Feat/implenting ruff

.pre-commit-config.yaml

@@ -29,28 +29,19 @@ repos:
       - id: pyupgrade
         args: [--py310-plus]
 
-  - repo: https://github.com/psf/black
-    rev: 23.3.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.13.1
     hooks:
-      - id: black
-
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
-
-  - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
-    hooks:
-      - id: flake8
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
 
   - repo: https://github.com/Riverside-Healthcare/djLint
     rev: v1.31.1
     hooks:
       - id: djlint-reformat-django
       - id: djlint-django
 
-
 # sets up .pre-commit-ci.yaml to ensure pre-commit dependencies stay up to date
 ci:
   autoupdate_schedule: weekly

.vscode/settings.json

@@ -1,47 +1,44 @@
 {
-    "editor.formatOnSave": true,
-    "diffEditor.codeLens": true,
-    "eslint.enable": true,
+  "editor.formatOnSave": true,
+  "diffEditor.codeLens": true,
+  "eslint.enable": true,
+  "editor.codeActionsOnSave": {
+    "source.organizeImports": "explicit",
+    "source.sortImports": "explicit",
+    "source.fixAll.markdownlint": "explicit",
+    "source.fixAll": "explicit"
+  },
+
+  "typescript.format.enable": true,
+  "prettier.requireConfig": true,
+
+  "[python]": {
+    "editor.defaultFormatter": "ms-python.black-formatter",
     "editor.codeActionsOnSave": {
-        "source.organizeImports": "explicit",
-        "source.sortImports": "explicit",
-        "source.fixAll.markdownlint": "explicit",
-        "source.fixAll": "explicit"
+       "source.fixAll": "explicit"
     },
-    "isort.args": [
-        "--profile",
-        "black"
-    ],
-    "typescript.format.enable": true,
-    "prettier.requireConfig": true,
-    "[python]": {
-      "editor.defaultFormatter": "ms-python.black-formatter",
-      "editor.tabSize": 4,
-      "editor.rulers": [
-        119
-      ]
-    },
-    "black-formatter.args": ["--line-length", "119"],
-    "flake8.args": [
-        "--max-line-length", "119"
-    ],
-    "[javascript]": {
-      "editor.defaultFormatter": "esbenp.prettier-vscode"
-    },
-    "[javascriptreact]": {
-      "editor.defaultFormatter": "esbenp.prettier-vscode"
-    },
-    "[typescript]": {
-      "editor.defaultFormatter": "esbenp.prettier-vscode"
-    },
-    "[typescriptreact]": {
-      "editor.defaultFormatter": "esbenp.prettier-vscode"
-    },
-    "[json]": {
-      "editor.defaultFormatter": "esbenp.prettier-vscode"
-    },
-    "files.eol": "\n",
-    "files.insertFinalNewline": true,
-    "files.trimTrailingWhitespace": true,
-    "python.analysis.typeCheckingMode": "basic"
+    "editor.tabSize": 4,
+    "editor.rulers": [119]
+  },
+
+  "[javascript]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+  "[javascriptreact]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+  "[typescript]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+  "[typescriptreact]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+  "[json]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
+
+  "files.eol": "\n",
+  "files.insertFinalNewline": true,
+  "files.trimTrailingWhitespace": true,
+  "python.analysis.typeCheckingMode": "basic"
 }

README.md

@@ -252,3 +252,6 @@ The local environment uses a local PostgreSQL database in a Docker container.
 ### Load fixtures with test data
 
     docker compose run --rm django python manage.py migrate
+### Linting
+
+This project uses Ruff for linting and formatting — it’s super fast and replaces tools like Black, isort, and Flake8 for a cleaner, all-in-one setup.

ami/base/models.py

@@ -153,7 +153,7 @@ def get_project(self):
     def __str__(self) -> str:
         """All django models should have this method."""
         if hasattr(self, "name"):
-            name = getattr(self, "name") or "Untitled"
+            name = self.name or "Untitled"
             return f"#{self.pk} {name}"
         else:
             return f"{self.__class__.__name__} #{self.pk}"

ami/base/serializers.py

@@ -13,7 +13,9 @@
 logger = logging.getLogger(__name__)
 
 
-def reverse_with_params(viewname: str, args=None, kwargs=None, request=None, params: dict = {}, **extra) -> str:
+def reverse_with_params(viewname: str, args=None, kwargs=None, request=None, params: dict = None, **extra) -> str:
+    if params is None:
+        params = {}
     query_string = urllib.parse.urlencode(params)
     base_url = reverse(viewname, request=request, args=args, kwargs=kwargs, **extra)
     url = urllib.parse.urlunsplit(("", "", base_url, query_string, ""))

ami/exports/format_types.py

@@ -63,7 +63,7 @@ def export(self):
             first = True
             f.write("[")
             records_exported = 0
-            for i, batch in enumerate(get_data_in_batches(self.queryset, self.get_serializer_class())):
+            for _i, batch in enumerate(get_data_in_batches(self.queryset, self.get_serializer_class())):
                 json_data = json.dumps(batch, cls=DjangoJSONEncoder)
                 json_data = json_data[1:-1]  # remove [ and ] from json string
                 f.write(",\n" if not first else "")
@@ -153,7 +153,7 @@ def export(self):
             writer = csv.DictWriter(csvfile, fieldnames=field_names)
             writer.writeheader()
 
