Merge branch 'main' into bug/timeseries-lens-settings-icon

.github/actions/setup-poetry/action.yml

@@ -38,7 +38,7 @@ runs:
               python-version: ${{ inputs.python-version }}
         - name: Install dependencies
           if: inputs.install-dependencies != 'false' && steps.setup-python-with-cache.outputs.cache-hit != 'true'
-          run: poetry install --sync --without playbook --no-interaction
+          run: poetry install --sync --all-extras --without playbook --no-interaction
           shell: bash
         - name: Get Spotlight version
           id: get-package-version

.github/workflows/ci.yml

@@ -395,7 +395,7 @@ jobs:
               run: python -m pip install --upgrade pip setuptools wheel
             - name: Install Spotlight
               id: setup
-              run: python -m pip install --find-links build/dist/ renumics-spotlight==${{ needs.prepare-python.outputs.version }}
+              run: python -m pip install --find-links build/dist/ renumics-spotlight[all]==${{ needs.prepare-python.outputs.version }}
             - name: Test Spotlight start (Windows)
               if: runner.os == 'Windows' && (success() || steps.setup.outcome == 'success')
               run: ./scripts/Test-SpotlightStart.ps1

CONTRIBUTING.md

@@ -0,0 +1,20 @@
+# Contribute to Spotlight
+
+Everyone is welcome to contribute, and we value everybody's contribution. Code
+contributions are not the only way to help the community.
+Reported bugs, suggested features, contributing design ideas,
+or offering feedback are alse extremely valuable to us.
+
+Technical details on how to contribute can be found in our [documentation](https://renumics.com/docs/development).
+
+## Ways to contribute
+
+There are several ways you can contribute to Spotlight:
+
+* Fix outstanding issues.
+* Implement new features.
+* Submit issues related to bugs or desired new features.
+* Share your use case
+
+If you don't know where to start, you might want to have a look at [hacktoberfest issues](https://github.com/Renumics/spotlight/issues?q=is%3Aissue+is%3Aopen+label%3Ahacktoberfest)
+and our guide on how to create a [new Lens](https://renumics.com/docs/development/lenses).

Makefile

@@ -12,12 +12,12 @@ help: ## Print this help message
 
 .PHONY: init
 init: ## Locally install all dev dependencies
-	poetry install --without playbook
+	poetry install --all-extras --without playbook
 	pnpm install
 
 .PHONY: init-playbook
 init-playbook: ## Locally install all playbook dev dependencies
-	poetry install
+	poetry install --all-extras
 
 .PHONY: clean
 clean: ## clean project

README.md

@@ -153,3 +153,11 @@ We have added crash report and perfomance collection. We do NOT collect user dat
 - 🤗 [Huggingface](https://huggingface.co/renumics) example spaces and datasets 
 - 🏀 [Playbook](https://renumics.com/docs/playbook/) for data-centric AI workflows
 - 🍰 [Sliceguard](https://github.com/Renumics/sliceguard) library for automatic slice detection
+
+## Contribute
+
+We are currently participating in the running [Hacktoberfest 2023](https://hacktoberfest.com/).
+
+If you would like to contribute to Spotlight, the easiest way is to have a look at our [Contribution Docs](https://renumics.com/docs/development) and the [CONTRIBUTING.md](./CONTRIBUTING.md).
+
+We are also equally happy about non-code contributions -- whether it's reporting bugs, suggesting features, contributing design ideas, or offering feedback, every non-code contribution is highly valued and helps make our project better for everyone.

pyproject.toml

@@ -75,7 +75,6 @@ imagecodecs = [
 av = "*"
 validators = "*"
 ipywidgets = "*"
-pycatch22 = "*"
 jinja2 = "*"
 toml = "*"
 cleanlab = "*"
@@ -89,6 +88,12 @@ pillow = "^10.0.0"
 httpx = "^0.23.0"
 datasets = {extras = ["audio"], version = "^2.12.0"}
 
+pycatch22 = {version = "!=0.4.4", optional = true}
+
+[tool.poetry.extras]
+descriptors = ["pycatch22"]
+all = ["pycatch22"]
+
 [tool.poetry.group.dev.dependencies]
 mypy = "*"
 types-setuptools = "^57.4.14"

renumics/spotlight/dataset/descriptors/__init__.py

@@ -1,9 +1,8 @@
 """make descriptor methods more available
 """
-from typing import List, Optional, Tuple
+from typing import Optional, Tuple
 
 import numpy as np
-import pycatch22
 from sklearn.decomposition import PCA
 from sklearn.preprocessing import StandardScaler
 from renumics.spotlight import dtypes
@@ -53,14 +52,6 @@ def pca(
     return embeddings, mask
 
 
-def get_catch22_feature_names(catch24: bool = False) -> List[str]:
-    """
-    Get Catch22 feature names in the same order as returned by :func:`catch22`.
-    """
-    # Run Catch22 with dummy data to get feature names.
-    return pycatch22.catch22_all([0], catch24)["names"]
-
-
 def catch22(
     dataset: Dataset,
     column: str,
@@ -74,6 +65,12 @@ def catch22(
     Generate Catch22 embeddings for the given column of a dataset and
     optionally write them back into dataset.
     """
+    try:
+        import pycatch22
+    except ModuleNotFoundError as e:
+        raise RuntimeError(
+            "Install Spotlight with 'descriptors' extras in order to use `catch22`."
+        ) from e
 
     if suffix is None:
         suffix = "catch24" if catch24 else "catch22"
@@ -86,7 +83,8 @@ def catch22(
 
     column_names = []
     if as_float_columns:
-        for name in get_catch22_feature_names(catch24):
+        feature_names = pycatch22.catch22_all([0], catch24)["names"]
+        for name in feature_names:
             column_names.append("-".join((column, suffix, name)))
     else:
         column_names.append(f"{column}-{suffix}")

tests/integration/dataset/test_descriptors.py

@@ -4,7 +4,7 @@
 
 from renumics.spotlight import Dataset
 from renumics.spotlight.dataset.descriptors import pca
-from renumics.spotlight.dataset.descriptors import catch22, get_catch22_feature_names
+from renumics.spotlight.dataset.descriptors import catch22
 
 
 class TestPCA:
@@ -293,9 +293,6 @@ def test_sequence_float_columns(self, descriptors_dataset: Dataset) -> None:
             as_float_columns=True,
             inplace=True,
         )
-        for prename in get_catch22_feature_names():
-            name = "sequence_1d_extended-catch22-" + prename
-            assert name in descriptors_dataset.keys()
 
     def test_sequence_nan(self, descriptors_dataset: Dataset) -> None:
         """