lamindb 0.64.1__tar.gz → 0.64.2__tar.gz

{lamindb-0.64.1 → lamindb-0.64.2}/.github/workflows/latest-changes.jinja2

@@ -1,2 +1 @@
-- {{pr.title}} [PR{{pr.number}}]({{pr.html_url}}) [@{{pr.user.login}}]({{pr.user.html_url}})
-
+- {{pr.title}} [PR{{pr.number}}]({{pr.html_url}}) [@{{pr.user.login}}]({{pr.user.html_url}})

lamindb-0.64.2/.pre-commit-config.yaml

@@ -0,0 +1,56 @@
+fail_fast: false
+default_language_version:
+  python: python3
+default_stages:
+  - commit
+  - push
+minimum_pre_commit_version: 2.16.0
+repos:
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v4.0.0-alpha.4
+    hooks:
+      - id: prettier
+        exclude: |
+          (?x)(
+            docs/changelog.md
+          )
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.6.1
+    hooks:
+      - id: nbstripout
+        exclude: |
+          (?x)(
+              docs/examples/|
+              docs/notes/
+          )
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.7
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: detect-private-key
+      - id: check-ast
+      - id: end-of-file-fixer
+        exclude: |
+          (?x)(
+              .github/workflows/latest-changes.jinja2
+            )
+      - id: mixed-line-ending
+        args: [--fix=lf]
+      - id: trailing-whitespace
+      - id: check-case-conflict
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.7.1
+    hooks:
+      - id: mypy
+        args: [--no-strict-optional, --ignore-missing-imports]
+        additional_dependencies:
+          ["types-pkg-resources", "types-requests", "types-attrs"]
+        exclude: |
+          (?x)(
+              test_notebooks.py
+          )

{lamindb-0.64.1 → lamindb-0.64.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lamindb
-Version: 0.64.1
+Version: 0.64.2
 Summary: A data framework for biology.
 Author-email: Lamin Labs <open-source@lamin.ai>
 Requires-Python: >=3.8

{lamindb-0.64.1 → lamindb-0.64.2}/docs/bio-registries.ipynb

@@ -500,7 +500,7 @@
    },
    "outputs": [],
    "source": [
-    "lb.CellType.filter().df()"
+    "lb.CellType.df()"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/changelog.md

@@ -6,12 +6,19 @@
 
 ## 0.64
 
-### 0.64.1 {small}`2023-11-24`
+### 0.64.2 {small}`2023-12-18`
+
+- 🚚 Deprecate `view_flow` in favor of `view_lineage` [PR1367](https://github.com/laminlabs/lamindb/pull/1367) [@falexwolf](https://github.com/falexwolf)
+- 🐛 Account for length zero label lists [PR1362](https://github.com/laminlabs/lamindb/pull/1362) [@falexwolf](https://github.com/falexwolf)
+- 🐛 Fix mypy [PR1359](https://github.com/laminlabs/lamindb/pull/1359) [@Koncopd](https://github.com/Koncopd)
+- 👷 Use ruff and clean up pre-commit [PR1358](https://github.com/laminlabs/lamindb/pull/1358) [@Zethson](https://github.com/Zethson)
+
+### 0.64.1 {small}`2023-12-13`
 
 - 🚸 Silence the httpx logger [PR1356](https://github.com/laminlabs/lamindb/pull/1356) [@falexwolf](https://github.com/falexwolf)
 - 🐛 Fix hash inference for cloud non-s3 objects and use stored gcs credentials [PR1355](https://github.com/laminlabs/lamindb/pull/1355) [@Koncopd](https://github.com/Koncopd)
 
-### 0.64.0 {small}`2023-11-24`
+### 0.64.0 {small}`2023-12-13`
 
 🏗️ Replace `File` with `Artifact` to model directories and directory-like array stores [PR1345](https://github.com/laminlabs/lamindb/pull/1345) [@falexwolf](https://github.com/falexwolf).
 