-            for i, batch in enumerate(get_data_in_batches(self.queryset, self.serializer_class)):
+            for _i, batch in enumerate(get_data_in_batches(self.queryset, self.serializer_class)):
                 writer.writerows(batch)
                 records_exported += len(batch)
                 self.update_job_progress(records_exported)

ami/exports/utils.py

@@ -80,7 +80,7 @@ def get_data_in_batches(QuerySet: models.QuerySet, Serializer: type[serializers.
     batch = []
 
     fake_request = generate_fake_request()
-    for i, item in enumerate(items):
+    for _i, item in enumerate(items):
         try:
             serializer = Serializer(
                 item,

ami/jobs/management/commands/update_stale_jobs.py

@@ -7,9 +7,7 @@
 
 
 class Command(BaseCommand):
-    help = (
-        "Update the status of all jobs that are not in a final state " "and have not been updated in the last X hours."
-    )
+    help = "Update the status of all jobs that are not in a final state and have not been updated in the last X hours."
 
     # Add argument for the number of hours to consider a job stale
     def add_arguments(self, parser):

ami/jobs/models.py

@@ -412,17 +412,17 @@ def run(cls, job: "Job"):
 
         for i, chunk in enumerate(chunks):
             request_sent = time.time()
-            job.logger.info(f"Processing image batch {i+1} of {len(chunks)}")
+            job.logger.info(f"Processing image batch {i + 1} of {len(chunks)}")
             try:
                 results = job.pipeline.process_images(
                     images=chunk,
                     job_id=job.pk,
                     project_id=job.project.pk,
                 )
-                job.logger.info(f"Processed image batch {i+1} in {time.time() - request_sent:.2f}s")
+                job.logger.info(f"Processed image batch {i + 1} in {time.time() - request_sent:.2f}s")
             except Exception as e:
                 # Log error about image batch and continue
-                job.logger.error(f"Failed to process image batch {i+1}: {e}")
+                job.logger.error(f"Failed to process image batch {i + 1}: {e}")
                 request_failed_images.extend([img.pk for img in chunk])
             else:
                 total_captures += len(results.source_images)
@@ -433,7 +433,7 @@ def run(cls, job: "Job"):
                     # @TODO add callback to report errors while saving results marking the job as failed
                     save_results_task: AsyncResult = job.pipeline.save_results_async(results=results, job_id=job.pk)
                     save_tasks.append((i + 1, save_results_task))
-                    job.logger.info(f"Saving results for batch {i+1} in sub-task {save_results_task.id}")
+                    job.logger.info(f"Saving results for batch {i + 1} in sub-task {save_results_task.id}")
 
             job.progress.update_stage(
                 "process",

ami/main/api/serializers.py

@@ -1299,12 +1299,12 @@ def get_determination_details(self, obj: Occurrence):
         else:
             prediction = ClassificationNestedSerializer(obj.best_prediction, context=context).data
 
-        return dict(
-            taxon=taxon,
-            identification=identification,
-            prediction=prediction,
-            score=obj.determination_score,
-        )
+        return {
+            "taxon": taxon,
+            "identification": identification,
+            "prediction": prediction,
+            "score": obj.determination_score,
+        }
 
 
 class OccurrenceSerializer(OccurrenceListSerializer):

ami/main/charts.py

@@ -91,7 +91,7 @@ def captures_per_day(project_pk: int):
     )
 
     if captures_per_date:
-        days, counts = list(zip(*captures_per_date))
+        days, counts = list(zip(*captures_per_date, strict=False))
         days = [day for day in days if day]
         # tickvals_per_month = [f"{d:%b}" for d in days]
         tickvals = [f"{days[0]:%b %d}", f"{days[-1]:%b %d}"]
@@ -119,7 +119,7 @@ def captures_per_month(project_pk: int):
     )
 
     if captures_per_month:
-        months, counts = list(zip(*captures_per_month))
+        months, counts = list(zip(*captures_per_month, strict=False))
         # tickvals_per_month = [f"{d:%b}" for d in days]
         tickvals = [f"{months[0]}", f"{months[-1]}"]
         # labels = [f"{d}" for d in months]
@@ -146,7 +146,7 @@ def events_per_week(project_pk: int):
     )
 
     if captures_per_week:
-        weeks, counts = list(zip(*captures_per_week))
+        weeks, counts = list(zip(*captures_per_week, strict=False))
         # tickvals_per_month = [f"{d:%b}" for d in days]
         tickvals = [f"{weeks[0]}", f"{weeks[-1]}"]
         labels = [f"{d}" for d in weeks]
@@ -172,7 +172,7 @@ def events_per_month(project_pk: int):
     )
 
     if captures_per_month:
-        months, counts = list(zip(*captures_per_month))
+        months, counts = list(zip(*captures_per_month, strict=False))
         # tickvals_per_month = [f"{d:%b}" for d in days]
         tickvals = [f"{months[0]}", f"{months[-1]}"]
         # labels = [f"{d}" for d in months]
@@ -257,7 +257,7 @@ def occurrences_accumulated(project_pk: int):
 
