careamics 0.0.1__py3-none-any.whl → 0.0.3__py3-none-any.whl

careamics/dataset/zarr_dataset.py

@@ -0,0 +1,151 @@
+"""Zarr dataset."""
+
+# from itertools import islice
+# from typing import Callable, Dict, List, Optional, Tuple, Union
+
+# import numpy as np
+# import torch
+# import zarr
+
+# from careamics.utils import RunningStats
+# from careamics.utils.logging import get_logger
+
+# from ..utils import normalize
+# from .dataset_utils import read_zarr
+# from .patching.patching import (
+#     generate_patches_unsupervised,
+# )
+
+# logger = get_logger(__name__)
+
+
+# class ZarrDataset(torch.utils.data.IterableDataset):
+#     """Dataset to extract patches from a zarr storage.
+
+#     Parameters
+#     ----------
+#     data_source : Union[zarr.Group, zarr.Array]
+#         Zarr storage.
+#     axes : str
+#         Description of axes in format STCZYX.
+#     patch_extraction_method : Union[ExtractionStrategies, None]
+#         Patch extraction strategy, as defined in extraction_strategy.
+#     patch_size : Optional[Union[List[int], Tuple[int]]], optional
+#         Size of the patches in each dimension, by default None.
+#     num_patches : Optional[int], optional
+#         Number of patches to extract, by default None.
+#     mean : Optional[float], optional
+#         Expected mean of the dataset, by default None.
+#     std : Optional[float], optional
+#         Expected standard deviation of the dataset, by default None.
+#     patch_transform : Optional[Callable], optional
+#         Patch transform callable, by default None.
+#     patch_transform_params : Optional[Dict], optional
+#         Patch transform parameters, by default None.
+#     running_stats_window_perc : float, optional
+#         Percentage of the dataset to use for calculating the initial mean and standard
+#         deviation, by default 0.01.
+#     mode : str, optional
+#         train/predict, controls running stats calculation.
+#     """
+
+#     def __init__(
+#         self,
+#         data_source: Union[zarr.Group, zarr.Array],
+#         axes: str,
+#         patch_extraction_method: Union[SupportedExtractionStrategy, None],
+#         patch_size: Optional[Union[List[int], Tuple[int]]] = None,
+#         num_patches: Optional[int] = None,
+#         mean: Optional[float] = None,
+#         std: Optional[float] = None,
+#         patch_transform: Optional[Callable] = None,
+#         patch_transform_params: Optional[Dict] = None,
+#         running_stats_window_perc: float = 0.01,
+#         mode: str = "train",
+#     ) -> None:
+#         self.data_source = data_source
+#         self.axes = axes
+#         self.patch_extraction_method = patch_extraction_method
+#         self.patch_size = patch_size
+#         self.num_patches = num_patches
+#         self.mean = mean
+#         self.std = std
+#         self.patch_transform = patch_transform
+#         self.patch_transform_params = patch_transform_params
+#         self.sample = read_zarr(self.data_source, self.axes)
+#         self.running_stats_window = int(
+#             np.prod(self.sample._cdata_shape) * running_stats_window_perc
+#         )
+#         self.mode = mode
+#         self.running_stats = RunningStats()
+
+#         self._calculate_initial_mean_std()
+
+#     def _calculate_initial_mean_std(self):
+#         """Calculate initial mean and std of the dataset."""
+#         if self.mean is None and self.std is None:
+#             idxs = np.random.randint(
+#                 0,
+#                 np.prod(self.sample._cdata_shape),
+#                 size=max(1, self.running_stats_window),
+#             )
+#             random_chunks = self.sample[idxs]
+#             self.running_stats.init(random_chunks.mean(), random_chunks.std())
+
+#     def _generate_patches(self):
+#         """Generate patches from the dataset and calculates running stats.
+
+#         Yields
+#         ------
+#         np.ndarray
+#             Patch.
+#         """
+#         patches = generate_patches_unsupervised(
+#             self.sample,
+#             self.patch_extraction_method,
+#             self.patch_size,
+#         )
+
+#         # num_patches = np.ceil(
+#         #     np.prod(self.sample.chunks)
+#         #     / (np.prod(self.patch_size) * self.running_stats_window)
+#         # ).astype(int)
+
+#         for idx, patch in enumerate(patches):
+#             if self.mode != "predict":
+#                 self.running_stats.update(patch.mean())
+#             if isinstance(patch, tuple):
+#                 normalized_patch = normalize(
+#                     img=patch[0],
+#                     mean=self.running_stats.avg_mean.value,
+#                     std=self.running_stats.avg_std.value,
+#                 )
+#                 patch = (normalized_patch, *patch[1:])
+#             else:
+#                 patch = normalize(
+#                     img=patch,
+#                     mean=self.running_stats.avg_mean.value,
+#                     std=self.running_stats.avg_std.value,
+#                 )
+
+#             if self.patch_transform is not None:
+#                 assert self.patch_transform_params is not None
+#                 patch = self.patch_transform(patch, **self.patch_transform_params)
+#             if self.num_patches is not None and idx >= self.num_patches:
+#                 return
+#             else:
+#                 yield patch
+#         self.mean = self.running_stats.avg_mean.value
+#         self.std = self.running_stats.avg_std.value
+
+#     def __iter__(self):
+#         """
+#         Iterate over data source and yield single patch.
+
+#         Yields
+#         ------
+#         np.ndarray
+#         """
+#         worker_info = torch.utils.data.get_worker_info()
+#         num_workers = worker_info.num_workers if worker_info is not None else 1
+#         yield from islice(self._generate_patches(), 0, None, num_workers)

