Inference Configuration

The shipped inference YAML is the canonical example. Active keys are listed below; unknown non-sparse_sc_* keys are not comprehensively rejected, so a misspelling can be ignored. Compare production configs with this table.

Key	Type/default	Contract
`schema_version`	string, `1.0`	Supported config schema.
`data_path`	string	Input CSV for file mode.
`location_col_name`	string	Geography identifier column.
`date_col_name`	string	Period column.
`date_format`	string	Explicit `pandas` date format.
`outcome_col_name`	string	Numeric outcome column.
`covariate_col_names`	list or null	Optional covariates passed to the loader.
`treatment_unit_ids`	list	Treated geography identifiers.
`intervention_date_str`	string	First observed treated period.
`cooldown_periods`	non-negative integer, `0`	Observed periods excluded after launch.
`measurement_start_date_str`	string or null	Optional explicit start; must agree with cooldown.
`duplicate_policy`	`error`, `mean`, `sum`	Duplicate unit-period handling.
`missing_outcome_policy`	`error`, `drop_unit`, `drop_period`, `impute_with_report`	Incomplete-panel handling.
`min_pre_treatment_periods`	integer, `12`	Minimum pre-period observations in file mode.
`min_post_treatment_periods`	integer, `1`	Minimum measured post-period observations in file mode.
`estimator`	`sparsesc`	Only implemented estimator selector.
`output_dir`	string	Artefact directory.
`create_plots`	boolean	CLI plot default.

SparseSC runtime keys:

Key	Default or role
`sparse_sc_model_type`	SparseSC model type, normally `retrospective`.
`sparse_sc_fast_estimation`	Selects SparseSC fast fitting path.
`sparse_sc_return_ci`	Requests placebo confidence intervals.
`sparse_sc_T0`, `sparse_sc_T1`	SparseSC history-length controls; not cooldown semantics.
`sparse_sc_max_n_pl`	Maximum placebo assignments used.
`sparse_sc_placebo_seed`	Non-negative seed for sampled placebo assignments; default `110011`.
`sparse_sc_level`	Requested interval level.
`sparse_sc_lasso_max_iter`, `sparse_sc_lasso_tol`	Forwarded as fast-path CV options; the RidgeCV-backed path may ignore them. They do not configure the full path.
`sparse_sc_cv_folds`, `sparse_sc_scoring`, `sparse_sc_gcv_mode`	Supported adapter controls.

Assumption keys are run_assumption_checks, require_assumption_checks, fail_on_assumption_error, parallel_trends_method, spillover_method, and assumption_alpha. Only the parallel-trends diagnostic is gate-eligible. The interference screen is always advisory.

The non-prefixed compatibility keys lasso_selection, lasso_fit_intercept, and lasso_normalize are forwarded only when the fast path is selected. Their support depends on the installed scikit-learn API; prefer the documented sparse_sc_* controls for new configurations.

There is no active treatment_col or end_date key. Define treatment through treatment_unit_ids; trim the input panel to a pre-specified end date. Inference also does not consume shapemap_file or shapemap_id_column; shapemap-backed maps belong to the donor stage.