junifer 0.0.5.dev86__py3-none-any.whl → 0.0.5.dev93__py3-none-any.whl

junifer/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.5.dev86'
-__version_tuple__ = version_tuple = (0, 0, 5, 'dev86')
+__version__ = version = '0.0.5.dev93'
+__version_tuple__ = version_tuple = (0, 0, 5, 'dev93')

junifer/storage/base.py

@@ -189,7 +189,7 @@ class BaseFeatureStorage(ABC):
 
         Parameters
         ----------
-        kind : {"matrix", "timeseries", "vector"}
+        kind : {"matrix", "timeseries", "vector", "scalar_table"}
             The storage kind.
         **kwargs
             The keyword arguments.
@@ -218,6 +218,10 @@ class BaseFeatureStorage(ABC):
             )
         elif kind == "vector":
             self.store_vector(meta_md5=meta_md5, element=t_element, **kwargs)
+        elif kind == "scalar_table":
+            self.store_scalar_table(
+                meta_md5=meta_md5, element=t_element, **kwargs
+            )
 
     def store_matrix(
         self,
@@ -313,6 +317,38 @@ class BaseFeatureStorage(ABC):
             klass=NotImplementedError,
         )
 
+    def store_scalar_table(
+        self,
+        meta_md5: str,
+        element: Dict,
+        data: np.ndarray,
+        col_names: Optional[Iterable[str]] = None,
+        row_names: Optional[Iterable[str]] = None,
+        row_header_col_name: Optional[str] = "feature",
+    ) -> None:
+        """Store table with scalar values.
+
+        Parameters
+        ----------
+        meta_md5 : str
+            The metadata MD5 hash.
+        element : dict
+            The element as a dictionary.
+        data : numpy.ndarray
+            The timeseries data to store.
+        col_names : list or tuple of str, optional
+            The column labels (default None).
+        row_names : str, optional
+            The row labels (default None).
+        row_header_col_name : str, optional
+            The column name for the row header column (default "feature").
+
+        """
+        raise_error(
+            msg="Concrete classes need to implement store_scalar_table().",
+            klass=NotImplementedError,
+        )
+
     @abstractmethod
     def collect(self) -> None:
         """Collect data."""

junifer/storage/hdf5.py

@@ -56,7 +56,8 @@ def _create_chunk(
     Raises
     ------
     ValueError
-        If `kind` is not one of ['vector', 'matrix', 'timeseries'].
+        If `kind` is not one of ['vector', 'matrix', 'timeseries',
+        'scalar_table'].
 
     """
     if kind in ["vector", "matrix"]:
@@ -77,7 +78,7 @@ def _create_chunk(
             chunk_size=tuple(array_chunk_size),
             n_chunk=i_chunk,
         )
-    elif kind == "timeseries":
+    elif kind in ["timeseries", "scalar_table"]:
         out = ChunkedList(
             data=chunk_data,
             size=element_count,
@@ -86,7 +87,8 @@ def _create_chunk(
     else:
         raise_error(
             f"Invalid kind: {kind}. "
-            "Must be one of ['vector', 'matrix', 'timeseries']."
+            "Must be one of ['vector', 'matrix', 'timeseries',"
+            "'scalar_table']."
         )
     return out
 
@@ -146,7 +148,7 @@ class HDF5FeatureStorage(BaseFeatureStorage):
             uri.parent.mkdir(parents=True, exist_ok=True)
 
         # Available storage kinds
-        storage_types = ["vector", "timeseries", "matrix"]
+        storage_types = ["vector", "timeseries", "matrix", "scalar_table"]
 
         super().__init__(
             uri=uri,
@@ -169,7 +171,7 @@ class HDF5FeatureStorage(BaseFeatureStorage):
             storage.
 
