Remove boilerplate (#70)

* Move stuff around Signed-off-by: zethson <[email protected]> * Move back Signed-off-by: zethson <[email protected]> * Fix checkout version Signed-off-by: zethson <[email protected]> * Remove unused imports Signed-off-by: zethson <[email protected]> * Fix docs Signed-off-by: zethson <[email protected]> * Fix docs Signed-off-by: zethson <[email protected]> * promote info to warning where more meaningful * exclude slow tests by default, keep them in ci * they're also omitted in ci --------- Signed-off-by: zethson <[email protected]> Co-authored-by: eroell <[email protected]>
theislab · Dec 4, 2024 · e06ea34 · e06ea34
1 parent 2bdceb3
commit e06ea34
Show file tree

Hide file tree

Showing 17 changed files with 20 additions and 218 deletions.
diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml
@@ -14,11 +14,11 @@ jobs:
   package:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.12"
           cache: "pip"
           cache-dependency-path: "**/pyproject.toml"
       - name: Install build dependencies

diff --git a/docs/api.md b/docs/api.md
@@ -40,31 +40,6 @@
     dt.mimic_ii
 ```
 
-## Preprocessing
-
-```{eval-rst}
-.. module:: ehrdata.pp
-.. currentmodule:: ehrdata
-
-.. autosummary::
-    :toctree: generated
-
-    pp.basic_preproc
-```
-
-## Tools
-
-```{eval-rst}
-.. module:: ehrdata.tl
-.. currentmodule:: ehrdata
-
-.. autosummary::
-    :toctree: generated
-
-    tl.basic_tool
-    tl.get_concept_name
-```
-
 ## Plotting
 
