junifer 0.0.7.dev105__py3-none-any.whl → 0.0.7.dev111__py3-none-any.whl

junifer/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.7.dev105'
-__version_tuple__ = version_tuple = (0, 0, 7, 'dev105')
+__version__ = version = '0.0.7.dev111'
+__version_tuple__ = version_tuple = (0, 0, 7, 'dev111')

junifer/onthefly/read_transform.py

@@ -5,6 +5,7 @@
 
 from typing import Optional
 
+import numpy as np
 import pandas as pd
 
 from ..typing import StorageLike
@@ -19,6 +20,7 @@ def read_transform(
     transform: str,
     feature_name: Optional[str] = None,
     feature_md5: Optional[str] = None,
+    nan_policy: Optional[str] = "bypass",
     transform_args: Optional[tuple] = None,
     transform_kw_args: Optional[dict] = None,
 ) -> pd.DataFrame:
@@ -35,6 +37,16 @@ def read_transform(
         Name of the feature to read (default None).
     feature_md5 : str, optional
         MD5 hash of the feature to read (default None).
+    nan_policy : str, optional
+        The policy to handle NaN values (default "ignore").
+        Options are:
+
+        * "bypass": Do nothing and pass NaN values to the transform function.
+        * "drop_element": Drop (skip) elements with NaN values.
+        * "drop_rows": Drop (skip) rows with NaN values.
+        * "drop_columns": Drop (skip) columns with NaN values.
+        * "drop_symmetric": Drop (skip) symmetric pairs with NaN values.
+
     transform_args : tuple, optional
         The positional arguments for the callable of ``transform``
         (default None).
@@ -47,6 +59,18 @@ def read_transform(
     pandas.DataFrame
         The transformed feature as a dataframe.
 
+    Raises
+    ------
+    ValueError
+        If ``nan_policy`` is invalid or
+        if *package* is invalid.
+    RuntimeError
+        If *package* is ``bctpy`` and stored data kind is not ``matrix``.
+    ImportError
+        If ``bctpy`` cannot be imported.
+    AttributeError
+        If *function* to be invoked in invalid.
+
     Notes
     -----
     This function has been only tested for:
@@ -63,6 +87,18 @@ def read_transform(
     transform_args = transform_args or ()
     transform_kw_args = transform_kw_args or {}
 
+    if nan_policy not in [
+        "bypass",
+        "drop_element",
+        "drop_rows",
+        "drop_columns",
+        "drop_symmetric",
+    ]:
+        raise_error(
+            f"Unknown nan_policy: {nan_policy}",
+            klass=ValueError,
+        )
+
     # Read storage
     stored_data = storage.read(
         feature_name=feature_name, feature_md5=feature_md5
@@ -106,22 +142,52 @@ def read_transform(
         except AttributeError as err:
             raise_error(msg=str(err), klass=AttributeError)
 
-        # Apply function and store subject-wise
+        # Apply function and store element-wise
         output_list = []
+        element_list = []
         logger.debug(
             f"Computing '{package}.{func_str}' for feature "
             f"{feature_name or feature_md5} ..."
         )
-        for subject in range(stored_data["data"].shape[2]):
+        for i_element, element in enumerate(stored_data["element"]):
+            t_data = stored_data["data"][:, :, i_element]
+            has_nan = np.isnan(np.min(t_data))
+            if nan_policy == "drop_element" and has_nan:
+                logger.debug(
+                    f"Skipping element {element} due to NaN values ..."
+                )
+                continue
+            elif nan_policy == "drop_rows" and has_nan:
+                logger.debug(
+                    f"Skipping rows with NaN values in element {element} ..."
+                )
+                t_data = t_data[~np.isnan(t_data).any(axis=1)]
+            elif nan_policy == "drop_columns" and has_nan:
+                logger.debug(
+                    f"Skipping columns with NaN values in element {element} "
+                    "..."
+                )
+                t_data = t_data[:, ~np.isnan(t_data).any(axis=0)]
+            elif nan_policy == "drop_symmetric":
+                logger.debug(
+                    f"Skipping pairs of rows/columns with NaN values in "
+                    f"element {element}..."
+                )
+                good_rows = ~np.isnan(t_data).any(axis=1)
+                good_columns = ~np.isnan(t_data).any(axis=0)
+                good_idx = np.logical_and(good_rows, good_columns)
+                t_data = t_data[good_idx][:, good_idx]
+
             output = func(
-                stored_data["data"][:, :, subject],
+                t_data,
                 *transform_args,
                 **transform_kw_args,
             )
             output_list.append(output)
+            element_list.append(element)
 
         # Create dataframe for index
-        idx_df = pd.DataFrame(data=stored_data["element"])
+        idx_df = pd.DataFrame(data=element_list)
         # Create multiindex from dataframe
         logger.debug(
             "Generating pandas.MultiIndex for feature "

junifer/onthefly/tests/test_read_transform.py

@@ -64,6 +64,36 @@ def matrix_storage(tmp_path: Path) -> HDF5FeatureStorage:
     return storage
 
 
+@pytest.fixture
+def matrix_storage_with_nan(tmp_path: Path) -> HDF5FeatureStorage:
+    """Return a HDF5FeatureStorage with matrix data.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+
+    """
+    storage = HDF5FeatureStorage(tmp_path / "matrix_store_nan.hdf5")
+    data = np.arange(36).reshape(3, 3, 4).astype(float)
+    data[1, 1, 2] = np.nan
+    data[1, 2, 2] = np.nan
+    for i in range(4):
+        storage.store(
+            kind="matrix",
+            meta={
+                "element": {"subject": f"test{i + 1}"},
+                "dependencies": [],
+                "marker": {"name": "matrix"},
+                "type": "BOLD",
+            },
+            data=data[:, :, i],
+            col_names=["f1", "f2", "f3"],
+            row_names=["g1", "g2", "g3"],
+        )
+    return storage
+
+
 def test_incorrect_package(matrix_storage: HDF5FeatureStorage) -> None:
     """Test error check for incorrect package name.
 
@@ -176,3 +206,57 @@ def test_bctpy_function(
         )
         assert "Computing" in caplog.text
         assert "Generating" in caplog.text
+
+
+@pytest.mark.parametrize(
+    "nan_policy, error_msg",
+    [
+        ("drop_element", None),
+        ("drop_rows", "square"),
+        ("drop_columns", "square"),
+        ("drop_symmetric", None),
+        ("bypass", "NaNs"),
+        ("wrong", "Unknown"),
+    ],
+)
+def test_bctpy_nans(
+    matrix_storage_with_nan: HDF5FeatureStorage,
+    caplog: pytest.LogCaptureFixture,
+    nan_policy: str,
+    error_msg: str,
+) -> None:
+    """Test working function of bctpy.
+
+    Parameters
+    ----------
+    matrix_storage_with_nan : HDF5FeatureStorage
+        The HDF5FeatureStorage with matrix data, as fixture.
+    caplog : pytest.LogCaptureFixture
+        The pytest.LogCaptureFixture object.
+    nan_policy : str
+        The NAN policy to test.
+    error_msg : str
+        The expected error message snippet. If None, no error should be raised.
+
+    """
+    # Skip test if import fails
+    pytest.importorskip("bct")
+
+    with caplog.at_level(logging.DEBUG):
+        if error_msg is None:
+            read_transform(
+                storage=matrix_storage_with_nan,  # type: ignore
+                feature_name="BOLD_matrix",
+                transform="bctpy_eigenvector_centrality_und",
+                nan_policy=nan_policy,
+            )
+            assert "Computing" in caplog.text
+            assert "Generating" in caplog.text
+        else:
+            with pytest.raises(ValueError, match=error_msg):
+                read_transform(
+                    storage=matrix_storage_with_nan,  # type: ignore
+                    feature_name="BOLD_matrix",
+                    transform="bctpy_eigenvector_centrality_und",
+                    nan_policy=nan_policy,
+                )

{junifer-0.0.7.dev105.dist-info → junifer-0.0.7.dev111.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: junifer
-Version: 0.0.7.dev105
+Version: 0.0.7.dev111
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

