Some dependency version updates and deprecation warnings

.github/workflows/ci.yml

@@ -1,6 +1,10 @@
 name: ci
 
-on: [push, pull_request, workflow_dispatch]
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
 
 jobs:
   test:
@@ -9,7 +13,7 @@ jobs:
 
     strategy:
       matrix:
-        python-version: ["3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
         os: [ubuntu-latest, macOs-latest]
       fail-fast: false
 

.gitignore

@@ -1,177 +1,86 @@
-
-
-# Byte-compiled / optimized / DLL files
+# Python
 __pycache__/
 *.py[cod]
 *$py.class
-
-# C extensions
 *.so
+*.egg-info/
+*.egg
+.eggs/
+MANIFEST
 
 # Distribution / packaging
-.Python
 build/
-develop-eggs/
 dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
 wheels/
-pip-wheel-metadata/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
+sdist/
 
-# Unit test / coverage reports
-htmlcov/
+# Testing & coverage
+.pytest_cache/
 .tox/
 .nox/
 .coverage
 .coverage.*
-.cache
-nosetests.xml
+htmlcov/
 coverage.xml
-*.cover
-*.py,cover
 .hypothesis/
-.pytest_cache/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-.python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
 
 # Environments
 .env
 .venv
 env/
 venv/
 ENV/
-env.bak/
-venv.bak/
 
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
+# Type checkers & linters
 .mypy_cache/
 .dmypy.json
 dmypy.json
-
-# Pyre type checker
 .pyre/
+.ruff_cache
 
-# Mac OS files
-.DS_Store
-__MACOSX
-.idea/
+# Jupyter
+.ipynb_checkpoints
 
 # Benchmarking
 **/lightning_logs
+experiments/benchmarking/logs
 
-# Extra directories/files
+# Data directories (not source code)
 /**data*/
+*test*.*
+!tests/
+!tests/*/
+!tests/**
+**/__pycache__/
 
-!tests/*/*
-agml/_helios
-agml/helios_config.sh
-agml/train
-
-# Controls for the `_internal` directory.
+# agml/_internal: only specific files are tracked
 agml/_internal/*
 !agml/_internal/preprocess*.py
 !agml/_internal/s3internal.py
 !agml/_internal/__init__.py
 !agml/_internal/utils.py
 
-# Training
-experiments/benchmarking/lightning_logs
-experiments/benchmarking/logs
+# Training outputs
 agml/models/training/*.log
 agml/models/training/*.err
 agml/models/training/*.out
 agml/models/training/*.csv
-# .*/
-/
+
+# Project-specific
+agml/_helios
+agml/helios_config.sh
+agml/train
 *.pptx
-.ruff_cache
-*test*.*
 image*.png
 .challenges
 .paper
 
-# under development
+# Under development
 agml/data/augmentations/
 agml/data/exporters/pascal_voc.py
 
-# vs code settings
+# IDEs & editors
+.DS_Store
+__MACOSX
+.idea/
 .vscode/

AUTHORS

@@ -4,3 +4,4 @@ Heesup Yun
 Mason Earles
 Pranav Raja
 Alexander Olenskyj
+Jared Smith

agml/__init__.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.7.4"
+__version__ = "0.8.0"
 __all__ = ["data", "synthetic", "backend", "viz", "io"]
 
 

agml/data/hf_loader.py

@@ -3,7 +3,7 @@
 from typing import List, Union
 
 try:
-    from datasets import load_dataset, DatasetDict, Image, Sequence, Value, ClassLabel
+    from datasets import load_dataset, DatasetDict, Image, Sequence, ClassLabel
 except ImportError:
     raise ImportError(
         "The `datasets` library is required to use the HuggingFaceDataLoader. "
@@ -66,24 +66,25 @@ def _setup_loader(self):
 
     def _cast_features(self):
         """Infers and casts image-like columns to the HF Image type for automated decoding."""
-        for split_name in self._hf_dataset.keys():
-            ds = self._hf_dataset[split_name]
-            features = ds.features
-
-            if "image" in features and not isinstance(features["image"], Image):
-                ds = ds.cast_column("image", Image())
-
-            # A "mask" column is always a pixel map — cast unconditionally.
-            if "mask" in features and not isinstance(features["mask"], Image):
-                ds = ds.cast_column("mask", Image())
-            # Cast "label" only when it looks like image data (string path or binary bytes),
-            # not when it is a ClassLabel or a numeric scalar.
-            elif "label" in features and not isinstance(features["label"], Image):
-                label_feat = features["label"]
-                if isinstance(label_feat, Value) and label_feat.dtype in ("string", "binary", "large_binary"):
-                    ds = ds.cast_column("label", Image())
-
-            self._hf_dataset[split_name] = ds
+        if isinstance(self._hf_dataset, DatasetDict):
+            splits = {name: self._hf_dataset[name] for name in self._hf_dataset.keys()}
+            for split_name, ds in splits.items():
+                self._hf_dataset[split_name] = self._cast_single(ds)
+        else:
+            self._hf_dataset = self._cast_single(self._hf_dataset)
+
+    def _cast_single(self, ds):
+        """Casts image-like columns on a single Dataset."""
+        features = ds.features
+
+        if "image" in features and not isinstance(features["image"], Image):
+            ds = ds.cast_column("image", Image())
+
+        # A "mask" column is always a pixel map — cast unconditionally.
+        if "mask" in features and not isinstance(features["mask"], Image):
+            ds = ds.cast_column("mask", Image())
+
+        return ds
 
     def split(self, 
               val_size: float = None, 

agml/data/public.py

@@ -15,6 +15,7 @@
 import functools
 
 from rich.console import Console
+from rich.table import Table
 import numpy as np
 
 from agml.backend.config import data_save_path

agml/utils/downloads.py

@@ -61,7 +61,7 @@ def download_dataset(dataset_name, dest_dir, redownload=False):
         "Loading datasets through the AgML S3 data loader is deprecated and will be "
         "removed in a future release. Please use the Hugging Face data loader instead.",
         DeprecationWarning,
-        stacklevel=2,
+        stacklevel=3,
     )
 
     # Connect to S3 and generate unsigned URL for bucket object

pyproject.toml

@@ -10,11 +10,12 @@ description = "A comprehensive library for agricultural deep learning"
 authors = [{name = "UC Davis Plant AI and Biophysics Lab", email = "jmearles@ucdavis.edu"}]
 maintainers = [{ name="Amogh Joshi", email="amnjoshi@ucdavis.edu"}]
 
-license = {text = "Apache 2.0"}
+license = "Apache-2.0"
+license-files = ["LICENSE"]
 readme = "README.md"
 packages = [{include = "agml", from = "agml", exclude ='agml/_internal'}]
-version = "0.7.4"
-requires-python = ">=3.9"
+version = "0.8.0"
+requires-python = ">=3.10"
 keywords = []
 classifiers = [
     "Development Status :: 4 - Beta",
@@ -23,7 +24,6 @@ classifiers = [
     "Programming Language :: Python",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3 :: Only",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
@@ -43,15 +43,12 @@ dependencies = [
     "opencv-python>=4.10.0.84",
     "opencv-python-headless>=4.10.0.84",
     "requests>=2.0.0",
-    "scikit-learn>=1.3.2",
     "tqdm>=4.67.0",
     "pyyaml>=6.0.2",
     "albumentations>=1.4.18",
     "dict2xml>=1.7.6",
-    "ipywidgets>=8.1.5",
     "rich>=14.0.0",
     "datasets",
-    "transformers"
 ]
 [project.urls]
 
@@ -66,6 +63,7 @@ dependencies = [
 dev = [
     "boto3>=1.35.66",
     "scikit-image>=0.21.0",
+    "scikit-learn>=1.3.2",
     "shapely>=2.0.6",
     "botocore>=1.35.66",
     "pandas>=2.0.3",
@@ -76,7 +74,5 @@ dev = [
     "mypy>=1.13.0",
     "coverage>=7.6.1",
     "interrogate>=1.7.0",
-    "datasets",
-    "transformers"
 ]