 ```{eval-rst}
@@ -74,7 +49,5 @@
 .. autosummary::
     :toctree: generated
 
-    pl.basic_plot
-    pl.BasicClass
     pl.vitessce.gen_config
 ```
diff --git a/docs/conf.py b/docs/conf.py
@@ -141,6 +141,7 @@
 # If building the documentation fails because of a missing link that is outside your control,
 # you can add an exception to this list:
 nitpick_ignore = [
+    ("py:class", "types.EllipsisType"),
     # https://github.com/duckdb/duckdb-web/issues/3806
     ("py:class", "duckdb.duckdb.DuckDBPyConnection"),
     # Is documented as a py:attribute instead

diff --git a/pyproject.toml b/pyproject.toml
@@ -29,6 +29,7 @@ dependencies = [
   "awkward",
   "duckdb",
   # for debug logging (referenced from the issue template)
+  "lamin-utils",
   "session-info",
   "xarray",
 ]

diff --git a/pytest.ini b/pytest.ini
@@ -0,0 +1,4 @@
+[pytest]
+markers =
+    slow: marks tests as slow (deselect with '-m "not slow"')
+addopts = -m "not slow"
diff --git a/src/ehrdata/__init__.py b/src/ehrdata/__init__.py
@@ -1,12 +1,8 @@
 from importlib.metadata import version
 
-from . import dt, io, pl, pp, tl
+from . import dt, io, pl
 from .core import EHRData
 
-__all__ = ["EHRData", "dt", "io", "pl", "pp", "tl"]
+__all__ = ["EHRData", "dt", "io", "pl"]
 
 __version__ = version("ehrdata")
-
-from .logging_config import configure_logging
-
-configure_logging()
diff --git a/src/ehrdata/utils/_omop_utils.py → src/ehrdata/_omop_utils.py b/src/ehrdata/utils/_omop_utils.py → src/ehrdata/_omop_utils.py
diff --git a/src/ehrdata/io/omop/omop.py b/src/ehrdata/io/omop/omop.py
@@ -12,6 +12,7 @@
 import pandas as pd
 from duckdb.duckdb import DuckDBPyConnection
 
+from ehrdata._omop_utils import get_table_catalog_dict
 from ehrdata.io.omop._check_arguments import (
     VALID_OBSERVATION_TABLES_JOIN,
     VALID_OBSERVATION_TABLES_SINGLE,
@@ -32,7 +33,6 @@
     _check_valid_variable_data_tables,
 )
 from ehrdata.io.omop._queries import _time_interval_table
-from ehrdata.utils._omop_utils import get_table_catalog_dict
 
 DOWNLOAD_VERIFICATION_TAG = "download_verification_tag"
 
@@ -328,7 +328,7 @@ def setup_variables(
     # dbms complains about our queries, which sometimes need a column to be of type e.g. datetime, when it can't infer types from data
     count = backend_handle.execute(f"SELECT COUNT(*) as count FROM {data_tables[0]}").df()["count"].item()
     if count == 0:
-        logging.info(f"No data found in {data_tables[0]}. Returning edata without additional variables.")
+        logging.warning(f"No data found in {data_tables[0]}. Returning edata without additional variables.")
         return edata
 
     ds = (
@@ -463,7 +463,7 @@ def setup_interval_variables(
     # dbms complains about our queries, which sometimes need a column to be of type e.g. datetime, when it can't infer types from data
     count = backend_handle.execute(f"SELECT COUNT(*) as count FROM {data_tables[0]}").df()["count"].item()
     if count == 0:
-        logging.info(f"No data in {data_tables}.")
+        logging.warning(f"No data in {data_tables}.")
         return edata
 
     ds = (

diff --git a/src/ehrdata/logging_config.py b/src/ehrdata/logging_config.py
diff --git a/src/ehrdata/pl/__init__.py b/src/ehrdata/pl/__init__.py
@@ -1,8 +1,6 @@
 from importlib.util import find_spec
 
-__all__ = ["BasicClass", "basic_plot", "vitessce"]
-
-from .basic import BasicClass, basic_plot
+__all__ = ["vitessce"]
 
 if find_spec("vitessce"):
     from . import vitessce
diff --git a/src/ehrdata/pl/basic.py b/src/ehrdata/pl/basic.py
diff --git a/src/ehrdata/pp/__init__.py b/src/ehrdata/pp/__init__.py
diff --git a/src/ehrdata/pp/basic.py b/src/ehrdata/pp/basic.py
diff --git a/src/ehrdata/tl/__init__.py b/src/ehrdata/tl/__init__.py
diff --git a/src/ehrdata/tl/basic.py b/src/ehrdata/tl/basic.py
diff --git a/src/ehrdata/tl/omop.py b/src/ehrdata/tl/omop.py
diff --git a/tests/test_dt/test_dt.py b/tests/test_dt/test_dt.py
@@ -13,6 +13,7 @@ def duckdb_connection():
     con.close()
 
 
+@pytest.mark.slow
 def test_mimic_iv_omop(tmp_path):
     duckdb_connection = duckdb.connect()
     ed.dt.mimic_iv_omop(data_path=tmp_path, backend_handle=duckdb_connection)
@@ -22,6 +23,7 @@ def test_mimic_iv_omop(tmp_path):
     duckdb_connection.close()
 
 
+@pytest.mark.slow
 def test_gibleed_omop(tmp_path):
     duckdb_connection = duckdb.connect()
     ed.dt.gibleed_omop(data_path=tmp_path, backend_handle=duckdb_connection)
@@ -31,6 +33,7 @@ def test_gibleed_omop(tmp_path):
     duckdb_connection.close()
 
 
+@pytest.mark.slow
 def test_synthea27nj_omop(tmp_path):
     duckdb_connection = duckdb.connect()
     ed.dt.synthea27nj_omop(data_path=tmp_path, backend_handle=duckdb_connection)
@@ -40,6 +43,7 @@ def test_synthea27nj_omop(tmp_path):
     duckdb_connection.close()
 
 
+@pytest.mark.slow
 def test_physionet2012():
     edata = ed.dt.physionet2012()
     assert edata.shape == (11988, 38)