ngio 0.5.0__py3-none-any.whl → 0.5.0a1__py3-none-any.whl

ngio/tables/backends/_py_arrow_backends.py

@@ -1,222 +0,0 @@
-from typing import Literal
-
-import polars as pl
-import pyarrow as pa
-import pyarrow.csv as pa_csv
-import pyarrow.dataset as pa_ds
-import pyarrow.fs as pa_fs
-import pyarrow.parquet as pa_parquet
-from pandas import DataFrame
-from polars import DataFrame as PolarsDataFrame
-from polars import LazyFrame
-from zarr.storage import FsspecStore, LocalStore, MemoryStore, ZipStore
-
-from ngio.tables.backends._abstract_backend import AbstractTableBackend
-from ngio.tables.backends._utils import normalize_pandas_df, normalize_polars_lf
-from ngio.utils import NgioValueError
-from ngio.utils._zarr_utils import _make_sync_fs
-
-
-class PyArrowBackend(AbstractTableBackend):
-    """A class to load and write small tables in CSV format."""
-
-    def __init__(
-        self,
-        table_name: str,
-        table_format: Literal["csv", "parquet"] = "parquet",
-    ):
-        self.table_name = table_name
-        self.table_format = table_format
-
-    @staticmethod
-    def implements_anndata() -> bool:
-        """Whether the handler implements the anndata protocol."""
-        return False
-
-    @staticmethod
-    def implements_pandas() -> bool:
-        """Whether the handler implements the dataframe protocol."""
-        return True
-
-    @staticmethod
-    def implements_polars() -> bool:
-        """Whether the handler implements the polars protocol."""
-        return True
-
-    @staticmethod
-    def backend_name() -> str:
-        """Return the name of the backend."""
-        raise NotImplementedError(
-            "The backend_name method must be implemented in the subclass."
-        )
-
-    def _raise_store_type_not_supported(self):
-        """Raise an error for unsupported store types."""
-        ext = self.table_name.split(".")[-1]
-        store = self._group_handler.store
-        raise NgioValueError(
-            f"Ngio does not support reading a {ext} table from a "
-            f"store of type {type(store)}. "
-            "Please make sure to use a compatible "
-            "store like a LocalStore, or "
-            "FsspecStore, or MemoryStore, or ZipStore."
-        )
-
-    def _load_from_local_store(self, store: LocalStore, path: str) -> pa_ds.Dataset:
-        """Load the table from a directory store."""
-        root_path = store.root
-        table_path = f"{root_path}/{path}/{self.table_name}"
-        dataset = pa_ds.dataset(table_path, format=self.table_format)
-        return dataset
-
-    def _load_from_fsspec_store(self, store: FsspecStore, path: str) -> pa_ds.Dataset:
-        """Load the table from an FS store."""
-        table_path = f"{store.path}/{path}/{self.table_name}"
-        fs = _make_sync_fs(store.fs)
-        dataset = pa_ds.dataset(table_path, format=self.table_format, filesystem=fs)
-        return dataset
-
-    def _load_from_in_memory_store(
-        self, store: MemoryStore, path: str
-    ) -> pa_ds.Dataset:
-        """Load the table from an in-memory store."""
-        table_path = f"{path}/{self.table_name}"
-        table = store._store_dict.get(table_path, None)
-        if table is None:
-            raise NgioValueError(
-                f"Table {self.table_name} not found in the in-memory store at "
-                f"path {path}."
-            )
-        assert isinstance(table, pa.Table)
-        dataset = pa_ds.dataset(table)
-        return dataset
-
-    def _load_from_zip_store(self, store: ZipStore, path: str) -> pa_ds.Dataset:
-        """Load the table from a zip store."""
-        raise NotImplementedError("Zip store loading is not implemented yet.")
-
-    def _load_pyarrow_dataset(self) -> pa_ds.Dataset:
-        """Load the table as a pyarrow Dataset."""
-        store = self._group_handler.store
-        path = self._group_handler.group.path
-        if isinstance(store, LocalStore):
-            return self._load_from_local_store(store, path)
-        elif isinstance(store, FsspecStore):
-            return self._load_from_fsspec_store(store, path)
-        elif isinstance(store, MemoryStore):
-            return self._load_from_in_memory_store(store, path)
-        elif isinstance(store, ZipStore):
-            return self._load_from_zip_store(store, path)
-        self._raise_store_type_not_supported()
-
-    def load_as_pandas_df(self) -> DataFrame:
-        """Load the table as a pandas DataFrame."""
-        dataset = self._load_pyarrow_dataset()
-        dataframe = dataset.to_table().to_pandas()
-        dataframe = normalize_pandas_df(
-            dataframe,
-            index_key=self.index_key,
-            index_type=self.index_type,
-            reset_index=False,
-        )
-        return dataframe
-
-    def load(self) -> DataFrame:
-        """Load the table as a pandas DataFrame."""
-        return self.load_as_pandas_df()
-
-    def load_as_polars_lf(self) -> LazyFrame:
-        """Load the table as a polars LazyFrame."""
-        dataset = self._load_pyarrow_dataset()
-        lazy_frame = pl.scan_pyarrow_dataset(dataset)
-        if not isinstance(lazy_frame, LazyFrame):
-            raise NgioValueError(
-                "Table is not a lazy frame. Please report this issue as an ngio bug."
-                f" {type(lazy_frame)}"
-            )
-
-        lazy_frame = normalize_polars_lf(
-            lazy_frame,
-            index_key=self.index_key,
-            index_type=self.index_type,
-        )
-        return lazy_frame
-
-    def _write_to_stream(self, stream, table: pa.Table) -> None:
-        """Write the table to a stream."""
-        if self.table_format == "parquet":
-            pa_parquet.write_table(table, stream)
-        elif self.table_format == "csv":
-            pa_csv.write_csv(table, stream)
-        else:
-            raise NgioValueError(
-                f"Unsupported table format: {self.table_format}. "
-                "Supported formats are 'parquet' and 'csv'."
-            )
-
-    def _write_to_local_store(
-        self, store: LocalStore, path: str, table: pa.Table
-    ) -> None:
-        """Write the table to a directory store."""
-        root_path = store.root
-        table_path = f"{root_path}/{path}/{self.table_name}"
-        self._write_to_stream(table_path, table)
-
-    def _write_to_fsspec_store(
-        self, store: FsspecStore, path: str, table: pa.Table
-    ) -> None:
-        """Write the table to an FS store."""
-        table_path = f"{store.path}/{path}/{self.table_name}"
-        fs = _make_sync_fs(store.fs)
-        fs = pa_fs.PyFileSystem(pa_fs.FSSpecHandler(fs))
-        with fs.open_output_stream(table_path) as out_stream:
-            self._write_to_stream(out_stream, table)
-
-    def _write_to_in_memory_store(
-        self, store: MemoryStore, path: str, table: pa.Table
-    ) -> None:
-        """Write the table to an in-memory store."""
-        table_path = f"{path}/{self.table_name}"
-        store._store_dict[table_path] = table
-
-    def _write_to_zip_store(self, store: ZipStore, path: str, table: pa.Table) -> None:
-        """Write the table to a zip store."""
-        raise NotImplementedError("Writing to zip store is not implemented yet.")
-
-    def _write_pyarrow_dataset(self, dataset: pa.Table) -> None:
-        """Write the table from a pyarrow Dataset."""
-        store = self._group_handler.store
-        path = self._group_handler.group.path
-        if isinstance(store, LocalStore):
-            return self._write_to_local_store(store=store, path=path, table=dataset)
-        elif isinstance(store, FsspecStore):
-            return self._write_to_fsspec_store(store=store, path=path, table=dataset)
-        elif isinstance(store, MemoryStore):
-            return self._write_to_in_memory_store(store=store, path=path, table=dataset)
-        elif isinstance(store, ZipStore):
-            return self._write_to_zip_store(store=store, path=path, table=dataset)
-        self._raise_store_type_not_supported()
-
-    def write_from_pandas(self, table: DataFrame) -> None:
-        """Write the table from a pandas DataFrame."""
