pandas 3.0 compatibility (#471)

Make library compatible with pandas 3.0.

Closes #469.

Author: dweindl

petab/v1/conditions.py

@@ -111,7 +111,7 @@ def get_parametric_overrides(condition_df: pd.DataFrame) -> list[str]:
     result = []
 
     for column in constant_parameters:
-        if np.issubdtype(condition_df[column].dtype, np.number):
+        if not pd.api.types.is_string_dtype(condition_df[column].dtype):
             continue
 
         floatified = condition_df.loc[:, column].apply(core.to_float_if_float)

petab/v1/lint.py

@@ -129,7 +129,7 @@ def check_condition_df(
         )
 
     for column_name in req_cols:
-        if not np.issubdtype(df[column_name].dtype, np.number):
+        if pd.api.types.is_string_dtype(df[column_name].dtype):
             assert_no_leading_trailing_whitespace(
                 df[column_name].values, column_name
             )
@@ -173,14 +173,14 @@ def check_measurement_df(
     _check_df(df, MEASUREMENT_DF_REQUIRED_COLS, "measurement")
 
     for column_name in MEASUREMENT_DF_REQUIRED_COLS:
-        if not np.issubdtype(df[column_name].dtype, np.number):
+        if pd.api.types.is_string_dtype(df[column_name].dtype):
             assert_no_leading_trailing_whitespace(
                 df[column_name].values, column_name
             )
 
     for column_name in MEASUREMENT_DF_OPTIONAL_COLS:
-        if column_name in df and not np.issubdtype(
-            df[column_name].dtype, np.number
+        if column_name in df and pd.api.types.is_string_dtype(
+            df[column_name].dtype
         ):
             assert_no_leading_trailing_whitespace(
                 df[column_name].values, column_name
@@ -243,7 +243,7 @@ def check_parameter_df(
     check_ids(df.index.values, kind="parameter")
 
     for column_name in PARAMETER_DF_REQUIRED_COLS[1:]:  # 0 is PARAMETER_ID
-        if not np.issubdtype(df[column_name].dtype, np.number):
+        if pd.api.types.is_string_dtype(df[column_name].dtype):
             assert_no_leading_trailing_whitespace(
                 df[column_name].values, column_name
             )
@@ -304,14 +304,14 @@ def check_observable_df(observable_df: pd.DataFrame) -> None:
     check_ids(observable_df.index.values, kind="observable")
 
     for column_name in OBSERVABLE_DF_REQUIRED_COLS[1:]:
-        if not np.issubdtype(observable_df[column_name].dtype, np.number):
+        if pd.api.types.is_string_dtype(observable_df[column_name].dtype):
             assert_no_leading_trailing_whitespace(
                 observable_df[column_name].values, column_name
             )
 
     for column_name in OBSERVABLE_DF_OPTIONAL_COLS:
-        if column_name in observable_df and not np.issubdtype(
-            observable_df[column_name].dtype, np.number
+        if column_name in observable_df and pd.api.types.is_string_dtype(
+            observable_df[column_name].dtype
         ):
             assert_no_leading_trailing_whitespace(
                 observable_df[column_name].values, column_name

petab/v1/visualize/data_overview.py

@@ -69,7 +69,7 @@ def get_data_per_observable(measurement_df: pd.DataFrame) -> pd.DataFrame:
         my_measurements[PREEQUILIBRATION_CONDITION_ID] = (
             my_measurements[PREEQUILIBRATION_CONDITION_ID]
             .astype("object")
-            .fillna("", inplace=True)
+            .fillna("")
         )
         index.append(PREEQUILIBRATION_CONDITION_ID)
 

pyproject.toml

@@ -12,7 +12,7 @@ description = "Parameter estimation tabular data"
 requires-python = ">=3.11"
 dependencies = [
     "numpy>=1.15.1",
-    "pandas>=1.2.0,<3",
+    "pandas>=1.2.0",
     "python-libsbml>=5.17.0",
     "sympy",
     "colorama",

tests/v1/test_petab.py

@@ -508,7 +508,7 @@ def test_flatten_timepoint_specific_output_overrides():
     )
 
     pd.testing.assert_frame_equal(
-        problem.observable_df, observable_df_expected
+        problem.observable_df, observable_df_expected, check_dtype=False
     )
     pd.testing.assert_frame_equal(
         problem.measurement_df, measurement_df_expected