dsa-helpers 0.4.dev4__tar.gz → 0.5__tar.gz

dsa_helpers-0.5/.gitignore

@@ -0,0 +1,11 @@
+# Python environment directories.
+env/
+pyenv/
+
+*.pyc
+*.egg-info
+dist/
+.env
+
+# Ignore data directory created for testing the package.
+tests/data/

{dsa_helpers-0.4.dev4/dsa_helpers.egg-info → dsa_helpers-0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.4.dev4
+Version: 0.5
 Summary: Utility functions for working with the DSA girder client.
 Author-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
 Maintainer-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
@@ -8,7 +8,7 @@ Project-URL: Repository, https://github.com/Gutman-Lab/dsa-python-utils
 Keywords: dsa,girder,girder_client
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.9
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: girder-client
@@ -22,9 +22,9 @@ Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
 Requires-Dist: shapely
 Requires-Dist: geopandas
+Requires-Dist: transformers[torch]
 Requires-Dist: torch
 Requires-Dist: datasets
-Requires-Dist: transformers
 Requires-Dist: torchvision
 
 # Digital Slide Archive (DSA) Helpers

dsa_helpers-0.5/dsa_helpers/__init__.py

@@ -0,0 +1,16 @@
+# Shadow imports.
+from .imread import imread
+from .imwrite import imwrite
+from . import girder_utils, image_utils, dash, ml, mongo_utils, utils
+
+# Modules that should be available.
+__all__ = [
+    "girder_utils",
+    "image_utils",
+    "dash",
+    "ml",
+    "imread",
+    "imwrite",
+    "mongo_utils",
+    "utils",
+]

dsa_helpers-0.5/dsa_helpers/dash/__init__.py

@@ -0,0 +1,3 @@
+from . import header
+
+__all__ = ["dash_paperdragon_utils", "header_callbacks", "header"]

dsa_helpers-0.5/dsa_helpers/dash/dash_paperdragon_utils.py

@@ -0,0 +1,76 @@
+def format_ann_docs_for_paperjs(
+    geojson_ann_docs: list[dict], return_as_input_to_paper: bool = False
+) -> list[dict]:
+    """Format DSA annotations in the geojson format into a format that paperdragon
+    can read and show as polygons.
+
+    Args:
+        geojson_ann_docs (list[dict]): A list of geojson annotation documents.
+        return_as_input_to_paper (bool): Whether to return the formatted documents as
+            input to paper. Defaults to False.
+
+    Returns:
+        list[dict]: A list of formatted annotation documents for paperjs. Note that
+            it will return an empty list if the documents could not be formatted.
+
+    """
+    # NOTE: hard-coded to only do the first doc.
+    formatted_docs = []
+
+    # Loop through each annotation document.
+    for ann_doc in geojson_ann_docs:
+        # Grab the features of this document, contains the polygon info.
+        features_to_include = []
+
+        for feature in ann_doc["features"]:
+            geometry = feature["geometry"]
+            if geometry["type"] == "Polygon":
+                properties = feature["properties"]
+                properties["rescale"] = {"strokeWidth": properties["lineWidth"]}
+                properties["strokeColor"] = properties["lineColor"]
+                properties["source"] = "dsa"
+
+                # Paperjs only supports multipolygons.
+                geometry["type"] = "MultiPolygon"
+
+                coordinates = geometry["coordinates"]
+
+                adjusted_coordinates = [
+                    [[[int(coord) for coord in point[:2]] for point in coordinates[0]]]
+                ]
+
+                geometry["coordinates"] = adjusted_coordinates
+
+                features_to_include.append(feature)
+
+        if len(features_to_include):
+            formatted_docs.append(features_to_include)
+
+    if return_as_input_to_paper:
+        return get_input_to_paper_dict(formatted_docs)
+
+    return formatted_docs
+
+
+def get_input_to_paper_dict(formatted_docs: list[dict] | None = None) -> dict:
+    """Get the input to paper dictionary.
+
+    Args:
+        formatted_docs (list[dict]): A list of formatted annotation documents for paperjs.
+
+    Returns:
+        dict: The input to paper dictionary.
+
+    """
+    input_to_paper = [{"type": "clearItems"}]
+
+    if formatted_docs is not None and len(formatted_docs):
+        for doc in formatted_docs:
+            input_to_paper.append(
+                {
+                    "type": "drawItems",
+                    "itemList": doc,
+                }
+            )
+
+    return {"actions": input_to_paper}

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers/image_utils.py

@@ -13,6 +13,8 @@ def tile_image(
     stride: int | None = None,
     fill: int | tuple = (255, 255, 255),
     prepend_name: str = "",
+    overwrite: bool = False,
+    grayscale: bool = False,
 ) -> pd.DataFrame:
     """Tile an image into smaller images.
 
@@ -25,6 +27,10 @@ def tile_image(
         fill (int | tuple, optional): The fill value for tiles over the edges.
             Defaults to (255, 255, 255).
         prepend_name (str, optional): A string to prepend to the tile names.
+        overwrite (bool, optional): Whether to overwrite existing images.
+            Defaults to False.
+        grayscale (bool, optional): Whether to save images as grayscale instead
+            of the default RGB. Defaults to False.
 
     Returns:
         pandas.DataFrame: A DataFrame with the tile locations.
@@ -38,9 +44,7 @@ def tile_image(
 
     # Pad the image to avoid tiles not of the right size.
     save_loc = Path(save_loc)
-
-    if not save_loc.exists():
-        save_loc.mkdir(parents=True)
+    save_loc.mkdir(parents=True, exist_ok=True)
 
     if stride is None:
         stride = tile_size
@@ -49,17 +53,22 @@ def tile_image(
 
     xys = [(x, y) for x in range(0, w, stride) for y in range(0, h, stride)]
 
+    if prepend_name:
+        prepend_name += "_"
+
     for xy in xys:
+        # Get the top left and bottom right coordinates of the tile.
         x, y = xy
-        # Get the tile from the image.
-        tile_img = img[x : x + tile_size, y : y + tile_size]
 
-        save_fp = str(save_loc.joinpath(f"{prepend_name}x-{x}y-{y}.png"))
+        # Filepath for saving tile.
+        save_fp = save_loc / f"{prepend_name}x{x}y{y}tilesize{tile_size}.png"
 
-        imwrite(save_fp, tile_img)
+        if not save_fp.is_file() or overwrite:
+            # Get the tile from the image.
+            tile_img = img[y : y + tile_size, x : x + tile_size]
 
-        df_data.append([save_fp, x, y])
+            imwrite(save_fp, tile_img, grayscale=grayscale)
 
-    df = pd.DataFrame(df_data, columns=["fp", "x", "y"])
+        df_data.append([save_fp, x, y, tile_size])
 
-    return df
+    return pd.DataFrame(df_data, columns=["fp", "x", "y", "tile_size"])

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers/ml/datasets/utils.py

@@ -37,6 +37,6 @@ def create_segformer_segmentation_dataset(
     )
 
     if transforms is not None:
-        dataset = dataset.set_transform(transforms)
+        dataset.set_transform(transforms)
 
     return dataset

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers/ml/metrics/binary_dice_coefficient_metric.py

@@ -7,7 +7,8 @@ def binary_dice_coefficient_metric(eval_pred):
     with torch.no_grad():
         logits, labels = eval_pred  # assumed both are numpy
 
-        logits_tensor = torch.from_numpy(logits)
+        logits_tensor = torch.from_numpy(logits).cpu()
+        labels_tensor = torch.from_numpy(labels).cpu()
 
         # Scale the logits to the size of the label.
         logits_tensor = nn.functional.interpolate(
@@ -17,6 +18,7 @@ def binary_dice_coefficient_metric(eval_pred):
             align_corners=False,
         ).argmax(dim=1)
 
-        pred_labels = logits_tensor.detach().cpu().numpy()
+        pred_labels = logits_tensor.detach().numpy()
+        labels = labels_tensor.numpy()
 
         return {"dice_coefficient": binary_dice_coefficient(pred_labels, labels)}

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers/ml/object_detection/__init__.py

@@ -2,4 +2,4 @@
 from .get_pearce_roi_images import get_pearce_roi_images
 from .tile_image import tile_image
 
-__all__ = ["utils"]
+__all__ = ["utils", "get_pearce_roi_images", "tile_image"]

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5/dsa_helpers.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.4.dev4
+Version: 0.5
 Summary: Utility functions for working with the DSA girder client.
 Author-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
 Maintainer-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
@@ -8,7 +8,7 @@ Project-URL: Repository, https://github.com/Gutman-Lab/dsa-python-utils
 Keywords: dsa,girder,girder_client
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.9
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: girder-client
@@ -22,9 +22,9 @@ Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
 Requires-Dist: shapely
 Requires-Dist: geopandas
+Requires-Dist: transformers[torch]
 Requires-Dist: torch
 Requires-Dist: datasets
-Requires-Dist: transformers
 Requires-Dist: torchvision
 
 # Digital Slide Archive (DSA) Helpers

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers.egg-info/SOURCES.txt

@@ -9,7 +9,6 @@ dsa_helpers/girder_utils.py
 dsa_helpers/image_utils.py
 dsa_helpers/imread.py
 dsa_helpers/imwrite.py
-dsa_helpers/login.py
 dsa_helpers/mongo_utils.py
 dsa_helpers/utils.py
 dsa_helpers.egg-info/PKG-INFO
@@ -18,6 +17,7 @@ dsa_helpers.egg-info/dependency_links.txt
 dsa_helpers.egg-info/requires.txt
 dsa_helpers.egg-info/top_level.txt
 dsa_helpers/dash/__init__.py
+dsa_helpers/dash/dash_paperdragon_utils.py
 dsa_helpers/dash/header.py
 dsa_helpers/dash/header_callbacks.py
 dsa_helpers/ml/__init__.py

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/dsa_helpers.egg-info/requires.txt

@@ -9,7 +9,7 @@ dash
 dash_bootstrap_components
 shapely
 geopandas
+transformers[torch]
 torch
 datasets
-transformers
 torchvision

{dsa_helpers-0.4.dev4 → dsa_helpers-0.5}/pyproject.toml

@@ -15,9 +15,9 @@ dependencies = [
     'dash_bootstrap_components',
     'shapely',
     'geopandas',
+    "transformers[torch]",
     "torch",
     "datasets",
-    "transformers",
     "torchvision"
 ]
 name = "dsa_helpers"
@@ -29,13 +29,13 @@ maintainers = [
 ]
 description = "Utility functions for working with the DSA girder client."
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.8"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
 ]
 keywords = ["dsa", "girder", "girder_client"]
-version = "v0.4dev4"
+version = "v0.5"
 
 [project.urls]
 Repository = "https://github.com/Gutman-Lab/dsa-python-utils"

dsa_helpers-0.5/requirements.txt

@@ -0,0 +1,23 @@
+# For developing the package locally.
+build
+twine
+
+# For tests.
+matplotlib
+jupyter
+
+# Mirrored requirements from pyproject.toml
+girder-client
+numpy
+setuptools
+opencv-python
+pandas
+pymongo
+pillow
+dash
+dash_bootstrap_components
+python-dotenv
+transformers[torch]
+torch
+datasets
+torchvision

