!ls data

!head -n 3 data/F1\ Practice.txt

from lxml import etree

pl=[]

practice_f='data/F1 Practice.txt'

for xml in open(practice_f, 'r'):
    pl.append(etree.fromstring(xml))

pl[100].attrib

pl[100][0].attrib

import pandas as pd

#Hacky load and parse of each row in the datafile
pl=[]
for xml in open('data/F1 Practice.txt', 'r'):
    pl.append(etree.fromstring(xml))

#Dataframe for current state timing screen
df_practice_pos=pd.DataFrame(columns=[
    "timestamp", "time",
    "classpos",  "classpos_colour",
    "racingNumber","racingNumber_colour",
    "name","name_colour",
],index=range(50))

#Column mappings
practiceMap={
    '1':'classpos',
    '2':'racingNumber',
    '3':'name',
    '4':'laptime',
    '5':'gap',
    '6':'sector1',
    '7':'sector2',
    '8':'sector3',
    '9':'laps',
    '21':'sector1_best',
    '22':'sector2_best',
    '23':'sector3_best'
}

def parse_practice(p,df_practice_pos):
    if p.attrib['identifier']=='101' and 'sessionstate' not in p[0].attrib:
        if p[0].attrib['column'] not in ['10','21','22','23']:
            colname=practiceMap[p[0].attrib['column']]
            row=int(p[0].attrib['row'])-1
            df_practice_pos.ix[row]['timestamp']=p.attrib['timestamp']
            tt=p.attrib['timestamp'].replace('.',':').split(':')
            df_practice_pos.ix[row]['time'] = datetime.time(int(tt[0]),int(tt[1]),int(tt[2]),int(tt[3])*1000)
            df_practice_pos.ix[row][colname]=p[0].attrib['value']
            df_practice_pos.ix[row][colname+'_colour']=p[0].attrib['colour']
    return df_practice_pos

for p in pl[:2850]:
    df_practice_pos=parse_practice(p,df_practice_pos)
df_practice_pos