Merge pull request #226 from Dana-Farber-AIOS/myFeature

added write functionality within run with optional flag, defaulting t…

README.md

@@ -13,7 +13,7 @@ A toolkit for computational pathology and machine learning.
 
 **View [documentation](https://pathml.readthedocs.io/en/latest/)**
 
-**Please cite [our paper](https://www.biorxiv.org/content/10.1101/2021.10.21.465212v1)**
+**Please cite [our paper](https://www.biorxiv.org/content/10.1101/2021.10.21.465212)**
 
 # Installation
 

pathml/core/slide_data.py

@@ -251,6 +251,7 @@ def run(
         level=0,
         tile_pad=False,
         overwrite_existing_tiles=False,
+        write_dir=None,
     ):
         """
         Run a preprocessing pipeline on SlideData.
@@ -269,6 +270,9 @@ def run(
                 Defaults to ``False``.
             overwrite_existing_tiles (bool): Whether to overwrite existing tiles. If ``False``, running a pipeline will
                 fail if ``tiles is not None``. Defaults to ``False``.
+            write_dir (str): Path to directory to write the processed slide to. The processed SlideData object
+                will be written to the directory immediately after the pipeline has completed running.
+                The filepath will default to "<write_dir>/<slide.name>.h5path. Defaults to ``None``.
         """
         assert isinstance(
             pipeline, pathml.preprocessing.pipeline.Pipeline
@@ -320,6 +324,9 @@ def run(
                 pipeline.apply(tile)
                 self.tiles.add(tile)
 
+        if write_dir:
+            self.write(Path(write_dir) / f"{self.name}.h5path")
+
     @property
     def shape(self):
         """

tests/core_tests/test_slide_data.py

@@ -170,3 +170,23 @@ def compare_dict_ignore_order(d1, d2):
         if d1[k1] != d2[k2]:
             return False
     return True
+
+
+@pytest.mark.parametrize("write", [True, False])
+def test_run_and_write(tmpdir, write):
+    wsi = HESlide("tests/testdata/small_HE.svs", backend="openslide", name="testwrite")
+    pipe = Pipeline()
+
+    if write:
+        write_dir_arg = tmpdir
+    else:
+        write_dir_arg = None
+
+    wsi.run(pipe, tile_size=500, distributed=False, write_dir=write_dir_arg)
+
+    written_path = tmpdir / "testwrite.h5path"
+
+    if write:
+        assert written_path.isfile()
+    else:
+        assert not written_path.isfile()

tests/core_tests/test_slide_dataset.py

@@ -3,7 +3,7 @@
 License: GNU GPL 2.0
 """
 
-from dask.distributed import Client
+import pytest
 from pathlib import Path
 
 from pathml.core import SlideData, Tile
@@ -38,3 +38,22 @@ def test_run_pipeline_and_tile_dataset_and_reshape(slide_dataset):
     tile_after_reshape = slide_dataset[0].tiles[0]
     assert isinstance(tile_after_reshape, Tile)
     assert tile_after_reshape.image.shape == (25, 25, 3)
+
+
+@pytest.mark.parametrize("write", [True, False])
+def test_run_and_write_dataset(tmpdir, write, slide_dataset):
+    pipe = Pipeline()
+
+    if write:
+        write_dir_arg = tmpdir
+    else:
+        write_dir_arg = None
+
+    slide_dataset.run(pipe, tile_size=500, distributed=False, write_dir=write_dir_arg)
+
+    for s in slide_dataset:
+        written_path = tmpdir / f"{s.name}.h5path"
+        if write:
+            assert written_path.isfile()
+        else:
+            assert not written_path.isfile()