add references for join_types (c7d8f8d5) · Commits · csst-cicd / csst-dag

csst_dag/dag/dispatcher.py

+38 −28

Original line number	Diff line number	Diff line
		@@ -8,7 +8,6 @@ from .._csst import csst

		# from csst_dag._csst import csst


		# THESE ARE GENERAL PARAMETERS!
		PLAN_PARAMS = {
		"dataset": None,
		@@ -50,6 +49,44 @@ PROC_PARAMS = {
		# should be capable to extend
		}

		# plan basis keys
		PLAN_BASIS_KEYS = (
		"dataset",
		"instrument",
		"obs_type",
		"obs_group",
		"obs_id",
		"n_frame",
		"_id",
		)

		# data basis keys
		DATA_BASIS_KEYS = (
		"dataset",
		"instrument",
		"obs_type",
		"obs_group",
		"obs_id",
		"detector",
		"file_name",
		"_id",
		)

		# join_type for data x plan
		PLAN_JOIN_TYPE = "inner"
		"""
		References:
		- https://docs.astropy.org/en/stable/api/astropy.table.join.html
		- https://docs.astropy.org/en/stable/table/operations.html#join

		Typical types:
		- inner join: Only matching rows from both tables
		- left join: All rows from left table, matching rows from right table
		- right join: All rows from right table, matching rows from left table
		- outer join: All rows from both tables
		- cartesian join: Every combination of rows from both tables
		"""


		def override_common_keys(d1: dict, d2: dict) -> dict:
		"""
		@@ -105,33 +142,6 @@ def split_data_basis(data_basis: table.Table, n_split: int = 1) -> list[table.Ta
		return chunks


		# plan basis keys
		PLAN_BASIS_KEYS = (
		"dataset",
		"instrument",
		"obs_type",
		"obs_group",
		"obs_id",
		"n_frame",
		"_id",
		)

		# data basis keys
		DATA_BASIS_KEYS = (
		"dataset",
		"instrument",
		"obs_type",
		"obs_group",
		"obs_id",
		"detector",
		"file_name",
		"_id",
		)

		# join_type for data x plan
		PLAN_JOIN_TYPE = "inner"


		class Dispatcher:
		"""
		A class to dispatch tasks based on the observation type.