     occurrences_exist = Occurrence.objects.filter(project=project_pk).exists()
     if occurrences_exist:
-        days, counts = list(zip(*occurrences_per_day))
+        days, counts = list(zip(*occurrences_per_day, strict=False))
         # Accumulate the counts
         counts = list(itertools.accumulate(counts))
         # tickvals = [f"{d:%b %d}" for d in days]
@@ -288,7 +288,9 @@ def event_detections_per_hour(event_pk: int):
     # hours, counts = list(zip(*detections_per_hour))
     if detections_per_hour:
         hours, counts = list(
-            zip(*[(d["source_image__timestamp__hour"], d["num_detections"]) for d in detections_per_hour])
+            zip(
+                *[(d["source_image__timestamp__hour"], d["num_detections"]) for d in detections_per_hour], strict=False
+            )
         )
         hours, counts = shift_to_nighttime(list(hours), list(counts))
         # @TODO show a tick for every hour even if there are no detections
@@ -317,7 +319,7 @@ def event_top_taxa(event_pk: int, top_n: int = 10):
     )
 
     if top_taxa:
-        taxa, counts = list(zip(*[(t["name"], t["num_detections"]) for t in reversed(top_taxa)]))
+        taxa, counts = list(zip(*[(t["name"], t["num_detections"]) for t in reversed(top_taxa)], strict=False))
         taxa = [t or "Unknown" for t in taxa]
         counts = [c or 0 for c in counts]
     else:
@@ -340,7 +342,7 @@ def project_top_taxa(project_pk: int, top_n: int = 10):
     )
 
     if top_taxa:
-        taxa, counts = list(zip(*[(t.name, t.occurrence_count) for t in reversed(top_taxa)]))
+        taxa, counts = list(zip(*[(t.name, t.occurrence_count) for t in reversed(top_taxa)], strict=False))
     else:
         taxa, counts = [], []
 
@@ -363,7 +365,7 @@ def unique_species_per_month(project_pk: int):
     )
 
     # Create a dictionary mapping month numbers to species counts
-    month_to_count = {month: count for month, count in unique_species_per_month}
+    month_to_count = dict(unique_species_per_month)
 
     # Create lists for all 12 months, using 0 for months with no data
     all_months = list(range(1, 13))  # 1-12 for January-December
@@ -393,7 +395,7 @@ def average_occurrences_per_month(project_pk: int):
     )
 
     # Create a dictionary mapping month numbers to occurrence counts
-    month_to_count = {month: count for month, count in occurrences_per_month}
+    month_to_count = dict(occurrences_per_month)
 
     # Create lists for all 12 months, using 0 for months with no data
     all_months = list(range(1, 13))  # 1-12 for January-December

ami/main/management/commands/import_taxa.py

@@ -15,7 +15,7 @@
 
 from ...models import TaxaList, Taxon, TaxonRank
 
-RANK_CHOICES = [rank for rank in TaxonRank]
+RANK_CHOICES = list(TaxonRank)
 
 logger = logging.getLogger(__name__)
 # Set level
@@ -34,7 +34,7 @@
 
 def read_csv(fname: str) -> list[dict]:
     reader = csv.DictReader(open(fname))
-    taxa = [row for row in reader]
+    taxa = list(reader)
     return taxa
 
 
@@ -79,7 +79,7 @@ def fix_generic_names(taxon_data: dict) -> dict:
     fixed_taxon_data = taxon_data.copy()
     generic_names = ["sp.", "sp", "spp", "spp.", "cf.", "cf", "aff.", "aff"]
     fallback_name_keys = ["bold_taxon_bin", "inat_taxon_id", "gbif_taxon_key"]
-    for key, value in taxon_data.items():
+    for _key, value in taxon_data.items():
         if value and value.lower() in generic_names:
             # set name to first fallback name that exists
             fallback_name = None
@@ -236,7 +236,7 @@ def handle(self, *args, **options):
 
         taxalist, created = TaxaList.objects.get_or_create(name=list_name)
         if created:
-            self.stdout.write(self.style.SUCCESS('Successfully created taxa list "%s"' % taxalist))
+            self.stdout.write(self.style.SUCCESS(f'Successfully created taxa list "{taxalist}"'))
 
         if options["purge"]:
             self.stdout.write(self.style.WARNING("Purging all taxa from the database in 5 seconds..."))
@@ -319,11 +319,11 @@ def create_taxon(self, taxon_data: dict, root_taxon_parent: Taxon) -> tuple[set[
                 # If the taxon already exists, use it and maybe update it
                 taxon, created = Taxon.objects.get_or_create(
                     name=name,
-                    defaults=dict(
-                        rank=rank,
-                        gbif_taxon_key=gbif_taxon_key,
-                        parent=parent_taxon,
-                    ),
+                    defaults={
+                        "rank": rank,
+                        "gbif_taxon_key": gbif_taxon_key,
+                        "parent": parent_taxon,
+                    },
                 )
                 taxa_in_row.append(taxon)