Batchalign: Difference between revisions
Jump to navigation
Jump to search
imported>Scott (Created page with "===Purpose=== Convert data columns based on matching ref col to target vector. ===Synopsis=== :aligned = batchalign(data,ref_column,target,options) ===Description=== Stretch...") |
imported>Jeremy |
||
| (7 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
===Purpose=== | ===Purpose=== | ||
Convert data columns based on matching | Convert data columns based on matching a reference column to a target vector. | ||
===Synopsis=== | ===Synopsis=== | ||
| Line 9: | Line 9: | ||
===Description=== | ===Description=== | ||
Stretch or contract data columns based on a | Stretch or contract data columns based on a '''target''' using given '''method'''. Savgol options can be used to exaggerate transitions in data prior to cow. | ||
====Inputs==== | ====Inputs==== | ||
| Line 27: | Line 27: | ||
* '''method''': [ 'linear' | {'cow'} | 'padwithnan' ] Alignment method. | * '''method''': [ 'linear' | {'cow'} | 'padwithnan' ] Alignment method. | ||
** 'linear' means the data columns are extented/contracted using linear interpolation to have the same number of data points as the target vector. | |||
** 'cow' applies Correlation Optimized Warping to match the reference column to the target vector, then apply the same transformation to the other columns. | |||
** 'padwithnan' uses NaN values to extend columns, or truncates columns, to have the same number of data points as the target vector. | |||
* '''savgolwidth''': Number of points in savgol filter. | * '''savgolwidth''': Number of points in savgol filter. | ||
| Line 32: | Line 35: | ||
* '''savgolderiv''': [0,1,2...] Order of derivative to take of target and ref_column before doing alignment (default = 0). | * '''savgolderiv''': [0,1,2...] Order of derivative to take of target and ref_column before doing alignment (default = 0). | ||
[[cow|Cow]] only options. | [[cow|Cow]] only options. | ||
* '''cow.segments ''': | * '''cow''': structure with the following fields: | ||
* '''cow.slack''': max range of warping. | ** '''cow.segments ''': Segment length. | ||
* '''cow.plots''': Governs plotting with COW (0 = no plots). | ** '''cow.slack''': max range of warping. 'slack' value must be less than or equal to segments minus 4. | ||
* '''cow.correlationpower''': correlation power. | ** '''cow.plots''': Governs plotting with COW (0 = no plots). | ||
* '''cow.forceequalsegs''': Force equal segment lengths in "xt" and "xP". | ** '''cow.correlationpower''': correlation power. | ||
* '''cow.fixmaxcorrection''': Fix maximum correction. | ** '''cow.forceequalsegs''': Force equal segment lengths in "xt" and "xP". | ||
** '''cow.fixmaxcorrection''': Fix maximum correction. | |||
===See Also=== | ===See Also=== | ||
[[alignmat]],[[cow]], [[matchrows]] | [[alignmat]], [[batchfold]], [[cow]], [[matchrows]] | ||
Latest revision as of 16:15, 9 June 2014
Purpose
Convert data columns based on matching a reference column to a target vector.
Synopsis
- aligned = batchalign(data,ref_column,target,options)
Description
Stretch or contract data columns based on a target using given method. Savgol options can be used to exaggerate transitions in data prior to cow.
Inputs
- data = (nsample, nvar) dataset or double array containing data columns to align.
- ref_column = scalar indicating the column # of data that we are going to match OR ref_vector which is a vector to use in match.
- target = (nsample, 1) vector or dataset to which we are trying to match the ref_column or ref_vector.
Outputs
- aligned: dataset or double array (depending on input data type) containing the aligned data. If it is a dataset of different number of rows from input then the class, axisscale and labels are set according to the closest row in input dataset.
Options
options = a structure array with the following fields:
- method: [ 'linear' | {'cow'} | 'padwithnan' ] Alignment method.
- 'linear' means the data columns are extented/contracted using linear interpolation to have the same number of data points as the target vector.
- 'cow' applies Correlation Optimized Warping to match the reference column to the target vector, then apply the same transformation to the other columns.
- 'padwithnan' uses NaN values to extend columns, or truncates columns, to have the same number of data points as the target vector.
- savgolwidth: Number of points in savgol filter.
- savgolorder: Order of savgol polynomial.
- savgolderiv: [0,1,2...] Order of derivative to take of target and ref_column before doing alignment (default = 0).
Cow only options.
- cow: structure with the following fields:
- cow.segments : Segment length.
- cow.slack: max range of warping. 'slack' value must be less than or equal to segments minus 4.
- cow.plots: Governs plotting with COW (0 = no plots).
- cow.correlationpower: correlation power.
- cow.forceequalsegs: Force equal segment lengths in "xt" and "xP".
- cow.fixmaxcorrection: Fix maximum correction.