import pandas as pd

data = pd.read_csv('/datasets/visits_eng.csv', sep='\t')
data['local_time'] = (
    pd.to_datetime(data['date_time'], format='%Y-%m-%dT%H:%M:%S')
    - pd.Timedelta(hours=7)
)
data['too_fast']=data['time_spent']<60
#print(data['too_fast'].mean())
too_fast_stat=data.pivot_table(index='id', values='too_fast')
#print(too_fast_stat.head(5))
too_fast_stat.hist(bins=30)
data['too_slow']=data['time_spent']>1000
data.pivot_table(index='id', values='too_slow').hist(bins=30)