ngio 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

ngio/hcs/_plate.py

@@ -200,7 +200,7 @@ class OmeZarrWell:
         )
 
 
-def _buil_extras(paths: Collection[str]) -> list[dict[str, str]]:
+def _build_extras(paths: Collection[str]) -> list[dict[str, str]]:
     """Build the extras for the images.
 
     Args:
@@ -1021,7 +1021,7 @@ class OmeZarrPlate:
                 if 'lazy', the table will be loaded as a lazy frame.
         """
         images = self.get_images(acquisition=acquisition)
-        extras = _buil_extras(images.keys())
+        extras = _build_extras(images.keys())
         return concatenate_image_tables(
             images=images.values(),
             extras=extras,
@@ -1055,7 +1055,7 @@ class OmeZarrPlate:
                 if 'lazy', the table will be loaded as a lazy frame.
         """
         images = self.get_images(acquisition=acquisition)
-        extras = _buil_extras(images.keys())
+        extras = _build_extras(images.keys())
         return concatenate_image_tables_as(
             images=images.values(),
             extras=extras,
@@ -1088,7 +1088,7 @@ class OmeZarrPlate:
                 if 'lazy', the table will be loaded as a lazy frame.
         """
         images = await self.get_images_async(acquisition=acquisition)
-        extras = _buil_extras(images.keys())
+        extras = _build_extras(images.keys())
         return await concatenate_image_tables_async(
             images=images.values(),
             extras=extras,
@@ -1122,7 +1122,7 @@ class OmeZarrPlate:
                 if 'lazy', the table will be loaded as a lazy frame.
         """
         images = await self.get_images_async(acquisition=acquisition)
-        extras = _buil_extras(images.keys())
+        extras = _build_extras(images.keys())
         return await concatenate_image_tables_as_async(
             images=images.values(),
             extras=extras,

ngio/tables/_tables_container.py

@@ -97,7 +97,7 @@ class Table(Protocol):
 
         Either a handler or a backend must be provided.
 
-        If the hanlder in none it will be inferred from the backend.
+        If the handler in none it will be inferred from the backend.
         If the backend is none, it will be inferred from the group attrs
         """
         ...

ngio/tables/backends/__init__.py

@@ -1,7 +1,7 @@
 """Ngio Tables backend implementations."""
 
 from ngio.tables.backends._abstract_backend import AbstractTableBackend, BackendMeta
-from ngio.tables.backends._anndata import AnnDataBackend
+from ngio.tables.backends._anndata import AnnDataBackend, AnnDataBackendV1
 from ngio.tables.backends._csv import CsvTableBackend
 from ngio.tables.backends._json import JsonTableBackend
 from ngio.tables.backends._parquet import ParquetTableBackend
@@ -31,6 +31,7 @@ from ngio.tables.backends._utils import (
 __all__ = [
     "AbstractTableBackend",
     "AnnDataBackend",
+    "AnnDataBackendV1",
     "BackendMeta",
     "CsvTableBackend",
     "DefaultTableBackend",

ngio/tables/backends/_anndata.py

@@ -75,3 +75,13 @@ class AnnDataBackend(AbstractTableBackend):
             index_key=self.index_key,
         )
         self.write_from_anndata(anndata)
+
+
+
+class AnnDataBackendV1(AnnDataBackend):
+    """A wrapper for the AnnData backend that for backwards compatibility."""
+
+    @staticmethod
+    def backend_name() -> str:
+        """Return the name of the backend."""
+        return "anndata_v1"

ngio/tables/backends/_table_backends.py

@@ -7,7 +7,7 @@ from pandas import DataFrame
 from polars import DataFrame as PolarsDataFrame
 from polars import LazyFrame
 
-from ngio.tables.backends._anndata import AnnDataBackend
+from ngio.tables.backends._anndata import AnnDataBackend, AnnDataBackendV1
 from ngio.tables.backends._csv import CsvTableBackend
 from ngio.tables.backends._json import JsonTableBackend
 from ngio.tables.backends._parquet import ParquetTableBackend
@@ -213,7 +213,8 @@ class ImplementedTableBackends:
                 )
 
 
-ImplementedTableBackends().add_backend(AnnDataBackend, aliases=["anndata_v1"])
+ImplementedTableBackends().add_backend(AnnDataBackend)
+ImplementedTableBackends().add_backend(AnnDataBackendV1)
 ImplementedTableBackends().add_backend(
     JsonTableBackend, aliases=["experimental_json_v1"]
 )

ngio/tables/v1/_condition_table.py

@@ -23,7 +23,7 @@ class ConditionTableV1(AbstractBaseTable):
     The condition table is a generic table that does not
     have a specific definition.
 