@@ -81,7 +88,7 @@ For artifacts that are simple files, rename `File` to `Artifact` along with the
 
 ### 0.60.3 {small}`2023-11-13`
 
-- 🚑  Fix visibility choices, updated intro [PR1294](https://github.com/laminlabs/lamindb/pull/1294) [@sunnyosun](https://github.com/sunnyosun)
+- 🚑 Fix visibility choices, updated intro [PR1294](https://github.com/laminlabs/lamindb/pull/1294) [@sunnyosun](https://github.com/sunnyosun)
 
 ### 0.60.1 {small}`2023-11-10`
 
@@ -99,7 +106,7 @@ For artifacts that are simple files, rename `File` to `Artifact` along with the
 
 ### 0.59.3 {small}`2023-11-04`
 
-- 💄 Show transform uid in view_flow [PR1280](https://github.com/laminlabs/lamindb/pull/1280) [@sunnyosun](https://github.com/sunnyosun)
+- 💄 Show transform uid in view_lineage [PR1280](https://github.com/laminlabs/lamindb/pull/1280) [@sunnyosun](https://github.com/sunnyosun)
 - 🚸 Improve search [PR1279](https://github.com/laminlabs/lamindb/pull/1279) [@sunnyosun](https://github.com/sunnyosun)
 
 ### 0.59.2 {small}`2023-11-04`
@@ -202,7 +209,7 @@ A dialogue guides you through the migration process.
 
 - ✨ Add labels transfer through `labels.add_from` [PR1211](https://github.com/laminlabs/lamindb/pull/1211) [@falexwolf](https://github.com/falexwolf)
 - ♻️ Perform outer join during load [PR1212](https://github.com/laminlabs/lamindb/pull/1212) [@falexwolf](https://github.com/falexwolf)
-- 🎨 Show both file and dataset in view_flow [PR1209](https://github.com/laminlabs/lamindb/pull/1209) [@sunnyosun](https://github.com/sunnyosun)
+- 🎨 Show both file and dataset in view_lineage [PR1209](https://github.com/laminlabs/lamindb/pull/1209) [@sunnyosun](https://github.com/sunnyosun)
 
 ### 0.54.3 {small}`2023-09-27`
 
@@ -211,7 +218,7 @@ A dialogue guides you through the migration process.
 
 ### 0.54.2 {small}`2023-09-26`
 
-- 🎨 Better implementation of `dataset.view_flow` [PR1194](https://github.com/laminlabs/lamindb/pull/1194) [@sunnyosun](https://github.com/sunnyosun)
+- 🎨 Better implementation of `dataset.view_lineage` [PR1194](https://github.com/laminlabs/lamindb/pull/1194) [@sunnyosun](https://github.com/sunnyosun)
 
 ### 0.54.1 {small}`2023-09-21`
 
@@ -315,7 +322,7 @@ A dialogue guides you through the migration process.
 - ♻️ Refactor storage [PR1067](https://github.com/laminlabs/lamindb/pull/1067) [@falexwolf](https://github.com/falexwolf)
 - 🐛 Fix tree view for anonymous access [PR1065](https://github.com/laminlabs/lamindb/pull/1065) [@falexwolf](https://github.com/falexwolf)
 - 🍱 Add the Iris images dev dataset [PR1062](https://github.com/laminlabs/lamindb/pull/1062) [@falexwolf](https://github.com/falexwolf)
-- 🚚 `Dataset.from_files` replaced with default constructor  [PR1060](https://github.com/laminlabs/lamindb/pull/1060) [@falexwolf](https://github.com/falexwolf)
+- 🚚 `Dataset.from_files` replaced with default constructor [PR1060](https://github.com/laminlabs/lamindb/pull/1060) [@falexwolf](https://github.com/falexwolf)
 - 🍱 Added `populate_registries` to some datasets [PR1061](https://github.com/laminlabs/lamindb/pull/1061) [@sunnyosun](https://github.com/sunnyosun)
 - ✨ Add `get_feature_set` to `.features` accessor [PR1057](https://github.com/laminlabs/lamindb/pull/1057) [@sunnyosun](https://github.com/sunnyosun)
 - 🚸 Allow `reference` & `reference_type` params in `ln.track()` [PR1053](https://github.com/laminlabs/lamindb/pull/1053) [@falexwolf](https://github.com/falexwolf)

{lamindb-0.64.1 → lamindb-0.64.2}/docs/faq/acid.ipynb

@@ -77,7 +77,7 @@
    "id": "0c582719-42de-4e9d-bdcb-51f8aabb3ca5",
    "metadata": {},
    "source": [
-    "Let's try to save a artifact to a storage location without permission."
+    "Let's try to save an artifact to a storage location without permission."
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/faq/delete.ipynb