-        table = normalize_pandas_df(
-            table,
-            index_key=self.index_key,
-            index_type=self.index_type,
-            reset_index=True,
-        )
-        table = pa.Table.from_pandas(table, preserve_index=False)
-        self._write_pyarrow_dataset(table)
-
-    def write_from_polars(self, table: PolarsDataFrame | LazyFrame) -> None:
-        """Write the table from a polars DataFrame or LazyFrame."""
-        table = normalize_polars_lf(
-            table,
-            index_key=self.index_key,
-            index_type=self.index_type,
-        )
-
-        if isinstance(table, LazyFrame):
-            table = table.collect()
-        table = table.to_arrow()
-        self._write_pyarrow_dataset(table)

ngio/utils/_cache.py

@@ -1,48 +0,0 @@
-from typing import Generic, TypeVar
-
-T = TypeVar("T")
-
-
-class NgioCache(Generic[T]):
-    """A simple cache for NGIO objects."""
-
-    def __init__(self, use_cache: bool = True):
-        self._cache: dict[str, T] = {}
-        self._use_cache = use_cache
-
-    def _cache_sanity_check(self) -> None:
-        if len(self._cache) > 0:
-            raise RuntimeError(
-                "Cache is disabled, but cache contains items. "
-                "This indicates a logic error."
-            )
-
-    @property
-    def use_cache(self) -> bool:
-        return self._use_cache
-
-    @property
-    def cache(self) -> dict[str, T]:
-        return self._cache
-
-    @property
-    def is_empty(self) -> bool:
-        return len(self._cache) == 0
-
-    def get(self, key: str, default: T | None = None) -> T | None:
-        if not self._use_cache:
-            self._cache_sanity_check()
-            return default
-        return self._cache.get(key, default)
-
-    def set(self, key: str, value: T, overwrite: bool = True) -> None:
-        if not self._use_cache:
-            self._cache_sanity_check()
-            return
-        self._cache[key] = value
-
-    def clear(self) -> None:
-        if not self._use_cache:
-            self._cache_sanity_check()
-            return
-        self._cache.clear()

ngio-0.5.0.dist-info/RECORD

@@ -1,88 +0,0 @@
-ngio/__init__.py,sha256=kyInohhWrBs4qkbMYFIQeAiy1CDpvbSOtXB4buFocbw,1535
-ngio/common/__init__.py,sha256=F3zAHQIhwig1xUA-SpmFVRtMeOrEj926-nHWhj-wS6c,684
-ngio/common/_dimensions.py,sha256=w8PYgyWxA8hgJETjFbw5CXf7WrasCL5FbzgfL1in86M,11361
-ngio/common/_masking_roi.py,sha256=-2IzQvaIpdgAxS8LY3DRb-Eax5efX6H0OhV7lNVdL1E,5202
-ngio/common/_pyramid.py,sha256=7kbvCY4J0hLl_iV5oT267j_h3UTkbqIdltqHcrwicvw,17571
-ngio/common/_roi.py,sha256=IM0rYaekNvEDSMctYbAEZkeG9iPaJ1qjtnJ9kOVV8as,11416
-ngio/common/_synt_images_utils.py,sha256=B6uYOW1NyrM06YMR-csca3_YnAAkPRTbvnbLdy9tk9E,3188
-ngio/common/_zoom.py,sha256=U01c-vqXjzZkrpd9Yvs24frVfTls_xPJeeaFCGmUwYI,6727
-ngio/experimental/__init__.py,sha256=3pmBtHi-i8bKjTsvrOJM56ZyRX3Pv_dceCdt88-8COQ,147
-ngio/experimental/iterators/__init__.py,sha256=TECOMGb5PEEZ0yXxt8pqIGvLKG41g_L1fTJU-zGPeV8,488
-ngio/experimental/iterators/_abstract_iterator.py,sha256=7aAoMI-6vYGCMKxO3M10WpuBMTdqX4zr0K-TutAOp88,13195
-ngio/experimental/iterators/_feature.py,sha256=OnqeSP-UMWku7AIBcutsDsAWqnFqPrjCJiMvMGM96fk,6714
-ngio/experimental/iterators/_image_processing.py,sha256=cM7sL7xgdcjSOKAu-6367Aov89o6wgiJ_wqCGkU2Bsw,5091
-ngio/experimental/iterators/_mappers.py,sha256=VVVsjems57wJUnWeufUFcgqa23k7VPeFL4Nc04HVw4o,1399
-ngio/experimental/iterators/_rois_utils.py,sha256=5foGjt3qrACNrO29LlvSUbJ4yfI0z6MhU2oVCzEU214,4363
-ngio/experimental/iterators/_segmentation.py,sha256=xzotGvTn04HPeMeXZ_URnQqWco6d2lH6Ng6vkCUh9NM,9153
-ngio/hcs/__init__.py,sha256=G8j9vD-liLeB_UeGtKYIgshWvJnUA6ks9GwjvWBLdHs,357
-ngio/hcs/_plate.py,sha256=-dFlUuB4DbzR-A5OONafiIGaTpasd9uybRybNgGDFPQ,46118
-ngio/images/__init__.py,sha256=9Whvt7GTiCgT_vXaEEqGnDaY1-UsRk3dhLTv091F_g4,1211
-ngio/images/_abstract_image.py,sha256=YUBLCqLOWD_9BlwhoVqNc6ISdmmqP1DUbZKn_sk8DJU,36022
-ngio/images/_create_synt_container.py,sha256=4hZa0wKfI5RL30vsPE841SCVhWNb9Kj8kJiaTsD-0BA,5399
-ngio/images/_create_utils.py,sha256=CxRO-b0_vyL27jMg6koXlt9vFNU1lmqKIWOU5ypAtvg,13811
-ngio/images/_image.py,sha256=Ei2_bqsLg7q1rhjDIKusXqSdqhar8Ojsd6mYZ9ar6GI,45558
-ngio/images/_label.py,sha256=iC9XPyM5SOWcI3Z3PZ0M1RUUCCUbBQ98zdrchva00Jw,16002
-ngio/images/_masked_image.py,sha256=25BFnEHTqWdq5ImLs6dbo_X-ryGLIL7vJ2mmbx4Npv8,18834
-ngio/images/_ome_zarr_container.py,sha256=ddcDRGhmJoyg47NHFaoNLZuWfXpLfNkZtP-hzLWWBIQ,56100
-ngio/images/_table_ops.py,sha256=jFv_AMqoB4JBpoWsMtZppZVW7dAOC_u-JpfNm8b33kY,15292
-ngio/io_pipes/__init__.py,sha256=arW_7GWzZs82kPNKdm_6B1sIDFV0lWwp-ZaORr9Q1FQ,2412
-ngio/io_pipes/_io_pipes.py,sha256=l85mmjj1l0uYU3qzsSHg9l8cMIEevInm_MTD-8MlXgw,10603
-ngio/io_pipes/_io_pipes_masked.py,sha256=uvfNIuW8prWux3fZ-a25l44zDfZW4qBaXZEm0TkhloA,16916
-ngio/io_pipes/_io_pipes_roi.py,sha256=HJHlItx2nsFYcE4OjvVR-W0lFMMK8CcyYK23dKUrP8w,4472
