# clusterify: Group Elementary Series Using W-correlation Matrix In Rssa: A Collection of Methods for Singular Spectrum Analysis

## Description

Group elemenatry series automatically via the hierarchical clustering with w-correlation matrix as a proximity matrix

## Usage

 ```1 2``` ```## S3 method for class 'ssa' grouping.auto.wcor(x, groups, nclust = length(groups) / 2, ...) ```

## Arguments

 `x` SSA object `groups` list of numeric vectors, indices of elementary components used for reconstruction `nclust` integer, desired number of output series `...` further arguments passed to `hclust`

## Details

Standard `hclust` routine is used to perform the grouping of the elementary components.

## Value

List of integer vectors holding the indices of the elementary components forming each grouped objects

`hclust`, `wcor`

## Examples

 ``` 1 2 3 4 5 6 7 8 9 10 11``` ```# Decompose 'co2' series with default parameters s <- ssa(co2) # Form 3 series from the initial 6 ones: lst <- grouping.auto(s, grouping.method = "wcor", groups = 1:6, nclust=3) # Automatic grouping: print(lst) plot(lst) # Check separability w <- wcor(s, groups = lst) plot(w) ```

### Example output

```Loading required package: svd

The following object is masked from 'package:stats':

decompose

\$`1`
[1] 1 4

\$`2`
[1] 2 3

\$`3`
[1] 5 6

attr(,"hclust")

Call:
hclust(d = as.dist((1 - w)/2))

Cluster method   : complete
Number of objects: 6

attr(,"wcor")
F1           F2           F3           F4           F5
F1 1.000000e+00 3.587609e-06 3.893247e-06 5.798656e-04 1.670659e-07
F2 3.587609e-06 1.000000e+00 9.991025e-01 6.711680e-04 3.082124e-04
F3 3.893247e-06 9.991025e-01 1.000000e+00 5.091794e-04 2.196507e-04
F4 5.798656e-04 6.711680e-04 5.091794e-04 1.000000e+00 9.857432e-05
F5 1.670659e-07 3.082124e-04 2.196507e-04 9.857432e-05 1.000000e+00
F6 1.630901e-07 4.239162e-04 1.227990e-04 6.242357e-05 9.995623e-01
F6
F1 1.630901e-07
F2 4.239162e-04
F3 1.227990e-04
F4 6.242357e-05
F5 9.995623e-01
F6 1.000000e+00
attr(,"class")
[1] "wcor.matrix"
attr(,"class")
[1] "grouping.auto.wcor"
```

Rssa documentation built on Oct. 4, 2017, 5:06 p.m.