@@ -56,14 +56,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.Artifact.filter().df()"
+    "ln.Artifact.df()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Trash a artifact"
+    "## Trash an artifact"
    ]
   },
   {
@@ -88,7 +88,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.Artifact.filter().df()"
+    "ln.Artifact.df()"
    ]
   },
   {
@@ -111,7 +111,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can restore a artifact from trash:"
+    "You can restore an artifact from trash:"
    ]
   },
   {
@@ -129,7 +129,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.Artifact.filter().df()"
+    "ln.Artifact.df()"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/faq/key.ipynb

@@ -28,7 +28,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We're simulating a artifact system with several nested folders and artifacts.\n",
+    "We're simulating an artifact system with several nested folders and artifacts.\n",
     "Such structures are resembled in, for example, the {doc}`docs:rxrx` guide."
    ]
   },
@@ -808,7 +808,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ln.Artifact.filter().df()"
+    "ln.Artifact.df()"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/faq/track-run-inputs.ipynb

@@ -159,7 +159,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let us manually track a artifact by passing `is_run_input` to either `.stage()`, `.load()` or `.backed()`:"
+    "Let us manually track an artifact by passing `is_run_input` to either `.stage()`, `.load()` or `.backed()`:"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/faq/visibility.ipynb

@@ -68,7 +68,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "When you delete a artifact, its visibility is set to -1 (\"trash\"):"
+    "When you delete an artifact, its visibility is set to -1 (\"trash\"):"
    ]
   },
   {
@@ -125,7 +125,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You can restore a artifact from trash:"
+    "You can restore an artifact from trash:"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/introduction.ipynb

@@ -143,7 +143,7 @@
     "artifact = ln.Artifact.filter(description__contains=\"RNA-seq\").first()\n",
     "\n",
     "# view data flow\n",
-    "artifact.view_flow()\n",
+    "artifact.view_lineage()\n",
     "\n",
     "# describe metadata\n",
     "artifact.describe()\n",
@@ -304,7 +304,7 @@
     "ln.save(genes)\n",
     "\n",
     "# query the entire Gene registry content as a DataFrame\n",
-    "lb.Gene.filter().df()\n",
+    "lb.Gene.df()\n",
     "\n",
     "# create artifact & validate features using the symbol field of Gene\n",
     "artifact = ln.Artifact.from_df(\n",
@@ -412,7 +412,7 @@
     "dataset = ln.Dataset([artifact, artifact2], name=\"my RNA-seq dataset\")\n",
     "dataset.save()\n",
     "dataset.describe()\n",
-    "dataset.view_flow()"
+    "dataset.view_lineage()"
    ]
   },
   {
@@ -466,7 +466,7 @@
     "Or, the generating flow of an artifact:\n",
     "\n",
     "```python\n",
-    "artifact.view_flow()\n",
+    "artifact.view_lineage()\n",
     "```\n",
     "\n",
     "<img src=\"https://lamin-site-assets.s3.amazonaws.com/.lamindb/KQmzmmLOeBN0C8Ykitjn.svg\" width=\"800\">\n",
@@ -548,7 +548,7 @@
     "\n",
     "### Why?\n",
     "\n",
-    "We wrote a [blog post](https://lamin.ai/blog/2022/problems) about the key problems Lamin tries to solve when starting to work on it.\n",
+    "See this [blog post](https://lamin.ai/blog/2022/problems).\n",
     "\n",
     "### Schema & API\n",
     "\n",
@@ -605,19 +605,14 @@
     "\n",
     "<img src=\"https://lamin-site-assets.s3.amazonaws.com/.lamindb/BunYmHkyFLITlM5MYQci.svg\" width=\"350px\" style=\"background: transparent\" align=\"right\">\n",
     "\n",
-    "1. Data is generated by instruments that process physical samples: it comes in batches stored as immutable artifacts.\n",
-    "2. artifacts are transformed into more useful data representations, e.g.:\n",
-    "   - Summary statistics, e.g., count matrices for fastq artifacts\n",
-    "   - Arrays of non-array-like input data (e.g., images)\n",
-    "   - Higher-level embeddings for lower-level array, text or graph representations\n",
-    "   - Concatenated arrays for large-scale atlas-like datasets\n",
+    "1. Data is generated in batches by instruments that process physical samples.\n",
+    "2. Batches are transformed into more useful representations\n",
     "3. Semantics of high-level embeddings (\"inflammatory\", \"lipophile\") are anchored in experimental metadata and knowledge (ontologies)\n",
     "4. Experimental metadata is another ontology type\n",
     "5. Experiments measure features ({class}`~lamindb.Feature`, {class}`~lnschema_bionty.CellMarker`, ...)\n",
     "6. Samples are annotated by labels ({class}`~lamindb.ULabel`, {class}`~lnschema_bionty.CellLine`, ...)\n",
     "7. Learning and data warehousing both iterate transformations (see **graphic**, {class}`~lamindb.Transform`)\n",
     "8. Basic biological entities should have the same meaning to anyone and across any data platform\n",
-    "9. Schema migrations should be easy\n",
     "\n",
     "### Influences\n",
     "\n",

