Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import pandas as pd
- data = pd.read_csv("/datasets/visits.csv", sep="\t")
- data['local_time'] = (
- pd.to_datetime(data['date_time'], format='%Y-%m-%dT%H:%M:%S')
- + pd.Timedelta(hours=3)
- )
- data['date_hour'] = data['local_time'].dt.round('1H')
- 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')
- 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")
- 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']
- 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)
- 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)
- final_stat.sort_values(by='median_time', ascending=True).dropna(subset=['median_time']).plot(y='median_time', kind='bar', grid=True, figsize=(10,5))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement