import pandas as pd

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

# filter excessively 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')
good_data = good_data.query('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_station_stat = good_data.pivot_table(index='id', values='time_spent', aggfunc='median')
name_stat = data.pivot_table(index='name', values='time_spent')
good_name_stat = good_data.pivot_table(index='name', values='time_spent', aggfunc='median')
name_stat['good_time_spent'] = good_name_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_station_stat)
station_stat_multi = data.pivot_table(index='id', values=['time_spent', 'too_fast', 'too_slow'])
print(station_stat_multi.corr())
pd.plotting.scatter_matrix(station_stat_multi, figsize=(9, 9))