The project involves using data from the World Happiness Report in applications related to data analysis, data science, data mining as well as utilizing machine learning methods, including supervised learning (regression) and unsupervised learning (clustering).
The World Happiness Report is an annual publication produced by the United Nations Sustainable Development Solutions Network, which ranks countries based on various factors related to happiness and well-being. The report is based on data collected from surveys and other sources that measure the quality of life, social support, freedom, corruption, and other factors that contribute to happiness. The report aims to provide policymakers with insights into the factors that drive happiness and well-being in different countries, and to encourage public debate and policy action on these issues.
Report and datasets are available at: https://worldhappiness.report/
Try it out with binder:
World Map - happiness score 2021
Comparing different regression algorithms in terms of MSE,MAE and R2 results within dataset
Elastic Net Regression variables influence on happiness score
XGB regression variables influence on happiness score
Spectral clustering
Gaussian Mixture Models clustering
Affinity Propagation clustering