repeat_measurement_matrix

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

repeat_measurement_matrix(table: FeatureTable, repeat_tables: Sequence[FeatureTable], feature: str, *, owner: str) → ndarray[source]

Build one feature’s (subjects x sessions) repeat-measurement matrix.

The primary table provides the first measurement session and the subject order; every table in repeat_tables contributes one further session, aligned to the primary rows by the identifier columns. Rows with a NaN in any session are dropped (pingouin’s nan_policy="omit", which the v0.1 ICC analysis relied on).

Parameters:

  • table – Primary-measurement table carrying feature.

  • repeat_tables – One table per repeat session, each with identical id_columns and carrying feature.

  • feature – Feature column to extract.

  • owner – Human-readable caller name for error messages.

Returns:

Array of shape (n_complete_subjects, 1 + len(repeat_tables)).

Raises:

HABITAPIError – If a repeat table declares different identifier columns, lacks the feature, or contains unknown identifiers.