-ngio/io_pipes/_io_pipes_types.py,sha256=PcRdnjBJIsXcDT1_dbH2LZiH6d3z6D7y48cmybyZCXk,1358
-ngio/io_pipes/_match_shape.py,sha256=sCAhJHzlqZwnz1MmwFCUQkH_6rohMSNwPCAmCuDElEA,13002
-ngio/io_pipes/_ops_axes.py,sha256=Geg4ZXxB0njWWopX9YeiwRJJ9Ef2GKfG0NIUafOmi2c,10043
-ngio/io_pipes/_ops_slices.py,sha256=hHMIOQ_niUSK9uFl8P2-10dP_K4GX3Do6vivN4fGRE0,14520
-ngio/io_pipes/_ops_slices_utils.py,sha256=mps_I0eTI4gdBVM9MCKsd8rCyefdo9bIK9fEmqwr23E,6633
-ngio/io_pipes/_ops_transforms.py,sha256=uITs6v6sZ7DQ_Hpw3JdX8MuPOzir-bihvGzY84Qn4wY,2934
-ngio/io_pipes/_zoom_transform.py,sha256=WBY1tO6_Qhf8FaDujfTdipuuqFf7PSi204wx5VKKs88,6884
-ngio/ome_zarr_meta/__init__.py,sha256=7VDrX-ev5Gg2zQfGsrlj-YPTeIGzbplxbptxw1u-vU0,1491
-ngio/ome_zarr_meta/_meta_handlers.py,sha256=u6a-z-q4Gu0TSahpD5qCmpIOLwnJqNjfoAnOyzzCyrg,14794
-ngio/ome_zarr_meta/ngio_specs/__init__.py,sha256=FukhukN9ksW-SDUiAtmiwpQ7c9qWAyq0cnTnSqZLsVc,1800
-ngio/ome_zarr_meta/ngio_specs/_axes.py,sha256=yfFylcr_xGda5HuXWRV25V4gRUbNJdfJwyn9mqXEB6I,20313
-ngio/ome_zarr_meta/ngio_specs/_channels.py,sha256=TDxIy-yVc2YaWPIFJRYnYwZbA8O5Ee_OiWppHYrEdpU,16647
-ngio/ome_zarr_meta/ngio_specs/_dataset.py,sha256=5YdAplk90koX3vjoIJimms-CJYxt095rJ9YagZSQg88,2872
-ngio/ome_zarr_meta/ngio_specs/_ngio_hcs.py,sha256=kktIwHWZ8u2f6xMUB4zXiUfNF6i-We86_agLjJ7XVOU,18363
-ngio/ome_zarr_meta/ngio_specs/_ngio_image.py,sha256=LJE_bA8e5KIEm_7pr15Etda-KhKCAqjWCUFHoCnwTag,15654
-ngio/ome_zarr_meta/ngio_specs/_pixel_size.py,sha256=4VF1djY9T5tp6GCJXppFrUJwALI1XgIm0imoM5rNvdE,3876
-ngio/ome_zarr_meta/v04/__init__.py,sha256=tRt3zGelL948EoLfy_gW-LKvJcBbSkbT9kwIgU0hQV8,721
-ngio/ome_zarr_meta/v04/_custom_models.py,sha256=5GxiDERvLuvq4QvApcA6EiKLS6hLFX1R0R_9rSaa85A,530
-ngio/ome_zarr_meta/v04/_v04_spec.py,sha256=S9a9Z3wYLI-WHnOZsg3RKPAcovssqGIr-x8GVAjV0IU,14321
-ngio/ome_zarr_meta/v05/__init__.py,sha256=B6VIUkrm5W4lcrvy4R7c7NZ6dEx-0a1AhqhZ7snCnCo,721
-ngio/ome_zarr_meta/v05/_custom_models.py,sha256=ZN3bE9nwx4y3tElhsYafI4S2zp_WzdkQKcyuuBiaXXo,530
-ngio/ome_zarr_meta/v05/_v05_spec.py,sha256=pCIoSsYmJjmrZ3jbgkdio7e6qKV2_ggd4WQe4zBSt8M,15225
-ngio/resources/__init__.py,sha256=pOo2YqxDlzTSWo6qyYQzXZbIKWSUoEl3iqX41Iw-oQI,1661
-ngio/resources/resource_model.py,sha256=mmx8gbfDHBg_gVNvtZZydAZDATdmcaM8DsOfnRVrXXA,858
-ngio/resources/20200812-CardiomyocyteDifferentiation14-Cycle1_B03/mask.png,sha256=g3QmxQdmeciAtBe5cTCRfR6yw3keG9cBYfjizMo6EGo,11890
-ngio/resources/20200812-CardiomyocyteDifferentiation14-Cycle1_B03/nuclei.png,sha256=Yw0k5pn2EHDMWTwyb7N51NX7WVk6-MlwfP9WZrhY-Ic,19446
