Runs an appropriate workflow based on the parameters passed in.

Source: R/analyze.R

The goal of this function is to compute all fundamental algorithms on the provided time series data. See details for more information.

analyze(
  ts,
  windows = NULL,
  query = NULL,
  sample_pct = 1,
  threshold = 0.98,
  n_jobs = 1L
)

Arguments

ts

a matrix or a vector. The time series to analyze.

windows

an int or a vector. The window(s) to compute the Matrix Profile. Note that it may be an int for a single matrix profile computation or a vector of int for computing the Pan-Matrix Profile.

query

a matrix or a vector. Optional The query to analyze. Note that when computing the Pan-Matrix Profile the query is ignored!

sample_pct

a numeric. A number between 0 and 1 representing how many samples to compute for the Matrix Profile or Pan-Matrix Profile. When it is 1, the exact algorithm is used. (default is 1.0).

threshold

a numeric. Correlation threshold. See details. (Default is 0.98).

n_jobs

an int. The number of cpu cores to use when computing the MatrixProfile. (default is 1).

Value

The appropriate Matrix Profile or Pan-Matrix Profile profile object and also plots the graphics.

Details

For now the following is computed:

  1. Matrix Profile - exact or approximate based on sample_pct given that a single windows is provided. By default is the exact algorithm;

  2. Top 3 Motifs;

  3. Top 3 Discords;

  4. Plot Matrix Profile, Motifs and Discords.

When windows is not provided or more than a single window is provided, the Pan-Matrix Profile is computed:

  1. Compute the upper bound when a threshold is provided (it is, by default);

  2. Compute Pan-Matrix Profile for all windows provided, below the upper bound, or a default range when no windows is provided;

  3. Top Motifs;

  4. Top Discords;

  5. Plot Pan-Matrix Profile, motifs and discords.

See also

Other Main API: compute(), discords(), motifs(), visualize()

Examples


# Matrix Profile
result <- analyze(mp_toy_data$data[, 1], 80)



# \donttest{
# Pan Matrix Profile
result <- analyze(mp_toy_data$data[, 1])
#> step: 1/17 binary idx: 1 window: 10
#> step: 2/17 binary idx: 9 window: 14
#> step: 3/17 binary idx: 5 window: 12
#> step: 4/17 binary idx: 13 window: 17
#> step: 5/17 binary idx: 3 window: 11
#> step: 6/17 binary idx: 7 window: 13
#> step: 7/17 binary idx: 11 window: 15
#> step: 8/17 binary idx: 15 window: 18
#> step: 9/17 binary idx: 2 window: 10
#> step: 10/17 binary idx: 4 window: 11
#> step: 11/17 binary idx: 6 window: 12
#> step: 12/17 binary idx: 8 window: 13
#> step: 13/17 binary idx: 10 window: 14
#> step: 14/17 binary idx: 12 window: 15
#> step: 15/17 binary idx: 14 window: 17
#> step: 16/17 binary idx: 16 window: 18
#> step: 17/17 binary idx: 17 window: 19



# }