Merge branch 'main' into il-gs-add-study

.github/workflows/pytest.yaml

@@ -30,6 +30,8 @@ jobs:
         run: poetry install --no-interaction --no-root
       - name: Install library
         run: poetry install --no-interaction
+      - name: Check dependencies
+        run: poetry run deptry .
       - name: Run tests
         run: poetry run pytest
       - name: Upload coverage to Codecov

mkdocs.yml

@@ -43,7 +43,7 @@ markdown_extensions:
       permalink: true
 
 hooks:
-  - src/scripts/schemadocs.py
+  - src/utils/schemadocs.py
 
 repo_name: opentargets/genetics_etl_python
 repo_url: https://github.com/opentargets/genetics_etl_python

pyproject.toml

@@ -18,11 +18,13 @@ scipy = "^1.11.4"
 hydra-core = "^1.3.2"
 pyliftover = "^0.4"
 xgboost = "^1.7.3"
-scikit-learn = "^1.2.1"
 numpy = "^1.26.1"
 hail = "0.2.126"
-pyarrow = "^14.0.1"
 wandb = "^0.16.0"
+google = "^3.0.0"
+omegaconf = "^2.3.0"
+typing-extensions = "^4.8.0"
+scikit-learn = "^1.3.2"
 
 [tool.poetry.dev-dependencies]
 pre-commit = "^3.5.0"
@@ -64,6 +66,7 @@ google-cloud-dataproc = "^5.7.0"
 apache-airflow = "^2.7.3"
 apache-airflow-providers-google = "^10.12.0"
 pydoclint = "^0.3.8"
+deptry = "^0.12.0"
 
 
 [tool.semantic_release]
@@ -83,6 +86,12 @@ build-backend = "poetry.core.masonry.api"
 [tool.isort]
 profile = "black"
 
+[tool.deptry]
+extend_exclude = ["src/conftest.py", "src/airflow", "src/utils"]
+
+[tool.deptry.per_rule_ignores]
+DEP001 = ["otg"]
+
 [tool.interrogate]
 fail-under = 95
 color = true
@@ -117,6 +126,9 @@ module = [
     "scipy",
     "scipy.stats",
     "chardet",
+    "omegaconf",
+    "xgboost",
+    "sklearn",
 ]
 ignore_missing_imports = true
 

src/otg/l2g.py

@@ -4,6 +4,7 @@
 from dataclasses import dataclass, field
 from typing import Any
 
+import sklearn
 from omegaconf import MISSING
 from xgboost.spark import SparkXGBClassifier
 
@@ -104,6 +105,7 @@ def __post_init__(self: LocusToGeneStep) -> None:
         Raises:
             ValueError: if run_mode is not one of "train" or "predict".
         """
+        print("Sci-kit learn version: ", sklearn.__version__)
         if self.run_mode not in ["train", "predict"]:
             raise ValueError(
                 f"run_mode must be one of 'train' or 'predict', got {self.run_mode}"