/OSMI-Data-Analysis

Data analysis on the 2014-2020 OSMI datasets and web-scraped data with standard Python statistical modeling and machine learning packages.

Primary LanguageJupyter Notebook

Evolution of Tech Workplace Disposition toward Mental Health

Data Analysis on the OSMI Survey Datasets

About the Datasets

The non-profit organization, OSMI is involved in raising awareness and providing resources to support mental health and wellness in tech and open source communities. It has contributed to the public a repository of datasets, collected throughout the years since 2014 through questionnaires. We look to aggregate these datasets to analyze overarching trends regarding attitudes and perception of mental health in the workplace throughout the years.

Sources for the datasets:

  1. Research from OSMI
  2. Kaggle Repositories for the OSMI Datasets

Problem Statements for Analysis

We look to analyze how the OSMI datasets ranging from the years 2014-2020 encapsulate the trend of employer acceptance of mental health and initiatives to tackle employee mental health. We also delve into:

  • the variation of employee attitudes towards sharing their issues with their employers,
  • how this attitude correlates to the inclination of employees to get treated, and
  • how this attitude correlates with employer initiatives.

Repository Structure

.
├── datasets
│   ├── final_2017.csv
│   ├── final_2018.csv
│   ├── final_2019.csv
│   ├── final_2020.csv
│   ├── initial_2014.csv
│   ├── initial_2016.csv
│   ├── initial_2017.csv
│   ├── initial_2018.csv
│   ├── initial_2019.csv
│   └── initial_2020.csv
├── eda
│   └── EDA_2014 Survey.ipynb
├── individual-drafts
│   ├── Shree_EDA.ipynb
│   └── Shruvi_EDA.ipynb
├── preprocessing
│   ├── Creating_Annual_Datasets.ipynb
│   └── Dataset Aggregation.ipynb
└── README.md