Merge pull request #47 from pyt-team/frantzen/cleanup

Project Cleanup
pyt-team · Jul 10, 2024 · 8d04c47 · 8d04c47
2 parents c05bf47 + b3549e2
commit 8d04c47
Show file tree

Hide file tree

Showing 15 changed files with 129 additions and 63 deletions.
diff --git a/.github/dependabot.yml b/.github/dependabot.yml
@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      actions:
+        patterns:
+          - "*"
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -5,6 +5,11 @@ on:
     branches: [main, github-actions-test]
   pull_request:
     branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
+
 permissions:
   contents: write
 
@@ -43,4 +48,4 @@ jobs:
           token: ${{ secrets.DOCUMENTATION_KEY }}
           repository-name: pyt-team/pyt-team.github.io
           target-folder: topoembedx
-          clean: true
+          clean: true
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -2,13 +2,17 @@ name: Linting
 
 on:
   push:
-    branches: [ main,github-actions-test ]
+    branches: [main, github-actions-test]
   pull_request:
-    branches: [ main ]
+    branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
 
 jobs:
   ruff:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: chartboost/ruff-action@v1
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -2,24 +2,26 @@ name: "Test"
 
 on:
   push:
-    branches: [main,github-actions-test]
+    branches: [main, github-actions-test]
     paths-ignore:
-    - 'docs/**'
-    - 'README.md'
-    - 'LICENSE.txt'
-    - '.gitignore'
+      - "docs/**"
+      - "README.md"
+      - "LICENSE.txt"
+      - ".gitignore"
 
   pull_request:
     branches: [main]
     paths-ignore:
-    - 'docs/**'
-    - 'README.md'
-    - 'LICENSE.txt'
-    - '.gitignore'
+      - "docs/**"
+      - "README.md"
+      - "LICENSE.txt"
+      - ".gitignore"
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
 
 jobs:
-
   pytest:
     runs-on: ${{ matrix.os }}
 
@@ -52,4 +54,4 @@ jobs:
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           file: coverage.xml
-          fail_ci_if_error: false
+          fail_ci_if_error: false
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,9 +1,6 @@
-default_language_version:
-  python: python3.10
-
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.6.0
     hooks:
       - id: fix-byte-order-marker
       - id: check-case-conflict
@@ -16,18 +13,35 @@ repos:
         args:
           - --maxkb=2048
       - id: trailing-whitespace
-      - id: requirements-txt-fixer
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.14
+    rev: v0.4.10
     hooks:
       - id: ruff
-        types_or: [ python, pyi, jupyter ]
-        args: [ --fix ]
+        types_or: [python, pyi, jupyter]
+        args: ["--fix", "--show-fixes"]
       - id: ruff-format
-        types_or: [ python, pyi, jupyter ]
+        types_or: [python, pyi, jupyter]
+
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: "1.16.0"
+    hooks:
+      - id: blacken-docs
+        additional_dependencies: [black==24.*]
 
   - repo: https://github.com/numpy/numpydoc
-    rev: v1.6.0
+    rev: v1.7.0
     hooks:
       - id: numpydoc-validation
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v3.1.0"
+    hooks:
+      - id: prettier
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: "v1.10.0"
+    hooks:
+      - id: rst-backticks
+      - id: rst-directive-colons
+      - id: rst-inline-touching-normal
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools", "wheel"]
+requires = ["setuptools"]
 build-backend = "setuptools.build_meta"
 
 [project]
@@ -64,7 +64,6 @@ homepage="https://github.com/pyt-team/TopoEmbedX"
 repository="https://github.com/pyt-team/TopoEmbedX"
 
 [tool.ruff]
-target-version = "py310"
 extend-include = ["*.ipynb"]
 
 [tool.ruff.format]
@@ -77,16 +76,23 @@ select = [
     "W", # warnings
     "I", # import order
     "UP", # pyupgrade rules
+    "B", # bugbear rules
+    "PIE", # pie rules
+    "Q", # quote rules
+    "RET", # return rules
     "SIM", # code simplifications
+    "NPY", # numpy rules
+    "PERF", # performance rules
+    "RUF", # miscellaneous rules
 ]
 ignore = ["E501"] # line too long
 
