corrp: An R package for multiple correlation-like analysis and clustering in mixed data

Correlation-like analysis provides an important statistical measure that describes the size and direction of an association between variables.However, there are few R packages that can efficiently perform this type of analysis on large datasets with mixed data types.The corrp package provides a full suite of solutions for computing various correlation-like measures, such as Pearson correlation (Pearson, 1895), Distance Correlation (Szkely et al., 2007), Maximal Information Coefficient (MIC) (Reshef et al., 2011), Predictive Power Score (PPS) (Wetschoreck et al., 2020), Cramr's V (Cramr, 1946), and the Uncertainty Coefficient (Theil, 1972).These methods support the analysis of data frames with mixed classes (integer, numeric, factor, and character).Additionally, it offers a C++ implementation of the Average Correlation Clustering Algorithm (ACCA) (Bhattacharya & De, 2010), which was originally developed for genetic studies using Pearson correlation as a similarity measure.In general, ACCA is an unsupervised clustering method, as it identifies patterns in the data without requiring predefined labels.Moreover, it requires the K parameter to be defined, similar to k-means.One of its main differences compared to other clustering methods is that it operates based on correlations rather than traditional distance metrics, such as Euclidean or Mahalanobis distance.In this package, the ACCA algorithm has been extended to work directly with correlation matrices derived from different association methods, depending on the data types and user preferences.Furthermore, the package is designed for parallel processing in R, making it highly efficient for large datasets.