data_set_new.md

updates for data_set_new.md

1. patents.factor is "<100" if it has rank smaller than 100 otherwise ">= 100"
2. rank_score is the standardize score for rank with higher number signifies higher rank. Harvard has near 100.
3. rank_levels is level of rank, Havard has rank 10 and school with least rank has level of 1.
4. employment_levels is level of employment with levels "low", "medium" and "high". Havard has "high" employment_levels
5. we also creates a column for the continents. Therefore 7 continents in total.