careamics/file_io/__init__.py

@@ -0,0 +1,15 @@
+"""Functions relating reading and writing image files."""
+
+__all__ = [
+    "read",
+    "write",
+    "get_read_func",
+    "get_write_func",
+    "ReadFunc",
+    "WriteFunc",
+    "SupportedWriteType",
+]
+
+from . import read, write
+from .read import ReadFunc, get_read_func
+from .write import SupportedWriteType, WriteFunc, get_write_func

careamics/file_io/read/__init__.py

@@ -0,0 +1,12 @@
+"""Functions relating to reading image files of different formats."""
+
+__all__ = [
+    "get_read_func",
+    "read_tiff",
+    "read_zarr",
+    "ReadFunc",
+]
+
+from .get_func import ReadFunc, get_read_func
+from .tiff import read_tiff
+from .zarr import read_zarr

careamics/file_io/read/get_func.py

@@ -0,0 +1,56 @@
+"""Module to get read functions."""
+
+from pathlib import Path
+from typing import Callable, Dict, Protocol, Union
+
+from numpy.typing import NDArray
+
+from careamics.config.support import SupportedData
+
+from .tiff import read_tiff
+
+
+# This is very strict, function signature has to match including arg names
+# See WriteFunc notes
+class ReadFunc(Protocol):
+    """Protocol for type hinting read functions."""
+
+    def __call__(self, file_path: Path, *args, **kwargs) -> NDArray:
+        """
+        Type hinted callables must match this function signature (not including self).
+
+        Parameters
+        ----------
+        file_path : pathlib.Path
+            Path to file.
+        *args
+            Other positional arguments.
+        **kwargs
+            Other keyword arguments.
+        """
+
+
+READ_FUNCS: Dict[SupportedData, ReadFunc] = {
+    SupportedData.TIFF: read_tiff,
+}
+
+
+def get_read_func(data_type: Union[str, SupportedData]) -> Callable:
+    """
+    Get the read function for the data type.
+
+    Parameters
+    ----------
+    data_type : SupportedData
+        Data type.
+
+    Returns
+    -------
+    callable
+        Read function.
+    """
+    if data_type in READ_FUNCS:
+        data_type = SupportedData(data_type)  # mypy complaining about dict key type
+        return READ_FUNCS[data_type]
+    else:
+        raise NotImplementedError(f"Data type '{data_type}' is not supported.")

