chore: squash commits for release

.editorconfig

@@ -0,0 +1,20 @@
+root = true
+
+[*]
+end_of_line = lf
+trim_trailing_whitespace = true
+insert_final_newline = true
+charset = utf-8
+indent_style = tab
+indent_size = 2
+
+# YAML doesn't support hard tabs
+# Templates that will be weird with hard tabs in the website editor
+[*.{yml,yaml,md}]
+indent_style = space
+indent_size = 2
+
+# Force python as python demands
+[*.{py,ipynb}]
+indent_size = 4
+indent_style = space

.flake8

@@ -0,0 +1,121 @@
+[flake8]
+extend-ignore =
+		# Allow function call as argument default
+		B008,
+		# Do not enforce trailing comma (lets Black decide what is best)
+		C812,C813,C814,C815,C816,C818,C819,
+		# Don't ask for docstring at top of module --- put it in the functions/classes
+		D100,
+		# Do not check for docstring within __init__ method
+    D107,
+		# Ignore whitespace before ';'
+    E203,
+		# Don't ask about line length, Black recommends using bugbear B950 instead
+		E501,
+		# Stop finding commented out code because it's mistaking shape annotations for code
+		E800,
+		# Just let the formatter complain about isort
+		I,
+		# Stop complaining about using functions from random
+		S311,
+		# Ignore errors for internal mypy traceback, stderr output, or an unmatched line.
+    T499,
+		# Do not complain about line-break before binary operator (caused by Black)
+		W503,
+		# Do not warn on too many imports.
+		WPS201,
+		# Do not warn on too many module members
+		WPS202,
+		# Do not warn when too many arguments in functions
+		WPS211,
+		# Do not warn on too many methods
+		WPS214,
+		# Allow lots of importing from the same module --- it can happen and thats okay!
+		WPS235,
+		# Do not warn on complex f-string
+		WPS237,
+		# Allow relative module references
+		WPS300,
+		# Allow f-strings
+    WPS305,
+		# Do not force base classes to inherit object
+		WPS306,
+		# Allow return statement that simply returns a prior statement
+		WPS331,
+		# Allow new lines to start with a dot (caused by Black)
+    WPS348,
+		# Allow logic in __init__ modules
+    WPS412,
+		# Google Python style is not RST until after processed by Napoleon
+		# See https://github.com/peterjc/flake8-rst-docstrings/issues/17
+		RST201,RST203,RST301,
+extend-select =
+	# Should raise AssertionError instead of assert False
+	B011,
+	# Use of break, continue or return in finally blocks will silence exceptions.
+	B012,
+	# Redundant exception types in except
+	B014,
+	# Pointless comparisons
+	B015,
+	# Cannot raise a literal
+	B016,
+	# Do not use `self.assertRaises(Exception)`
+	B017,
+	# Find useless expressions
+	B018,
+	# Use namedtuple instead of dataclass when only `__init__` attributes are set
+	B903,
+	# Within an except clause, raise exceptions with `raise ... from err` or `raise ...
+	# from None` to distinguish them from errors in exception handling
+	B904,
+	#	Counterpart to W503, enforce having the operator at the start of a new line.
+	W504,
+
+max-line-length = 99
+max-complexity = 18
+max-methods = 10
+max-line-complexity = 18
+max-local-variables = 20
+max-expressions = 20
+max-function-expressions = 10
+max-module-expressions = 20
+max-string-usages = 10
+max-annotation-complexity = 4
+min-name-length = 1
+max-try-body-length = 2
+format = wemake
+
+# Black enforces double quotes.
+inline-quotes = double
+
+docstring-convention = google
+
+# Darglint
+docstring_style = google
+strictness = long
+
+nested-classes-whitelist =
+	Meta
+	Params
+	Config
+
+allowed-domain-names =
+		data
+		utils
+		util
+		params
+
+per-file-ignores =
+		src/*/_version.py:WPS410
+    src/**/__init__.py:D,F401,WPS436
+		tests/*:D,F401,WPS118,WPS202,WPS204,WPS214,WPS218,WPS226,WPS231,WPS232,WPS235,WPS301,WPS432,WPS437,WPS442,S101
+		scripts/update_torch_cuda.py:S404,S603,S607,WPS323,WPS333,WPS432,WPS433,WPS459
+
+extend-exclude=
+	.venv/,
+	*_cache/,
+	.cache/,
+	logs/,
+	storage/,
+	docs/

