Fix typos

R/CENTROIDS-shape-extraction.R

@@ -27,7 +27,7 @@
 #' series will be chosen at random and used as reference. The output series will then have the same
 #' length as the chosen series.
 #'
-#' This centroid computation is casted as an optimization problem called maximization of Rayleigh
+#' This centroid computation is cast as an optimization problem called maximization of Rayleigh
 #' Quotient. It depends on the [SBD()] algorithm. See the cited article for more details.
 #'
 #' @return Centroid time series (z-normalized).

R/GENERICS-cvi.R

@@ -9,9 +9,9 @@
 #' @importFrom methods setGeneric
 #'
 #' @param a An object returned by [tsclust()], for crisp partitions a vector that can be coerced to
-#'   integers which indicate the cluster memeberships, or the membership matrix for soft clustering.
+#'   integers which indicate the cluster memberships, or the membership matrix for soft clustering.
 #' @param b If needed, a vector that can be coerced to integers which indicate the cluster
-#'   memeberships. The ground truth (if known) should be provided here.
+#'   memberships. The ground truth (if known) should be provided here.
 #' @param type Character vector indicating which indices are to be computed. See supported values
 #'   below.
 #' @param ... Arguments to pass to and from other methods.

README.Rmd

@@ -68,7 +68,7 @@ The latest version from CRAN can be installed with `install.packages("dtwclust")
 If you want to test the latest version from github,
 first install the
 [prerequisites for R package development](https://support.rstudio.com/hc/en-us/articles/200486498-Package-Development-Prerequisites)
-(LaTeX is only neccesary if you want to build the vignette)
+(LaTeX is only necessary if you want to build the vignette)
 as well as the
 [remotes package](https://cran.r-project.org/package=remotes),
 and then type `remotes::install_github("asardaes/dtwclust")`.

README.md

@@ -65,7 +65,7 @@ The latest version from CRAN can be installed with
 If you want to test the latest version from github, first install the
 [prerequisites for R package
 development](https://support.rstudio.com/hc/en-us/articles/200486498-Package-Development-Prerequisites)
-(LaTeX is only neccesary if you want to build the vignette) as well as
+(LaTeX is only necessary if you want to build the vignette) as well as
 the [remotes package](https://cran.r-project.org/package=remotes), and
 then type `remotes::install_github("asardaes/dtwclust")`.
 

vignettes/dtwclust.Rnw

@@ -643,7 +643,7 @@ The triangular constraint is similar to the window constraints that can be used
 When $T = 0$ or $T \rightarrow \infty$,
 the TGAK converges to the original GA kernel.
 When $T = 1$, the TGAK becomes a slightly modified Gaussian kernel that can only compare series of equal length.
-If $T > 1$, then only the alignments that fulfil $-T < \pi_1(i) - \pi_2(i) < T$ are considered.
+If $T > 1$, then only the alignments that fulfill $-T < \pi_1(i) - \pi_2(i) < T$ are considered.
 
 \citet{cuturi2011} also proposed a strategy to estimate the value of $\sigma$ based on the time-series themselves and their lengths,
 namely $c \cdot \text{med}(\left\lVert x - y \right\rVert) \cdot \sqrt{\text{med}(|\text{x}|)}$,
@@ -1016,8 +1016,8 @@ starting with all data in one cluster and dividing them until each member is in
 Both strategies suffer from a lack of flexibility,
 because they cannot perform adjustments once a split or merger has been done.
 
-The intergroup dissimilarity is also known as linkage.
-As an example, single linkage takes the intergroup dissimilarity to be that of the closest (least dissimilar) pair \citep{hastie2009}.
+The inter-group dissimilarity is also known as linkage.
+As an example, single linkage takes the inter-group dissimilarity to be that of the closest (least dissimilar) pair \citep{hastie2009}.
 There are many linkage methods available,
 although if the data can be ``easily'' grouped,
 they should all provide similar results.
@@ -1026,7 +1026,7 @@ and all its linkage methods are supported.
 However, it is possible to use other clustering functions,
 albeit with some limitations (see \cref{app:hc}).
 
-The created hierarchy can be visualized as a binary tree where the height of each node is proportional to the value of the intergroup dissimilarity between its two daughter nodes \citep{hastie2009}.
+The created hierarchy can be visualized as a binary tree where the height of each node is proportional to the value of the inter-group dissimilarity between its two daughter nodes \citep{hastie2009}.
 Such a plot is called a dendrogram,
 an example of which can be seen in \cref{fig:dendrogram}.
 These plots can be a useful way of summarizing the whole data in an interpretable way,
@@ -1067,7 +1067,7 @@ The total number of desired clusters must be specified beforehand,
 which can be a limiting factor,
 although this can be ameliorated by using validity indices (see \cref{sec:evaluation}).
 
-Partitional procedures can be stated as combinatorial optimization problems that minimize the intracluster distance while maximizing the intercluster distance.
+Partitional procedures can be stated as combinatorial optimization problems that minimize the intra-cluster distance while maximizing the inter-cluster distance.
 However, finding a global optimum would require enumerating all possible groupings,
 something which is infeasible even for relatively small datasets \citep{hastie2009}.
 Therefore, iterative greedy descent strategies are used instead,

vignettes/parallelization-considerations.Rmd

@@ -225,7 +225,7 @@ and the following parallelization scenarios were tested on a machine with 4 core
 
 - 4 workers required 7.36 minutes to finish.
 - 2 workers and 2 threads per worker required 7.97 minutes to finish.
-- 2 workers and 4 threads per workrer required 7.46 minutes to finish.
+- 2 workers and 4 threads per worker required 7.46 minutes to finish.
 - No workers and 4 threads required 10.35 minutes to finish.
 
 The last scenario has the possible advantage that tracing is still possible.