{junifer-0.0.7.dev105.dist-info → junifer-0.0.7.dev111.dist-info}/RECORD

@@ -1,6 +1,6 @@
 junifer/__init__.py,sha256=2McgH1yNue6Z1V26-uN_mfMjbTcx4CLhym-DMBl5xA4,266
 junifer/__init__.pyi,sha256=SsTvgq2Dod6UqJN96GH1lCphH6hJQQurEJHGNhHjGUI,508
-junifer/_version.py,sha256=jFH3nrzs5AspealBCIydRQVFvENTPE2XjxPHECcRoME,528
+junifer/_version.py,sha256=LnYX032f40evsucLrn5L758qPtoWuq5rSV96EwT5oTA,528
 junifer/conftest.py,sha256=PWYkkRDU8ly2lYwv7VBKMHje4et6HX7Yey3Md_I2KbA,613
 junifer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 junifer/stats.py,sha256=e9aaagMGtgpRfW3Wdpz9ocpnYld1IWylCDcjFUgX9Mk,6225
@@ -237,8 +237,8 @@ junifer/markers/tests/test_parcel_aggregation.py,sha256=04OqtY_Z-KW4W1jU5K6GeWnL
 junifer/markers/tests/test_sphere_aggregation.py,sha256=HPaLD6xKdewTt0iANz3nYOD7ZI-g7BqMTiRdV-4sM8M,10669
 junifer/onthefly/__init__.py,sha256=TA6tPuw54ynDlumb9Ii-2p59hw2rGoCMe1-vQ89JzZ8,238
 junifer/onthefly/_brainprint.py,sha256=-BswaAV9SLHU8mmWJ2KbPL7FgERJzIQIbSdV-NYiiYI,3802
-junifer/onthefly/read_transform.py,sha256=JfTJIiZnautkJ6DzsjeWQ7AEDRHV4omfinvDkow3FFM,4272
-junifer/onthefly/tests/test_read_transform.py,sha256=Ed6gtj8bsD11fe0Y1AxG2JndtITDSBje4g3hx3wkbAo,4718
+junifer/onthefly/read_transform.py,sha256=pUwwsO4oBwq6u4ybRpnQ5s6MujtwD_1AOMv-RdavAFg,6690
+junifer/onthefly/tests/test_read_transform.py,sha256=U8BwImmgH9e2eA_WXVWyKgGzFQNEoD0teCNv2Udlhok,7246
 junifer/pipeline/__init__.py,sha256=rxKQGRwc6_sts1KhVIcVVpuXeiFABf11mQQ2h5jgA3U,194
 junifer/pipeline/__init__.pyi,sha256=hhcvNcABhtLaUQiZdTjo5sMWC3rtDkwVshL0sxD5JAE,399
 junifer/pipeline/marker_collection.py,sha256=1Kmf5f0E2MFhDpO9OBui046b_6h1u9U64AdEqrxso-o,5377
@@ -324,10 +324,10 @@ junifer/utils/tests/test_config.py,sha256=7ltIXuwb_W4Mv_1dxQWyiyM10XgUAfsWKV6D_i
 junifer/utils/tests/test_fs.py,sha256=WQS7cKlKEZ742CIuiOYYpueeAhY9PqlastfDVpVVtvE,923
 junifer/utils/tests/test_helpers.py,sha256=k5qqfxK8dFyuewTJyR1Qn6-nFaYNuVr0ysc18bfPjyU,929
 junifer/utils/tests/test_logging.py,sha256=W4tFKmaf8_CxnWZ-o_-XxM7DQbhGG18RsLZJk8bZelI,8163
-junifer-0.0.7.dev105.dist-info/licenses/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
-junifer-0.0.7.dev105.dist-info/licenses/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
-junifer-0.0.7.dev105.dist-info/METADATA,sha256=y9qwZWakS8Oc_XurJ3dN1hQ-ndxPyy5BdikbsZsaIG8,8388
-junifer-0.0.7.dev105.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-junifer-0.0.7.dev105.dist-info/entry_points.txt,sha256=6O8ru0BP-SP7YMUZiizFNoaZ2HvJpadO2G7nKk4PwjI,48
-junifer-0.0.7.dev105.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
-junifer-0.0.7.dev105.dist-info/RECORD,,
+junifer-0.0.7.dev111.dist-info/licenses/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
+junifer-0.0.7.dev111.dist-info/licenses/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
+junifer-0.0.7.dev111.dist-info/METADATA,sha256=ZPvs0K5JekuTwe2VzukElpA4wD4nwWpYjOFqENx3AcQ,8388
+junifer-0.0.7.dev111.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+junifer-0.0.7.dev111.dist-info/entry_points.txt,sha256=6O8ru0BP-SP7YMUZiizFNoaZ2HvJpadO2G7nKk4PwjI,48
+junifer-0.0.7.dev111.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
+junifer-0.0.7.dev111.dist-info/RECORD,,