Refactor emulation + MC sampling modules, dev + package modernization

.gitignore

@@ -5,12 +5,13 @@
 .pdm-python
 __pycache__/
 
+# JS (pre-commit)
+node_modules/
+
 # VScode
 *.code-workspace
 .vscode/
 
 # Data
 data/
 output/
-
-

.pre-commit-config.yaml

@@ -0,0 +1,92 @@
+ci:
+  autoupdate_commit_msg: "chore: update pre-commit hooks"
+  autofix_commit_msg: "style: pre-commit fixes"
+
+repos:
+  # Useful to determine which files are included/excluded, tests of pre-commit, etc.
+  # Don't enable by default because it seems noisy. But I'll keep it around because
+  # it can be quite useful for debugging
+  # See: https://github.com/pre-commit/pre-commit/issues/1173#issuecomment-542341362
+  #- repo: meta
+  #  hooks:
+  #  - id: identity
+  #    name: identity (all)
+
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: "1.20.0"
+    hooks:
+      - id: blacken-docs
+        additional_dependencies: [black==24.*]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: "v6.0.0"
+    hooks:
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+        exclude: ".patch"
+      - id: mixed-line-ending
+      - id: name-tests-test
+        args: ["--pytest-test-first"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+        exclude: ".patch"
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: "v1.10.0"
+    hooks:
+      - id: rst-backticks
+      - id: rst-directive-colons
+      - id: rst-inline-touching-normal
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v4.0.0-alpha.8"
+    hooks:
+      - id: prettier
+        types_or: [yaml, markdown, html, css, scss, javascript, json]
+        args: ["--prose-wrap=preserve", "--print-width=120"]
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.14.6"
+    hooks:
+      - id: ruff-check
+        args: ["--fix", "--show-fixes"]
+      - id: ruff-format
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: "v2.4.1"
+    hooks:
+      - id: codespell
+        additional_dependencies: [tomli]
+        # While it would be nice to have spell checking there, it doesn't handle the encoding of the output properly.
+        exclude: .ipynb
+
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: "v0.11.0.1"
+    hooks:
+      - id: shellcheck
+
+  - repo: local
+    hooks:
+      - id: disallow-caps
+        name: Disallow improper capitalization
+        language: pygrep
+        entry: PyBind|Numpy|Cmake|CCache|Github|PyTest
+        exclude: .pre-commit-config.yaml
+
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: "v0.24.1"
+    hooks:
+      - id: validate-pyproject
+        additional_dependencies: ["validate-pyproject-schema-store[all]"]
+
+  - repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: "0.35.0"
+    hooks:
+      - id: check-dependabot
+      - id: check-github-workflows
+      - id: check-readthedocs

config/rehlers.yaml

@@ -49,6 +49,7 @@ parameters:
   #-------------------------------------------
   # Emulator parameters
   emulator_parameters: &default_emulator_parameters
+    emulator_package: "sk_learn"
 
     force_retrain: False
     n_pc: 10

pyproject.toml

@@ -10,16 +10,14 @@ build-backend = "pdm.pep517.api"
 name = "jetscape-bayesian"
 description = "Analysis pipeline to implement Bayesian inference in high-energy physics "
 license = {text = "BSD-3-Clause"}
-# NOTE: <3.13 cap needed for tensorflow-io-gcs-filesystem
-requires-python = ">=3.10,<3.13"
+requires-python = ">=3.10"
 authors = [
   { name = "Raymond Ehlers", email = "raymond.ehlers@cern.ch" },
   { name = "Luna (Yi) Chen", email = "chen.yi.first@gmail.com" },
   { name = "Christal Martin", email = "cbaillar@vols.utk.edu" },
   { name = "Cameron Parker", email = "cameron.parker@tamu.edu" },
 ]
-# For hatch, need to remove the dependencies references here
-dynamic = ["dependencies", "optional-dependencies", "version"]
+dynamic = ["version"]
 dependencies = [
     # Data analysis and plotting
     "matplotlib >=3.5.2",
@@ -29,7 +27,7 @@ dependencies = [
     "seaborn >=0.11.2",
     "silx >=1.0.0",
     # Emulator training
-    "gpflow >=2.5.2",
+    # "gpflow >=2.5.2",
     "pymc >=4.0.0",
     "scikit-learn >=1.1.1",
     "emcee>=3.1.4",
@@ -39,14 +37,19 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
+test = [
+    "pytest >=6.2.4",
+    "pytest-cov >=3",
+    "pytest-sugar >=0.9.5",
+]
 dev = [
     "ruff >=0.0.209",
-    "black >=22.1.0",
     "mypy>=1.13.0",
     "ipython >=8.0",
     "ipykernel >=6.15.1",
     "pytest >=7.4.0",
     "pocoMC >=1.2.2",
+    "ipython>=8.37.0",
 ]
 