careamics/file_io/read/tiff.py

@@ -0,0 +1,58 @@
+"""Functions to read tiff images."""
+
+import logging
+from fnmatch import fnmatch
+from pathlib import Path
+
+import numpy as np
+import tifffile
+
+from careamics.config.support import SupportedData
+from careamics.utils.logging import get_logger
+
+logger = get_logger(__name__)
+
+
+def read_tiff(file_path: Path, *args: list, **kwargs: dict) -> np.ndarray:
+    """
+    Read a tiff file and return a numpy array.
+
+    Parameters
+    ----------
+    file_path : Path
+        Path to a file.
+    *args : list
+        Additional arguments.
+    **kwargs : dict
+        Additional keyword arguments.
+
+    Returns
+    -------
+    np.ndarray
+        Resulting array.
+
+    Raises
+    ------
+    ValueError
+        If the file failed to open.
+    OSError
+        If the file failed to open.
+    ValueError
+        If the file is not a valid tiff.
+    ValueError
+        If the data dimensions are incorrect.
+    ValueError
+        If the axes length is incorrect.
+    """
+    if fnmatch(
+        file_path.suffix, SupportedData.get_extension_pattern(SupportedData.TIFF)
+    ):
+        try:
+            array = tifffile.imread(file_path)
+        except (ValueError, OSError) as e:
+            logging.exception(f"Exception in file {file_path}: {e}, skipping it.")
+            raise e
+    else:
+        raise ValueError(f"File {file_path} is not a valid tiff.")
+
+    return array

careamics/file_io/read/zarr.py

@@ -0,0 +1,60 @@
+"""Function to read zarr images."""
+
+from typing import Union
+
+from zarr import Group, core, hierarchy, storage
+
+
+def read_zarr(
+    zarr_source: Group, axes: str
+) -> Union[core.Array, storage.DirectoryStore, hierarchy.Group]:
+    """Read a file and returns a pointer.
+
+    Parameters
+    ----------
+    zarr_source : Group
+        Zarr storage.
+    axes : str
+        Axes of the data.
+
+    Returns
+    -------
+    np.ndarray
+        Pointer to zarr storage.
+
+    Raises
+    ------
+    ValueError, OSError
+        if a file is not a valid tiff or damaged.
+    ValueError
+        if data dimensions are not 2, 3 or 4.
+    ValueError
+        if axes parameter from config is not consistent with data dimensions.
+    """
+    if isinstance(zarr_source, hierarchy.Group):
+        array = zarr_source[0]
+
+    elif isinstance(zarr_source, storage.DirectoryStore):
+        raise NotImplementedError("DirectoryStore not supported yet")
+
+    elif isinstance(zarr_source, core.Array):
+        # array should be of shape (S, (C), (Z), Y, X), iterating over S ?
+        if zarr_source.dtype == "O":
+            raise NotImplementedError("Object type not supported yet")
+        else:
+            array = zarr_source
+    else:
+        raise ValueError(f"Unsupported zarr object type {type(zarr_source)}")
+
+    # sanity check on dimensions
+    if len(array.shape) < 2 or len(array.shape) > 4:
+        raise ValueError(
+            f"Incorrect data dimensions. Must be 2, 3 or 4 (got {array.shape})."
+        )
+
+    # sanity check on axes length
+    if len(axes) != len(array.shape):
+        raise ValueError(f"Incorrect axes length (got {axes}).")
+
+    # arr = fix_axes(arr, axes)
+    return array

careamics/file_io/write/__init__.py

@@ -0,0 +1,15 @@
+"""Functions relating to writing image files of different formats."""
+
+__all__ = [
+    "get_write_func",
+    "write_tiff",
+    "WriteFunc",
+    "SupportedWriteType",
+]
+
+from .get_func import (
+    SupportedWriteType,
+    WriteFunc,
+    get_write_func,
+)
+from .tiff import write_tiff