{lamindb-0.64.1 → lamindb-0.64.2}/docs/test_notebooks.py

@@ -5,7 +5,7 @@ import nbproject_test as test
 
 sys.path[:0] = [str(Path(__file__).parent.parent)]
 
-from noxfile import GROUPS  # noqa
+from noxfile import GROUPS
 
 DOCS = Path(__file__).parents[1] / "docs/"
 

{lamindb-0.64.1 → lamindb-0.64.2}/docs/transfer.ipynb

@@ -73,8 +73,8 @@
    "outputs": [],
    "source": [
     "# get a QuerySet containing all artifacts in cellxgene\n",
-    "# artifacts = ln.Artifact.using(\"laminlabs/cellxgene\")\n",
-    "# artifacts.df().head()"
+    "artifacts = ln.Artifact.using(\"laminlabs/cellxgene\")\n",
+    "artifacts.df().head()"
    ]
   },
   {
@@ -90,8 +90,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact = artifacts.filter(description__icontains=\"tabula sapiens\").first()\n",
-    "# artifact"
+    "artifact = artifacts.filter(description__icontains=\"tabula sapiens\").first()\n",
+    "artifact"
    ]
   },
   {
@@ -107,7 +107,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.describe()"
+    "artifact.describe()"
    ]
   },
   {
@@ -123,7 +123,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.id"
+    "artifact.id"
    ]
   },
   {
@@ -139,7 +139,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.transform"
+    "artifact.transform"
    ]
   },
   {
@@ -155,7 +155,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.created_by"
+    "artifact.created_by"
    ]
   },
   {
@@ -164,7 +164,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.storage"
+    "artifact.storage"
    ]
   },
   {
@@ -180,7 +180,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.save()"
+    "artifact.save()"
    ]
   },
   {
@@ -196,7 +196,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.describe()"
+    "artifact.describe()"
    ]
   },
   {
@@ -212,7 +212,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.id"
+    "artifact.id"
    ]
   },
   {
@@ -221,7 +221,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.created_by"
+    "artifact.created_by"
    ]
   },
   {
@@ -230,7 +230,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# artifact.transform"
+    "artifact.transform"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/tutorial.ipynb

@@ -279,7 +279,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    ":::{dropdown} Which fields are populated when creating a artifact record?\n",
+    ":::{dropdown} Which fields are populated when creating an artifact record?\n",
     "\n",
     "Basic fields:\n",
     "\n",
@@ -365,7 +365,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Because we called {func}`~lamindb.track`, we know that the artifact was saved in the current notebook ({meth}`~lamindb.dev.Data.view_flow`):"
+    "Because we called {func}`~lamindb.track`, we know that the artifact was saved in the current notebook ({meth}`~lamindb.dev.Data.view_lineage`):"
    ]
   },
   {
@@ -374,7 +374,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact.view_flow()"
+    "artifact.view_lineage()"
    ]
   },
   {
@@ -473,7 +473,7 @@
    "source": [
     "If the data is large, you'll likely want to query it via {meth}`~lamindb.Artifact.backed`. For more on this, see: {doc}`data`.\n",
     "\n",
-    ":::{dropdown} How do I update a artifact?\n",
+    ":::{dropdown} How do I update an artifact?\n",
     "\n",
     "If you'd like to replace the underlying stored object, use {meth}`~lamindb.Artifact.replace`.\n",
     "\n",
@@ -683,7 +683,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "artifact.view_flow()"
+    "artifact.view_lineage()"
    ]
   },
   {
@@ -697,7 +697,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "If you'd like to version a artifact or transform, either provide the `version` parameter when creating it or create new versions through `is_new_version_of`.\n",
+    "If you'd like to version an artifact or transform, either provide the `version` parameter when creating it or create new versions through `is_new_version_of`.\n",
     "\n",
     "For instance:\n",
     "```\n",

