import pandas as pd

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

# фильтруем слишком быстрые и медленные заезды и АЗС
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')
good_data = good_data.query('60 <= time_spent <= 1000')

# считаем данные по отдельным АЗС и по сетям
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')
stat = data.pivot_table(index='name', values='time_spent')
good_stat = good_data.pivot_table(index='name', values='time_spent', aggfunc='median')
stat['good_time_spent'] = good_stat['time_spent']

id_name = good_data.pivot_table(index='id', values='name', aggfunc=['first', 'count'])
id_name.columns = ['name', 'count']
station_stat_full = id_name.join(good_stations_stat)

# считаем показатели сетей из показателей АЗС,
# а не усреднённые заезды на все АЗС сети
good_stat2 = (
    station_stat_full
    .query('count > 30')
    .pivot_table(index='name', values='time_spent', aggfunc=['median', 'count'])
)
good_stat2.columns = ['median_time', 'stations']
final_stat = stat.join(good_stat2)

big_nets_stat = final_stat.query('stations > 10')
#print(big_nets_stat.head())
#print(station_stat_full.head())
station_stat_full['group_name'] = station_stat_full.where(station_stat_full['name'].isin(big_nets_stat.index))
print(station_stat_full.head())