         """
-        return ["matrix", "vector", "timeseries"]
+        return ["matrix", "vector", "timeseries", "scalar_table"]
 
     def _fetch_correct_uri_for_io(self, element: Optional[Dict]) -> str:
         """Return proper URI for I/O based on `element`.
@@ -508,6 +510,26 @@ class HDF5FeatureStorage(BaseFeatureStorage):
             columns = hdf_data["column_headers"]
             # Convert data from 3D to 2D
             reshaped_data = np.concatenate(all_data, axis=0)
+        elif hdf_data["kind"] == "scalar_table":
+            # Create dictionary for aggregating index data
+            element_idx = defaultdict(list)
+            all_data = []
+            for idx, element in enumerate(hdf_data["element"]):
+                # Get row count for the element
+                t_data = hdf_data["data"][idx]
+                all_data.append(t_data)
+                n_rows = len(hdf_data["row_headers"])
+                # Set rows for the index
+                for key, val in element.items():
+                    element_idx[key].extend([val] * n_rows)
+                # Add extra column for row header column name
+                element_idx[hdf_data["row_header_column_name"]].extend(
+                    hdf_data["row_headers"]
+                )
+            # Set column headers for dataframe
+            columns = hdf_data["column_headers"]
+            # Convert data from 3D to 2D
+            reshaped_data = np.concatenate(all_data, axis=0)
 
         # Create dataframe for index
         idx_df = pd.DataFrame(data=element_idx)  # type: ignore
@@ -643,7 +665,7 @@ class HDF5FeatureStorage(BaseFeatureStorage):
 
         Parameters
         ----------
-        kind : {"matrix", "vector", "timeseries"}
+        kind : {"matrix", "vector", "timeseries", "scalar_table"}
             The storage kind.
         meta_md5 : str
             The metadata MD5 hash.
@@ -739,8 +761,8 @@ class HDF5FeatureStorage(BaseFeatureStorage):
             )
 
             t_data = stored_data["data"]
-            if kind == "timeseries":
-                t_data.append(data)
+            if kind in ["timeseries", "scalar_table"]:
+                t_data += data
             else:
                 t_data = np.concatenate((t_data, data), axis=-1)
             # Existing entry; append to existing
@@ -921,6 +943,43 @@ class HDF5FeatureStorage(BaseFeatureStorage):
             row_header_column_name="timepoint",
         )
 
+    def store_scalar_table(
+        self,
+        meta_md5: str,
+        element: Dict,
+        data: np.ndarray,
+        col_names: Optional[Iterable[str]] = None,
+        row_names: Optional[Iterable[str]] = None,
+        row_header_col_name: Optional[str] = "feature",
+    ) -> None:
+        """Store table with scalar values.
+
+        Parameters
+        ----------
+        meta_md5 : str
+            The metadata MD5 hash.
+        element : dict
+            The element as a dictionary.
+        data : numpy.ndarray
+            The scalar table data to store.
+        col_names : list or tuple of str, optional
+            The column labels (default None).
+        row_names : str, optional
+            The row labels (default None).
+        row_header_col_name : str, optional
+            The column name for the row header column (default "feature").
+
+        """
+        self._store_data(
+            kind="scalar_table",
+            meta_md5=meta_md5,
+            element=[element],  # convert to list
+            data=[data],  # convert to list
+            column_headers=col_names,
+            row_headers=row_names,
+            row_header_column_name=row_header_col_name,
+        )
+
     def collect(self) -> None:
         """Implement data collection.
 
@@ -1029,7 +1088,7 @@ class HDF5FeatureStorage(BaseFeatureStorage):
                     kind = static_data["kind"]
 
                 # Append the "dynamic" data
-                if kind == "timeseries":
+                if kind in ["timeseries", "scalar_table"]:
                     chunk_data.extend(t_data["data"])
                 else:
                     chunk_data.append(t_data["data"])

junifer/storage/tests/test_hdf5.py

@@ -25,7 +25,12 @@ from junifer.storage.utils import (
 def test_get_valid_inputs() -> None:
     """Test valid inputs."""
     storage = HDF5FeatureStorage(uri="/tmp")
-    assert storage.get_valid_inputs() == ["matrix", "vector", "timeseries"]
+    assert storage.get_valid_inputs() == [
+        "matrix",
+        "vector",
+        "timeseries",
+        "scalar_table",
+    ]
 
 
 def test_single_output(tmp_path: Path) -> None:
@@ -808,7 +813,7 @@ def test_store_timeseries(tmp_path: Path) -> None:
     data = np.array([[10], [20], [30], [40], [50]])
     col_names = ["signal"]
 
