Python API name changes

.github/workflows/py-build.yml

@@ -30,12 +30,12 @@ jobs:
 
       - name: Build
         run: python -m build
-        working-directory: api/python/cell_census/
+        working-directory: api/python/cellxgene_census/
 
       - name: Upload build artifact
         uses: actions/upload-artifact@v3
         with:
-          path: api/python/cell_census/dist/*
+          path: api/python/cellxgene_census/dist/*
 
   build_docker_container:
     name: Build Docker image for Census Builder

.github/workflows/py-unittests.yml

@@ -1,4 +1,4 @@
-name: Python cell_census package unit tests
+name: Python cellxgene_census package unit tests
 
 on:
   pull_request:
@@ -25,11 +25,11 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install -U pip setuptools wheel
-          pip install -r ./api/python/cell_census/scripts/requirements-dev.txt
-          pip install -e ./api/python/cell_census/
+          pip install -r ./api/python/cellxgene_census/scripts/requirements-dev.txt
+          pip install -e ./api/python/cellxgene_census/
       - name: Test with pytest (API)
         run: |
-          PYTHONPATH=. coverage run --parallel-mode -m pytest --durations=20 ./api/python/cell_census/tests/
+          PYTHONPATH=. coverage run --parallel-mode -m pytest --durations=20 ./api/python/cellxgene_census/tests/
       - uses: actions/upload-artifact@v3
         with:
           name: coverage

.pre-commit-config.yaml

@@ -9,9 +9,9 @@ repos:
         files: ^api/python/notebooks
         args: ["--config", "./api/python/notebooks/pyproject.toml"]
       - id: black
-        name: black-cell-census
-        files: ^api/python/cell_census
-        args: ["--config", "./api/python/cell_census/pyproject.toml"]
+        name: black-cellxgene-census
+        files: ^api/python/cellxgene_census
+        args: ["--config", "./api/python/cellxgene_census/pyproject.toml"]
       - id: black
         name: black-tools
         files: ^tools
@@ -21,9 +21,9 @@ repos:
     rev: v0.0.249
     hooks:
       - id: ruff
-        name: ruff-cell-census
-        files: ^api/python/cell_census
-        args: ["--config=./api/python/cell_census/pyproject.toml", "--fix"]
+        name: ruff-cellxgene-census
+        files: ^api/python/cellxgene_census
+        args: ["--config=./api/python/cellxgene_census/pyproject.toml", "--fix"]
       - id: ruff
         name: ruff-tools
         files: ^tools
@@ -33,9 +33,9 @@ repos:
     rev: v1.0.1
     hooks:
       - id: mypy
-        name: mypy-cell-census
-        files: ^api/python/cell_census
-        args: ["--config-file=./api/python/cell_census/pyproject.toml"]
+        name: mypy-cellxgene-census
+        files: ^api/python/cellxgene_census
+        args: ["--config-file=./api/python/cellxgene_census/pyproject.toml"]
         additional_dependencies:
           - types-requests
           - pytest

api/python/cell_census/pyproject.toml → api/python/cellxgene_census/pyproject.toml

@@ -3,9 +3,9 @@ requires = ["setuptools>=45", "setuptools_scm[toml]>=6.2"]
 build-backend = "setuptools.build_meta"
 
 [project]
-name = "cell_census"
+name = "cellxgene_census"
 dynamic = ["version"]
-description = "API to facilitate the use of the CZ CELLxGENE Discover Cell Census. For more information about the API and the project visit https://github.com/chanzuckerberg/cell-census/"
+description = "API to facilitate the use of the CZ CELLxGENE Discover Census. For more information about the API and the project visit https://github.com/chanzuckerberg/cellxgene-census/"
 authors = [
     { name = "Chan Zuckerberg Initiative", email = "[email protected]" }
 ]
@@ -41,12 +41,12 @@ dependencies= [
 ]
 
 [project.urls]
-homepage = "https://github.com/chanzuckerberg/cell-census"
-repository = "https://github.com/chanzuckerberg/cell-census"
+homepage = "https://github.com/chanzuckerberg/cellxgene-census"
+repository = "https://github.com/chanzuckerberg/cellxgene-census"
 
 [tool.setuptools.packages.find]
 where = ["src"]
-include = ["cell_census*"]  # package names should match these glob patterns (["*"] by default)
+include = ["cellxgene_census*"]  # package names should match these glob patterns (["*"] by default)
 exclude = ["tests*"]  # exclude packages matching these glob patterns (empty by default)
 
 [tool.setuptools_scm]
@@ -65,7 +65,7 @@ plugins = "numpy.typing.mypy_plugin"
 
 [tool.pytest.ini_options]
 markers = [
-    "live_corpus: runs on the live Cell Census data corpus and small enough to run in CI",
+    "live_corpus: runs on the live CELLxGENE Census data corpus and small enough to run in CI",
     "expensive: too expensive to run regularly or in CI",
 ]
 
@@ -76,4 +76,4 @@ line-length = 120
 target-version = "py39"
 
 [tool.ruff.isort]
-known-first-party =["cell_census"]
+known-first-party =["cellxgene_census"]

api/python/cell_census/release_process.md → api/python/cellxgene_census/release_process.md

@@ -1,8 +1,8 @@
-# cell_census Python package release process
+# cellxgene_census Python package release process
 
-The following approach is used to manage releases of the Python cell_census package:
+The following approach is used to manage releases of the Python cellxgene_census package:
 
-1. The cell_census package is automatically built (sdist and wheels) in a GitHub action, and build artifacts are uploaded to GitHub.
+1. The cellxgene_census package is automatically built (sdist and wheels) in a GitHub action, and build artifacts are uploaded to GitHub.
 2. Release candidate testing is done by installing built assets from Github.
 3. Build versions are managed via [`setuptools_scm`](https://github.com/pypa/setuptools_scm) and the version is automatically determined from git tags.
 4. Releases are created and managed via GitHub Releases, leaving a tag in place from which future branches (eg, emergency fixes) can be created.
@@ -12,8 +12,8 @@ The following approach is used to manage releases of the Python cell_census pack
 
 While not strictly required, this process assumes you have met the following prerequisites:
 
-- You have write access to the chanzuckerberg/cell_census repo
-- You have an account on pypi.org and test.pypi.org, both with access to the cell_census project
+- You have write access to the `chanzuckerberg/cellxgene-census` repo
+- You have an account on pypi.org and test.pypi.org, both with access to the cellxgene_census project
 - You have the Github CLI tool (`gh`) installed. See [documentation](https://cli.github.com/).
 - You have the `pipx` CLI tool installed. See [documentation](https://pypa.github.io/pipx/).
 
@@ -43,14 +43,14 @@ Any pre-built asset on Github can be installed and tested from the Github URL. F
    ```shell
    $ unzip artifact.zip -d ./artifact/
    Archive:  artifact.zip
-     inflating: ./artifact/cell_census-0.0.1.dev0-py3-none-any.whl
-     inflating: ./artifact/cell_census-0.0.1.dev0.tar.gz
+     inflating: ./artifact/cellxgene_census-0.0.1.dev0-py3-none-any.whl
+     inflating: ./artifact/cellxgene_census-0.0.1.dev0.tar.gz
    ```
 
 3. Install and test the downloaded build, e.g.,
    ```shell
-   $ pip uninstall cell_census
-   $ pip install ./artifact/cell_census-*-any.whl
+   $ pip uninstall cellxgene-census
+   $ pip install ./artifact/cellxgene_census-*-any.whl
    ```
 
 To test a release candidate:

api/python/cell_census/src/cell_census/__init__.py → api/python/cellxgene_census/src/cellxgene_census/__init__.py

@@ -1,16 +1,14 @@
 """
-Cell Census convience API
-
-An API to facilitate use of the CZI Science Cell Census. The Cell Census is a versioned container of single-cell data hosted at [CELLxGENE Discover](https://cellxgene.cziscience.com/).
+An API to facilitate use of the CZI Science CELLxGENE Census. The Census is a versioned container of single-cell data hosted at [CELLxGENE Discover](https://cellxgene.cziscience.com/).
 
 The API is built on the `tiledbsoma` SOMA API, and provides a number of helper functions including:
 
-    * Open a named version of the Cell Census, for use with the SOMA API
-    * Get a list of available Cell Census versions, and for each version, a description
-    * Get a slice of the Cell Census as an AnnData, for use with ScanPy
+    * Open a named version of the Census, for use with the SOMA API
+    * Get a list of available Census versions, and for each version, a description
+    * Get a slice of the Census as an AnnData, for use with ScanPy
     * Get the URI for, or directly download, underlying data in H5AD format
 
-For more information on the API, visit the [cell_census repo](https://github.com/chanzuckerberg/cell-census/). For more information on SOMA, see the [tiledbsoma repo](https://github.com/single-cell-data/TileDB-SOMA).
+For more information on the API, visit the [cellxgene_census repo](https://github.com/chanzuckerberg/cellxgene-census/). For more information on SOMA, see the [tiledbsoma repo](https://github.com/single-cell-data/TileDB-SOMA).
 """
 
 try:
@@ -25,7 +23,7 @@
 from ._release_directory import get_census_version_description, get_census_version_directory
 
 try:
-    __version__ = metadata.version("cell_census")
+    __version__ = metadata.version("cellxgene_census")
 except metadata.PackageNotFoundError:
     # package is not installed
     __version__ = "0.0.0-unknown"

api/python/cell_census/tests/test_acceptance.py → api/python/cellxgene_census/tests/test_acceptance.py

@@ -1,5 +1,5 @@
 """
-Acceptance tests for the Census.
+Acceptance tests for the CELLxGENE Census.
 
