63 lines
2.6 KiB
Python
63 lines
2.6 KiB
Python
#Bits and bobs used for many different projects. Junk drawer module
|
|
import pandas as pd
|
|
import numpy as np
|
|
|
|
|
|
#Useful functions for parsing race-like durations, and normalizing their string reps
|
|
def t2f(S):
|
|
if not(S or False):
|
|
return None
|
|
m,s = ('0:%s' % S).split(':')[-2:]
|
|
try:
|
|
return np.round(60*int(m) + float(s),2)
|
|
except:
|
|
return -1
|
|
|
|
def f2t(S):
|
|
if not(S or False) or (int(''.join([c for c in '0'+str(S) if c.isdigit()])) == 0) or (S <= 0):
|
|
return ''
|
|
S = float(S)
|
|
m = int(S/60)
|
|
s = S-60*m
|
|
hs = s-int(s)
|
|
s = int(s)
|
|
return f'{m:02}:{s:02}.{round(hs*100):02}'
|
|
|
|
#Canada Summer Games eligible events
|
|
CSG = pd.DataFrame([
|
|
{'Stroke':'Butterfly','Distance':50,'SportClass':[1,2,3,4,5,6,7]},
|
|
{'Stroke':'Butterfly','Distance':100,'SportClass':[8,9,10,11,12,13,14]},
|
|
{'Stroke':'Backstroke','Distance':50,'SportClass':[1,2,3,4,5]},
|
|
{'Stroke':'Backstroke','Distance':100,'SportClass':[1,2,6,7,8,9,10,11,12,13,14]},
|
|
{'Stroke':'Breaststroke','Distance':50,'SportClass':[1,2,3]},
|
|
{'Stroke':'Breaststroke','Distance':100,'SportClass':[4,5,6,7,8,9,11,12,13,14]},
|
|
{'Stroke':'Medley','Distance':150,'SportClass':[1,2,3,4]},
|
|
{'Stroke':'Medley','Distance':200,'SportClass':[5,6,7,8,9,10,11,12,13,14]},
|
|
{'Stroke':'Freestyle','Distance':50,'SportClass':[1,2,3,4,5,6,7,8,9,10,11,12,13,14]},
|
|
{'Stroke':'Freestyle','Distance':100,'SportClass':[1,2,3,4,5,6,7,8,9,10,11,12,13,14]},
|
|
{'Stroke':'Freestyle','Distance':200,'SportClass':[1,2,3,4,5,14]},
|
|
{'Stroke':'Freestyle','Distance':400,'SportClass':[6,7,8,9,10,11,12,13]},
|
|
]).explode('SportClass').reset_index(drop=True)
|
|
|
|
def parse_WPS_rankings(DF):
|
|
'''Takes a pandas dataframe, usually loaded from an excel file, and cleans it up for use'''
|
|
return (
|
|
DF
|
|
#Makes .dot notation easier
|
|
.pipe(lambda df: df.rename(columns={c:c.replace(' ','_') for c in df.columns}))
|
|
|
|
#Drop VACANT events and relay results
|
|
.pipe(lambda df: df[df.SDMS_ID.notnull()])
|
|
|
|
#Parse out event information into useful columns
|
|
.pipe(lambda df: pd.concat([df,df.Event.str.extract(r"'s (?P<Distance>\d+) m (Individual )*(?P<Stroke>[A-z]+) [SBM]+(?P<SportClass>\d+)")],axis=1))
|
|
|
|
#Cleanup column dtypes
|
|
.assign(Date=lambda df: pd.to_datetime(df.Date))
|
|
.assign(Year=lambda df: df.Date.dt.year)
|
|
.assign(Seconds=lambda df: df.Result.apply(t2f))
|
|
.astype({'SportClass':int,'Distance':int,'SDMS_ID':int})
|
|
|
|
#Drop excess columns
|
|
.pipe(lambda df: df['Gender SportClass Distance Stroke Result Seconds SDMS_ID NPC Given_Name Family_Name Date'.split()])
|
|
)
|