Join the newly launched
Discord community for real-time discussions, peer support, and direct interaction with the Meridian team!
meridian.model.knots.get_knot_info
Stay organized with collections
Save and categorize content based on your preferences.
Returns the number of knots, knot locations, and weights.
meridian.model.knots.get_knot_info(
n_times: int,
knots: (int | Collection[int] | None),
enable_aks: bool = False,
data: (meridian.data.input_data.InputData | None) = None,
is_national: bool = False
) -> meridian.model.knots.KnotInfo
Args |
|---|
n_times
|
The number of time periods in the data.
|
knots
|
An optional integer or a collection of integers indicating the knots
used to estimate time effects. When knots is a collection of integers,
the knot locations are provided by that collection. Zero corresponds to a
knot at the first time period, one corresponds to a knot at the second
time, ..., and (n_times - 1) corresponds to a knot at the last time
period. When knots is an integer, then there are knots with locations
equally spaced across the time periods (including knots at zero and
(n_times - 1). When knots is 1, there is a single common regression
coefficient used for all time periods. If knots is None, then the
numbers of knots used is equal to the number of time periods. This is
equivalent to each time period having its own regression coefficient.
|
enable_aks
|
A boolean indicating whether to use the Automatic Knot Selection
algorithm to select optimal number of knots for running the model instead
of the default 1 for national and n_times for non-national models.
|
data
|
An Optional InputData object used by the Automatic Knot Selection
algorithm to calculate optimal number of knots from the provided Input
Data.
|
is_national
|
A boolean indicator whether to adapt the knot information for a
national model.
|
Returns |
|---|
|
A KnotInfo that contains the number of knots, the location of knots, and the
weights used to multiply with the knot values to get time-varying
coefficients.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-09-05 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-05 UTC."],[[["\u003cp\u003eThis function, \u003ccode\u003eget_knot_info\u003c/code\u003e, determines the necessary information about knots used for estimating time effects, including the number of knots, their locations, and associated weights.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003en_times\u003c/code\u003e argument specifies the total number of time periods in the dataset that the knots refer to.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eknots\u003c/code\u003e argument can be an integer, a collection of integers, or \u003ccode\u003eNone\u003c/code\u003e, controlling the number and placement of knots across the time periods; when it is an integer, they will be equally spaced, when a collection, it directly indicates their locations, when \u003ccode\u003eNone\u003c/code\u003e, each time period gets its own coefficient.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eis_national\u003c/code\u003e boolean argument indicates if the knot information will need to be adjusted for a national model.\u003c/p\u003e\n"],["\u003cp\u003eThe function ultimately returns a \u003ccode\u003eKnotInfo\u003c/code\u003e object, which encapsulates the calculated knot count, locations, and the corresponding weights.\u003c/p\u003e\n"]]],["The function `get_knot_info` determines knot-related information for time-effect estimation. It takes `n_times` (number of time periods), optional `knots` (locations or count), and `is_national` (national model indicator) as input. If `knots` is a collection, these are used directly as locations; if an integer, knots are equally spaced; `None` equals each time period having its own knot. The output includes the total number of knots, their locations, and associated weights.\n"],null,["\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/google/meridian/blob/v1.2.0/meridian/model/knots.py#L152-L235) |\n\nReturns the number of knots, knot locations, and weights. \n\n meridian.model.knots.get_knot_info(\n n_times: int,\n knots: (int | Collection[int] | None),\n enable_aks: bool = False,\n data: (../../../meridian/data/input_data/InputData.md | None) = None,\n is_national: bool = False\n ) -\u003e ../../../meridian/model/knots/KnotInfo.md\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|---------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `n_times` | The number of time periods in the data. |\n| `knots` | An optional integer or a collection of integers indicating the knots used to estimate time effects. When `knots` is a collection of integers, the knot locations are provided by that collection. Zero corresponds to a knot at the first time period, one corresponds to a knot at the second time, ..., and `(n_times - 1)` corresponds to a knot at the last time period. When `knots` is an integer, then there are knots with locations equally spaced across the time periods (including knots at zero and `(n_times - 1)`. When `knots` is `1`, there is a single common regression coefficient used for all time periods. If `knots` is `None`, then the numbers of knots used is equal to the number of time periods. This is equivalent to each time period having its own regression coefficient. |\n| `enable_aks` | A boolean indicating whether to use the Automatic Knot Selection algorithm to select optimal number of knots for running the model instead of the default 1 for national and n_times for non-national models. |\n| `data` | An Optional InputData object used by the Automatic Knot Selection algorithm to calculate optimal number of knots from the provided Input Data. |\n| `is_national` | A boolean indicator whether to adapt the knot information for a national model. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| A KnotInfo that contains the number of knots, the location of knots, and the weights used to multiply with the knot values to get time-varying coefficients. ||\n\n\u003cbr /\u003e"]]
View source on GitHub