.github/PULL_REQUEST_TEMPLATE/new_downstream_dataset.md

@@ -0,0 +1,35 @@
+<!-- Adding a new downstream dataset -->
+
+## Description
+
+<!-- What have you added and why? -->
+
+## Checklist
+
+- [ ] I have read the ["How to add a new downstream dataset" instructions](docs/how-to-add-a-new-downstream-dataset.md)
+- [ ] A subset of the raw data has been added for testing the new dataset
+- [ ] This PRs metadata is complete
+
+### Adding a new dataset
+
+- [ ] The dataset name has been added to the `DatasetName` enum
+- [ ] The value for the new option in `DatasetName` is formatted like the public dataset name
+- [ ] The dataset name has been added to the `DatasetModalityMap`
+- [ ] The dataset name has been included in the `AnnotationDatasetMap`
+
+### Creating the instance
+
+- [ ] A new instance exists for the dataset, and it inherits from `BaseInstance`
+- [ ] The new instance model for the dataset has tests (in `tests/datamodels/`)
+- [ ] The new instance has been included in `emma_datasets/datamodels/datasets/__init__.py`
+- [ ] The class name for the instance is in pascal case
+- [ ] The instance is well-documented to ensure others can easily know what is happening and why
+
+### Adding the dataset to the `downstream` command
+
+- [ ] There is a new command to process the downstream dataset
+- [ ] The name of the command is consistent with other commands
+- [ ] The function has a docstring for the help of the command
+- [ ] The function is listed as a command
+- [ ] There are tests for the new dataset with the `DownstreamDbCreator` (in `tests/test_downstream_db_creator.py`)
+- [ ] There are tests for the new command (in `tests/commands/test_create_downstream_dbs.py`)

.github/labels.yml

@@ -0,0 +1,90 @@
+---
+# Labels names are important as they are used by Release Drafter to decide
+# regarding where to record them in changelog or if to skip them.
+#
+# The repository labels will be automatically configured using this file and
+# the GitHub Action https://github.com/marketplace/actions/github-labeler.
+## more info https://github.com/crazy-max/ghaction-github-labeler
+
+# ------------------------- Conventional Commit types ------------------------ #
+# From https://github.com/commitizen/conventional-commit-types/blob/master/index.json
+
+- name: feature
+  description: A new enhancement or feature
+  color: 0A8844
+  from_name: "enhancement"
+
+- name: fix
+  description: A bug fix
+  color: d23832
+  from_name: "bug"
+
+- name: documentation
+  description: Documentation changes only
+  color: 8AD9F5
+
+- name: style
+  description: Changes that do not affect meaning of code (formatting, etc.)
+  color: F9CD8E
+
+- name: refactor
+  description: Code change that neither fixes a bug nor adds a feature
+  color: FBCA0C
+  from_name: refactoring
+
+- name: performance
+  description: Code change that improves performance
+  color: F2A33C
+
+- name: test
+  description: Adding missing tests or correcting existing tests
+  color: 34FFB3
+
+- name: build
+  description: Changes that affect the build system or external dependencies
+  color: 8F4FBB
+
+- name: continuous integration
+  description: Changes to CI configuration and scripts
+  color: FCBFE3
+
+- name: chore
+  description: Other changes that don't modify src or test files
+  color: d3d3d3
+
+- name: revert
+  description: Revert a previous commit
+  color: 1e1e1e
+
+- name: backwards incompatible
+  description: incompatible changes to how the application works
+  color: AB2232
+
+- name: question
+  description: Further information is requested
+  color: EE328E
+
+# ------------------------------- Dependencies ------------------------------- #
+- name: dependencies
+  description: Pull requests that update dependencies
+  color: 0366d6
+
+# ------------------------------ Utility labels ------------------------------ #
+- name: automerge
+  color: "ffffff"
+  description: "Automerge this PR"
+
+- name: "stale"
+  color: "ffffff"
+  description: ""
+# - name: duplicate
+#   description: This issue or pull request already exists
+#   color: ffffff
+
+# - name: invalid
+#   description: This doesn't seem right
+#   color: ffffff
+
+# - name: wontfix
+#   description: This will not be worked on
+#   color: ffffff