dsa_helpers-0.5/tests/test.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests\n",
+    "Test different functions of the library."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import the library.\n",
+    "import dsa_helpers as dh\n",
+    "from pathlib import Path\n",
+    "import matplotlib.pyplot as plt\n",
+    "from shutil import rmtree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Constants\n",
+    "DATA_DIR = \"data\"\n",
+    "DSA_API_URL = \"https://computablebrain.emory.edu/api/v1\"\n",
+    "DSA_WSI_ITEM_ID = \"670fd3e2897872a4bba54097\"\n",
+    "THUMBNAIL_MAG = 2.0\n",
+    "TILE_SIZE = 512"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Authenticate girder client.\n",
+    "gc = dh.girder_utils.login(DSA_API_URL)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Clean up the data directory.\n",
+    "rmtree(DATA_DIR, ignore_errors=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1.1. Get thumbnail at specified magnification."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Read a sample thumbnail from the DSA.\n",
+    "thumbnail_img = dh.girder_utils.get_thumbnail(\n",
+    "    gc, \n",
+    "    DSA_WSI_ITEM_ID,\n",
+    "    mag=THUMBNAIL_MAG\n",
+    ")[:, :, :3]\n",
+    "\n",
+    "plt.imshow(thumbnail_img)\n",
+    "plt.title(f'Thumbnail Image (mag={THUMBNAIL_MAG})')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1.2. Tile thumbnail from numpy array."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create location to save tiles.\n",
+    "save_dir = Path(DATA_DIR) / \"thumbnail_tile_images\"\n",
+    "\n",
+    "# Tile the image.\n",
+    "tiles_df = dh.image_utils.tile_image(\n",
+    "    thumbnail_img,\n",
+    "    save_dir, \n",
+    "    tile_size=TILE_SIZE,\n",
+    "    fill=(114, 114, 114),\n",
+    "    prepend_name=\"thumbnail\",\n",
+    ")\n",
+    "\n",
+    "tiles_df.head()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

dsa_helpers-0.4.dev4/.gitignore

@@ -1,11 +0,0 @@
-# Python environment directories.
-env/
-pyenv/
-
-# Do not push the version file.
-dsa_utils/_version.py
-
-*.pyc
-*.egg-info
-dist/
-.env

dsa_helpers-0.4.dev4/dsa_helpers/__init__.py

@@ -1,8 +0,0 @@
-# Shadow imports.
-from .imread import imread
-from .imwrite import imwrite
-
-# Modules that should be available.
-# from . import girder_utils, image_utils, dash
-
-__all__ = ["girder_utils", "image_utils", "dash", "ml"]

dsa_helpers-0.4.dev4/dsa_helpers/dash/__init__.py

@@ -1 +0,0 @@
-from . import header

dsa_helpers-0.4.dev4/dsa_helpers/login.py

@@ -1,36 +0,0 @@
-# Login / authenticate function for the girder client.
-from girder_client import GirderClient
-
-
-def login(
-    api_url: str,
-    login_or_email: str | None = None,
-    password: str | None = None,
-    api_key: str | None = None,
-) -> GirderClient:
-    """Authenticate a girder client with the given credentials or interactively
-    if none is given.
-
-    Args:
-        api_url (str): The DSA girder API url.
-        login_or_email (str | None): The login or email. Defaults to None.
-        password (str | None): Password for login / email. Defaults to None.
-        api_key (str | None): The api key to authenticate with. Defaults to None.
-
-    Returns:
-        girder_client.GirderClient: The authenticated girder client.
-
-    """
-    gc = GirderClient(apiUrl=api_url)
-
-    if api_key is None:
-        if login_or_email is None:
-            _ = gc.authenticate(interactive=True)
-        elif password is None:
-            _ = gc.authenticate(username=login_or_email, interactive=True)
-        else:
-            _ = gc.authenticate(username=login_or_email, password=password)
-    else:
-        _ = gc.authenticate(apiKey=api_key)
-
-    return gc

dsa_helpers-0.4.dev4/requirements.txt

@@ -1,15 +0,0 @@
-girder-client
-numpy
-setuptools
-opencv-python
-pandas
-pymongo
-jupyter
-pillow
-dash
-dash_bootstrap_components
-python-dotenv
-torch
-datasets
-transformers
-torchvision

dsa_helpers-0.4.dev4/tests/test.ipynb

@@ -1,79 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Test Python Package Build"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Import all modules.\n",
-    "from dsa_helpers import *"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Authenticate girder client."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "gc = girder_utils.login(\"\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Get DSA items recursively"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Get items from a folder.\n",
-    "items = girder_utils.get_items(gc, \"\")\n",
-    "print(f\"Got {len(items)} items from folder.\")\n",
-    "\n",
-    "items = girder_utils.get_items(gc, \"\")\n",
-    "print(f\"Got {len(items)} items from collection.\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "env",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}