-    # Store vector
+    # Store timeseries
     storage.store_timeseries(
         meta_md5=meta_md5,
         element=element_to_store,
@@ -822,6 +827,53 @@ def test_store_timeseries(tmp_path: Path) -> None:
     assert_array_equal(read_df.values, data)
 
 
+def test_store_scalar_table(tmp_path: Path) -> None:
+    """Test scalar table store.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        The path to the test directory.
+
+    """
+    uri = tmp_path / "test_store_scalar_table.hdf5"
+    storage = HDF5FeatureStorage(uri=uri)
+    # Metadata to store
+    element = {"subject": "test"}
+    meta = {
+        "element": element,
+        "dependencies": ["numpy"],
+        "marker": {"name": "brainprint"},
+        "type": "FreeSurfer",
+    }
+    # Process the metadata
+    meta_md5, meta_to_store, element_to_store = process_meta(meta)
+    # Store metadata
+    storage.store_metadata(
+        meta_md5=meta_md5, element=element_to_store, meta=meta_to_store
+    )
+
+    # Data to store
+    data = np.array([[10, 20], [30, 40], [50, 60]])
+    col_names = ["roi1", "roi2"]
+    row_names = ["ev1", "ev2", "ev3"]
+
+    # Store timeseries
+    storage.store_scalar_table(
+        meta_md5=meta_md5,
+        element=element_to_store,
+        data=data,
+        col_names=col_names,
+        row_names=row_names,
+        row_header_col_name="eigenvalue",
+    )
+
+    # Read into dataframe
+    read_df = storage.read_df(feature_md5=meta_md5)
+    # Check if data are equal
+    assert_array_equal(read_df.values, data)
+
+
 def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
     """Create data to store.
 
@@ -854,13 +906,19 @@ def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
             "col_names": [f"col-{i}" for i in range(10)],
             "matrix_kind": "full",
         }
-    elif kind == "timeseries":
+    elif kind in "timeseries":
         data_to_store = {
             "data": np.arange(20).reshape(2, 10),
             "col_names": [f"col-{i}" for i in range(10)],
         }
-    else:
-        raise ValueError(f"Unknown kind {kind}.")
+    elif kind in "scalar_table":
+        data_to_store = {
+            "data": np.arange(50).reshape(5, 10),
+            "row_names": [f"row-{i}" for i in range(5)],
+            "col_names": [f"col-{i}" for i in range(10)],
+            "row_header_col_name": "row",
+        }
+
     for i in range(n_elements):
         element = {"subject": f"sub-{i // 2}", "session": f"ses-{i % 2}"}
         meta = {
@@ -903,6 +961,7 @@ def _create_data_to_store(n_elements: int, kind: str) -> Tuple[str, Dict]:
         (10, 3, "matrix"),
         (10, 5, "matrix"),
         (10, 5, "timeseries"),
+        (10, 5, "scalar_table"),
     ],
 )
 def test_multi_output_store_and_collect(
@@ -930,21 +989,20 @@ def test_multi_output_store_and_collect(
     meta_md5, all_data = _create_data_to_store(n_elements, kind)
 
     for t_data in all_data:
-        # Store metadata for tables
+        # Store metadata
         storage.store_metadata(
             meta_md5=meta_md5,
             element=t_data["element"],
             meta=t_data["meta"],
         )
+        # Store data
         if kind == "vector":
-            # Store tables
             storage.store_vector(
                 meta_md5=meta_md5,
                 element=t_data["element"],
                 **t_data["data"],
             )
         elif kind == "matrix":
-            # Store tables
             storage.store_matrix(
                 meta_md5=meta_md5,
                 element=t_data["element"],
@@ -956,11 +1014,17 @@ def test_multi_output_store_and_collect(
                 element=t_data["element"],
                 **t_data["data"],
             )
+        elif kind == "scalar_table":
+            storage.store_scalar_table(
+                meta_md5=meta_md5,
+                element=t_data["element"],
+                **t_data["data"],
+            )
     # Check that base URI does not exist yet
     assert not uri.exists()
 
     for t_data in all_data:
-        # Convert element to preifx
+        # Convert element to prefix
         prefix = element_to_prefix(t_data["element"])
         # URIs for data storage
         elem_uri = uri.parent / f"{prefix}{uri.name}"
@@ -977,7 +1041,7 @@ def test_multi_output_store_and_collect(
     # Check that base URI exists now
     assert uri.exists()
 
-    # # Read unified metadata
+    # Read unified metadata
     read_unified_meta = storage.list_features()
     assert meta_md5 in read_unified_meta
 
@@ -989,6 +1053,10 @@ def test_multi_output_store_and_collect(
         data_size = np.sum([x["data"]["data"].shape[0] for x in all_data])
         assert len(all_df) == data_size
         idx_names = [x for x in all_df.index.names if x != "timepoint"]
+    elif kind == "scalar_table":
+        data_size = np.sum([x["data"]["data"].shape[0] for x in all_data])
+        assert len(all_df) == data_size
+        idx_names = [x for x in all_df.index.names if x != "row"]
     else:
         assert len(all_df) == len(all_data)
         idx_names = all_df.index.names
@@ -1013,6 +1081,10 @@ def test_multi_output_store_and_collect(
             assert_array_equal(t_series.values, t_data["data"]["data"])
             series_names = t_series.columns.values.tolist()
             assert series_names == t_data["data"]["col_names"]
+        elif kind == "scalar_table":
+            assert_array_equal(t_series.values, t_data["data"]["data"])
+            series_names = t_series.columns.values.tolist()
+            assert series_names == t_data["data"]["col_names"]
 
 
 def test_collect_error_single_output() -> None:

{junifer-0.0.5.dev86.dist-info → junifer-0.0.5.dev93.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.5.dev86
+Version: 0.0.5.dev93
 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-0.0.5.dev86.dist-info → junifer-0.0.5.dev93.dist-info}/RECORD

