dsa-helpers 0.4__tar.gz → 0.4.dev1__tar.gz

{dsa_helpers-0.4/dsa_helpers.egg-info → dsa_helpers-0.4.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.4
+Version: 0.4.dev1
 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>
@@ -22,10 +22,6 @@ Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
 Requires-Dist: shapely
 Requires-Dist: geopandas
-Requires-Dist: torch
-Requires-Dist: datasets
-Requires-Dist: transformers
-Requires-Dist: torchvision
 
 # Digital Slide Archive (DSA) Helpers
 Digital Slide Archive Python utility library.
@@ -40,11 +36,9 @@ This Python PyPI package is found [here](https://pypi.org/project/dsa-helpers/).
 1. Install requirements for building and distributing package:
 ```
 $ python3 -m pip install --upgrade build  # for building package
-$ python3 -m pip install --upgrade twine  # for uploading to PyPI
+$ python3 -m pip install --upgrade build  # for uploading to PyPI
 ```
 2. When ready to build:
     - Modify "pyproject.toml" file, change the "version" key to a different value than a version already pushed.
     - Run ```$ python3 -m build```. This will create a dist directory and put your new wheel and tar distribution files there.
 3. To install locally for development: ```$ pip3 install dist/dsa_helpers-*.whl```, choosing the wheel version you want to test.
-4. Upload to PyPI using twine: ```python3 -m twine upload --repository pypi dist/*```
-    * You can specify specific files to upload, the line above pushes everything in dist directory.

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/README.md

@@ -11,11 +11,9 @@ This Python PyPI package is found [here](https://pypi.org/project/dsa-helpers/).
 1. Install requirements for building and distributing package:
 ```
 $ python3 -m pip install --upgrade build  # for building package
-$ python3 -m pip install --upgrade twine  # for uploading to PyPI
+$ python3 -m pip install --upgrade build  # for uploading to PyPI
 ```
 2. When ready to build:
     - Modify "pyproject.toml" file, change the "version" key to a different value than a version already pushed.
     - Run ```$ python3 -m build```. This will create a dist directory and put your new wheel and tar distribution files there.
-3. To install locally for development: ```$ pip3 install dist/dsa_helpers-*.whl```, choosing the wheel version you want to test.
-4. Upload to PyPI using twine: ```python3 -m twine upload --repository pypi dist/*```
-    * You can specify specific files to upload, the line above pushes everything in dist directory.
+3. To install locally for development: ```$ pip3 install dist/dsa_helpers-*.whl```, choosing the wheel version you want to test.

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/dsa_helpers/__init__.py

@@ -5,4 +5,4 @@ from .imwrite import imwrite
 # Modules that should be available.
 # from . import girder_utils, image_utils, dash
 
-__all__ = ["girder_utils", "image_utils", "dash", "ml"]
+__all__ = ["girder_utils", "image_utils", "dash"]

dsa_helpers-0.4.dev1/dsa_helpers/ml/__init__.py

@@ -0,0 +1,2 @@
+# Modules that can be imported.
+__all__ = ["object_detection"]

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/dsa_helpers/mongo_utils.py

@@ -13,7 +13,7 @@ def get_mongo_client(
     username: str | None = None,
     password: str | None = None,
     port: int | None = None,
-):
+) -> pymongo.MongoClient:
     """Get a mongo client by providing the key parts of the URL. By default
     when the parameters are not passed, it sets them to default values first
     by looking at key environment variables. If the environment variables are
@@ -36,7 +36,7 @@ def get_mongo_client(
             missing it will default to 27017.
 
     Returns:
-        The mongo client.
+        pymongo.MongoClient: The mongo client.
 
     """
     if username is None:
@@ -67,7 +67,7 @@ def chunks(lst: list, n=500):
 
 
 def add_many_to_collection(
-    mongo_collection,
+    mongo_collection: pymongo.collection.Collection,
     items: dict | list,
     key: str = "_id",
 ) -> dict[str | dict]:
@@ -75,7 +75,7 @@ def add_many_to_collection(
     user key.
 
     Args:
-        mongo_collection: The mongo collection to add to.
+        mongo_collection (pymongo.collection.Collection): The mongo collection to add to.
         items (dict | list): The items to add to the collection.
         key (str): The key to use to identify the items.
 
@@ -89,8 +89,10 @@ def add_many_to_collection(
 
     operations = []
 
-    for _id, item in items.items():
-        operations.append(pymongo.UpdateOne({"_id": _id}, {"$set": item}, upsert=True))
+    for item in items:
+        operations.append(
+            pymongo.UpdateOne({"_id": item[key]}, {"$set": item}, upsert=True)
+        )
 
     for chunk in chunks(operations):
         _ = mongo_collection.bulk_write(chunk)
@@ -98,11 +100,13 @@ def add_many_to_collection(
     return items
 
 
-def get_img_from_db(mongo_db, img_id: str) -> Union[np.ndarray, None]:
+def get_img_from_db(
+    mongo_db: pymongo.database.Database, img_id: str
+) -> Union[np.ndarray, None]:
     """Get an image from the database by its location id.
 
     Args:
-        mongo_db: The mongo database.
+        mongo_db (pymongo.database.Database): The mongo database.
         img_loc (str): The image id in mongo.
 
     Returns:
@@ -127,13 +131,13 @@ def get_img_from_db(mongo_db, img_id: str) -> Union[np.ndarray, None]:
 
 
 def add_img_to_db(
-    mongo_db,
+    mongo_db: pymongo.database.Database,
     img: Image.Image | np.ndarray,
 ) -> str:
     """Add an image to the database.
 
     Args:
-        mongo_db: The mongo database.
+        mongo_db (pymongo.database.Database): The mongo database.
         img (np.ndarray or PIL.Image.Image): The image.
 
     Returns:

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1/dsa_helpers.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.4
+Version: 0.4.dev1
 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>
@@ -22,10 +22,6 @@ Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
 Requires-Dist: shapely
 Requires-Dist: geopandas
-Requires-Dist: torch
-Requires-Dist: datasets
-Requires-Dist: transformers
-Requires-Dist: torchvision
 
 # Digital Slide Archive (DSA) Helpers
 Digital Slide Archive Python utility library.
@@ -40,11 +36,9 @@ This Python PyPI package is found [here](https://pypi.org/project/dsa-helpers/).
 1. Install requirements for building and distributing package:
 ```
 $ python3 -m pip install --upgrade build  # for building package
-$ python3 -m pip install --upgrade twine  # for uploading to PyPI
+$ python3 -m pip install --upgrade build  # for uploading to PyPI
 ```
 2. When ready to build:
     - Modify "pyproject.toml" file, change the "version" key to a different value than a version already pushed.
     - Run ```$ python3 -m build```. This will create a dist directory and put your new wheel and tar distribution files there.
 3. To install locally for development: ```$ pip3 install dist/dsa_helpers-*.whl```, choosing the wheel version you want to test.
-4. Upload to PyPI using twine: ```python3 -m twine upload --repository pypi dist/*```
-    * You can specify specific files to upload, the line above pushes everything in dist directory.

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/dsa_helpers.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ LICENSE
 README.md
 app.py
 pyproject.toml
+readthedocs.yaml
 requirements.txt
 dsa_helpers/__init__.py
 dsa_helpers/girder_utils.py
@@ -11,7 +12,6 @@ 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
 dsa_helpers.egg-info/SOURCES.txt
 dsa_helpers.egg-info/dependency_links.txt
@@ -21,18 +21,8 @@ dsa_helpers/dash/__init__.py
 dsa_helpers/dash/header.py
 dsa_helpers/dash/header_callbacks.py
 dsa_helpers/ml/__init__.py
-dsa_helpers/ml/datasets/SegFormerSegmentationDataset.py
-dsa_helpers/ml/datasets/__init__.py
-dsa_helpers/ml/datasets/utils.py
-dsa_helpers/ml/metrics/__init__.py
-dsa_helpers/ml/metrics/binary_dice_coefficient_metric.py
 dsa_helpers/ml/object_detection/__init__.py
 dsa_helpers/ml/object_detection/get_pearce_roi_images.py
 dsa_helpers/ml/object_detection/tile_image.py
 dsa_helpers/ml/object_detection/utils.py
-dsa_helpers/ml/transforms/__init__.py
-dsa_helpers/ml/transforms/segformer_transforms.py
-tests/docker-compose.yaml
-tests/test.ipynb
-tests/app/Dockerfile
-tests/app/app.py
+tests/test.ipynb

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/dsa_helpers.egg-info/requires.txt

@@ -9,7 +9,3 @@ dash
 dash_bootstrap_components
 shapely
 geopandas
-torch
-datasets
-transformers
-torchvision

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/pyproject.toml

@@ -14,11 +14,7 @@ dependencies = [
     'dash',
     'dash_bootstrap_components',
     'shapely',
-    'geopandas',
-    "torch",
-    "datasets",
-    "transformers",
-    "torchvision"
+    'geopandas'
 ]
 name = "dsa_helpers"
 authors = [
@@ -35,7 +31,7 @@ classifiers = [
     "License :: OSI Approved :: MIT License",
 ]
 keywords = ["dsa", "girder", "girder_client"]
-version = "v0.4"
+version = "v0.4dev1"
 
 [project.urls]
 Repository = "https://github.com/Gutman-Lab/dsa-python-utils"

dsa_helpers-0.4.dev1/readthedocs.yaml

@@ -0,0 +1,27 @@
+# .readthedocs.yaml
+# 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:
+  tools:
+    python: "3.9"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF and ePub
+# formats:
+#    - pdf
+#    - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+# python:
+#    install:
+#    - requirements: docs/requirements.txt

{dsa_helpers-0.4 → dsa_helpers-0.4.dev1}/requirements.txt

@@ -8,8 +8,4 @@ jupyter
 pillow
 dash
 dash_bootstrap_components
-python-dotenv
-torch
-datasets
-transformers
-torchvision
+python-dotenv

dsa_helpers-0.4.dev1/tests/test.ipynb

@@ -0,0 +1,79 @@
+{
+ "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
+}

dsa_helpers-0.4/dsa_helpers/ml/__init__.py

@@ -1,2 +0,0 @@
-# Modules that can be imported.
-__all__ = ["object_detection", "datasets", "metrics", "transforms"]

dsa_helpers-0.4/dsa_helpers/ml/datasets/SegFormerSegmentationDataset.py

@@ -1,33 +0,0 @@
-from torch.utils.data import Dataset
-import pandas as pd
-from PIL import Image
-import numpy as np
-
-
-class SegFormerSegmentationDataset(Dataset):
-    """PyTorch dataset class for semantic segmentation using HuggingFaces SegFormer
-    model.
-
-    """
-
-    def __init__(self, df: pd.DataFrame):
-        """Initiate an instance of the segmentation dataset.
-
-        Args:
-            df (pandas.DataFrame): A pandas DataFrame with columns "fp" and "mask_fp".
-
-        """
-        self.image_files = df["fp"].tolist()
-        self.mask_files = df["mask_fp"].tolist()
-        self.df = df  # store potential metadata
-
-    def __len__(self):
-        return len(self.image_files)
-
-    def __getitem__(self, idx):
-        # Get the filepath to the image and its mask.
-        image_path = self.image_files[idx]
-        mask_path = self.mask_files[idx]
-
-        # Return image & mask as PIL images in a dictionary.
-        return {"pixel_values": Image.open(image_path), "label": Image.open(mask_path)}

