ide_salary_stats.py

"""
Gets stats for salaries by IDE

Inpired by: https://stackoverflow.blog/2017/06/15/developers-use-spaces-make-money-use-tabs/
Data from: https://drive.google.com/uc?export=download&id=0B0DL28AqnGsrV0VldnVIT1hyb0E
"""
import collections
import csv


def print_stats(ide_salaries):
    print "Rank".ljust(5), "IDE".ljust(20), "Median".rjust(10), "Avg".rjust(10), "Cnt".rjust(6)
    for rank, (ide, median, avg, cnt) in enumerate(ide_salaries, 1):
        print str(rank).ljust(5), str(ide).ljust(20), str(round(median)).rjust(10), str(round(avg)).rjust(10), str(cnt).rjust(6)


def main():
    with open("survey_results_public.csv") as f:
        d = collections.defaultdict(list)
        reader = csv.DictReader(f)
        for r in reader:
            ides = r["IDE"]
            salary = r["Salary"]

            # Only consider those who make money
            if r["Professional"] != "Professional developer":
                continue

            if not ides:
                continue
            if not salary:
                continue
            if salary == "NA":
                continue
            salary = float(salary)  # some salaries stored in scientific notation

            # Will over count here (e.g. same salaries applied to multiple IDEs)
            for ide in ides.split(";"):
                ide = ide.strip()
                d[ide].append(salary)

        print "Total # salaries: %s" % sum(len(s) for s in d.itervalues())
        print

        # Sort for median
        for salaries in d.itervalues():
            salaries.sort()
        ide_salaries = [(i, salaries[len(salaries) / 2], sum(salaries) / len(salaries), len(salaries)) for i, salaries in d.iteritems()]

        print "IDEs by median salary"
        print_stats(sorted(ide_salaries, key=lambda (i, m, a, c): m, reverse=True))
        print

        print "IDEs by average salary"
        print_stats(sorted(ide_salaries, key=lambda (i, m, a, c): a, reverse=True))


if __name__ == "__main__":
    main()