln.ULabel(name=\"My project 1c\")"
    ]
   },
   {
@@ -401,7 +401,7 @@
     "artifact3 = ln.Artifact(filepath, description=\"My fcs artifact\")\n",
     "assert artifact3.id == artifact2.id\n",
     "assert artifact3.run != artifact2.run\n",
-    "assert artifact3.replicating_runs.first() == artifact2.run"
+    "assert artifact3.previous_runs.first() == artifact2.run"
    ]
   },
   {

{lamindb-0.71.3 → lamindb-0.72.0}/docs/introduction.ipynb

@@ -66,7 +66,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
    "outputs": [],
    "source": [
     "# store artifacts in a local directory `./lamin-intro`\n",
@@ -79,7 +83,9 @@
    "source": [
     "### Track\n",
     "\n",
-    "Run {meth}`~lamindb.track` to track the input and output data of your code ({class}`~lamindb.Transform`)."
+    "Run {meth}`~lamindb.track` to track the inputs and outputs of your code ({class}`~lamindb.Transform`).\n",
+    "\n",
+    "When you first run `ln.track()`, it creates a `stem_uid` & `version` to unambiguously identify your notebook or script."
    ]
   },
   {
@@ -94,11 +100,11 @@
    "source": [
     "import lamindb as ln\n",
     "\n",
-    "# auto-generated identifiers for your notebook or script\n",
-    "ln.settings.transform.stem_uid = \"FPnfDtJz8qbE\"\n",
-    "ln.settings.transform.version = \"1\"\n",
+    "# copy-pasted identifiers for your notebook or script\n",
+    "ln.settings.transform.stem_uid = \"FPnfDtJz8qbE\"  # <-- auto-generated by running ln.track()\n",
+    "ln.settings.transform.version = \"1\"  # <-- auto-generated by running ln.track()\n",
     "\n",
-    "# track the execution of your code\n",
+    "# track the execution of your notebook or script\n",
     "ln.track()"
    ]
   },
@@ -844,9 +850,12 @@
     "\n",
     "<img src=\"https://lamin-site-assets.s3.amazonaws.com/.lamindb/BunYmHkyFLITlM5MYQci.svg\" width=\"350px\" style=\"background: transparent\" align=\"right\">\n",
     "\n",
-    "The complexity of modern R&D data often blocks realizing the scientific progress it promises.\n",
+    "The complexity of modern R&D data often blocks realizing the scientific progress it promises: see this [blog post](https://lamin.ai/blog/problems).\n",
+    "\n",
+    "More basically: The pydata family of objects is at the heart of most data science, ML & comp bio workflows: `DataFrame`, `AnnData`, `pytorch.DataLoader`, `zarr.Array`, `pyarrow.Table`, `xarray.Collection`, etc. We couldn’t find a tool to link these objects to context so that they could be analyzed in context:\n",
     "\n",
-    "See this [blog post](https://lamin.ai/blog/problems).\n",
+    "- provenance: data sources, data transformations, models, users\n",
+    "- domain knowledge & experimental metadata: the features & labels derived from domain entities\n",
     "\n",
     "### Assumptions\n",
     "\n",
@@ -893,6 +902,11 @@
     "\n",
     "LaminDB was influenced by many other projects, see {doc}`docs:influences`."
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
   }
  ],
  "metadata": {

{lamindb-0.71.3 → lamindb-0.72.0}/docs/storage/prepare-transfer-local-to-cloud.ipynb

@@ -24,7 +24,7 @@
    "source": [
     "import lamindb as ln\n",
     "import bionty as bt\n",
-    "import wetlab as ln1\n",
+    "import wetlab as wl\n",
     "import pandas as pd"
    ]
   },
@@ -49,15 +49,15 @@
     "\n",
     "features = bt.CellMarker.from_values([\"PD1\", \"CD21\"], field=bt.CellMarker.name, organism=\"human\")\n",
     "ln.save(features)\n",
-    "artifact.features.add(features, slot=\"var\")\n",
+    "artifact.features.add_feature_set(ln.FeatureSet(features), slot=\"var\")\n",
     "\n",
     "organism = bt.Organism.from_public(name=\"human\")\n",
     "organism.save()\n",
     "artifact.labels.add(organism)\n",
     "\n",
-    "experiment_type = ln1.ExperimentType(name=\"experiment-type-test-transfer-to-cloud\")\n",
+    "experiment_type = wl.ExperimentType(name=\"experiment-type-test-transfer-to-cloud\")\n",
     "experiment_type.save()\n",
-    "experiment = ln1.Experiment(name=\"experiment-test-transfer-to-cloud\")\n",
+    "experiment = wl.Experiment(name=\"experiment-test-transfer-to-cloud\")\n",
     "experiment.experiment_type = experiment_type\n",
     "experiment.save()\n",
     "\n",

{lamindb-0.71.3 → lamindb-0.72.0}/docs/storage/transfer-local-to-cloud.ipynb

@@ -31,12 +31,14 @@
    "outputs": [],
    "source": [
     "def cleanup(artifact: ln.Artifact):\n",
-    "    artifact.feature_sets.all().delete()\n",
-    "    artifact.experiments.all().delete()\n",
+    "    features_sets = artifact.feature_sets.all()\n",
+    "    experiments = artifact.experiments.all()\n",
     "    try:\n",
     "        artifact.delete(permanent=True)\n",
     "    except Exception:\n",
     "        pass\n",
+    "    features_sets.delete()\n",
+    "    experiments.delete()\n",
     "\n",
     "artifacts = ln.Artifact.filter(description='test-transfer-to-cloud').all()\n",
     "for artifact in artifacts:\n",
@@ -78,7 +80,7 @@
    "outputs": [],
    "source": [
     "assert artifact._state.db == \"default\"\n",
-    "assert artifact.organism.get().name == \"human\"\n",
+    "assert artifact.organisms.get().name == \"human\"\n",
     "assert artifact.experiments.get().name == \"experiment-test-transfer-to-cloud\"\n",
     "assert artifact.features[\"var\"].count() == 2"
    ]

{lamindb-0.71.3 → lamindb-0.72.0}/docs/tutorial.ipynb

@@ -134,8 +134,11 @@
    },
    "outputs": [],
    "source": [
-    "ln.settings.transform.stem_uid = \"NJvdsWWbJlZS\"\n",
-    "ln.settings.transform.version = \"0\"\n",
+    "# copy-pasted identifiers for your notebook or script\n",
+    "ln.settings.transform.stem_uid = \"NJvdsWWbJlZS\"  # <-- auto-generated by running ln.track()\n",
+    "ln.settings.transform.version = \"0\"  # <-- auto-generated by running ln.track()\n",
+    "\n",
+    "# track the execution of your notebook or script\n",
     "ln.track()"
    ]
   },
@@ -533,8 +536,7 @@
    },
    "outputs": [],
    "source": [
-    "study0_data = ln.Artifact(f\"s3://lamindb-dev-datasets/iris_studies/study0_raw_images\")\n",
-    "study0_data.save()\n",
+    "study0_data = ln.Artifact(f\"s3://lamindb-dev-datasets/iris_studies/study0_raw_images\").save()\n",
     "ln.Artifact.df()"
    ]
   },

{lamindb-0.71.3 → lamindb-0.72.0}/docs/tutorial2.ipynb

@@ -5,7 +5,7 @@
    "metadata": {},
    "source": [
     "![](https://img.shields.io/badge/tutorial2/2-lightgrey)\n",
-    "[![](https://img.shields.io/badge/Source%20on%20GitHub-orange)](https://github.com/laminlabs/lamindb/blob/main/docs/tutorial1.ipynb)\n",
+    "[![](https://img.shields.io/badge/Source%20on%20GitHub-orange)](https://github.com/laminlabs/lamindb/blob/main/docs/tutorial2.ipynb)\n",
     "[![](https://img.shields.io/badge/Source%20%26%20report%20on%20LaminHub-mediumseagreen)](https://lamin.ai/laminlabs/lamindata/transform/dMtrt8YMSdl6z8)"
    ]
   },
@@ -20,12 +20,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In the previous tutorial ({doc}`/tutorial`), we learned about about how to leverage basic metadata for artifacts to access data (query, search, cache & load).\n",
+    "In {doc}`/tutorial`, we learned about provenance and data access. Here, we walk through validating & annotating datasets with features & labels to improve:\n",
     "\n",
-    "Here, we walk through annotating & validating data with features & labels to improve:\n",
-    "\n",
-    "1. Finding data: Which collections measured expression of cell marker `CD14`? Which characterized cell line `K562`? Which collections have a test & train split? Etc.\n",
-    "2. Using data: Are there typos in feature names? Are there typos in sampled labels? Are units of features consistent? Etc."
+    "1. Findability: Which collections measured expression of cell marker `CD14`? Which characterized cell line `K562`? Which collections have a test & train split? Etc.\n",
+    "2. Usability: Are there typos in feature names? Are there typos in sampled labels? Are types and units of features consistent? Etc."
    ]
   },
   {
@@ -34,27 +32,68 @@
    "source": [
     ":::{hint}\n",
     "\n",
-    "This is a low-level tutorial aimed at a basic understanding of features and labels.\n",
+    "This is a low-level tutorial aimed at a basic understanding of registering features and labels for annotation & validation.\n",
     "\n",
-    "If you want to a high-level flow for validating and annotating features and labels, see {doc}`annotate`.\n",
+    "If you're just looking to readily validate and annotate a dataset with features and labels, see this guide: {doc}`annotate`.\n",
     "\n",
     ":::"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "import lamindb as ln\n",
+    "import pandas as pd\n",
+    "\n",
+    "ln.settings.verbosity = \"hint\""
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    ":::{dropdown} What was LaminDB's most basic inspiration?\n",
-    "\n",
-    "The pydata family of data objects is at the heart of most data science, ML & comp bio workflows: `DataFrame`, `AnnData`, `pytorch.DataLoader`, `zarr.Array`, `pyarrow.Table`, `xarray.Collection`, ...\n",
-    "\n",
-    "We couldn’t find a tool to link these objects to context so that they could be analyzed in context:\n",
-    "\n",
-    "- data sources, data transformations, models, users & pipelines that performed transformations (provenance)\n",
-    "- the domain entities in which data is generated and modeled (features & labels)\n",
-    "\n",
-    ":::"
+    "## Re-cap"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's briefly re-cap what we learned in {doc}`/introduction`. We started with simple labeling:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "hide-output"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "# create a label\n",
+    "study0 = ln.ULabel(name=\"Study 0: initial plant gathering\", description=\"My initial study\").save()\n",
+    "# query an artifact from the previous tutorial\n",
+    "artifact = ln.Artifact.filter(key=\"iris_studies/study0_raw_images\").one()\n",
+    "# label the artifact\n",
+    "artifact.labels.add(study0)\n",
+    "# look at artifact metadata\n",
+    "artifact.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In general, it's good practice to associate labels with features so that we can later feed them into learning algorithms with a defined dimension:"
    ]
   },
   {
@@ -63,10 +102,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import lamindb as ln\n",
-    "import pandas as pd\n",
-    "\n",
-    "ln.settings.verbosity = \"hint\""
+    "feature = ln.Feature(name=\"study_name\", dtype=\"cat\").save()\n",
+    "artifact.labels.add(study0, feature)\n",
+    "artifact.describe()"
    ]
   },
   {
@@ -82,9 +120,9 @@
    "source": [
     "Features and labels are the primary ways of registering domain-knowledge related metadata in LaminDB.\n",
     "\n",
-    "Features represent measurement dimensions (e.g. organism) and labels represent measured values (e.g. iris setosa, iris versicolor, iris virginica).\n",
+    "Features represent measurement dimensions (e.g. `\"species\"`) and labels represent measured values (e.g. `\"iris setosa\"`, `\"iris versicolor\"`, `\"iris virginica\"`).\n",
     "\n",
-    "In statistics, you'd say a feature is a categorical or numerical variable. A label is a simple category. Categorical variables draw their values from a set of categories."
+    "In statistics, you'd say a feature is a categorical or numerical variable while a label is a simple category. Categorical variables draw their values from a set of categories."