-    It is used to store informations about the particular conditions
+    It is used to store information about the particular conditions
     used to generate the data.
     - How much drug was used in the experiment
     - What treatment was used

ngio/utils/__init__.py

@@ -3,7 +3,11 @@
 import os
 
 from ngio.common._common_types import ArrayLike
-from ngio.utils._datasets import download_ome_zarr_dataset, list_ome_zarr_datasets
+from ngio.utils._datasets import (
+    download_ome_zarr_dataset,
+    list_ome_zarr_datasets,
+    print_datasets_infos,
+)
 from ngio.utils._errors import (
     NgioFileExistsError,
     NgioFileNotFoundError,
@@ -34,13 +38,13 @@ __all__ = [
     "NgioValueError",
     "StoreOrGroup",
     "ZarrGroupHandler",
-    # Datasets
+    # Other
     "download_ome_zarr_dataset",
-    # Fractal
     "fractal_fsspec_store",
     "list_ome_zarr_datasets",
     # Logger
     "ngio_logger",
     "open_group_wrapper",
+    "print_datasets_infos",
     "set_logger_level",
 ]

ngio/utils/_datasets.py

@@ -1,35 +1,124 @@
 """Download testing OME-Zarr datasets."""
 
+import shutil
 from pathlib import Path
+from typing import Literal
 
 import pooch
 
 from ngio.utils._errors import NgioValueError
 
+
+class UnzipAndRename(pooch.Unzip):
+    """Unzip and rename the extracted directory."""
+
+    def __init__(
+        self,
+        extract_dir: str = "",
+        out_name: str = "ome-zarr.zarr",
+        re_unzip: bool = True,
+        **kwargs,
+    ):
+        super().__init__(extract_dir=extract_dir, **kwargs)
+        self.out_name = out_name
+        self.re_unzip = re_unzip
+
+    def output_file(self) -> Path:
+        """Return the output file path."""
+        if self.extract_dir is None:
+            raise NgioValueError("extract_dir must be set for UnzipAndRename.")
+
+        return Path(self.extract_dir) / self.out_name
+
+    def _extract_file(self, fname, extract_dir):
+        """Extract the file and rename it."""
+        output_path = self.output_file()
+        if output_path.exists() and not self.re_unzip:
+            # Nothing to do, the file already exists and we are not re-unzipping
+            return None
+
+        tmp_dir = Path(extract_dir) / "tmp"
+        super()._extract_file(fname, tmp_dir)
+
+        list_extracted_dirs = tmp_dir.iterdir()
+        # Keep only if ends with .zarr
+        list_extracted_dirs = filter(
+            lambda x: x.name.endswith(".zarr"),
+            list_extracted_dirs,
+        )
+        list_extracted_dirs = list(list_extracted_dirs)
+        if len(list_extracted_dirs) != 1:
+            raise NgioValueError(
+                "Expected one directory to be extracted, "
+                f"got {len(list_extracted_dirs)}."
+            )
+
+        extracted_dir = list_extracted_dirs[0]
+        if output_path.exists():
+            shutil.rmtree(output_path, ignore_errors=True)
+
+        extracted_dir.rename(output_path)
+        # Clean up the temporary directory
+        shutil.rmtree(tmp_dir, ignore_errors=True)
+
+
 _ome_zarr_zoo = {
     "CardiomyocyteTiny": {
         "url": "https://zenodo.org/records/13305156/files/20200812-CardiomyocyteDifferentiation14-Cycle1.zarr.zip",
         "known_hash": "md5:efc21fe8d4ea3abab76226d8c166452c",
-        "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1.zarr.zip",
-        "processor": pooch.Unzip(extract_dir=""),
+        "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1-tiny.zarr.zip",
+        "description": "Tiny cardiomyocyte dataset 3D (32MB).",
+    },
+    "CardiomyocyteTinyMip": {
+        "url": "https://zenodo.org/records/13305156/files/20200812-CardiomyocyteDifferentiation14-Cycle1_mip.zarr.zip",
+        "known_hash": "md5:51809479777cafbe9ac0f9fa5636aa95",
+        "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1-tiny-mip.zarr.zip",
+        "description": "Tiny cardiomyocyte dataset 2D MIP (16.4MB).",
+    },
+    "CardiomyocyteSmall": {
+        "url": "https://zenodo.org/records/13305316/files/20200812-CardiomyocyteDifferentiation14-Cycle1.zarr.zip",
+        "known_hash": "md5:d5752ed4b72a9092a0290b3c04c0b9c2",
+        "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1-small.zarr.zip",
+        "description": "Small cardiomyocyte dataset 3D (750MB).",
     },
     "CardiomyocyteSmallMip": {
         "url": "https://zenodo.org/records/13305316/files/20200812-CardiomyocyteDifferentiation14-Cycle1_mip.zarr.zip",
         "known_hash": "md5:3ed3ea898e0ed42d397da2e1dbe40750",
+        "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1-small-mip.zarr.zip",
+        "description": "Small cardiomyocyte dataset 2D MIP (106MB).",
+    },
+    "CardiomyocyteMediumMip": {
+        "url": "https://zenodo.org/records/14826000/files/20200812-CardiomyocyteDifferentiation14-Cycle1_mip.zarr.zip",
+        "known_hash": "md5:3f932bbf7fc0577f58b97471707816a1",
         "fname": "20200812-CardiomyocyteDifferentiation14-Cycle1_mip.zarr.zip",
-        "processor": pooch.Unzip(extract_dir=""),
+        "description": "Medium cardiomyocyte dataset 2D MIP (30GB).",
     },
 }
 
+AVAILABLE_DATASETS = Literal[
+    "CardiomyocyteTiny",
+    "CardiomyocyteTinyMip",
+    "CardiomyocyteSmall",
+    "CardiomyocyteSmallMip",
+    "CardiomyocyteMediumMip",
+]
+
 
 def list_ome_zarr_datasets() -> list[str]:
     """List available OME-Zarr datasets."""
     return list(_ome_zarr_zoo.keys())
 
 
+def print_datasets_infos() -> None:
+    for dataset_name, dataset_info in _ome_zarr_zoo.items():
+        print(f"{dataset_name} - Description: {dataset_info['description']}")
+
+
 def download_ome_zarr_dataset(
-    dataset_name: str,
+    dataset_name: AVAILABLE_DATASETS | str,
     download_dir: str | Path = "data",
+    re_unzip: bool = True,
+    progressbar: bool = False,
 ) -> Path:
     """Download an OME-Zarr dataset.
 
@@ -38,16 +127,28 @@ def download_ome_zarr_dataset(
     Args:
         dataset_name (str): The dataset name.
         download_dir (str): The download directory. Defaults to "data".
+        re_unzip (bool): If True, it will unzip the dataset even if it already exists.
+        progressbar (bool): If True, show a progress bar during download.
     """
     if dataset_name not in _ome_zarr_zoo:
         raise NgioValueError(f"Dataset {dataset_name} not found in the OME-Zarr zoo.")
-    ome_zarr_url = _ome_zarr_zoo[dataset_name]
+    zenodo_infos = _ome_zarr_zoo[dataset_name]
+
+    fname = zenodo_infos["fname"]
+    zarrname = fname.replace(".zip", "")
+
+    processor = UnzipAndRename(
+        extract_dir="",
+        out_name=zarrname,
+        re_unzip=re_unzip,
+    )
+
     pooch.retrieve(
+        url=zenodo_infos["url"],
+        known_hash=zenodo_infos["known_hash"],
+        fname=fname,
         path=download_dir,
-        **ome_zarr_url,
+        processor=processor,
+        progressbar=progressbar,
     )
-    path = Path(download_dir) / ome_zarr_url["fname"]
-
-    if isinstance(ome_zarr_url["processor"], pooch.Unzip):
-        path = path.with_suffix("")
-    return path
+    return processor.output_file()