careamics/file_io/write/get_func.py

@@ -0,0 +1,63 @@
+"""Module to get write functions."""
+
+from pathlib import Path
+from typing import Literal, Protocol
+
+from numpy.typing import NDArray
+
+from careamics.config.support import SupportedData
+
+from .tiff import write_tiff
+
+SupportedWriteType = Literal["tiff", "custom"]
+
+
+# This is very strict, arguments have to be called file_path & img
+# Alternative? - doesn't capture *args & **kwargs
+# WriteFunc = Callable[[Path, NDArray], None]
+class WriteFunc(Protocol):
+    """Protocol for type hinting write functions."""
+
+    def __call__(self, file_path: Path, img: NDArray, *args, **kwargs) -> None:
+        """
+        Type hinted callables must match this function signature (not including self).
+
+        Parameters
+        ----------
+        file_path : pathlib.Path
+            Path to file.
+        img : numpy.ndarray
+            Image data to save.
+        *args
+            Other positional arguments.
+        **kwargs
+            Other keyword arguments.
+        """
+
+
+WRITE_FUNCS: dict[SupportedData, WriteFunc] = {
+    SupportedData.TIFF: write_tiff,
+}
+
+
+def get_write_func(data_type: SupportedWriteType) -> WriteFunc:
+    """
+    Get the write function for the data type.
+
+    Parameters
+    ----------
+    data_type : {"tiff", "custom"}
+        Data type.
+
+    Returns
+    -------
+    callable
+        Write function.
+    """
+    # error raised here if not supported
+    data_type_ = SupportedData(data_type)  # new variable for mypy
+    # error if no write func.
+    if data_type_ not in WRITE_FUNCS:
+        raise NotImplementedError(f"No write function for data type '{data_type}'.")
+
+    return WRITE_FUNCS[data_type_]

careamics/file_io/write/tiff.py

@@ -0,0 +1,40 @@
+"""Write tiff function."""
+
+from fnmatch import fnmatch
+from pathlib import Path
+
+import tifffile
+from numpy.typing import NDArray
+
+from careamics.config.support import SupportedData
+
+
+def write_tiff(file_path: Path, img: NDArray, *args, **kwargs) -> None:
+    # TODO: add link to tiffile docs for args kwrgs?
+    """
+    Write tiff files.
+
+    Parameters
+    ----------
+    file_path : pathlib.Path
+        Path to file.
+    img : numpy.ndarray
+        Image data to save.
+    *args
+        Positional arguments passed to `tifffile.imwrite`.
+    **kwargs
+        Keyword arguments passed to `tifffile.imwrite`.
+
+    Raises
+    ------
+    ValueError
+        When the file extension of `file_path` does not match the Unix shell-style
+        pattern '*.tif*'.
+    """
+    if not fnmatch(
+        file_path.suffix, SupportedData.get_extension_pattern(SupportedData.TIFF)
+    ):
+        raise ValueError(
+            f"Unexpected extension '{file_path.suffix}' for save file type 'tiff'."
+        )
+    tifffile.imwrite(file_path, img, *args, **kwargs)

careamics/lightning/__init__.py

@@ -0,0 +1,18 @@
+"""CAREamics PyTorch Lightning modules."""
+
+__all__ = [
+    "FCNModule",
+    "VAEModule",
+    "create_careamics_module",
+    "TrainDataModule",
+    "create_train_datamodule",
+    "PredictDataModule",
+    "create_predict_datamodule",
+    "HyperParametersCallback",
+    "ProgressBarCallback",
+]
+
+from .callbacks import HyperParametersCallback, ProgressBarCallback
+from .lightning_module import FCNModule, VAEModule, create_careamics_module
+from .predict_data_module import PredictDataModule, create_predict_datamodule
+from .train_data_module import TrainDataModule, create_train_datamodule

careamics/lightning/callbacks/__init__.py

@@ -0,0 +1,11 @@
+"""Callbacks module."""
+
+__all__ = [
+    "HyperParametersCallback",
+    "ProgressBarCallback",
+    "PredictionWriterCallback",
+]
+
+from .hyperparameters_callback import HyperParametersCallback
+from .prediction_writer_callback import PredictionWriterCallback
+from .progress_bar_callback import ProgressBarCallback