 NOTE: those marked `expensive` are not run in the CI as they are, well, expensive...
 
@@ -17,13 +17,13 @@
 import tiledb
 import tiledbsoma as soma
 
-import cell_census
-from cell_census._open import DEFAULT_TILEDB_CONFIGURATION
+import cellxgene_census
+from cellxgene_census._open import DEFAULT_TILEDB_CONFIGURATION
 
 
 def make_context(census_version: str, config: Optional[Dict[str, Any]] = None) -> soma.SOMATileDBContext:
     config = config or {}
-    version = cell_census.get_census_version_description(census_version)
+    version = cellxgene_census.get_census_version_description(census_version)
     s3_region = version["soma"].get("s3_region", "us-west-2")
     config.update({"vfs.s3.region": s3_region})
     return soma.options.SOMATileDBContext(tiledb_ctx=tiledb.Ctx(config))
@@ -33,7 +33,7 @@ def make_context(census_version: str, config: Optional[Dict[str, Any]] = None) -
 @pytest.mark.parametrize("organism", ["homo_sapiens", "mus_musculus"])
 def test_load_axes(organism: str) -> None:
     """Verify axes can be loaded into a Pandas DataFrame"""
-    census = cell_census.open_soma(census_version="latest")
+    census = cellxgene_census.open_soma(census_version="latest")
 
     # use subset of columns for speed
     obs_df = (
@@ -76,7 +76,7 @@ def test_incremental_read(organism: str) -> None:
     # open census with a small (default) TileDB buffer size, which reduces
     # memory use, and makes it feasible to run in a GHA.
     context = make_context("latest")
-    with cell_census.open_soma(census_version="latest", context=context) as census:
+    with cellxgene_census.open_soma(census_version="latest", context=context) as census:
         assert table_iter_is_ok(census["census_data"][organism].obs.read(column_names=["soma_joinid", "tissue"]))
         assert table_iter_is_ok(
             census["census_data"][organism].ms["RNA"].var.read(column_names=["soma_joinid", "feature_id"])
@@ -93,7 +93,7 @@ def test_incremental_read(organism: str) -> None:
 def test_incremental_query(organism: str, obs_value_filter: str, stop_after: Optional[int]) -> None:
     """Verify incremental read of query result."""
     # use default TileDB configuration
-    with cell_census.open_soma(census_version="latest") as census:
+    with cellxgene_census.open_soma(census_version="latest") as census:
         with census["census_data"][organism].axis_query(
             measurement_name="RNA", obs_query=soma.AxisQuery(value_filter=obs_value_filter)
         ) as query:
@@ -140,6 +140,6 @@ def test_get_anndata(
     """Verify query and read into AnnData"""
     ctx_config = ctx_config or {}
     context = make_context("latest", ctx_config)
-    with cell_census.open_soma(census_version="latest", context=context) as census:
-        ad = cell_census.get_anndata(census, organism, obs_value_filter=obs_value_filter, obs_coords=obs_coords)
+    with cellxgene_census.open_soma(census_version="latest", context=context) as census:
+        ad = cellxgene_census.get_anndata(census, organism, obs_value_filter=obs_value_filter, obs_coords=obs_coords)
         assert ad is not None

api/python/cell_census/tests/test_directory.py → api/python/cellxgene_census/tests/test_directory.py

@@ -4,8 +4,8 @@
 import requests_mock as rm
 import s3fs
 
-import cell_census
-from cell_census._release_directory import CELL_CENSUS_RELEASE_DIRECTORY_URL
+import cellxgene_census
+from cellxgene_census._release_directory import CELL_CENSUS_RELEASE_DIRECTORY_URL
 
 DIRECTORY_JSON = {
     "latest": "2022-11-01",
@@ -45,7 +45,7 @@ def directory_mock(requests_mock: rm.Mocker) -> Any:
 
 
 def test_get_census_version_directory(directory_mock: Any) -> None:
-    directory = cell_census.get_census_version_directory()
+    directory = cellxgene_census.get_census_version_directory()
 
     assert isinstance(directory, dict)
     assert len(directory) > 0
@@ -60,12 +60,12 @@ def test_get_census_version_directory(directory_mock: Any) -> None:
     assert directory["latest"] == directory["2022-11-01"]
 
     for tag in directory:
-        assert directory[tag] == cell_census.get_census_version_description(tag)
+        assert directory[tag] == cellxgene_census.get_census_version_description(tag)
 
 
 def test_get_census_version_description_errors() -> None:
     with pytest.raises(KeyError):
-        cell_census.get_census_version_description(census_version="no/such/version/exists")
+        cellxgene_census.get_census_version_description(census_version="no/such/version/exists")
 
