-
-
Save legale/34c6abbf02a58be6fd165318d6ae3b61 to your computer and use it in GitHub Desktop.
Yandex.Praktikum 🍂
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) | |
station_stat_multi = pd.pivot_table(data, index='id', values=['time_spent', 'too_fast', 'too_slow']) | |
print(station_stat_multi.corr()) | |
pd.plotting.scatter_matrix(station_stat_multi, figsize=(9, 9)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Результат | |
time_spent too_fast too_slow | |
time_spent 1.000000 -0.640658 0.802247 | |
too_fast -0.640658 1.000000 -0.255876 | |
too_slow 0.802247 -0.255876 1.000000 | |
Если долго стоять, то можно простоять слишком долго. А если быстро сбежать, то не больно-то и задержишься. | |
Как ни смешно, это окончательное подтверждение того, что вы отрезали ненужное там, где надо. | |
Если бы не получались результаты «капитана очевидность», пришлось бы вернуться и пришивать отрезанное на место. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
data = pd.read_csv("/datasets/visits.csv", sep="\t") | |
data['local_time'] = ( | |
pd.to_datetime(data['date_time'], yearfirst=True) | |
+ 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'] | |
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) | |
big_nets_stat = final_stat.query('stations > 10') | |
station_stat_full['group_name'] = ( | |
station_stat_full['name'] | |
.where(station_stat_full['name'].isin(big_nets_stat.index), 'Другие') | |
) | |
stat_grouped = ( | |
station_stat_full | |
.query('count > 30') | |
.pivot_table(index='group_name', values='time_spent', aggfunc=['median', 'count']) | |
) | |
stat_grouped.columns = ['time_spent', 'count'] | |
good_data['group_name'] = ( | |
good_data['name'] | |
.where(good_data['name'].isin(big_nets_stat.index), 'Другие') | |
) | |
for group_name, group_data in good_data.groupby('group_name'): | |
group_data.plot(kind='hist', y='time_spent', bins=50, title=group_name) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment