Shows the distribution of batting averages for MLB players by the handedness they bat with. (Right, Left, Both)

compare_batting_avg.py

import pandas
from ggplot import *

# Shows the distribution of batting averages for MLB players by the handedness they bat with. (Right, Left, Both)

def compare_averages(filename):
    """
    Data from: https://www.dropbox.com/s/xcn0u2uxm8c4n6l/baseball_data.csv
    
    Example output: http://imgur.com/21Rs287
    """

    data = pandas.read_csv(filename)
    plotdata = data[data['avg'] != 0] # filters out players with no batting average
    
    p = ggplot(aes(x='avg', color='handedness'), data=plotdata) \
      + geom_density() \
      + labs(x="Batting Average", y="Density")

    print p
    
if __name__ == "__main__":
    compare_averages('baseball_data.csv')