 
 @pytest.mark.live_corpus
@@ -78,11 +78,11 @@ def test_live_directory_contents() -> None:
 
     fs = s3fs.S3FileSystem(anon=True, cache_regions=True)
 
-    directory = cell_census.get_census_version_directory()
+    directory = cellxgene_census.get_census_version_directory()
     assert "latest" in directory
 
     for version, version_description in directory.items():
-        with cell_census.open_soma(census_version=version) as census:
+        with cellxgene_census.open_soma(census_version=version) as census:
             assert census is not None
 
         assert fs.exists(version_description["soma"]["uri"])

api/python/cell_census/tests/test_get_anndata.py → api/python/cellxgene_census/tests/test_get_anndata.py

@@ -1,18 +1,18 @@
 import pytest
 import tiledbsoma as soma
 
-import cell_census
+import cellxgene_census
 
 
 @pytest.fixture
 def census() -> soma.Collection:
-    return cell_census.open_soma(census_version="latest")
+    return cellxgene_census.open_soma(census_version="latest")
 
 
 @pytest.mark.live_corpus
 def test_get_anndata_value_filter(census: soma.Collection) -> None:
     with census:
-        ad = cell_census.get_anndata(
+        ad = cellxgene_census.get_anndata(
             census,
             organism="Mus musculus",
             obs_value_filter="tissue_general == 'vasculature'",
@@ -33,7 +33,9 @@ def test_get_anndata_value_filter(census: soma.Collection) -> None:
 @pytest.mark.live_corpus
 def test_get_anndata_coords(census: soma.Collection) -> None:
     with census:
-        ad = cell_census.get_anndata(census, organism="Mus musculus", obs_coords=slice(1000), var_coords=slice(2000))
+        ad = cellxgene_census.get_anndata(
+            census, organism="Mus musculus", obs_coords=slice(1000), var_coords=slice(2000)
+        )
 
     assert ad is not None
     assert ad.n_vars == 2001
@@ -47,13 +49,13 @@ def test_get_anndata_allows_missing_obs_or_var_filter(census: soma.Collection) -
     with census:
         mouse = census["census_data"]["mus_musculus"]
 
-        adata = cell_census.get_anndata(census, organism="Mus musculus", obs_value_filter="tissue == 'aorta'")
+        adata = cellxgene_census.get_anndata(census, organism="Mus musculus", obs_value_filter="tissue == 'aorta'")
         assert adata.n_obs == len(
             mouse.obs.read(value_filter="tissue == 'aorta'", column_names=["soma_joinid"]).concat()
         )
         assert adata.n_vars == len(mouse.ms["RNA"].var.read(column_names=["soma_joinid"]).concat())
 
-        adata = cell_census.get_anndata(
+        adata = cellxgene_census.get_anndata(
             census,
             organism="Mus musculus",
             obs_coords=slice(10000),

api/python/cell_census/tests/test_get_helpers.py → api/python/cellxgene_census/tests/test_get_helpers.py

@@ -1,13 +1,13 @@
 import pytest
 import scipy.sparse
 
-import cell_census
-from cell_census._experiment import _get_experiment
+import cellxgene_census
+from cellxgene_census._experiment import _get_experiment
 
 
 @pytest.mark.live_corpus
 def test_get_experiment() -> None:
-    with cell_census.open_soma(census_version="latest") as census:
+    with cellxgene_census.open_soma(census_version="latest") as census:
         mouse_uri = census["census_data"]["mus_musculus"].uri
         human_uri = census["census_data"]["homo_sapiens"].uri
 
@@ -26,11 +26,11 @@ def test_get_experiment() -> None:
 @pytest.mark.live_corpus
 @pytest.mark.parametrize("organism", ["homo_sapiens", "mus_musculus"])
 def test_get_presence_matrix(organism: str) -> None:
-    census = cell_census.open_soma(census_version="latest")
+    census = cellxgene_census.open_soma(census_version="latest")
 
     census_datasets = census["census_info"]["datasets"].read().concat().to_pandas()
 
-    pm = cell_census.get_presence_matrix(census, organism)
+    pm = cellxgene_census.get_presence_matrix(census, organism)
     assert isinstance(pm, scipy.sparse.csr_matrix)
     assert pm.shape[0] == len(census_datasets)
     assert pm.shape[1] == len(