dsa_helpers-0.4/dsa_helpers/ml/datasets/__init__.py

@@ -1,3 +0,0 @@
-from .SegFormerSegmentationDataset import SegFormerSegmentationDataset
-
-__all__ = ["SegFormerSegmentationDataset", "utils"]

dsa_helpers-0.4/dsa_helpers/ml/datasets/utils.py

@@ -1,42 +0,0 @@
-# Utility functions, usualy for creating Datasets in specific formats.
-import pandas as pd
-from .SegFormerSegmentationDataset import SegFormerSegmentationDataset
-from datasets import Dataset, Features, Image
-
-
-def dataset_generator(dataset):
-    """Yield a dataset."""
-    for item in dataset:
-        yield item
-
-
-def create_segformer_segmentation_dataset(
-    df: pd.DataFrame | str, low_memory: bool = True, transforms=None
-):
-    """Create a SegFormer segmentation dataset from a DataFrame.
-
-    Args:
-        df (pd.DataFrame | str): A pandas DataFrame with columns "fp" and "mask_fp" or a
-            path to a CSV file.
-        low_memory (bool): Whether to read the CSV file in low memory mode.
-        transforms: A function that takes in a batch of samples (dictionary with
-            pixel_values and label keys) and returns a transformed batch.
-
-    Returns:
-        A Dataset object to be used for HuggingFaces SegFormer model training.
-
-    """
-    if isinstance(df, str):
-        df = pd.read_csv(df, low_memory=low_memory)
-
-    dataset = SegFormerSegmentationDataset(df)
-
-    dataset = Dataset.from_generator(
-        generator=lambda: dataset_generator(dataset),
-        features=Features({"pixel_values": Image(), "label": Image()}),  # Example shape
-    )
-
-    if transforms is not None:
-        dataset.set_transform(transforms)
-
-    return dataset

dsa_helpers-0.4/dsa_helpers/ml/metrics/__init__.py

@@ -1,3 +0,0 @@
-from .binary_dice_coefficient_metric import binary_dice_coefficient_metric
-
-__all__ = ["binary_dice_coefficient_metric"]

dsa_helpers-0.4/dsa_helpers/ml/metrics/binary_dice_coefficient_metric.py

@@ -1,24 +0,0 @@
-import torch
-from torch import nn
-from ...utils import binary_dice_coefficient
-
-
-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).cpu()
-        labels_tensor = torch.from_numpy(labels).cpu()
-
-        # Scale the logits to the size of the label.
-        logits_tensor = nn.functional.interpolate(
-            logits_tensor,
-            size=labels.shape[-2:],
-            mode="bilinear",
-            align_corners=False,
-        ).argmax(dim=1)
-
-        pred_labels = logits_tensor.detach().numpy()
-        labels = labels_tensor.numpy()
-
-        return {"dice_coefficient": binary_dice_coefficient(pred_labels, labels)}

dsa_helpers-0.4/dsa_helpers/ml/transforms/__init__.py

@@ -1 +0,0 @@
-__all__ = ["segformer_transforms"]

dsa_helpers-0.4/dsa_helpers/ml/transforms/segformer_transforms.py

@@ -1,23 +0,0 @@
-from transformers import SegformerImageProcessor
-from torchvision.transforms import ColorJitter
-
-
-def train_transforms(example_batch):
-    """Default transforms for training images."""
-    processor = SegformerImageProcessor()  # required for using SegFormer model.
-    jitter = ColorJitter(brightness=0.25, contrast=0.25, saturation=0.25, hue=0.1)
-
-    images = [jitter(x) for x in example_batch["pixel_values"]]
-    labels = [x for x in example_batch["label"]]
-    inputs = processor(images, labels)
-    return inputs
-
-
-def val_transforms(example_batch):
-    """Default transforms for validation images."""
-    processor = SegformerImageProcessor()  # required for using SegFormer model.
-
-    images = [x for x in example_batch["pixel_values"]]
-    labels = [x for x in example_batch["label"]]
-    inputs = processor(images, labels)
-    return inputs