{lamindb-0.64.1 → lamindb-0.64.2}/docs/tutorial2.ipynb

@@ -275,7 +275,7 @@
    "source": [
     "Labeling a set of artifacts is useful if we want to make the set queryable among a large number of artifacts.\n",
     "\n",
-    "You can label a artifact by calling `artifact.labels.add()` and pass a single or multiple label records.\n",
+    "You can label an artifact by calling `artifact.labels.add()` and pass a single or multiple label records.\n",
     "\n",
     "Let's do this based on the labels in `meta.csv`:"
    ]
@@ -649,7 +649,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dataset.artifact.view_flow()"
+    "dataset.artifact.view_lineage()"
    ]
   },
   {
@@ -710,7 +710,7 @@
    "source": [
     "Assume we already ran all preprocessing including the ML model.\n",
     "\n",
-    "We get a DataFrame and store it as a artifact:"
+    "We get a DataFrame and store it as an artifact:"
    ]
   },
   {
@@ -818,7 +818,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "dataset.view_flow()"
+    "dataset.view_lineage()"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/docs/validate.ipynb

@@ -184,7 +184,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Creating a artifact or dataset with the same content automatically returns the existing record:"
+    "Creating an artifact or dataset with the same content automatically returns the existing record:"
    ]
   },
   {

{lamindb-0.64.1 → lamindb-0.64.2}/lamindb/__init__.py

@@ -54,7 +54,7 @@ Modules & settings:
 
 """
 
-__version__ = "0.64.1"  # denote a release candidate for 0.1.0 with 0.1rc1
+__version__ = "0.64.2"  # denote a release candidate for 0.1.0 with 0.1rc1
 
 import os as _os
 
@@ -72,7 +72,7 @@ _py_version_warning("3.8", "3.11")
 _TESTING = _lamindb_setup._TESTING
 _INSTANCE_SETUP = _check_instance_setup(from_lamindb=True)
 # allow the user to call setup
-from . import setup  # noqa
+from . import setup
 
 
 class InstanceNotSetupError(Exception):
@@ -90,7 +90,7 @@ def __getattr__(name):
 if _INSTANCE_SETUP:
     del InstanceNotSetupError
     del __getattr__  # delete so that imports work out
-    from lnschema_core import (  # noqa
+    from lnschema_core import (
         Artifact,
         Dataset,
         Feature,
@@ -104,25 +104,25 @@ if _INSTANCE_SETUP:
 
     File = Artifact  # backward compat
     from . import _artifact  # noqa
-    from . import _dataset  # noqa
-    from . import _feature  # noqa
-    from . import _feature_set  # noqa
-    from . import _parents  # noqa
-    from . import _registry  # noqa
-    from . import _run  # noqa
-    from . import _storage  # noqa
-    from . import _transform  # noqa
-    from . import _ulabel  # noqa
-    from . import _validate  # noqa
-    from . import dev  # noqa
-    from ._delete import delete  # noqa
-    from ._save import save  # noqa
-    from ._view import view  # noqa
-    from .dev._run_context import run_context  # noqa
+    from . import _dataset
+    from . import _feature
+    from . import _feature_set
+    from . import _parents
+    from . import _registry
+    from . import _run
+    from . import _storage
+    from . import _transform
+    from . import _ulabel
+    from . import _validate
+    from . import dev
+    from ._delete import delete
+    from ._save import save
+    from ._view import view
+    from .dev._run_context import run_context
     from .dev._settings import settings
 
     # schema modules
     _reload_schema_modules(_lamindb_setup.settings.instance)
 
-    track = run_context._track  # noqa
+    track = run_context._track
     settings.__doc__ = """Global :class:`~lamindb.dev.Settings`."""