Fun with NFL scores.

gistfile1.txt

import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import vincent

# source: http://www.pro-football-reference.com/boxscores/game_scores.cgi
SOURCE_FILE = "./nflscores.csv"

data = pd.read_csv(SOURCE_FILE, header=0)

header_rows = data.apply(lambda row : row['Rk'] == 'Rk', axis=1) 
data = data[~header_rows]

data[['PtDif', 'Count']] = data[['PtDif', 'Count']].astype('int')

score_differentials = data.groupby('PtDif').sum()['Count']

populate_histogram = lambda diff: score_differentials[diff] if diff in score_differentials else 0
histogram = [populate_histogram(i) for i in range(74)]

line = vincent.Bar(histogram)
line.axis_titles(x='Point differential', y='Games')
line.height = 300
line.width = 900
ax = vincent.AxisProperties(labels = vincent.PropertySet(angle=vincent.ValueRef(value=90)))
line.axes[0].properties = ax

line.to_json('test.json')

data[['PtsW', 'PtsL']] = data[['PtsW', 'PtsL']].astype('int')
pivoted_data = data.pivot(index='PtsW', columns='PtsL', values='Count')
# This is devestatingly ugly code.
populate_heatmap = lambda x, y: pivoted_data[x][y] if x in pivoted_data and y in pivoted_data[x] else 0
heatmap_data = pd.DataFrame([[populate_heatmap(x, y) for y in range(73)] for x in range(73)])

fig, ax = plt.subplots()
plt.pcolor(heatmap_data, cmap=plt.cm.Blues, alpha=0.8, vmin=0, vmax=50)
ax.set_xlim([0, 73])
ax.set_xlabel("Winning team's points")
ax.set_ylim([0, 73])
ax.set_ylabel("Losing team's points")
ax = plt.gca()
ax = plt.gca()

for t in ax.xaxis.get_major_ticks():
    t.tick1On = False
    t.tick2On = False
for t in ax.yaxis.get_major_ticks():
    t.tick1On = False
    t.tick2On = False
plt.show()