Comparative analysis between theoretical and simulatory learning methods by data science methodology approach

Abstract

Abstract Data Science is the most trending interdisciplinary science that integrates the steps of data collection, preprocessing data, transforming data, storing data, data visualization, and hence extracting the insights from the data to serve stakeholder’s purposes. Python is commonly used and, along with being a versatile and open-source language, is a favorite tool in Data science studies. The vast libraries are being used to manipulate data and are very simple for even a beginner data scientist to understand. In the present work, we intend to apply the data science methodology to decision making and predictive analysis using the python programming language. We consider the problem of selecting the better mode of study concerning some of the impractical phenomena from physics for the exact understanding of the process. Data collection has been from an educational institute and the comparison has been made between theoretical learning and simulatory learning for selected topics from the vast fields like mechanics, thermodynamics, fluid dynamics, and radioactivity. The steps of data science methodology are germinated to achieve the insights into the data procured and the results are wangled concerning the teaching methodology that could be employed. In the present work, we undertake a comparative study between the theoretical and simulatory modes of teaching by exploring the modes individually through evaluating the responses imparted by a class of high school students. The analysis reported the more inclination of the student’s responses towards the simulatory methods when compared to the theoretical method of learning.