A data science project that takes Stack Overflow survey data from 2017 to try and predict salaries from survey data of 2018. Raw data can be found at: https://insights.stackoverflow.com/survey/?utm_source=so-owned&utm_medium=blog&utm_campaign=dev-survey-2017&utm_content=blog-link&utm_term=data
2/15/2019: Processed lower bounds of salary data. Ran data through random forest again, 2018 salaries got an r2 score of ~0.51.
2/6/2019: Looked at residual plots, added a file to show how I processed salary data.
2/4/2019: Ran data through a quick random forest model. Training and validation r2 scores were 0.93 and 0.63 respectively, indicating overfitting. Predicting the 2018 salaries got an r2 score of ~0.
2/1/2019: Uploaded pre-processed data