import pandas as pd

data = pd.read_csv('/datasets/visits_eng.csv', sep='\t')

# filter abnormally fast and slow visits and gas stations
data['too_fast'] = data['time_spent'] < 60
data['too_slow'] = data['time_spent'] > 1000
too_fast_stat = data.pivot_table(index='id', values='too_fast')
good_ids = too_fast_stat.query('too_fast < 0.5')
good_data = data.query('id in @good_ids.index and 60 <= time_spent <= 1000')

# consider data by individual gas station and by chains
station_stat = data.pivot_table(index='id', values='time_spent', aggfunc='median')
good_stations_stat = good_data.pivot_table(index='id', values='time_spent', aggfunc='median')
good_stations_stat.hist(bins=50)