Add test data for gcages

gcages/.gitignore

@@ -0,0 +1,162 @@
+# Raw scenario database file
+tests/test-data/AR6_Scenarios_Database_World_ALL_CLIMATE_v1.1.csv
+
+# Notebooks
+*.ipynb
+
+# Auto-generated docs and helper files
+docs/api/*
+!docs/api/.gitkeep
+docs/cli/*
+!docs/cli/.gitkeep
+
+# pdm stuff
+.pdm-python
+
+# Databases
+*.db
+
+# Jupyter cache
+.jupyter_cache
+
+# IDE stuff
+.idea/
+
+# Ruff cache
+.ruff_cache
+
+# Licence check
+licence-check.txt
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# 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
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+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
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Mac stuff
+*.DS_Store

gcages/scripts/changelog-to-release-template.py

@@ -0,0 +1,52 @@
+"""
+Extract the changes from the latest version in our CHANGELOG
+
+These can then be used in our release template.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import typer
+
+
+def main() -> None:
+    """
+    Extract the latest version changes from our CHANGELOG
+
+    They are printed to stdout
+    """
+    CHANGELOG = Path("docs") / "changelog.md"
+
+    with open(CHANGELOG) as fh:
+        changelog_raw = fh.read()
+
+    check_for_next_version = False
+    grab_notes = False
+    latest_version_notes: list[str] = []
+    for line in changelog_raw.splitlines():
+        if not check_for_next_version:
+            if line == "<!-- towncrier release notes start -->":
+                check_for_next_version = True
+
+            continue
+
+        if not grab_notes:
+            if line.startswith("## Global Climate Assessment of Global Emission Scenarios"):
+                grab_notes = True
+
+            continue
+
+        # We are grabbing notes now
+        # If we've reached the next version's notes, break
+        if line.startswith("## Global Climate Assessment of Global Emission Scenarios"):
+            break
+
+        latest_version_notes.append(line)
+
+    print("\n".join(latest_version_notes))
+
+
+if __name__ == "__main__":
+    typer.run(main)

gcages/scripts/convert_ar6_res_to_test_csvs.py

@@ -0,0 +1,39 @@
+"""
+Convert the test file from xls to csvs we can use in the repo
+"""
+
+from pathlib import Path
+
+import pandas as pd
+import pandas_indexing as pix
+import tqdm
+
+TEST_DATA_DIR = Path(__file__).parents[1] / "tests" / "test-data"
+# This file is available from the scenario explorer.
+# It's nearly 1GB, which is why we don't include it here.
+# It's md5sum is:
+# 4b8aea8270566584db9d893ff7b4562e  tests/test-data/AR6_Scenarios_Database_World_ALL_CLIMATE_v1.1.csv
+# (Generated with `md5sum tests/test-data/AR6_Scenarios_Database_World_ALL_CLIMATE_v1.1.csv`)
+
+raw = pd.read_csv(TEST_DATA_DIR / "AR6_Scenarios_Database_World_ALL_CLIMATE_v1.1.csv").set_index(
+    ["Model", "Scenario", "Variable", "Unit", "Region"]
+)
+
+emissions = raw[pix.ismatch(Variable="**Emissions**")]
+temperature_magicc = raw[pix.ismatch(Variable="**|Surface Temperature**MAGICC**")]
+
+temperature_magicc.index.to_frame()[["Model", "Scenario"]].drop_duplicates().to_csv(
+    TEST_DATA_DIR / "ar6_scenarios_raw_model_scenario_combinations.csv", index=False
+)
+
+for (model, scenario), msdf in tqdm.tqdm(temperature_magicc.groupby(["Model", "Scenario"])):
+    filename = f"ar6_scenarios__{model}__{scenario}__temperatures.csv"
+    filename = filename.replace("/", "_").replace(" ", "_")
+    out_file = TEST_DATA_DIR / filename
+
+    msdf.to_csv(out_file)
+
+    filename_emissions = f"ar6_scenarios__{model}__{scenario}__emissions.csv"
+    filename_emissions = filename_emissions.replace("/", "_").replace(" ", "_")
+    out_file_emissions = TEST_DATA_DIR / filename_emissions
+    emissions[pix.ismatch(Model=model) & pix.ismatch(Scenario=scenario)].to_csv(out_file_emissions)

gcages/scripts/test-install.py

@@ -0,0 +1,29 @@
+"""
+Test that all of our modules can be imported
+
+Also test that associated constants are set correctly
+
+Thanks https://stackoverflow.com/a/25562415/10473080
+"""
+
+import importlib
+import pkgutil
+
+import gcages
+
+
+def import_submodules(package_name: str) -> None:
+    """
+    Test import of submodules
+    """
+    package = importlib.import_module(package_name)
+
+    for _, name, is_pkg in pkgutil.walk_packages(package.__path__):
+        full_name = package.__name__ + "." + name
+        importlib.import_module(full_name)
+        if is_pkg:
+            import_submodules(full_name)
+
+
+import_submodules("gcages")
+print(gcages.__version__)