Merge pull request #334 from Dana-Farber-AIOS/merge-master

Merge main branch into dev

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203 E501
+per-file-ignores = __init__.py:F401

.github/workflows/precommit-hooks.yaml

@@ -0,0 +1,17 @@
+name: pre-commit-hooks
+
+on: [pull_request]
+
+jobs:
+ build:
+ runs-on: ubuntu-latest
+ steps:
+ - uses: actions/checkout@v2
+ - name: Set up Python 3.8
+ uses: actions/setup-python@v1
+ with:
+ python-version: 3.8
+ - name: Linting
+ run: |
+ pip install pre-commit
+ pre-commit run --all-files

.pre-commit-config.yaml

@@ -5,12 +5,22 @@ repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
  rev: v4.0.1
  hooks:
- - id: trailing-whitespace
- - id: end-of-file-fixer
- - id: check-yaml
- - id: check-added-large-files
+ - id: trailing-whitespace
+ - id: end-of-file-fixer
+ - id: check-yaml
+ - id: check-added-large-files
+
  - repo: https://github.com/psf/black
- rev: 21.6b0 # Replace by any tag/version: https://github.com/psf/black/tags
+ rev: 22.8.0
  hooks:
  - id: black
- language_version: python3 # Should be a command that runs python3.6+
+
+ - repo: https://github.com/timothycrosley/isort
+ rev: 5.10.1
+ hooks:
+ - id: isort
+
+ - repo: https://github.com/pycqa/flake8
+ rev: 5.0.4
+ hooks:
+ - id: flake8

CITATION.cff

@@ -0,0 +1,64 @@
+cff-version: 1.2.0
+message: "Citation for this repository"
+authors:
+ - family-names: Rosenthal
+ given-names: Jacob
+ - family-names: Carelli
+ given-names: Ryan
+ - family-names: Mohammed
+ given-names: Omar
+ - family-names: Brundage
+ given-names: David
+ - family-names: Halbert
+ given-names: Ella
+ - family-names: Nyman
+ given-names: Jackson
+ - family-names: Hari
+ given-names: Surya
+ - family-names: Van Allen
+ given-names: Eliezer
+ - family-names: Marchionni
+ given-names: Luigi
+ - family-names: Umeton
+ given-names: Renato
+ - family-names: Loda
+ given-names: Massimo
+title: "Building Tools for Machine Learning and Artificial Intelligence in Cancer Research: Best Practices and a Case Study with the PathML Toolkit for Computational Pathology"
+date-released: 2022-02-03
+doi: 10.1158/1541-7786.MCR-21-0665
+url: https://github.com/Dana-Farber-AIOS/pathml
+preferred-citation:
+ type: article
+ authors:
+ - family-names: Rosenthal
+ given-names: Jacob
+ - family-names: Carelli
+ given-names: Ryan
+ - family-names: Mohammed
+ given-names: Omar
+ - family-names: Brundage
+ given-names: David
+ - family-names: Halbert
+ given-names: Ella
+ - family-names: Nyman
+ given-names: Jackson
+ - family-names: Hari
+ given-names: Surya
+ - family-names: Van Allen
+ given-names: Eliezer
+ - family-names: Marchionni
+ given-names: Luigi
+ - family-names: Umeton
+ given-names: Renato
+ - family-names: Loda
+ given-names: Massimo
+ doi: 10.1158/1541-7786.MCR-21-0665
+ journal: "Molecular Cancer Research"
+ publisher: American Academy of Cancer Research
+ month: 2
+ year: 2022
+ issue: 2
+ volume: 20
+ start: 202
+ title: "Building Tools for Machine Learning and Artificial Intelligence in Cancer Research: Best Practices and a Case Study with the PathML Toolkit for Computational Pathology"
+ url: https://doi.org/10.1158/1541-7786.MCR-21-0665

README.md

@@ -92,6 +92,8 @@ pip install -e .
 
 First, download or build the PathML Docker container:
 