 [tool.hatch]
@@ -94,6 +97,8 @@ exclude = [
     'dist',
 ]
 line-length = 120
+
+[tool.ruff.lint]
 select = [
     "E", "F", "W", # flake8
     "C901",        # mccabe
@@ -131,15 +136,17 @@ unfixable = [
     "T20",      # flake8-print
     "F841",     # Removes unused variables
 ]
+# Allow for characters that could be confused (per ruff)
+allowed-confusables = ["σ", "ρ", "×"]
 
-[tool.ruff.mccabe]
+[tool.ruff.lint.mccabe]
 max-complexity = 12
 
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = []
 
 [tool.pylint]
-master.py-version = "3.9"
+master.py-version = "3.10"
 master.ignore-paths= []
 reports.output-format = "colorized"
 similarities.ignore-imports = "yes"

src/bayesian/analysis.py

@@ -0,0 +1,76 @@
+"""Primary analysis parameters.
+
+.. codeauthor:: Raymond Ehlers <raymond.ehlers@cern.ch>, LBL/UCB
+"""
+
+from __future__ import annotations
+
+import logging
+from pathlib import Path
+from typing import Any
+
+import attrs
+import yaml
+
+logger = logging.getLogger(__name__)
+
+
+@attrs.define
+class AnalysisIO:
+    observables_table_dir: Path | str = attrs.field(converter=Path)
+    observables_config_dir: Path | str = attrs.field(converter=Path)
+    observables_filename: str = attrs.field()
+    _output_dir: Path = attrs.field()
+
+    @classmethod
+    def from_config(cls, config: dict[str, Any]) -> AnalysisIO:
+        return cls(
+            observables_table_dir=config["observable_table_dir"],
+            observables_config_dir=config["observable_config_dir"],
+            observables_filename=config["observables_filename"],
+            output_dir=config["output_dir"],
+        )
+
+    @classmethod
+    def from_config_file(cls, config_file: str | Path) -> AnalysisIO:
+        with Path(config_file).open() as stream:
+            config = yaml.safe_load(stream)
+
+        return cls.from_config(config=config)
+
+    def output_dir(self, analysis_config: AnalysisSettings) -> Path:
+        return self._output_dir / f"{analysis_config.name}_{analysis_config.parameterization}"
+
+
+@attrs.define
+class AnalysisSettings:
+    name: str
+    parameterization: str
+    config_file: Path = attrs.field(converter=Path)
+    io: AnalysisIO
+    raw_analysis_config: dict[str, Any] = attrs.field(factory=dict)
+
+    @classmethod
+    def from_config(cls, analysis_name: str, config_file: Path, config: dict[str, Any]) -> AnalysisSettings:
+        """
+        Initialize the analysis configuration from a config file.
+        """
+        raw_analysis_config = config["analyses"][analysis_name]
+        return cls(
+            name=analysis_name,
+            parameterization=raw_analysis_config["parameterization"],
+            config_file=config_file,
+            io=AnalysisIO.from_config(config=config),
+            raw_analysis_config=raw_analysis_config,
+        )
+
+    @classmethod
+    def from_config_file(cls, analysis_name: str, config_file: str | Path) -> AnalysisSettings:
+        with Path(config_file).open() as stream:
+            config = yaml.safe_load(stream)
+
+        return cls.from_config(analysis_name=analysis_name, config_file=Path(config_file), config=config)
+
+    @property
+    def output_dir(self) -> Path:
+        return self.io.output_dir(self)