Created
January 14, 2015 01:48
-
-
Save kellbot/1bab3ae83d7b80ee382a to your computer and use it in GitHub Desktop.
runner stats
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
import matplotlib.pyplot as plt | |
from datetime import datetime, timedelta | |
import glob | |
import os | |
#time data is provided as a string in the format of HH:MM:SS but hours are omitted in shorter races | |
def str_to_time_delta(x): | |
if x != x: | |
return | |
if len(x) == 5: | |
x = "00:" + x | |
t = datetime.strptime(x,"%H:%M:%S") | |
delta = timedelta(hours=t.hour, minutes=t.minute, seconds=t.second) | |
return delta | |
pd.set_option('display.mpl_style', 'default') # Make the graphs a bit prettier | |
def load_runners(race, csvpath, headers=["Group Place","Name","Bib","Age","Place","Gender Place","5K Split","Clock Time","Net Time","Hometown"]): | |
runners = pd.DataFrame() | |
distance = 6.2 | |
os.chdir(csvpath) | |
if race == 'half': | |
distance = 13.1 | |
elif race == 'full': | |
distance = 26.2 | |
for filename in glob.glob("*.csv"): | |
print('Parsing' + filename) | |
thisgroup = pd.read_csv(filename, skiprows=[0,1], names=headers, index_col="Place") | |
runners = runners.append(thisgroup) | |
runners.sort_index(inplace=True) | |
#There's probably a way to do this all at once but I don't know it | |
runners["Clock Time"] = runners["Clock Time"].map(str_to_time_delta) | |
#runners["5K Split"] = runners["5K Split"].map(str_to_time_delta) | |
runners["Net Time"] = runners["Net Time"].map(str_to_time_delta) | |
runners["Start Time"] = runners["Clock Time"].subtract(runners["Net Time"]) | |
#because pandas can't plot timedeltas we have to convert the time to something it can deal with | |
runners["Net Num"] = runners["Net Time"].map(lambda x: x/np.timedelta64(1, 's')) | |
runners["Clock Num"] = runners["Clock Time"].map(lambda x: x/np.timedelta64(1, 's')) | |
runners["Start Num"] = runners["Start Time"].map(lambda x: x/np.timedelta64(1, 's')) | |
return runners | |
full = load_runners('full',"./Full/",["Group Place","Name","Bib","Age","Place","Gender Place","5M Split","10M Split","Half Split","20M Split","Clock Time","Net Time","Hometown"]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment