Merge pull request #51 from openml/feature/update-mlcroissant-1_0_8-t…

…o-1_0_12 Feature/update mlcroissant 1 0 8 to 1 0 12
openml · Dec 20, 2024 · 0561cd7 · 0561cd7
2 parents cc4b6d4 + dd76d9a
commit 0561cd7
Show file tree

Hide file tree

Showing 5 changed files with 16 additions and 17 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,7 +2,7 @@ repos:
 -   hooks:
     -   id: pre-commit-update
     repo: https://gitlab.com/vojko.pribudic.foss/pre-commit-update
-    rev: v0.6.0post1
+    rev: v0.6.1
 -   hooks:
     -   id: check-ast
     -   id: check-toml
@@ -19,7 +19,7 @@ repos:
         -   python/pyproject.toml
         id: bandit
     repo: https://github.com/PyCQA/bandit
-    rev: 1.7.10
+    rev: 1.8.0
 -   hooks:
     -   additional_dependencies:
         -   fastapi
@@ -34,7 +34,7 @@ repos:
         -   --exit-non-zero-on-fix
         id: ruff
     repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.2
+    rev: v0.8.4
 -   hooks:
     -   id: black
         args: [--line-length=100]

diff --git a/python/openml_croissant/_src/conversion.py b/python/openml_croissant/_src/conversion.py
@@ -121,7 +121,7 @@ def _enum_recordsets(dataset: OpenMLDataset, settings: Settings) -> Iterator[mlc
                         data_types=[mlc.DataType.TEXT],
                     ),
                 ],
-                data=[{"value": value} for value in feature.nominal_values],
+                data=[{f"{id_}/value": value} for value in feature.nominal_values],
             )
 
 

diff --git a/python/openml_croissant/_src/tests/resources/croissant/constructed.json b/python/openml_croissant/_src/tests/resources/croissant/constructed.json
@@ -111,25 +111,25 @@
             ],
             "data": [
                 {
-                    "value": "april"
+                    "enumerations/date/value": "april"
                 },
                 {
-                    "value": "august"
+                    "enumerations/date/value": "august"
                 },
                 {
-                    "value": "july"
+                    "enumerations/date/value": "july"
                 },
                 {
-                    "value": "june"
+                    "enumerations/date/value": "june"
                 },
                 {
-                    "value": "may"
+                    "enumerations/date/value": "may"
                 },
                 {
-                    "value": "october"
+                    "enumerations/date/value": "october"
                 },
                 {
-                    "value": "september"
+                    "enumerations/date/value": "september"
                 }
             ]
         },
@@ -150,10 +150,10 @@
             ],
             "data": [
                 {
-                    "value": "no"
+                    "enumerations/lodging/value": "no"
                 },
                 {
-                    "value": "yes"
+                    "enumerations/lodging/value": "yes"
                 }
             ]
         },

diff --git a/python/openml_croissant/_src/tests/test_converter.py b/python/openml_croissant/_src/tests/test_converter.py
@@ -8,7 +8,7 @@
 
 def test_minimal_conversion():
     metadata_openml = openml.datasets.OpenMLDataset(
-        dataset_id="1",
+        dataset_id=1,
         name="anneal",
         description="description",
         licence="Public",

diff --git a/python/pyproject.toml b/python/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "openml-croissant"
-version = "1.1.20241018"
+version = "1.1.20241220"
 authors = [
   { name="Jos van der Velde" },
 ]
@@ -14,10 +14,9 @@ classifiers = [
 dependencies = [
     "fastapi==0.115.0",
     "minio==7.2.12",
-    "mlcroissant==1.0.8",
+    "mlcroissant==1.0.12",
     "langcodes==3.5.0",
     "language_data==1.2.0",
-    "numpy<2.0.0",
     "openml==0.15.0",
     "python-dateutil==2.9.0.post0",
     "python-dotenv==1.0.1",
-Original file line number
+Diff line change
@@ Expand Up @@
                             data_types=[mlc.DataType.TEXT],
                         ),
                     ],
-                    data=[{"value": value} for value in feature.nominal_values],
+                    data=[{f"{id_}/value": value} for value in feature.nominal_values],
                 )
@@ Expand Down @@