Abstract

Effective machine learning models hinge upon meticulous data preprocessing for optimal performance. This study introduces a versatile data preprocessing tool developed within the Flask framework, a Python-based web framework. The application not only streamlines conventional preprocessing tasks for structured datasets but also addresses a significant gap in the preprocessing landscape by accommodating qualitative data. Users can seamlessly interact with the program through a web-based interface or command-line input to upload datasets, perform operations such as column deletion, handle missing values, compress categories, and standardize or normalize facts. The versatility of the tool, coupled with its accessibility and comprehensive functionality, positions it as a valuable asset for researchers and practitioners in the machine learning community. Moreover, the tool integrates popular machine learning algorithms such as linear regression, decision trees, random forest, k-nearest neighbours (KNN), logistic regression, and support vector machines (SVM). This inclusive approach, coupled with a no-code environment, empowers users of varying technical backgrounds to effortlessly prepare datasets for machine learning endeavours. The tool's adaptability extends to incorporating these algorithms into the preprocessing workflow, allowing users to perform model training and evaluation seamlessly within the same environment.