import pandas as pd
#import numpy as np

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)
)
#print(data.head)

#data["too_fast"] = data["time_spent"].apply(lambda x: True if x <60 else False)
data["too_fast"] = data["time_spent"]<60


#print(data["too_fast"].mean())
too_fast_stat = pd.pivot_table(data, values='too_fast', index=['id'])
#print(too_fast_stat.head())
too_fast_stat.hist(bins = 30)

data["too_slow"] =data["time_spent"]>1000
data.pivot_table(values='too_slow', index=['id']).hist(bins = 30 )