{ngio-0.3.2.dist-info → ngio-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngio
-Version: 0.3.2
+Version: 0.3.4
 Summary: Next Generation file format IO
 Project-URL: homepage, https://github.com/fractal-analytics-platform/ngio
 Project-URL: repository, https://github.com/fractal-analytics-platform/ngio

{ngio-0.3.2.dist-info → ngio-0.3.4.dist-info}/RECORD

@@ -11,7 +11,7 @@ ngio/common/_slicer.py,sha256=AKpwXRncOmF9nhjKYma0C_41WqAgSv860beKGx-aw-0,3075
 ngio/common/_table_ops.py,sha256=ToNR7F053l1dubVv-gvBD-523T10HnE2UzqeU2BuNy8,15494
 ngio/common/_zoom.py,sha256=KsURa5VuixmpbAAY5-6obmuQV8vfiHKZqBxZDXvchpM,5473
 ngio/hcs/__init__.py,sha256=G8j9vD-liLeB_UeGtKYIgshWvJnUA6ks9GwjvWBLdHs,357
-ngio/hcs/_plate.py,sha256=o8g4WkbFPABV8mBRqyVLbLrKhwFvsf94LwwcBZac_7A,44260
+ngio/hcs/_plate.py,sha256=o-Myg1sPUT9mCfYjHOuUTIpm2Nl0siacmuztGoPcYc0,44265
 ngio/images/__init__.py,sha256=PlYvbHOMvZLDgn_PeGrytOEU3e_-AO8GWpRjEqoX_Gw,536
 ngio/images/_abstract_image.py,sha256=8PNQPZjiDz-pcTFXSJAVw7nUr4yL_iRwqDEUTKkAnp0,10266
 ngio/images/_create.py,sha256=XYn30m_2OSZeHHASYHc3eK9u_gZIYy9wo6mGdRGaq5c,9473
@@ -33,29 +33,29 @@ ngio/ome_zarr_meta/v04/_custom_models.py,sha256=5GxiDERvLuvq4QvApcA6EiKLS6hLFX1R
 ngio/ome_zarr_meta/v04/_v04_spec_utils.py,sha256=05tEr2eEP_XVIfBMOAWLT7lzJV4KS5eYrpK8l94tn3w,15876
 ngio/tables/__init__.py,sha256=_BV3sclNMLITu_J8_3DkkUrCB6Kro0HzeWLDCD1ivKM,877
 ngio/tables/_abstract_table.py,sha256=rwGa47TzbFmosucBWVfFq6JEXtgGvOdUVtU9DIelV88,8204
-ngio/tables/_tables_container.py,sha256=w1rT_5kMh23OHXpFJI3edTH1-tul0YLIYY6x5lMn2k4,12173
-ngio/tables/backends/__init__.py,sha256=nQZVazwTL1IHU08gL-BZcFZd7Cehhbc_AsJ3t3XSps0,1577
+ngio/tables/_tables_container.py,sha256=3xmpREaN671l40MPprnl1BD-VoOb6xfjECb5mNoMW0w,12173
+ngio/tables/backends/__init__.py,sha256=MwSRXNF1rWQBFOTDA_vT3oGoNZpviVgytsL5Txnu08I,1619
 ngio/tables/backends/_abstract_backend.py,sha256=tsbHzSPTX88fiCbVc8khXv5aN68ck6HKG8r5OHkY3S8,7457
-ngio/tables/backends/_anndata.py,sha256=8RX2NO15CLxys3p6gw54Nd-_0WATU4WBlNndX06wvzI,2587
+ngio/tables/backends/_anndata.py,sha256=EdzGH0Zr85GBjVVBy3OxnRoDGgsi5zZLWRWpSLF2GhQ,2832
 ngio/tables/backends/_anndata_utils.py,sha256=DBWIcR0btnH-DIvDvzlcnMXoYhhtXc9DstryiOP0Qsg,3122
 ngio/tables/backends/_csv.py,sha256=Ev61D-AUKo4LIhXRmWPJgYbHI7eQdxiajQR574DevEM,932
