Python Docs
causalis
Package entry
causalisRoot package overview and namespace mapNamespaces
causalis.scenarios.synthetic_control._utilsSubmodule causalis.scenarios.synthetic_control._utils with no child pages and 7 documented members.
Functions
Jump directly into the documented functions for this page.
causalis.scenarios.synthetic_control._utils.rmseCompute root mean squared error.
Parameters
Input array-like values. The input is flattened before computation.
Returns
Root mean squared error. Returns 0.0 for empty input.
Canonical target
causalis.scenarios.synthetic_control._utils.rmse
Sections
causalis.scenarios.synthetic_control._utils.project_to_simplexProject a vector onto the probability simplex.
The simplex is defined as non-negative vectors whose entries sum to one.
Parameters
One-dimensional coefficient vector.
Returns
Projected vector with non-negative entries summing to one.
Raises
If the input is empty or contains non-finite values.
Canonical target
causalis.scenarios.synthetic_control._utils.project_to_simplex
Sections
causalis.scenarios.synthetic_control._utils.solve_linear_systemSolve a linear system with least-squares fallback.
Parameters
Coefficient matrix.
Right-hand side vector or matrix.
Returns
Exact solution when a is non-singular, otherwise least-squares solution.
Canonical target
causalis.scenarios.synthetic_control._utils.solve_linear_system
Sections
causalis.scenarios.synthetic_control._utils.circular_shift_indicesGenerate circular-shift index permutations.
Parameters
Sequence length.
Returns
All n_total circular shifts of arange(n_total).
Canonical target
causalis.scenarios.synthetic_control._utils.circular_shift_indices
Sections
causalis.scenarios.synthetic_control._utils.cwz_stat_from_residualsCompute CWZ post-window residual aggregation statistic.
Parameters
Residual vector containing pre-period entries first, then post-period entries.
Number of pre-period residuals.
Returns
|sum(post_residuals)| / sqrt(n_post).
Raises
If n_pre does not satisfy 1 <= n_pre < len(residuals).
Canonical target
causalis.scenarios.synthetic_control._utils.cwz_stat_from_residuals
Sections
causalis.scenarios.synthetic_control._utils.accepted_segmentsConvert a boolean acceptance mask into contiguous grid segments.
Parameters
One-dimensional, ordered grid of candidate parameter values.
Boolean mask with the same length as grid.
Returns
Closed intervals corresponding to contiguous accepted regions.
Raises
If grid and accepted_mask are not one-dimensional arrays of the same length.
Canonical target
causalis.scenarios.synthetic_control._utils.accepted_segments
Sections
causalis.scenarios.synthetic_control._utils.build_average_att_blocksBuild consecutive pre-period holdout blocks for average ATT inference.
Parameters
Number of pre-treatment periods T0.
Number of post-treatment periods T1.
Requested number of folds K.
Returns
(blocks, k_used, block_length) where blocks are consecutive holdout indices over the pre-period.
Notes
If n_pre is not divisible by k_used, the rule
r = min(floor(T0 / K), T1) is applied on the first K * r periods.
Remaining pre-periods are included in every fold’s training subset.
Raises
If the configuration cannot produce at least two folds and a positive holdout block length.
Canonical target
causalis.scenarios.synthetic_control._utils.build_average_att_blocks
Sections