update 7 files

pyproject.toml

@@ -35,7 +35,7 @@ dependencies = [
   "frozendict>=2.3.4",
   "coloredlogs>14.0.0",
   "tqdm>4.1.0",
-  "polars>0.19.0",
+  "polars>=0.19.0",
   "iterpy==1.6.0",
   "rich>=13.0.0",
   "ipykernel[docs]>=6.29.5",
@@ -70,7 +70,7 @@ docs = [
   "sphinx_design==0.3.0",
   "ipykernel>=6.29.5",
 ]
-tutorials = ["jupyter>=1.0.0,<1.1.0", "skimpy>=0.0.11"]
+tutorials = ["jupyter>=1.0.0,<1.1.0", "skimpy==0.0.15"]
 
 [project.readme]
 file = "README.md"
@@ -81,20 +81,8 @@ homepage = "https://github.com/Aarhus-Psychiatry-Research/timeseriesflattener"
 repository = "https://github.com/Aarhus-Psychiatry-Research/timeseriesflattener"
 documentation = "https://aarhus-psychiatry-research.github.io/timeseriesflattener/"
 
-[tool]
-rye = { dev-dependencies = [
-  "pytest>=7.1.3, <7.3.0",
-  "pytest-cov>=3.0.0, <3.1.0",
-  "pytest-xdist>=3.0.0, <3.2.0",
-  "pytest-sugar>=0.9.4, <0.10.0",
-  "pytest-testmon==2.1.0",
-  "pytest-benchmark==4.0.0",
-  "pytest-codspeed==2.2.0",
-  "invoke==2.1.1",
-  "pyright==1.1.330.post0",
-  "pandas-stubs>=2.0.3.230814",
-  "ruff>=0.2.2",
-] }
+[tool.uv]
+override-dependencies = ["polars >= 1.0"]
 
 [tool.pyright]
 exclude = [".*venv*/", ".venv38/", ".tox", ".benchmark_cache"]

src/timeseriesflattener/main_test.py

@@ -45,8 +45,8 @@ def assert_frame_equal(
     result: pl.DataFrame, expected: pl.DataFrame, ignore_colums: Sequence[str] = ()
 ):
     polars_testing.assert_frame_equal(
-        result.drop(ignore_colums),
-        expected.drop(ignore_colums),
+        result.drop(ignore_colums, strict=False),
+        expected.drop(ignore_colums, strict=False),
         check_dtypes=False,
         check_column_order=False,
     )

src/timeseriesflattener/processors/temporal.py

@@ -130,9 +130,10 @@ def _aggregate_masked_frame(
     )
     rename_mapping = dict(value_columns)
 
-    with_fallback = grouped_frame.with_columns(
-        cs.contains(masked_frame.value_col_names).fill_null(fallback)
-    ).rename(rename_mapping)
+    for col in masked_frame.value_col_names:
+        with_fallback = grouped_frame.with_columns(cs.contains(col).fill_null(fallback)).rename(
+            rename_mapping
+        )
 
     return with_fallback
 

src/timeseriesflattener/specs/outcome.py

@@ -4,6 +4,7 @@
 from dataclasses import InitVar, dataclass
 from typing import TYPE_CHECKING
 
+import pandas as pd
 import polars as pl
 from timeseriesflattener.specs import _lookdistance_to_timedelta
 
@@ -114,7 +115,7 @@ def df(self) -> pl.DataFrame:
 
     @staticmethod
     def from_primitives(
-        df: pl.DataFrame,
+        df: pl.DataFrame | pd.DataFrame,
         entity_id_col_name: str,
         lookahead_days: Sequence[float | tuple[float, float]],
         aggregators: Sequence[AggregatorName],

src/timeseriesflattener/testing/load_synth_data.py

@@ -37,7 +37,7 @@ def synth_predictor_binary() -> pl.DataFrame:
 def load_synth_outcome() -> pl.DataFrame:
     # Get first row for each id
     df = load_raw_test_csv("synth_raw_binary_2.csv")
-    df = df.groupby("entity_id").last()
+    df = df.group_by("entity_id").last()
 
     # Drop all rows with a value equal to 1
     df = df.filter(pl.col("value") == 1)