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401", "F403"]
+
 [tool.ruff.lint.pydocstyle]
 convention = "numpy"
 
-[tool.ruff.per-file-ignores]
-"__init__.py" = ["F401", "F403"]
-
 [tool.setuptools.dynamic]
 version = {attr = "topoembedx.__version__"}
 
@@ -104,4 +110,16 @@ disable_error_code = ["import-untyped"]
 plugins = "numpy.typing.mypy_plugin"
 
 [tool.pytest.ini_options]
-addopts = "--capture=no"
+minversion = "7.0"
+addopts = ["-ra", "--showlocals", "--strict-markers", "--strict-config"]
+xfail_strict = true
+filterwarnings = [
+    "error",
+    "ignore::FutureWarning",
+    "ignore::scipy.sparse._base.SparseEfficiencyWarning",
+]
+log_cli_level = "info"
+testpaths = ["test"]
+
+[tool.coverage.report]
+exclude_lines = ["pragma: not covered", "@overload"]
diff --git a/test/classes/test_cell2vec.py b/test/classes/test_cell2vec.py
@@ -12,7 +12,7 @@ class TestCell2Vec:
     def test_fit_and_get_embedding(self):
         """Test get_embedding."""
         # Create a small complex
-        cx = tnx.classes.CellComplex([[1, 2, 3, 4], [3, 4, 5, 6, 7, 8]], ranks=2)
+        cx = tnx.CellComplex([[1, 2, 3, 4], [3, 4, 5, 6, 7, 8]], ranks=2)
 
         # Create a Cell2Vec object
         dc = Cell2Vec(dimensions=5)

diff --git a/topoembedx/classes/cell2vec.py b/topoembedx/classes/cell2vec.py
@@ -6,6 +6,7 @@
 import numpy as np
 import toponetx as tnx
 from karateclub import Node2Vec
+from scipy.sparse import csr_matrix
 
 from topoembedx.neighborhood import neighborhood_from_complex
 
@@ -50,14 +51,14 @@ class Cell2Vec(Node2Vec):
         Random seed value.
     """
 
-    A: np.ndarray
+    A: csr_matrix
     ind: list
 
     def fit(
         self,
         complex: tnx.Complex,
         neighborhood_type: Literal["adj", "coadj"] = "adj",
-        neighborhood_dim={"rank": 0, "via_rank": -1},
+        neighborhood_dim=None,
     ) -> None:
         """Fit a Cell2Vec model.
 
@@ -93,7 +94,8 @@ def fit(
             complex, neighborhood_type, neighborhood_dim
         )
 
-        g = nx.from_numpy_matrix(self.A)
+        g = nx.from_numpy_array(self.A)
+        g.add_edges_from((index, index) for index in range(g.number_of_nodes()))
 
         super().fit(g)
 
@@ -112,5 +114,5 @@ def get_embedding(self, get_dict: bool = False) -> dict | np.ndarray:
         """
         emb = super().get_embedding()
         if get_dict:
-            return dict(zip(self.ind, emb))
+            return dict(zip(self.ind, emb, strict=True))
         return emb
diff --git a/topoembedx/classes/cell_diff2vec.py b/topoembedx/classes/cell_diff2vec.py
@@ -6,6 +6,7 @@
 import numpy as np
 import toponetx as tnx
 from karateclub import Diff2Vec
+from scipy.sparse import csr_matrix
 
 from topoembedx.neighborhood import neighborhood_from_complex
 
@@ -35,14 +36,14 @@ class CellDiff2Vec(Diff2Vec):
         Random seed value.
     """
 
-    A: np.ndarray
+    A: csr_matrix
     ind: list
 
     def fit(
         self,
         complex: tnx.Complex,
         neighborhood_type: Literal["adj", "coadj"] = "adj",
-        neighborhood_dim={"rank": 0, "via_rank": -1},
+        neighborhood_dim=None,
     ) -> None:
         """Fit a CellDiff2Vec model.
 
