Use ruff instead of black/isort/flake8/pylint (#749)

Author: benfred

.pre-commit-config.yaml

@@ -1,21 +1,11 @@
 repos:
-      - repo: https://github.com/timothycrosley/isort
-        rev: 8.0.1
+      - repo: https://github.com/astral-sh/ruff-pre-commit
+        rev: v0.15.12
         hooks:
-        - id: isort
-          additional_dependencies: [toml]
-      - repo: https://github.com/python/black
-        rev: 26.1.0
-        hooks:
-        - id: black
-      - repo: https://github.com/pycqa/flake8
-        rev: 7.3.0
-        hooks:
-        - id: flake8
-      - repo: https://github.com/pycqa/pylint
-        rev: v4.0.5
-        hooks:
-        - id: pylint
+        - id: ruff-check
+          types_or: [ python, pyi, jupyter, pyproject ]
+          args: [ --fix ]
+        - id: ruff-format
       - repo: https://github.com/codespell-project/codespell
         rev: v2.2.4
         hooks:

examples/tutorial_lastfm.ipynb

@@ -85,11 +85,12 @@
    "source": [
     "from implicit.nearest_neighbours import bm25_weight\n",
     "\n",
-    "# weight the matrix, both to reduce impact of users that have played the same artist thousands of times\n",
-    "# and to reduce the weight given to popular items\n",
+    "# weight the matrix, both to reduce impact of users that have played the same artist thousands\n",
+    "# of times and to reduce the weight given to popular items\n",
     "artist_user_plays = bm25_weight(artist_user_plays, K1=100, B=0.8)\n",
     "\n",
-    "# get the transpose since the most of the functions in implicit expect (user, item) sparse matrices instead of (item, user)\n",
+    "# get the transpose since the most of the functions in implicit expect (user, item) sparse\n",
+    "# matrices instead of (item, user)\n",
     "user_plays = artist_user_plays.T.tocsr()"
    ]
   },
@@ -293,7 +294,14 @@
     "# Use pandas to display the output in a table, pandas isn't a dependency of implicit otherwise\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "pd.DataFrame({\"artist\": artists[ids], \"score\": scores, \"already_liked\": np.isin(ids, user_plays[userid].indices)})"
+    "\n",
+    "pd.DataFrame(\n",
+    "    {\n",
+    "        \"artist\": artists[ids],\n",
+    "        \"score\": scores,\n",
+    "        \"already_liked\": np.isin(ids, user_plays[userid].indices),\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -423,7 +431,7 @@
    ],
    "source": [
     "# get related items for the beatles (itemid = 25512)\n",
-    "ids, scores= model.similar_items(252512)\n",
+    "ids, scores = model.similar_items(252512)\n",
     "\n",
     "# display the results using pandas for nicer formatting\n",
     "pd.DataFrame({\"artist\": artists[ids], \"score\": scores})"

implicit/ann/annoy.py

@@ -124,9 +124,7 @@ def similar_items(
 
         # support recalculate_item if possible. TODO: refactor this
         if hasattr(self.model, "_item_factor"):
-            factor = self.model._item_factor(
-                itemid, item_users, recalculate_item
-            )  # pylint: disable=protected-access
+            factor = self.model._item_factor(itemid, item_users, recalculate_item)  # pylint: disable=protected-access
         elif recalculate_item:
             raise NotImplementedError(f"recalculate_item isn't supported with {self.model}")
         else:
@@ -191,9 +189,7 @@ def recommend(
 