+![pathml-docker-installation](https://user-images.githubusercontent.com/25375373/191053363-477497a1-9804-48f3-91f9-767dc7f859ed.gif)
+
 - Option A: download PathML container from Docker Hub
  ````
  docker pull pathml/pathml:latest

pathml/__init__.py

@@ -3,9 +3,9 @@
 License: GNU GPL 2.0
 """
 
-from .core import *
 from . import datasets as ds
 from . import ml
 from . import preprocessing as pp
 from ._logging import PathMLLogger
 from ._version import __version__
+from .core import * # noqa: F403

pathml/_logging.py

@@ -3,10 +3,11 @@
 License: GNU GPL 2.0
 """
 
-from loguru import logger
 import functools
 import sys
 
+from loguru import logger
+
 
 class PathMLLogger:
  """

pathml/_version.py

@@ -3,4 +3,4 @@
 License: GNU GPL 2.0
 """
 
-__version__ = "2.0.4"
+__version__ = "2.1.0"

pathml/core/__init__.py

@@ -4,16 +4,16 @@
 """
 
 from .masks import Masks
-from .slide_backends import OpenSlideBackend, BioFormatsBackend, DICOMBackend
+from .slide_backends import BioFormatsBackend, DICOMBackend, OpenSlideBackend
 from .slide_data import (
- SlideData,
+ CODEXSlide,
  HESlide,
+ IHCSlide,
  MultiparametricSlide,
+ SlideData,
  VectraSlide,
- CODEXSlide,
- IHCSlide,
 )
 from .slide_dataset import SlideDataset
+from .slide_types import SlideType, types
 from .tile import Tile
 from .tiles import Tiles
-from .slide_types import SlideType, types

pathml/core/h5managers.py

@@ -3,15 +3,14 @@
 License: GNU GPL 2.0
 """
 
-import itertools
 import os
 import tempfile
-from collections import OrderedDict
 
 import anndata
-from loguru import logger
 import h5py
 import numpy as np
+from loguru import logger
+
 import pathml.core
 import pathml.core.masks
 import pathml.core.tile
@@ -35,10 +34,10 @@ def __init__(self, h5path=None, slidedata=None):
  if h5path:
  assert (
  not slidedata
- ), f"if creating h5pathmanager from h5path, slidedata should not be required"
+ ), "if creating h5pathmanager from h5path, slidedata should not be required"
  assert check_valid_h5path_format(
  h5path
- ), f"h5path must conform to .h5path standard, see documentation"
+ ), "h5path must conform to .h5path standard, see documentation"
  # copy h5path into self.h5
  for ds in h5path.keys():
  if ds in ["fields", "masks", "tiles"]:
@@ -52,19 +51,19 @@ def __init__(self, h5path=None, slidedata=None):
  )
 
  else:
- assert slidedata, f"must pass slidedata object to create h5path"
+ assert slidedata, "must pass slidedata object to create h5path"
  # initialize h5path file hierarchy
  # fields
  fieldsgroup = self.h5.create_group("fields")
  # name, shape, labels
  fieldsgroup.attrs["name"] = slidedata.name
  fieldsgroup.attrs["shape"] = slidedata.slide.get_image_shape()
- labelsgroup = self.h5["fields"].create_group("labels")
+ self.h5["fields"].create_group("labels")
  if slidedata.labels:
  for key, label in slidedata.labels.items():
  self.h5["fields/labels"].attrs[key] = label
  # slidetype
- slidetypegroup = self.h5["fields"].create_group("slide_type")
+ self.h5["fields"].create_group("slide_type")
  if slidedata.slide_type:
  for key, val in slidedata.slide_type.asdict().items():
  self.h5["fields/slide_type"].attrs[key] = val
@@ -75,9 +74,9 @@ def __init__(self, h5path=None, slidedata=None):
  # initialize stride with 0
  tilesgroup.attrs["tile_stride"] = b"(0, 0)"
  # masks
- masksgroup = self.h5.create_group("masks")
+ self.h5.create_group("masks")
  # counts
- countsgroup = self.h5.create_group("counts")
+ self.h5.create_group("counts")
 
  slide_type_dict = {
  key: val for key, val in self.h5["fields/slide_type"].attrs.items()
@@ -150,7 +149,7 @@ def add_tile(self, tile):
  if tile.masks:
  # create a group to hold tile-level masks
  if "masks" not in self.h5["tiles"][str(tile.coords)].keys():
- masksgroup = self.h5["tiles"][str(tile.coords)].create_group("masks")
+ self.h5["tiles"][str(tile.coords)].create_group("masks")
 
  # add tile-level masks
  for key, mask in tile.masks.items():
@@ -168,7 +167,7 @@ def add_tile(self, tile):
  self.h5["tiles"][str(tile.coords)].attrs["name"] = (
  str(tile.name) if tile.name else 0
  )
- tilelabelsgroup = self.h5["tiles"][str(tile.coords)].create_group("labels")
+ self.h5["tiles"][str(tile.coords)].create_group("labels")
  if tile.labels:
  for key, val in tile.labels.items():
  self.h5["tiles"][str(tile.coords)]["labels"].attrs[key] = val
@@ -198,7 +197,7 @@ def get_tile(self, item):
  Tile(pathml.core.tile.Tile)
  """
  if isinstance(item, bool):
- raise KeyError(f"invalid key, pass str or tuple")
+ raise KeyError("invalid key, pass str or tuple")
  if isinstance(item, (str, tuple)):
  item = str(item)
  if item not in self.h5["tiles"].keys():
@@ -246,7 +245,7 @@ def remove_tile(self, key):
  Remove tile from self.h5 by key.
  """
  if not isinstance(key, (str, tuple)):
- raise KeyError(f"key must be str or tuple, check valid keys in repr")
+ raise KeyError("key must be str or tuple, check valid keys in repr")
  if str(key) not in self.h5["tiles"].keys():
  raise KeyError(f"key {key} is not in Tiles")
  del self.h5["tiles"][str(key)]
@@ -270,7 +269,7 @@ def add_mask(self, key, mask):
  raise ValueError(
  f"key {key} already exists in 'masks'. Cannot add. Must update to modify existing mask."
  )
- newmask = self.h5["masks"].create_dataset(key, data=mask)
+ self.h5["masks"].create_dataset(key, data=mask)
 
  def update_mask(self, key, mask):
  """
@@ -340,7 +339,7 @@ def remove_mask(self, key):
  f"masks keys must be of type(str) but key was passed of type {type(key)}"
  )
  if key not in self.h5["masks"].keys():
- raise KeyError(f"key is not in Masks")
+ raise KeyError("key is not in Masks")
  del self.h5["masks"][key]
 
  def get_slidetype(self):

pathml/core/masks.py

@@ -3,13 +3,10 @@
 License: GNU GPL 2.0
 """
 
-import numpy as np
-import os
-from pathlib import Path
-from collections import OrderedDict
-import h5py
 import reprlib
-from loguru import logger
+from collections import OrderedDict
+
+import numpy as np
 
 import pathml.core.h5managers