Fast Change Point Detection via Sequential Gradient Descent

Implements fast change point detection algorithm based on the paper "Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis" by Xianyang Zhang, Trisha Dawn < https://proceedings.mlr.press/v206/zhang23b.html>. The algorithm is based on dynamic programming with pruning and sequential gradient descent. See Li and Zhang (2026) for details.

Flexible Tool for Bias Detection, Visualization, and Mitigation

Measure fairness metrics in one place for many models. Check how big is model's bias towards different races, sex, nationalities etc. Use measures such as Statistical Parity, Equal odds to detect the discrimination against unprivileged groups. Visualize the bias using heatmap, radar plot, biplot, bar chart (and more!). There are various pre-processing and post-processing bias mitigation algorithms implemented. Package also supports calculating fairness metrics for regression models. Find more details in (Wiśniewski, Biecek (2021)) .

Outliers Detection

Provides functions for detecting outliers in datasets using statistical methods. The package supports identification of anomalous observations in numerical data and is intended for use in data cleaning, exploratory data analysis, and preprocessing workflows.

'Arrow' Database Connectivity ('ADBC') 'SQLite' Driver

Provides a developer-facing interface to the 'Arrow' Database Connectivity ('ADBC') 'SQLite' driver for the purposes of building high-level database interfaces for users. 'ADBC' < https://arrow.apache.org/adbc/> is an API standard for database access libraries that uses 'Arrow' for result sets and query parameters.

Detect and Treat Outliers in Data Mining

Implements a suite of tools for outlier detection and treatment in data mining. It includes univariate methods (Z-score, Interquartile Range), multivariate detection using Mahalanobis distance, and density-based detection (Local Outlier Factor) via the 'dbscan' package. It also provides functions for visualization using 'ggplot2' and data cleaning via Winsorization.

Multivariate Outlier Detection Methods

Provides methods for detecting multivariate outliers in numeric datasets. The package implements classical Mahalanobis distance, robust Minimum Covariance Determinant (MCD), and Principal Component Analysis (PCA)-based approaches for outlier detection. The methodology is informed by Aggarwal (2017) and Grentzelos, Caroni and Barranco-Chamorro (2020) . Visualization functions are included to aid interpretation of detected outliers. Mahalanobis distance calculations are accelerated using 'C++' through 'Rcpp'.

QTL Hotspot Detection

This function produces both the numerical and graphical summaries of the QTL hotspot detection in the genomes that are available on the worldwide web including the flanking markers of QTLs.

Geometrically Inspired Multivariate Changepoint Detection

Implements the high-dimensional changepoint detection method GeomCP and the related mappings used for changepoint detection. These methods view the changepoint problem from a geometrical viewpoint and aim to extract relevant geometrical features in order to detect changepoints. The geomcp() function should be your first point of call. References: Grundy et al. (2020) .

Detecting Outliers in Network Meta-Analysis

A set of functions providing several outlier (i.e., studies with extreme findings) and influential detection measures and methodologies in network meta-analysis : - simple outlier and influential detection measures - outlier and influential detection measures by considering study deletion (shift the mean) - plots for outlier and influential detection measures - Q-Q plot for network meta-analysis - Forward Search algorithm in network meta-analysis. - forward plots to monitor statistics in each step of the forward search algorithm - forward plots for summary estimates and their confidence intervals in each step of forward search algorithm.

Change Point Detection with Missing Values

A four step change point detection method that can detect break points with the presence of missing values proposed by Liu and Safikhani (2023) < https://drive.google.com/file/d/1a8sV3RJ8VofLWikTDTQ7W4XJ76cEj4Fg/view?usp=drive_link>.