Merge pull request #1 from swaradgat19/fix/geojson_command

Fix/geojson command

.github/workflows/ci.yml

@@ -68,8 +68,8 @@ jobs:
             --wsi-dir slides/ --results-dir results/ --model breast-tumor-resnet34.tcga-brca
           test -f results/run_metadata_*.json
           test -f results/patches/JP2K-33003-1.h5
-          test -f results/model-outputs/JP2K-33003-1.csv
-          test $(wc -l < results/model-outputs/JP2K-33003-1.csv) -eq 675
+          test -f results/model-outputs-csv/JP2K-33003-1.csv
+          test $(wc -l < results/model-outputs-csv/JP2K-33003-1.csv) -eq 675
 
   # This is run on multiple operating systems.
   test-package:
@@ -104,8 +104,8 @@ jobs:
           wsinfer run --wsi-dir slides/ --results-dir results/ --model breast-tumor-resnet34.tcga-brca
           test -f results/run_metadata_*.json
           test -f results/patches/JP2K-33003-1.h5
-          test -f results/model-outputs/JP2K-33003-1.csv
-          test $(wc -l < results/model-outputs/JP2K-33003-1.csv) -eq 675
+          test -f results/model-outputs-csv/JP2K-33003-1.csv
+          test $(wc -l < results/model-outputs-csv/JP2K-33003-1.csv) -eq 675
       # FIXME: tissue segmentation has different outputs on Windows. The patch sizes
       # are the same but the coordinates found are different.
       - name: Run 'wsinfer run' on Windows
@@ -118,7 +118,7 @@ jobs:
           wsinfer run --wsi-dir slides/ --results-dir results/ --model breast-tumor-resnet34.tcga-brca
           Test-Path -Path results/run_metadata_*.json -PathType Leaf
           Test-Path -Path results/patches/JP2K-33003-1.h5 -PathType Leaf
-          Test-Path -Path results/model-outputs/JP2K-33003-1.csv -PathType Leaf
+          Test-Path -Path results/model-outputs-csv/JP2K-33003-1.csv -PathType Leaf
           # test $(python -c "print(sum(1 for _ in open('results/model-outputs/JP2K-33003-1.csv')))") -eq 675
 
   style-and-types:

docs/conf.py

@@ -99,7 +99,7 @@
     },
     "use_edit_page_button": True,
     "show_toc_level": 1,
-    # "navbar_align": "content",
+    "navbar_align": "left",
     "github_url": "https://github.com/SBU-BMI/wsinfer",
     "navbar_end": ["version-switcher", "theme-switcher", "navbar-icon-links"],
     "show_version_warning_banner": True,
@@ -112,5 +112,5 @@
     ],
     "header_links_before_dropdown": 6,
 }
-# html_logo = "_static/logo.svg"
-# html_favicon = "_static/log
+
+html_favicon = "_static/logo.svg"

docs/qupath_ext.rst

@@ -4,5 +4,4 @@ QuPath extension
 ================
 
 WSInfer has a QuPath extension for interactive model inference.
-
-This documentation is a work in progress.
+See `the documentation on QuPath's website <https://qupath.readthedocs.io/en/latest/docs/deep/wsinfer.html>`_.

pyproject.toml

@@ -55,7 +55,7 @@ dependencies = [
     "torch>=1.7",
     "torchvision",
     "tqdm",
-    "wsinfer-zoo",
+    "wsinfer-zoo>=0.6.2",
 ]
 dynamic = ["version"]
 

wsinfer/cli/infer.py

@@ -302,7 +302,7 @@ def run(
     # different directory, both directories need to be bind mounted onto the container.
     # If only the symlinked directory is included, then the patching script will fail,
     # even though it looks like there are files in the wsi_dir directory.
-    files_in_wsi_dir = [p for p in wsi_dir.glob("*") if p.exists()]
+    files_in_wsi_dir = [p for p in wsi_dir.iterdir() if p.is_file()]
     if not files_in_wsi_dir:
         raise FileNotFoundError(f"no files exist in the slide directory: {wsi_dir}")
 

wsinfer/modellib/run_inference.py

@@ -69,7 +69,7 @@ def run_inference(
     wsi_dir = Path(wsi_dir)
     if not wsi_dir.exists():
         raise errors.WholeSlideImageDirectoryNotFound(f"directory not found: {wsi_dir}")
-    wsi_paths = list(wsi_dir.glob("*"))
+    wsi_paths = [p for p in wsi_dir.iterdir() if p.is_file()]
     if not wsi_paths:
         raise errors.WholeSlideImagesNotFound(wsi_dir)
     results_dir = Path(results_dir)

wsinfer/patchlib/__init__.py

@@ -347,7 +347,7 @@ def segment_and_patch_directory_of_slides(
 
     _validate_wsi_directory(wsi_dir)
 
-    slide_paths = sorted(wsi_dir.glob("*"))
+    slide_paths = sorted([p for p in wsi_dir.iterdir() if p.is_file()])
 
     # NOTE: we could use multi-processing here but then the logs would get
     # discombobulated.

wsinfer/write_geojson.py

@@ -6,12 +6,10 @@
 from __future__ import annotations
 
 import json
-import shutil
 import uuid
 from functools import partial
 from pathlib import Path
 
-import click
 import pandas as pd
 from tqdm.contrib.concurrent import process_map
 
@@ -91,9 +89,10 @@ def write_geojsons(csvs: list[Path], results_dir: Path, num_workers: int) -> Non
         )
     if not (results_dir / "model-outputs-csv").exists():
         raise FileExistsError(
-            "Expected results_dir to contain a 'model-outputs-csv' directory but it does"
-            " not. Please provide the path to the directory that contains"
-            " model-outputs, masks, and patches."
+            "Expected results_dir to contain a 'model-outputs-csv' "
+            "directory but it does not."
+            "Please provide the path to the directory"
+            "that contains model-outputs, masks, and patches."
         )
     if output.exists():
         geojsons = list((results_dir / "model-outputs-geojson").glob("*.json"))

wsinfer/wsi.py

@@ -221,11 +221,10 @@ def _get_mpp_tiffslide(
 def _get_mpp_tifffile(slide_path: str | Path) -> tuple[float, float]:
     """Read MPP using Tifffile."""
     with tifffile.TiffFile(slide_path) as tif:
-        try:
-            series0 = tif.series[0]
-            page0 = series0[0]
-        except:
-            raise CannotReadSpacing()
+        series0 = tif.series[0]
+        page0 = series0[0]
+        if not isinstance(page0, tifffile.TiffPage):
+            raise CannotReadSpacing("not a tifffile.TiffPage instance")
         try:
             resolution_unit = page0.tags["ResolutionUnit"].value
             x_resolution = Fraction(*page0.tags["XResolution"].value)
@@ -291,7 +290,7 @@ def get_avg_mpp(slide_path: Path | str) -> float:
 def _validate_wsi_directory(wsi_dir: str | Path) -> None:
     """Validate a directory of whole slide images."""
     wsi_dir = Path(wsi_dir)
-    maybe_slides = sorted(wsi_dir.glob("*"))
+    maybe_slides = [p for p in wsi_dir.iterdir() if p.is_file()]
     uniq_stems = set(p.stem for p in maybe_slides)
     if len(uniq_stems) != len(maybe_slides):
         raise DuplicateFilePrefixesFound(