Use the idxmax method to get the column name with the highest race percentage for each row:
>>> highest_percentage_race = college_ugds.idxmax(axis='columns') >>> highest_percentage_race.head() INSTNM
Alabama A & M University UGDS_BLACK
University of Alabama at Birmingham UGDS_WHITE
Amridge University UGDS_BLACK
University of Alabama in Huntsville UGDS_WHITE
Alabama State University UGDS_BLACK
dtype: object
Use the value_counts method to return the distribution of maximum occurrences: