Sakinah Emoshioke Ali

Analysis of Global Trends in Mental Health Disorder Using Linear Regression

Introduction

The prevalence of mental health disorders varies across countries. This variability is particularly concerning as it reflects a multifaceted interplay of cultural, societal, economic, and healthcare factors. Understanding and addressing these differences is crucial for developing effective strategies to support mental health on a global scale. The main aim of this project is to explore the prevalence of mental health disorders in countries using Data Visualization techniques and Machine Learning algorithms. In the context of this project, an essential question to answer is “In which countries are mental health issues most and least prevalent?”.

Data Description

The dataset was a single dataset obtained from Kaggle which contains mental health disorders columns such as depression, and other columns such as countries, Year, and Code.

Methodology

The guideline of CRISP-DM, an iterative open-source data methodology was used. The Python libraries used in this project were Pandas, Numpy, Geopandas, Plotly, and Scikit Learn. Pandas and Numpy were used for data cleaning, Plotly was used for the data visualization and Scikit Learn was used to build a linear regression model.

Data Exploration

Exploring Common Mental Health Disorders Across Countries and Years

bubbleplot

Depression

Schizophrenia

Visualization of the other maps can be viewed here Google Collab

Project Code: Github

Project Article:Article