@@ -1,5 +1,5 @@
 junifer/__init__.py,sha256=x1UR2jUcrUdm2HNl-3Qvyi4UUrU6ms5qm2qcmNY7zZk,391
-junifer/_version.py,sha256=tHlKxu4A7NZdSkP4AlDO2Vd1oZbG-OnTzclmDpcl29M,426
+junifer/_version.py,sha256=OuEXOAHKhbHnm8jc8By5AoScd2qmQjT4HRDoRe1JlYM,426
 junifer/stats.py,sha256=jN22_qFvWYBU9ZIMnCSzN4iOscWnWrcrUPIdLeDkV64,6163
 junifer/api/__init__.py,sha256=pSj8V8tmwOAQ3sshWJfRfB-n3z5bcJj3pHOBX4-8ONc,251
 junifer/api/cli.py,sha256=53pews3mXkJ7DUDSkV51PbitYnuVAdQRkWG-gjO08Uw,16142
@@ -225,12 +225,12 @@ junifer/preprocess/warping/_fsl_warper.py,sha256=eELmS44LYYANQaWR3VDKv8iwpEC2qnF
 junifer/preprocess/warping/space_warper.py,sha256=BW7ymZdr4h7lJRtPLi3RT7qwgmu-HFJFqzZNUl341YU,6589
 junifer/preprocess/warping/tests/test_space_warper.py,sha256=hHF97XUrMeAu8pIPBUrqD77PijbSv5_dAj9-Zte7UZM,5622
 junifer/storage/__init__.py,sha256=5ve0Vy1stGmn9iQv0c4w-76-sg-gFqZE2IlRlJhFWpQ,337
-junifer/storage/base.py,sha256=UxDvj81gSmqqHspbSs1X_i9HvW5wXysDippI7HWM7aM,9654
-junifer/storage/hdf5.py,sha256=oxdPuCG0hxzSDNH0uHnYFwVr_wp0g9yvgZf8bv3PkJM,35631
+junifer/storage/base.py,sha256=X4AYx21tW1MGDhiMA8AFilbzbrMbDzcuzdAuMjM4Az0,10836
+junifer/storage/hdf5.py,sha256=BVvojmiRNICOcxrmqpDdIsBT94wqLNQ6pk6MGLaHmXo,37951
 junifer/storage/pandas_base.py,sha256=Qu3Az-xEaFftsiZwordONnOF2UBO1JgkrP8tmxhXUN4,7473
 junifer/storage/sqlite.py,sha256=P-eKlrptY-vRxA4mDAC5UyJzqCWNC2C_rgKlZFGjiKg,21244
 junifer/storage/utils.py,sha256=I-is6bGE29bNwlqv2P8B5QN2zAnY7A7fm8Y-AwMJ0MU,7258
-junifer/storage/tests/test_hdf5.py,sha256=ACTGcO6p9iP_HVGBK9RJ4wF3sixR_aFewSL8PK8OBSI,29338
+junifer/storage/tests/test_hdf5.py,sha256=PybSXK0VA1UUFve1xqV-_Wqc7UyCDZGj_C58Z48c6tc,31512
 junifer/storage/tests/test_pandas_base.py,sha256=y_TfUGpuXkj_39yVon3rMDxMeBrZXs58ZW6OSty5LNw,4058
 junifer/storage/tests/test_sqlite.py,sha256=JPfE6r34o86XkKaB6yjMVmO_2vUV40DjsaHICagUtjk,28318
 junifer/storage/tests/test_storage_base.py,sha256=YzgfspuggzXejyPIoRCPST3ZzH9Pi7dgl0IHN7kynXM,3071
@@ -253,10 +253,10 @@ junifer/utils/logging.py,sha256=furcU3XIUpUvnpe4PEwzWWIWgmH4j2ZA4MQdvSGWjj0,9216
 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=l8oo-AiBV7H6_IzlsNcj__cLeZBUvgIGoaMszD9VaJg,7754
-junifer-0.0.5.dev86.dist-info/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
-junifer-0.0.5.dev86.dist-info/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
-junifer-0.0.5.dev86.dist-info/METADATA,sha256=czsUrw6gz_iDxuAzASxfrFxc1EZzRwLbZliDG4dE0Cc,8234
-junifer-0.0.5.dev86.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-junifer-0.0.5.dev86.dist-info/entry_points.txt,sha256=DxFvKq0pOqRunAK0FxwJcoDfV1-dZvsFDpD5HRqSDhw,48
-junifer-0.0.5.dev86.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
-junifer-0.0.5.dev86.dist-info/RECORD,,
+junifer-0.0.5.dev93.dist-info/AUTHORS.rst,sha256=rmULKpchpSol4ExWFdm-qu4fkpSZPYqIESVJBZtGb6E,163
+junifer-0.0.5.dev93.dist-info/LICENSE.md,sha256=MqCnOBu8uXsEOzRZWh9EBVfVz-kE9NkXcLCrtGXo2yU,34354
+junifer-0.0.5.dev93.dist-info/METADATA,sha256=GPQBJL5Fvtivl1q6VYeAV6eoIDVCjubyMZCizh3mn9k,8234
+junifer-0.0.5.dev93.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+junifer-0.0.5.dev93.dist-info/entry_points.txt,sha256=DxFvKq0pOqRunAK0FxwJcoDfV1-dZvsFDpD5HRqSDhw,48
+junifer-0.0.5.dev93.dist-info/top_level.txt,sha256=4bAq1R2QFQ4b3hohjys2JBvxrl0GKk5LNFzYvz9VGcA,8
+junifer-0.0.5.dev93.dist-info/RECORD,,