    ]
   },
   {
@@ -98,7 +136,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We study 3 organism of the Iris plant: `setosa`, `versicolor` & `virginica`. Let's create 3 labels with {class}`~lamindb.ULabel`."
+    "We study 3 species of the Iris plant: `setosa`, `versicolor` & `virginica`. Let's create 3 labels with {class}`~lamindb.ULabel`."
    ]
   },
   {
@@ -111,8 +149,8 @@
    },
    "outputs": [],
    "source": [
-    "organisms = [ln.ULabel(name=name) for name in [\"setosa\", \"versicolor\", \"virginica\"]]\n",
-    "ln.save(organisms)"
+    "speciess = [ln.ULabel(name=name) for name in [\"setosa\", \"versicolor\", \"virginica\"]]\n",
+    "ln.save(speciess)"
    ]
   },
   {
@@ -139,7 +177,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Anticipating that we'll have many different labels when working with more data, we'd like to express that all 3 labels are organism labels:"
+    "Anticipating that we'll have many different labels when working with more data, we'd like to express that all 3 labels are species labels:"
    ]
   },
   {
@@ -152,16 +190,9 @@
    },
    "outputs": [],
    "source": [
-    "is_organism = ln.ULabel(name=\"is_organism\").save()\n",
-    "is_organism.children.set(organisms)\n",
-    "is_organism.view_parents(with_children=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In addition to organism, we want like to track the studies that produced the data:"
+    "is_species = ln.ULabel(name=\"is_species\").save()\n",
+    "is_species.children.set(speciess)\n",
+    "is_species.view_parents(with_children=True)"
    ]
   },
   {
@@ -181,20 +212,6 @@
     "is_study.view_parents(with_children=True)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    ":::{dropdown} Why label a dataset by study?\n",
-    "\n",
-    "We can then\n",
-    "\n",
-    "1. query all artifacts link to this experiment\n",
-    "2. model it as a confounder when we'll analyze similar data from a follow-up experiment, and concatenate data using the label as a feature in a data matrix\n",
-    "\n",
-    ":::"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -210,7 +227,7 @@
     "\n",
     "When we integrate datasets, feature names will label columns that store data.\n",
     "\n",
-    "Let's create and save two {class}`~lamindb.Feature` records to identify measurements of the iris organism label and the study:"
+    "Let's create and save two {class}`~lamindb.Feature` records to identify measurements of the iris species label and the study:"
    ]
   },
   {
@@ -223,8 +240,8 @@
    },
    "outputs": [],
    "source": [
-    "ln.Feature(name=\"iris_organism_name\", type=\"category\").save()\n",
-    "ln.Feature(name=\"study_name\", type=\"category\").save()\n",
+    "ln.Feature(name=\"iris_species_name\", dtype=\"cat\").save()\n",
+    "\n",
     "# create a lookup object so that we can access features with auto-complete\n",
     "features = ln.Feature.lookup()"
    ]
@@ -340,8 +357,8 @@
     "for artifact, study in zip(study_artifacts, study_labels):\n",
     "    artifact.labels.add(study, feature=features.study_name)\n",
     "    df = pd.read_csv(artifact.path / \"meta.csv\", index_col=0)\n",
-    "    organism_labels = ln.ULabel.from_values(df[\"1\"].unique())\n",
-    "    artifact.labels.add(organism_labels, feature=features.iris_organism_name)"
+    "    species_labels = ln.ULabel.from_values(df[\"1\"].unique())\n",
+    "    artifact.labels.add(species_labels, feature=features.iris_species_name)"
    ]
   },
   {
@@ -355,7 +372,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Using the new annotations, you can now query image artifacts by organism & study labels:"
+    "Using the new annotations, you can now query image artifacts by species & study labels:"
    ]
   },
   {
@@ -418,8 +435,8 @@
    "source": [
     "collection = ln.Collection.filter(name__startswith=\"Iris collection\", version=\"1\").one()\n",
     "collection.labels.add(ulabels.study0, feature=features.study_name)\n",
-    "all_organism_labels = ln.ULabel.filter(parents__name=\"is_organism\").all()\n",
-    "collection.labels.add(all_organism_labels, feature=features.iris_organism_name)"
+    "all_species_labels = ln.ULabel.filter(parents__name=\"is_species\").all()\n",
+    "collection.labels.add(all_species_labels, feature=features.iris_species_name)"
    ]
   },
   {
@@ -597,7 +614,7 @@
    },
    "outputs": [],
    "source": [
-    "artifact.features.add(new_features)"
+    "artifact.features.add_feature_set(ln.FeatureSet(new_features), slot=\"columns\")"
    ]
   },
   {
@@ -665,7 +682,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "There is one categorical feature, let's add the organism labels:"
+    "There is one categorical feature, let's add the species labels:"
    ]
   },
   {
@@ -678,8 +695,8 @@
    },
    "outputs": [],
    "source": [
-    "organism_labels = ln.ULabel.filter(parents__name=\"is_organism\").all()\n",
-    "artifact.labels.add(organism_labels, feature=features.iris_organism_name)"
+    "species_labels = ln.ULabel.filter(parents__name=\"is_species\").all()\n",
+    "artifact.labels.add(species_labels, feature=features.iris_species_name)"
    ]
   },
   {