@@ -78,11 +79,14 @@ def fit(
             complex, neighborhood_type, neighborhood_dim
         )
 
-        g = nx.from_numpy_matrix(self.A)
+        self.A.setdiag(1)
+        g = nx.from_numpy_array(self.A)
+
         if self.diffusion_cover > g.number_of_nodes():
             raise ValueError(
                 "The diffusion_cover is too large for the size of the graph."
             )
+
         super().fit(g)
 
     def get_embedding(self, get_dict: bool = False) -> dict | np.ndarray:
@@ -100,5 +104,5 @@ def get_embedding(self, get_dict: bool = False) -> dict | np.ndarray:
         """
         emb = super().get_embedding()
         if get_dict:
-            return dict(zip(self.ind, emb))
+            return dict(zip(self.ind, emb, strict=True))
         return emb
diff --git a/topoembedx/classes/deepcell.py b/topoembedx/classes/deepcell.py
@@ -6,6 +6,7 @@
 import numpy as np
 import toponetx as tnx
 from karateclub import DeepWalk
+from scipy.sparse import csr_matrix
 
 from topoembedx.neighborhood import neighborhood_from_complex
 
@@ -35,14 +36,14 @@ class DeepCell(DeepWalk):
         Random seed to use for reproducibility.
     """
 
-    A: np.ndarray
+    A: csr_matrix
     ind: list
 
     def fit(
         self,
         complex: tnx.Complex,
         neighborhood_type: Literal["adj", "coadj"] = "adj",
-        neighborhood_dim={"rank": 0, "via_rank": -1},
+        neighborhood_dim=None,
     ) -> None:
         """Fit the model.
 
@@ -78,7 +79,8 @@ def fit(
             complex, neighborhood_type, neighborhood_dim
         )
 
-        g = nx.from_numpy_matrix(self.A)
+        self.A.setdiag(1)
+        g = nx.from_numpy_array(self.A)
 
         super().fit(g)
 
@@ -97,5 +99,5 @@ def get_embedding(self, get_dict: bool = False) -> dict | np.ndarray:
         """
         emb = super().get_embedding()
         if get_dict:
-            return dict(zip(self.ind, emb))
+            return dict(zip(self.ind, emb, strict=True))
         return emb
diff --git a/topoembedx/classes/higher_order_laplacian_eigenmaps.py b/topoembedx/classes/higher_order_laplacian_eigenmaps.py
@@ -6,6 +6,7 @@
 import numpy as np
 import toponetx as tnx
 from karateclub import LaplacianEigenmaps
+from scipy.sparse import csr_matrix
 
 from topoembedx.neighborhood import neighborhood_from_complex
 
@@ -23,7 +24,7 @@ class HigherOrderLaplacianEigenmaps(LaplacianEigenmaps):
         Random seed value.
     """
 
-    A: np.ndarray
+    A: csr_matrix
     ind: list
 
     def __init__(
@@ -39,7 +40,7 @@ def fit(
         self,
         complex: tnx.Complex,
         neighborhood_type: Literal["adj", "coadj"] = "adj",
-        neighborhood_dim={"rank": 0, "via_rank": -1},
+        neighborhood_dim=None,
     ) -> None:
         """Fit a Higher Order Laplacian Eigenmaps model.
 
@@ -75,7 +76,8 @@ def fit(
             complex, neighborhood_type, neighborhood_dim
         )
 
-        g = nx.from_numpy_matrix(self.A)
+        self.A.setdiag(1)
+        g = nx.from_numpy_array(self.A)
 
         super().fit(g)
 
@@ -94,5 +96,5 @@ def get_embedding(self, get_dict: bool = False) -> dict | np.ndarray:
         """
         emb = super().get_embedding()
         if get_dict:
-            return dict(zip(self.ind, emb))
+            return dict(zip(self.ind, emb, strict=True))
         return emb