         # support recalculate_user if possible (TODO: come back to this since its a bit of a hack)
         if hasattr(self.model, "+_user_factor"):
-            user = self.model._user_factor(
-                userid, user_items, recalculate_user
-            )  # pylint: disable=protected-access
+            user = self.model._user_factor(userid, user_items, recalculate_user)  # pylint: disable=protected-access
         elif recalculate_user:
             raise NotImplementedError(f"recalculate_user isn't supported with {self.model}")
         else:

implicit/ann/faiss.py

@@ -151,9 +151,7 @@ def similar_items(
 
         # support recalculate_item if possible. TODO: refactor this
         if hasattr(self.model, "_item_factor"):
-            factors = self.model._item_factor(
-                itemid, item_users, recalculate_item
-            )  # pylint: disable=protected-access
+            factors = self.model._item_factor(itemid, item_users, recalculate_item)  # pylint: disable=protected-access
         elif recalculate_item:
             raise NotImplementedError(f"recalculate_item isn't supported with {self.model}")
         else:
@@ -223,9 +221,7 @@ def recommend(
 
         # support recalculate_user if possible (TODO: come back to this since its a bit of a hack)
         if hasattr(self.model, "+_user_factor"):
-            user = self.model._user_factor(
-                userid, user_items, recalculate_user
-            )  # pylint: disable=protected-access
+            user = self.model._user_factor(userid, user_items, recalculate_user)  # pylint: disable=protected-access
         elif recalculate_user:
             raise NotImplementedError(f"recalculate_user isn't supported with {self.model}")
         else:

implicit/ann/nmslib.py

@@ -128,9 +128,7 @@ def similar_items(
 
         # support recalculate_item if possible. TODO: refactor this
         if hasattr(self.model, "_item_factor"):
-            factors = self.model._item_factor(
-                itemid, item_users, recalculate_item
-            )  # pylint: disable=protected-access
+            factors = self.model._item_factor(itemid, item_users, recalculate_item)  # pylint: disable=protected-access
         elif recalculate_item:
             raise NotImplementedError(f"recalculate_item isn't supported with {self.model}")
         else:
@@ -199,9 +197,7 @@ def recommend(
 
         # support recalculate_user if possible (TODO: come back to this since its a bit of a hack)
         if hasattr(self.model, "+_user_factor"):
-            user = self.model._user_factor(
-                userid, user_items, recalculate_user
-            )  # pylint: disable=protected-access
+            user = self.model._user_factor(userid, user_items, recalculate_user)  # pylint: disable=protected-access
         elif recalculate_user:
             raise NotImplementedError(f"recalculate_user isn't supported with {self.model}")
         else:

implicit/approximate_als.py

@@ -15,7 +15,7 @@ def NMSLibAlternatingLeastSquares(
     index_params=None,
     query_params=None,
     use_gpu=implicit.gpu.HAS_CUDA,
-    **kwargs
+    **kwargs,
 ):
     # delay importing here in case nmslib isn't installed
     from implicit.ann.nmslib import NMSLibModel
@@ -39,7 +39,7 @@ def AnnoyAlternatingLeastSquares(
     n_trees=50,
     search_k=-1,
     use_gpu=implicit.gpu.HAS_CUDA,
-    **kwargs
+    **kwargs,
 ):
     als_model = implicit.als.AlternatingLeastSquares(*args, use_gpu=use_gpu, **kwargs)
     from implicit.ann.annoy import AnnoyModel
@@ -60,7 +60,7 @@ def FaissAlternatingLeastSquares(
     nlist=400,
     nprobe=20,
     use_gpu=implicit.gpu.HAS_CUDA,
-    **kwargs
+    **kwargs,
 ):
     # note that we're using the factory function here to instantiate a CPU/GPU model as appropriate
     als_model = implicit.als.AlternatingLeastSquares(*args, use_gpu=use_gpu, **kwargs)

pyproject.toml

@@ -1,7 +1,3 @@
-[tool.black]
-
-line-length = 100
-
 [build-system]
 requires = [
     "setuptools>=42",
@@ -39,3 +35,12 @@ archs = ["x86_64", "universal2", "arm64"]
 
 [tool.pytest.ini_options]
 filterwarnings = ['ignore::implicit.utils.ParameterWarning']
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["implicit"]

requirements-dev.txt

@@ -2,8 +2,5 @@
 
 scikit-build>=0.13.1
 pytest
-black==22.3.0
-flake8
-isort
+ruff
 codespell
-pylint