Computing Statistics of NBA salaries.

nba.py

# nba
# Analyzes the NBA Salary to PER data set
#
# Author:   Benjamin Bengfort <[email protected]>
# Created:  Sat Sep 20 09:35:11 2014 -0400
#
# Copyright (C) 2014 Bengfort.com
# For license information, see LICENSE.txt
#
# ID: nba.py [] [email protected] $

"""
Analyzes the NBA Salary to PER data set
"""

##########################################################################
## Imports
##########################################################################

import os
import pandas as pd
import numpy as np

import matplotlib.pyplot as plt

PATH = os.path.abspath('fixtures/nba_players.csv')

def read_data(path=PATH):
    return pd.DataFrame(pd.read_csv(PATH))

def graph_data(path=PATH, xkey='PER', ykey='SALARY'):
    data = read_data(path)
    xval = data['PER']
    yval = data['SALARY']

    fig,axe = plt.subplots()
    plt.scatter(xval, yval, alpha=0.7)
    plt.ylim([-10000, data['SALARY'].max()+500000])

    plt.ylabel('salary')
    plt.xlabel('player efficiency rating')
    plt.title('NBA 2013 Player Efficieny Rating and Salary Correlation')

    plt.grid(True)
    plt.show()

if __name__ == '__main__':
    graph_data()

per.py

# per
# Analyzes the NBA Salary to PER data set
#
# Author:   Benjamin Bengfort <[email protected]>
# Created:  Sat Sep 20 09:35:11 2014 -0400
#
# Copyright (C) 2014 Bengfort.com
# For license information, see LICENSE.txt
#
# ID: per.py [] [email protected] $

"""
Computes summary statistics for the nba_players.csv file
"""

##########################################################################
## Imports
##########################################################################

import csv

from collections import Counter
from operator import itemgetter

##########################################################################
## Analysis functions
##########################################################################

def load_data(path):
    """
    Loads the data from a file into a list.
    """
    with open(path, 'r') as data:
        reader = csv.DictReader(data)
        for row in reader:
            row['SALARY'] = int(row['SALARY'])
            row['PER'] = float(row['PER'])
            yield row

def statistics(path):
    data  = list(load_data(path))
    data  = sorted(data, key=itemgetter('SALARY'))

    count = 0
    total = 0.0
    freqs = Counter()

    for row in data:
        count += 1
        total += row['SALARY']
        freqs[row['SALARY']] += 1

    stats = {
        'maximum': data[-1]['SALARY'],
        'minimum': data[0]['SALARY'],
        'median': data[count / 2]['SALARY'],
        'mode': freqs.most_common(2),
        'mean': total / count,
    }

    return stats

if __name__ == '__main__':
    import json
    print json.dumps(statistics('fixtures/nba_players.csv'), indent=4)