 ngio/tables/backends/_json.py,sha256=1ZsEuXDJm1rOZV_KjFm8CB0qhv7L1W7L2EGWPf4q_p0,3137
 ngio/tables/backends/_non_zarr_backends.py,sha256=SvPPhT6n5TrKUOyV1mNcdHQK49huZ5lwR8EVe9MdydM,7254
 ngio/tables/backends/_parquet.py,sha256=ic-p86h8lce8q9luBJGRzy6vxlWyJvA0-2l5cUD6OqY,1398
-ngio/tables/backends/_table_backends.py,sha256=QUS59VU395966AEul2SNJQAzklSitvISL0wnZTKWZa0,7267
+ngio/tables/backends/_table_backends.py,sha256=56lMLrkmRS8-NTwNF0wkMzrRwTmOFLk1g_LBDA2i6wg,7318
 ngio/tables/backends/_utils.py,sha256=tJBSWN6OhO_1ybxl4vT2l3ImB028Fb6h0vaitPRcr8A,19668
 ngio/tables/v1/__init__.py,sha256=Wr1_9RZFpaN8FYMTnxT9Yjkw4AS7y9FMWailmB_uj5g,617
-ngio/tables/v1/_condition_table.py,sha256=IMU3sds8wrKGqU-C20HbpFCVGZX1L_V7Sh8f7CHB_x0,1781
+ngio/tables/v1/_condition_table.py,sha256=T0Uq5BKkmMoEspt_Rx0U99Ow6S9GAMZDHqvUO5obCAM,1780
 ngio/tables/v1/_feature_table.py,sha256=n9uMHwoBh-_dlOhUXCFbmAjXFVXncNCR3SjE2qzXI68,3821
 ngio/tables/v1/_generic_table.py,sha256=1ktJHeuv7U1g5Z8PFUuTkCjOzcYMQd8xegKHKUedJB8,1240
 ngio/tables/v1/_roi_table.py,sha256=DgXhp-DHTeEJwzSsSRSlnPghjMhYGa3IGSpwTt5LKZU,13603
-ngio/utils/__init__.py,sha256=r3nuLWgp6-cQlS4ODjYSBrfgdTLkCOVke9jKbn1NpkA,1129
-ngio/utils/_datasets.py,sha256=EdYJHIifpRou4f43dIuiKsdxe4K6FaeS4f1_e_EYrcI,1727
+ngio/utils/__init__.py,sha256=VxPVDKF0QF9HtG8wY0J6PXESNcWLaMXQNZiw5dHflBU,1179
+ngio/utils/_datasets.py,sha256=2g-Neg78dNcqyDz39QQw-Ifp9GITHjVHisdqgvvDNDE,5475
 ngio/utils/_errors.py,sha256=pKQ12LUjQLYE1nUawemA5h7HsgznjaSvV1n2PQU33N0,759
 ngio/utils/_fractal_fsspec_store.py,sha256=RdcCFOgHexRKX9zZvJV5RI-5OPc7VOPS6q_IeRxm24I,1548
 ngio/utils/_logger.py,sha256=HIuqD_2ShfFGDswBddcouStbKfL0Vz_ah8cAIFGhbS8,888
 ngio/utils/_zarr_utils.py,sha256=qOI-HL2HsfFLCj_yxsTR-aq4oHpSqS9KR13aEIvhGDY,13593
-ngio-0.3.2.dist-info/METADATA,sha256=lTCmsFw4q7EZUvjlH6aSpnqVDnUnP025vdUrp1o7pyY,5868
-ngio-0.3.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-ngio-0.3.2.dist-info/licenses/LICENSE,sha256=UgN_a1QCeNh9rZWfz-wORQFxE3elQzLWPQaoK6N6fxQ,1502
-ngio-0.3.2.dist-info/RECORD,,
+ngio-0.3.4.dist-info/METADATA,sha256=CejDvwMriZ2JvTO2bLW3AA0W3zlAGmWjU10Hw20thy8,5868
+ngio-0.3.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+ngio-0.3.4.dist-info/licenses/LICENSE,sha256=UgN_a1QCeNh9rZWfz-wORQFxE3elQzLWPQaoK6N6fxQ,1502
+ngio-0.3.4.dist-info/RECORD,,