dsa_helpers-0.4/dsa_helpers/utils.py

@@ -1,28 +0,0 @@
-# Basic utility functions.
-import numpy as np
-
-
-def binary_dice_coefficient(mask1: np.ndarray, mask2: np.ndarray) -> float:
-    """Calculate the dice coefficient between two binary masks.
-
-    Args:
-        mask1 (np.ndarray): A binary mask.
-        mask2 (np.ndarray): A binary mask.
-
-    Returns:
-        float: The dice coefficient between the two masks.
-
-    """
-    # Convert the masks to binary.
-    mask1 = mask1 > 0
-    mask2 = mask2 > 0
-
-    # Calculate dice.
-    intersection = np.sum(mask1 * mask2)
-
-    sum_masks = np.sum(mask1) + np.sum(mask2)
-
-    if sum_masks == 0:
-        return 1.0  # Both masks are empty
-
-    return 2.0 * intersection / sum_masks

dsa_helpers-0.4/tests/app/Dockerfile

@@ -1,18 +0,0 @@
-FROM python:3.11-slim-buster
-
-ENV PYTHONUNBUFFERED True
-
-RUN apt-get update && apt-get install ffmpeg libsm6 libxext6 -y
-
-WORKDIR /app
-
-COPY requirements.txt /app
-
-RUN pip install --upgrade pip
-
-RUN python -m pip install pymongo==4.9.1
-
-RUN pip install --no-cache-dir -r requirements.txt
-
-COPY dsa_helpers-0.4.dev1-py3-none-any.whl /app
-RUN pip install dsa_helpers-0.4.dev1-py3-none-any.whl

dsa_helpers-0.4/tests/app/app.py

@@ -1,55 +0,0 @@
-from dash import html, Dash, callback, Output, Input, State, no_update
-import dash_bootstrap_components as dbc
-from dsa_helpers.dash.header import get_header
-from os import getenv
-from dash_ag_grid import AgGrid
-
-table = AgGrid(
-    id="table",
-    columnDefs=[],
-    rowData=[],
-)
-
-app = Dash(
-    __name__,
-    external_stylesheets=[
-        dbc.themes.BOOTSTRAP,
-    ],
-    title="Test Application",
-)
-
-app.layout = html.Div(
-    [
-        get_header(
-            getenv("DSA_API_URL"),
-            title="Test Application",
-            store_id="user-store",
-        ),
-        dbc.Row(
-            [dbc.Col(dbc.Button("Get items", id="get-item-btn"), width="auto")],
-            justify="start",
-        ),
-        table
-    ]
-)
-
-
-@callback(
-    [
-        Output("table", "columnDefs"),
-        Output("table", "rowData"),
-    ],
-    Input("get-item-btn", "n_clicks"),
-    prevent_initial_call=True,
-)
-def get_items(n_clicks):
-    """Get the items."""
-    
-    
-
-if __name__ == "__main__":
-    app.run(
-        host="0.0.0.0",
-        port=8060,
-        debug=True,
-    )

dsa_helpers-0.4/tests/docker-compose.yaml

@@ -1,31 +0,0 @@
-volumes:
-  mongodb-data-volume:
-
-services:
-  mongodb:
-    image: mongo:7.0.6-jammy
-    restart: always
-    platform: linux/amd64
-    container_name: mongodb
-    volumes:
-      - mongodb-data-volume:/data/db
-    ports:
-      - 27017:27017
-    env_file: .env
-    command: [ "--quiet", "--maxConns", "1000" ]
-    logging:
-      options:
-        max-size: "10M"
-        max-file: "5"
-        
-  dash:
-    build: app/
-    platform: linux/amd64
-    volumes:
-      - ./app:/app
-    ports:
-      - 8060:8060
-    env_file: .env
-    command: python app.py
-    depends_on:
-      - mongodb