This project addresses the application of natural language processing (NLP) techniques to enhance the chi-square test for goodness of fit and independence, crucial tools in statistical analysis for comparing observed data with expected distributions. Leveraging NLP, specifically through the use of regular expressions, this project streamlines data extraction from complex textual inputs, thereby facilitating more accurate and efficient statistical testing. The methodology focuses on automating the extraction of relevant data, identifying the type of chi-square test required, and executing the test using the extracted parameters. Our results demonstrate that the integration of NLP not only simplifies the process of setting up and performing these tests but also improves the accuracy of the outcomes, making this approach a valuable asset in fields requiring robust data analysis and hypothesis testing.