careamics/lightning/callbacks/hyperparameters_callback.py

@@ -0,0 +1,49 @@
+"""Callback saving CAREamics configuration as hyperparameters in the model."""
+
+from pytorch_lightning import LightningModule, Trainer
+from pytorch_lightning.callbacks import Callback
+
+from careamics.config import Configuration
+
+
+class HyperParametersCallback(Callback):
+    """
+    Callback allowing saving CAREamics configuration as hyperparameters in the model.
+
+    This allows saving the configuration as dictionary in the checkpoints, and
+    loading it subsequently in a CAREamist instance.
+
+    Parameters
+    ----------
+    config : Configuration
+        CAREamics configuration to be saved as hyperparameter in the model.
+
+    Attributes
+    ----------
+    config : Configuration
+        CAREamics configuration to be saved as hyperparameter in the model.
+    """
+
+    def __init__(self, config: Configuration) -> None:
+        """
+        Constructor.
+
+        Parameters
+        ----------
+        config : Configuration
+            CAREamics configuration to be saved as hyperparameter in the model.
+        """
+        self.config = config
+
+    def on_train_start(self, trainer: Trainer, pl_module: LightningModule) -> None:
+        """
+        Update the hyperparameters of the model with the configuration on train start.
+
+        Parameters
+        ----------
+        trainer : Trainer
+            PyTorch Lightning trainer, unused.
+        pl_module : LightningModule
+            PyTorch Lightning module.
+        """
+        pl_module.hparams.update(self.config.model_dump())

careamics/lightning/callbacks/prediction_writer_callback/__init__.py

@@ -0,0 +1,20 @@
+"""A package for the `PredictionWriterCallback` class and utilities."""
+
+__all__ = [
+    "PredictionWriterCallback",
+    "create_write_strategy",
+    "WriteStrategy",
+    "WriteImage",
+    "CacheTiles",
+    "WriteTilesZarr",
+    "select_write_extension",
+    "select_write_func",
+]
+
+from .prediction_writer_callback import PredictionWriterCallback
+from .write_strategy import CacheTiles, WriteImage, WriteStrategy, WriteTilesZarr
+from .write_strategy_factory import (
+    create_write_strategy,
+    select_write_extension,
+    select_write_func,
+)

careamics/lightning/callbacks/prediction_writer_callback/file_path_utils.py

@@ -0,0 +1,56 @@
+"""Module containing file path utilities for `WriteStrategy` to use."""
+
+from pathlib import Path
+from typing import Union
+
+from careamics.dataset import IterablePredDataset, IterableTiledPredDataset
+
+
+# TODO: move to datasets package ?
+def get_sample_file_path(
+    dataset: Union[IterableTiledPredDataset, IterablePredDataset], sample_id: int
+) -> Path:
+    """
+    Get the file path for a particular sample.
+
+    Parameters
+    ----------
+    dataset : IterableTiledPredDataset or IterablePredDataset
+        Dataset.
+    sample_id : int
+        Sample ID, the index of the file in the dataset `dataset`.
+
+    Returns
+    -------
+    Path
+        The file path corresponding to the sample with the ID `sample_id`.
+    """
+    return dataset.data_files[sample_id]
+
+
+def create_write_file_path(
+    dirpath: Path, file_path: Path, write_extension: str
+) -> Path:
+    """
+    Create the file name for the output file.
+
+    Takes the original file path, changes the directory to `dirpath` and changes
+    the extension to `write_extension`.
+
+    Parameters
+    ----------
+    dirpath : pathlib.Path
+        The output directory to write file to.
+    file_path : pathlib.Path
+        The original file path.
+    write_extension : str
+        The extension that output files should have.
+
+    Returns
+    -------
+    Path
+        The output file path.
+    """
+    file_name = Path(file_path.stem).with_suffix(write_extension)
+    file_path = dirpath / file_name
+    return file_path