fix test

eds_scikit/biology/utils/prepare_measurement.py

@@ -80,12 +80,14 @@ def prepare_measurement_table(
         logger.info(
             "Lazy preparation not available if convert_units=True. Computed table will be cached."
         )
-        measurement.cache() if is_koalas(measurement) else None
-        conversion_table = (
-            to("koalas", get_conversion_table(measurement, concept_sets))
-            if is_koalas(measurement)
-            else get_conversion_table(measurement, concept_sets)
-        )
+        if is_koalas(measurement):
+            measurement.cache()
+            conversion_table = to(
+                "koalas", get_conversion_table(measurement, concept_sets)
+            )
+        else:
+            conversion_table = get_conversion_table(measurement, concept_sets)
+
         measurement = measurement.merge(
             conversion_table, on=["concept_set", "unit_source_value"]
         )

eds_scikit/biology/utils/process_measurement.py

@@ -1,8 +1,6 @@
 from datetime import datetime
 from typing import Tuple
 
-from loguru import logger
-
 from eds_scikit.utils.checks import check_columns
 from eds_scikit.utils.framework import get_framework, to
 from eds_scikit.utils.typing import DataFrame
@@ -54,10 +52,6 @@ def filter_measurement_by_date(
         df=measurement, required_columns=["measurement_date"], df_name="measurment"
     )
 
-    if "measurement_datetime" in measurement.columns:
-        measurement = measurement
-        # measurement = _select_adequate_date_column(measurement=measurement)
-
     measurement.measurement_date = measurement.measurement_date.astype("datetime64[ns]")
 
     measurement.dropna(subset=["measurement_date"], inplace=True)
@@ -171,24 +165,3 @@ def normalize_unit(measurement: DataFrame):
         measurement["unit_source_value"].str.lower().fillna("Unknown")
     )
     return measurement
-
-
-def _select_adequate_date_column(measurement: DataFrame):
-    missing_date = measurement.measurement_date.isna().sum()
-    if missing_date > 0:
-        missing_datetime = measurement.measurement_datetime.isna().sum()
-        if missing_date > missing_datetime:
-            measurement = measurement.drop(columns="measurement_date").rename(
-                columns={"measurement_datetime": "measurement_date"}
-            )
-            logger.warning(
-                "As the measurement_date column is not reliable ({} missing dates), it has been replaced by the measurement_datetime column ({} missing datetimes)",
-                missing_date,
-                missing_datetime,
-            )
-            missing_date = missing_datetime
-        else:
-            measurement = measurement.drop(columns="measurement_datetime")
-    else:
-        measurement = measurement.drop(columns="measurement_datetime")
-    return measurement

eds_scikit/biology/viz/stats_summary.py

@@ -1,3 +1,6 @@
+from eds_scikit.utils.framework import to
+
+
 def measurement_values_summary(measurement, category_cols, value_column, unit_column):
     # Count measurements with no units
 
@@ -68,6 +71,6 @@ def measurement_values_summary(measurement, category_cols, value_column, unit_co
         [*stats_summary.columns[::-1][:3], *stats_summary.columns[:-3]]
     ]
 
-    stats_summary = stats_summary.to_pandas()
+    stats_summary = to("pandas", stats_summary)
 
     return stats_summary

tests/test_biology.py

@@ -1,11 +1,16 @@
+import numpy as np
 import pytest
 
 from eds_scikit.biology import (
     ConceptsSet,
     bioclean,
+    measurement_values_summary,
     plot_biology_summary,
     prepare_measurement_table,
 )
+from eds_scikit.biology.utils.prepare_relationship import (
+    prepare_biology_relationship_table,
+)
 from eds_scikit.biology.utils.process_concepts import fetch_all_concepts_set
 from eds_scikit.biology.utils.process_units import Units
 from eds_scikit.datasets import load_biology_data
@@ -83,12 +88,17 @@ def test_units(data):
     units = Units()
 
     units.add_target_unit("g")
+
     assert units.can_be_converted("g", "mg")
     assert not units.can_be_converted("g", "l")
 
+    assert units.get_category("m/h/xxxx") == ["m", "Time", "Unkown"]
+    assert units.to_base("mm") == 0.001
+    assert np.isnan(units.to_base("xxxx"))
+
     assert abs(units.convert_unit("L", "ml") - 1000) < 1e-6
     assert abs(units.convert_unit("m/s", "m/h") - 3600.0) < 1e-6
-
+    assert np.isnan(units.convert_unit("m/s/xxxx", "m/h/s"))
     units.add_conversion("mol", "g", 10)
     assert abs(units.convert_unit("g", "mol") - 0.1) < 1e-6
 
@@ -101,16 +111,15 @@ def test_prepare_measurement(data, concepts_sets):
         convert_units=True,
         start_date=data.t_start,
         end_date=data.t_end,
-    )
-
-    measurement = prepare_measurement_table(
-        data=data,
-        concept_sets=concepts_sets,
-        convert_units=False,
-        start_date=data.t_start,
-        end_date=data.t_end,
+        get_all_terminologies=False,
     )
 
+    try:
+        prepare_biology_relationship_table(
+            data, concepts_sets, get_all_terminologies=False
+        )
+    except Exception:
+        pass
     try:
         plot_biology_summary(measurement)
     except ValueError:
@@ -125,3 +134,17 @@ def test_prepare_measurement(data, concepts_sets):
     )
 
     plot_biology_summary(measurement, "value_as_number", terminologies=["GLIMS_ANABIO"])
+
+    measurement_values_summary(
+        measurement, ["concept_set"], "value_as_number", "unit_source_value"
+    )
+
+    data.convert_to_koalas()
+
+    measurement = prepare_measurement_table(
+        data=data,
+        concept_sets=concepts_sets,
+        convert_units=False,
+        start_date=data.t_start,
+        end_date=data.t_end,
+    )