-ngio/resources/20200812-CardiomyocyteDifferentiation14-Cycle1_B03/raw.jpg,sha256=82lejQAIokj5w9g-qqhysDTWpHtNvJTkdURG_BjqIxQ,37743
-ngio/tables/__init__.py,sha256=_BV3sclNMLITu_J8_3DkkUrCB6Kro0HzeWLDCD1ivKM,877
-ngio/tables/_abstract_table.py,sha256=rwGa47TzbFmosucBWVfFq6JEXtgGvOdUVtU9DIelV88,8204
-ngio/tables/_tables_container.py,sha256=4frJpcfuW-J8N13enzFuH6wQIVwRVRKN7FOLWx_VxRc,14035
-ngio/tables/backends/__init__.py,sha256=MwSRXNF1rWQBFOTDA_vT3oGoNZpviVgytsL5Txnu08I,1619
-ngio/tables/backends/_abstract_backend.py,sha256=M1ogsBpWBiQMV65YweZhA845PAtkzG2BsZCPN_7Xp8U,7613
-ngio/tables/backends/_anndata.py,sha256=T67N-SPNO4eqe7-VGAUfgtwaSy_o2DqCvZgE2yRH5jE,4582
-ngio/tables/backends/_anndata_utils.py,sha256=PoHiLkGeDhBgPsEMJi9QH-NejHmfrfILcwj1CYubyCM,3095
-ngio/tables/backends/_csv.py,sha256=iZJNLHOXYysV_2iq6Lmekq0XXYsVE7OYrKz2HP2TU9w,479
-ngio/tables/backends/_json.py,sha256=A4iaKOIc5Q_XKDOm321QNqAN4DAOuA-dEinnfTlk1Fk,3091
-ngio/tables/backends/_parquet.py,sha256=Fi3VZlTH5UTykk0eqr43_e_Qt_GQcEN-3pHK07XFBwk,503
-ngio/tables/backends/_py_arrow_backends.py,sha256=lxxI5TN4lFYwpsjD1g1xAxEt4lZ9Mu7YW3-m3nIuo2g,8587
-ngio/tables/backends/_table_backends.py,sha256=ksP2NAosXZkNMZf-IMrLx7bjQgp_eKfvPYK4vMdT1A8,7250
-ngio/tables/backends/_utils.py,sha256=t4dLXSPxx2AnJvVtj0GIwrLoO11h4Ges6U7hj4md0hY,19730
-ngio/tables/v1/__init__.py,sha256=Wr1_9RZFpaN8FYMTnxT9Yjkw4AS7y9FMWailmB_uj5g,617
-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=DuKJlDmtQtLOfL0g4CSdncfm4hBsKWG6F6fkMUpt4Nk,17821
-ngio/transforms/__init__.py,sha256=JA0-Ui7skbXkm9ofN-AEhU1FTLutkMkwTdVD-310frQ,113
-ngio/transforms/_zoom.py,sha256=otyE-vxFnywUJ8U4mHjat-bNG_7_jv62ckTpqDMxyVQ,550
-ngio/utils/__init__.py,sha256=d2OHQGMFPpf8-_ipuqquxtqCNGJpX5yXt34A65nScUU,1037
-ngio/utils/_cache.py,sha256=Ey9fgc_BTdMyqg6c80C0CuGDhOafln8-3e_1MQ0MFzw,1283
-ngio/utils/_datasets.py,sha256=YOV367skFA8nbKAqbyK0EsUU7E9UId_u5ButuLesrzk,5896
-ngio/utils/_errors.py,sha256=pKQ12LUjQLYE1nUawemA5h7HsgznjaSvV1n2PQU33N0,759
-ngio/utils/_fractal_fsspec_store.py,sha256=RdcCFOgHexRKX9zZvJV5RI-5OPc7VOPS6q_IeRxm24I,1548
-ngio/utils/_zarr_utils.py,sha256=n9EvUIZFNIBIHBoadefSz_7r9q8GLu7x7FF2G6Dgb94,18095
-ngio-0.5.0.dist-info/METADATA,sha256=tecky39dej2Kd41NqWTJaAloeiXQAgGDtoyXJNJdWgU,6424
-ngio-0.5.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-ngio-0.5.0.dist-info/licenses/LICENSE,sha256=UgN_a1QCeNh9rZWfz-wORQFxE3elQzLWPQaoK6N6fxQ,1502
-ngio-0.5.0.dist-info/RECORD,,