merge main

Author: srivarra

.readthedocs.yaml

@@ -0,0 +1,28 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.12"
+  jobs:
+    post_build:
+      - python docs/scripts/fix_md_links.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/conf.py

viscy/utils/meta_utils.py

@@ -7,10 +7,10 @@
 import iohub.ngff as ngff
 import numpy as np
 import pandas as pd
-from numpy.typing import NDArray
+import tensorstore
+from tqdm import tqdm
 
-import viscy.utils.mp_utils as mp_utils
-from viscy.utils.cli_utils import show_progress_bar
+from viscy.utils.mp_utils import get_val_stats
 
 
 def write_meta_field(position: ngff.Position, metadata, field_name, subfield_name):
@@ -54,6 +54,21 @@ def write_meta_field(position: ngff.Position, metadata, field_name, subfield_nam
         position.zattrs[field_name] = field_metadata
 
 
+def _grid_sample(
+    position: ngff.Position, grid_spacing: int, channel_index: int, num_workers: int
+):
+    return (
+        position["0"]
+        .tensorstore(
+            context=tensorstore.Context(
+                {"data_copy_concurrency": {"limit": num_workers}}
+            )
+        )[:, channel_index, :, ::grid_spacing, ::grid_spacing]
+        .read()
+        .result()
+    )
+
+
 def generate_normalization_metadata(
     zarr_dir: str | Path,
     num_workers: int = 4,
@@ -181,8 +196,7 @@ def generate_normalization_metadata(
                 subfield_name=str(channel_id),
             )
 
-    print(f"Generated normalization metadata for {len(channel_ids)} channels")
-    print(f"Dataset-level statistics: {final_dataset_stats}")
+    plate.close()
 
 
 def compute_normalization_stats(

viscy/utils/mp_utils.py

@@ -323,71 +323,3 @@ def get_val_stats(sample_values: list[float]) -> dict[str, float]:
         "iqr": float(scipy.stats.iqr(sample_values)),
     }
     return meta_row
-
-
-def mp_sample_im_pixels(
-    fn_args: list[tuple[Any, ...]], workers: int
-) -> list[list[Any]]:
-    """Read and compute statistics of images with multiprocessing.
-
-    Parameters
-    ----------
-    fn_args : list[tuple[Any, ...]]
-        List with tuples of function arguments.
-    workers : int
-        Max number of workers.
-
-    Returns
-    -------
-    list[list[Any]]
-        List of paths and corresponding returned df from get_im_stats.
-    """
-    with ProcessPoolExecutor(workers) as ex:
-        # can't use map directly as it works only with single arg functions
-        res = ex.map(sample_im_pixels, *zip(*fn_args))
-    return list(map(list, zip(*list(res))))
-
-
-def sample_im_pixels(
-    position: ngff.Position,
-    grid_spacing: int,
-    channel: int,
-) -> tuple[ngff.Position, NDArray]:
-    # TODO move out of mp utils into normalization utils
-    """Read and compute statistics of images for each point in a grid.
-
-    Grid spacing determines distance in pixels between grid points
-    for rows and cols. By default, samples from every time position and every z-depth,
-    and assumes that the data in the zarr store is stored in [T,C,Z,Y,X] format,
-    for time, channel, z, y, x.
-
-    Parameters
-    ----------
-    position : ngff.Position
-        NGFF position node object.
-    grid_spacing : int
-        Spacing of sampling grid in x and y.
-    channel : int
-        Channel to sample from.
-
-    Returns
-    -------
-    tuple[ngff.Position, NDArray]
-        Position and array with intensity data for each grid point.
-    """
-    image_zarr = position.data
-
-    all_sample_values = []
-    all_time_indices = list(range(image_zarr.shape[0]))
-    all_z_indices = list(range(image_zarr.shape[2]))
-
-    for time_index in all_time_indices:
-        for z_index in all_z_indices:
-            image_slice = image_zarr[time_index, channel, z_index, :, :]
-            _, _, sample_values = image_utils.grid_sample_pixel_values(
-                image_slice, grid_spacing
-            )
-            all_sample_values.append(sample_values)
-    sample_values = np.stack(all_sample_values, 0).flatten()
-
-    return position, sample_values