motifs_search_plot: Plot Motif Search Results

In funMoDisco: Motif Discovery in Functional Data

Plot Motif Search Results

Description

The 'motifs_search_plot' function visualizes the results obtained from the 'motifs_search' function. It generates plots for detected motifs across multiple dimensions, displaying both the motifs and their corresponding derivative curves (if available). Users can filter motifs based on frequency thresholds and choose to display either all motifs or the top 'n' motifs. Additionally, the function provides an option to plot all underlying curves with colored motifs highlighted.

Usage

motifs_search_plot(
  motifs_search_results,
  ylab = "",
  freq_threshold = 5,
  top_n = "all",
  plot_curves = TRUE,
  transformed = FALSE
)

Arguments

motifs_search_results	A list containing the output from the 'motifs_search' function. This includes elements such as 'V0', 'V1', 'V_frequencies', 'Y0', 'Y1', 'V_length', 'V_occurrences', 'V_mean_diss', and 'R_motifs', which store information about the detected motifs and their properties.
ylab	A character string specifying the label for the y-axis in the plots. This label will be appended with the dimension number to create individual titles for each plot. Default is an empty string ('”').
freq_threshold	An integer indicating the minimum frequency a motif must have to be included in the plots. Only motifs with a frequency equal to or greater than 'freq_threshold' will be visualized. Default value is '5'.
top_n	Determines how many motifs to plot based on their frequency. If set to ''all'', all motifs meeting the 'freq_threshold' will be plotted. If an integer is provided, only the top ‘top_n' motifs with the highest frequencies will be displayed. Default is '’all''.
plot_curves	A logical value indicating whether to plot all underlying curves with colored motifs highlighted. If 'TRUE', the function overlays motifs on the curves for better visualization. Default is 'TRUE'.
transformed	A logical value indicating whether to normalize the curve segments to the interval [0,1] before applying the dissimilarity measure. Setting 'transformed = TRUE' scales each curve segment between 0 and 1, which allows for the identification of motifs with consistent shapes but different amplitudes. This normalization is useful for cases where motif occurrences may vary in amplitude but have similar shapes, enabling better pattern recognition across diverse data scales.

Details

The 'motifs_search_plot' function performs the following steps:

1. Validates input parameters, ensuring that the frequency threshold and 'top_n' are appropriate.

2. Selects motifs that meet the frequency threshold and, if specified, limits the number of motifs to the top 'n'.

3. For each dimension, it plots the motif centers ('V0') and their derivatives ('V1', if available).

4. If 'plot_curves' is 'TRUE', it overlays the motifs on the original curves, highlighting them with distinct colors.

5. Adds legends to the plots for clear identification of each motif.

Value

The function does not return a value but generates plots visualizing the motifs and their occurrences across different dimensions. It creates separate plots for each dimension and includes legends for easy identification of motifs.

funMoDisco documentation built on April 16, 2025, 1:10 a.m.