Merge pull request #568 from Aarhus-Psychiatry-Research/add-docstring…

…-to-flattenerr docs: add docstring to flattener
Aarhus-Psychiatry-Research · May 17, 2024 · 3d662f8 · 3d662f8
2 parents 6996013 + dfdf5dd
commit 3d662f8
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 3 deletions.
diff --git a/src/timeseriesflattener/flattener.py b/src/timeseriesflattener/flattener.py
@@ -97,10 +97,25 @@ class Flattener:
     predictiontime_frame: PredictionTimeFrame
     compute_lazily: bool = False
     n_workers: int | None = None
+    """Flatten multiple irregular time series to a static feature set.
+    
+    Args:
+        predictiontime_frame: A frame that contains the prediction times.
+        compute_lazily: If True, the computation will be done lazily.
+        n_workers: The number of workers to use for multiprocessing. 
+            If None, multiprocessing will be handled entirely by polars, otherwise, 
+            specify the number of workers to use with joblib. """
 
     def aggregate_timeseries(
         self, specs: Sequence[ValueSpecification], step_size: dt.timedelta | None = None
     ) -> AggregatedFrame:
+        """Perform the aggregation/flattening.
+        
+        Args:
+            specs: The specifications for the features to be created.
+            step_size: The step size for the aggregation. 
+                If not None, will aggregate prediction times in chunks of step_size. 
+                Reduce if you encounter memory issues."""
         if self.compute_lazily:
             print(
                 "We have encountered performance issues on Windows when using lazy evaluation. If you encounter performance issues, try setting lazy=False."

diff --git a/src/timeseriesflattener/test_aggregators.py b/src/timeseriesflattener/test_aggregators.py
@@ -42,6 +42,7 @@ class SingleVarAggregatorExample:
     aggregator: Aggregator
     input_values: Sequence[float | None]
     expected_output_values: Sequence[float]
+    fallback_str: str = "nan"
 
     @property
     def input_frame(self) -> pl.LazyFrame:
@@ -58,7 +59,7 @@ def expected_output(self) -> pl.DataFrame:
         return pl.DataFrame(
             {
                 "prediction_time_uuid": [1],
-                f"value_{self.aggregator.name}_fallback_nan": self.expected_output_values,
+                f"value_{self.aggregator.name}_fallback_{self.fallback_str}": self.expected_output_values,
             }
         )
 
@@ -90,12 +91,13 @@ def expected_output(self) -> pl.DataFrame:
             aggregator=VarianceAggregator(), input_values=[1, 2], expected_output_values=[0.5]
         ),
         SingleVarAggregatorExample(
-            aggregator=HasValuesAggregator(), input_values=[1, 2], expected_output_values=[1]
+            aggregator=HasValuesAggregator(), input_values=[1, 2], expected_output_values=[1], fallback_str="False"
         ),
         SingleVarAggregatorExample(
             aggregator=HasValuesAggregator(),
             input_values=[None],  # type: ignore
             expected_output_values=[0],
+            fallback_str="False",
         ),
         ComplexAggregatorExample(
             aggregator=SlopeAggregator(timestamp_col_name="timestamp"),
@@ -153,7 +155,7 @@ def test_aggregator(example: AggregatorExampleType):
             timestamp_col_name="timestamp",
         ),
         aggregators=[example.aggregator],
-        fallback=np.nan,
+        fallback=np.nan if example.aggregator.name != "bool" else False,
     )
 
     assert_frame_equal(result.collect(), example.expected_output)