Add various tree utilities

Author: dpoznik

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ repos:
     hooks:
       - id: isort
   - repo: [email protected]:psf/black.git
-    rev: 23.12.1
+    rev: 24.1.0
     hooks:
       - id: black
   - repo: [email protected]:pre-commit/pre-commit-hooks.git
@@ -15,6 +15,7 @@ repos:
       - id: check-yaml
         args: [--allow-multiple-documents]
       - id: pretty-format-json
+        exclude: .*.ipynb
       - id: trailing-whitespace
         exclude: tests/fixtures/output/haplogroups\..*\.txt|data/variants/isogg\.[0-9]{4}\.[0-9]{2}\.[0-9]{2}\.txt
   - repo: [email protected]:PyCQA/flake8.git

CHANGELOG.md

@@ -3,7 +3,29 @@
 Format based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 
 
-## [2.1.0] - 2024-01
+## [2.1.4] - 2024-01-29
+
+### Added
+- Support for querying multiple SNPs from the command line
+- Support for generating aligned-tip Newick representations of subtrees
+- Support for node lookup by SNP-based haplogroup label
+- `Node` methods:
+  - `Node.iter_depth_first`
+  - `Node.iter_breath_first`
+  - `Node.remove_children`
+- `tree.get_bounded_subtree` function
+
+### Changed
+- `Tree` constructor's `Config` parameter is now optional
+- `Node.is_root` and `Node.is_leaf` are now properties
+
+### Fixed
+- Output format of `--snp_query` option
+
+[2.1.4]: https://github.com/23andMe/yhaplo/compare/2.1.0...2.1.4
+
+
+## [2.1.0] - 2024-01-12
 
 This release improves haplogroup calling by identifying and correcting various errors in
 the ISOGG variant metadata and, internally, by pruning poorly performing v5 SNPs.

Makefile

@@ -1,17 +1,18 @@
 # Make variables
 #----------------------------------------------------------------------
-BOLD_CYAN = \033[1;36m
+CYAN := \033[0;36m
+GREEN := \033[0;32m
+BOLD_CYAN := \033[1;36m
 BOLD_GREEN := \033[1;32m
-GREEN = \033[0;32m
-NO_COLOR = \033[0m
+NO_COLOR := \033[0m
 
 
 ## General
 # ----------------------------------------------------------------------
 help:  ## Print this help message
 	@egrep -h '(\s|^)##\s' $(MAKEFILE_LIST) \
-	| sed -E "s/^## (.*)/\n$$(printf "${BOLD_CYAN}")\1$$(printf "${NO_COLOR}")/g" \
-	| awk 'BEGIN {FS = ":.*?## "}; {printf "${GREEN}%-25s${NO_COLOR} %s\n", $$1, $$2}'
+	| sed -E "s/^## (.*)/\n$$(printf "${BOLD_GREEN}")\1$$(printf "${NO_COLOR}")/g" \
+	| awk 'BEGIN {FS = ":.*?## "}; {printf "${CYAN}%-25s${NO_COLOR} %s\n", $$1, $$2}'
 	@echo
 
 

pyproject.toml

@@ -65,12 +65,14 @@ ignore_missing_imports = true
 # D107 Missing docstring in __init__
 # D202 No blank lines allowed after function docstring
 #      Ignoring allows blank lines after one-line docstrings.
+# D203 1 blank line required before class docstring
+#      Conflicts with black 24.
 # D211 No blank lines allowed before class docstring
 #      Contradicts D203.
 # D213 Multi-line docstring summary should start at the second line
 #      Contradicts D212.
 #      https://github.com/PyCQA/pydocstyle/issues/242#issuecomment-288166773
-ignore = "D107,D202,D211,D213"
+ignore = "D107,D202,D203,D211,D213"
 match_dir = "(?!tests|\\.).*"
 
 [tool.pytest.ini_options]

scripts/validate_yhaplo.sh

@@ -36,10 +36,12 @@ echo -e "\n${BOLD_CYAN}Removed${NO_COLOR}: ${GREEN}${output_dir}\n\n${NO_COLOR}"
 
 echo -e "${BOLD_CYAN}Text Input${NO_COLOR}\n"
 yhaplo --example_text \
+    --hg_genos Q \
     --breadth_first \
     --depth_first \
     --depth_first_table \
-    --hg_genos Q
+    --mrca Q J \
+    --snp_query L1335,S730,S530,foo
 echo -e "\n"
 
 

yhaplo/api/command_line_args.py

@@ -197,14 +197,14 @@ def get_command_line_args(set_defaults: bool = False) -> argparse.Namespace:
         nargs=2,
         dest="mrca_haplogroup_list",
         metavar=("haplogroup1", "haplogroup2"),
-        help="Output mrca of two haplogroups",
+        help="Output MRCA of two haplogroups",
     )
     group.add_argument(
         "-sq",
         "--snp_query",
-        dest="query_snp_name",
-        metavar="snp_name",
-        help="List phylogenetic path for a query SNP",
+        dest="query_snp_names",
+        metavar="snp_names",
+        help="List phylogenetic path for each SNP in comma-separated list",
     )
     group.add_argument(
         "-pt",
@@ -282,7 +282,6 @@ def get_command_line_arg_defaults() -> argparse.Namespace:
 
 
 class RawTextWithDefaultsHelpFormatter(argparse.RawDescriptionHelpFormatter):
-
     """Help message formatter that retains formatting and adds defaults.
 
     Combines argparse.RawTextHelpFormatter and argparse.ArgumentDefaultsHelpFormatter.

yhaplo/config.py

@@ -22,7 +22,6 @@
 
 
 class Config:
-
     """Yhaplo configuration class.
 
     This class is a container for parameters, constants, filenames, etc.