degree project at bachelor level

Weka package that allows listening in on data as it passes through filter pipelines.

kDMI employs two levels of horizontal partitioning (based on a decision tree and k-NN algorithm) of a data set, in order to find the records that are very similar to the one with missing value/s. Additionally, it uses a novel approach to automatically find the value of k for each record.

Using VnTokenizer to token document in Java

SiMI imputes numerical and categorical missing values by making an educated guess based on records that are similar to the record having a missing value. Using the similarity and correlations, missing values are then imputed. To achieve a higher quality of imputation some segments are merged together using a novel approach.

Implementation of C4.5 + Binarization (OVO / OVA) with/without SMOTE preprocessing. This way, multi-class imbalanced problems can be addressed

PRETO: A High-performance Text Mining Tool for Preprocessing Turkish Texts

Complex event processing for data stream preprocessing

DMI Class implements the DMI imputation algorithm for imputing missing values in a dataset from Rahman, M. G., and Islam, M. Z. (2013): Missing Value Imputation Using Decision Trees and Decision Forests by Splitting and Merging Records: Two Novel Techniques

Dali Preprocessing Pipeline

Split and tokenization text data

Exploration of the different phases of Data Mining: Data visualization, their preprocessing and the implementation of multiple algorithms for Data Mining.

EDI uses two layers/steps of imputation namely the Early-Imputation step and the Advanced-Imputation step.

Shader management and preprocessing

Weka package using the mXparser library.

A parser written for the BabyCobol language, using the ANTLR framework. This repository is part of my bachelor thesis.

Language processing interface: some tools to process different natural languages

Weka package with filters that allow modifying attribute/instance weights.

A simple table data editor, with easily scalable functions and operations & a nice GUI

LFD is a data-driven discretization technique that does not require any user input. LFD uses low frequency values as cut points and thus reduces the information loss due to discretization. It uses all other categorical attributes and any numerical attribute that has already been categorized.