End to End Data analytics project on StackOverflow developer survey over last 4yrs.
- Python
- Pandas,Numpy,Seaborn,Statsmodels,scipy,matplotlib,csv
- Tableau Public
- Collected Last 4yrs of StackOverflow data and combined them from here
- Made data more stable by cleaning and transforming values wherever needed.
- Missing value imputation for data was done wherever needed. For example, for salary, as it was right skewed 'Group median Imputation' was performed on that data, grouping by years.
-
Analyzed Trends, distributions in the data for various programming languages & databases over the last 4yrs.
-
Performed Descriptive and Inferential statistic on data like building 95% CI's and z-tests for hypothesis after transforming data.
-
Answered a lot of questions like employment type of people, their education level, world's contribution on stackoverflow and impact of these factors on Salary.
-
All Visuals/reports are published in a free cloud environment (Tableau Public) so that anyone/everyone can carry on their own analysis, a few visuals are --