{lamindb-0.71.3 → lamindb-0.72.0}/lamindb/__init__.py

@@ -41,7 +41,7 @@ Modules & settings:
 """
 
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "0.71.3"
+__version__ = "0.72.0"
 
 import os as _os
 
@@ -72,6 +72,7 @@ if _check_instance_setup(from_lamindb=True):
         User,
     )
 
+    from . import core  # isort: split
     from . import (
         _annotate,
         _artifact,
@@ -86,7 +87,6 @@ if _check_instance_setup(from_lamindb=True):
         _storage,
         _transform,
         _ulabel,
-        core,
     )
 
     dev = core  # backward compat

{lamindb-0.71.3 → lamindb-0.72.0}/lamindb/_annotate.py

@@ -9,18 +9,14 @@ from lamin_utils import colors, logger
 from lamindb_setup.core._docs import doc_args
 from lnschema_core import Artifact, Collection, Feature, Registry, Run, ULabel
 
+from .core.exceptions import ValidationError
+
 if TYPE_CHECKING:
     from lamindb_setup.core.types import UPathStr
     from lnschema_core.types import FieldAttr
     from mudata import MuData
 
 
-class ValidationError(ValueError):
-    """Validation error."""
-
-    pass
-
-
 class AnnotateLookup:
     """Lookup categories from the reference instance."""
 
@@ -566,7 +562,7 @@ class MuDataAnnotator:
             save_function="add_new_from_var_index",
             using=self._using,
             validated_only=validated_only,
-            type="number",
+            dtype="number",
             **kwargs,
         )
 
@@ -1034,7 +1030,7 @@ def update_registry(
     validated_only: bool = True,
     df: pd.DataFrame | None = None,
     organism: str | None = None,
-    type: str | None = None,
+    dtype: str | None = None,
     **kwargs,
 ) -> None:
     """Save features or labels records in the default instance from the using instance.
@@ -1048,7 +1044,7 @@ def update_registry(
         validated_only: If True, only save validated labels.
         df: A DataFrame to save labels from.
         organism: The organism name.
-        type: The type of the feature.
+        dtype: The type of the feature.
         kwargs: Additional keyword arguments to pass to the registry model to create new records.
     """
     from lamindb._save import save as ln_save
@@ -1102,7 +1098,7 @@ def update_registry(
                 for value in labels_saved["without reference"]:
                     filter_kwargs[field.field.name] = value
                     if registry == Feature:
-                        filter_kwargs["type"] = "category" if type is None else type
+                        filter_kwargs["dtype"] = "cat" if dtype is None else dtype
                     non_validated_records.append(registry(**filter_kwargs, **kwargs))
             ln_save(non_validated_records)
 

{lamindb-0.71.3 → lamindb-0.72.0}/lamindb/_artifact.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import os
 import shutil
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path, PurePath, PurePosixPath
@@ -212,7 +213,10 @@ def get_stat_or_artifact(
                 file_size = file.stat().st_size
                 return hash_file(file, file_size)[0], file_size
 
-            n_workers = len(psutil.Process().cpu_affinity())
+            try:
+                n_workers = len(psutil.Process().cpu_affinity())
+            except AttributeError:
+                n_workers = psutil.cpu_count()
             if n_workers > 1:
                 with ThreadPoolExecutor(n_workers) as pool:
                     hashes_sizes = pool.map(hash_size, files)
@@ -345,7 +349,7 @@ def get_artifact_kwargs_from_data(
             # save the information that this artifact was previously
             # produced by another run
             if artifact.run is not None:
-                artifact.run.replicated_output_artifacts.add(artifact)
+                artifact.run.output_artifacts_with_later_updates.add(artifact)
             # update the run of the artifact with the latest run
             stat_or_artifact.run = run
             stat_or_artifact.transform = run.transform