is.ulstu.ru/social-clusters
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Return ndarray instead DataFrame in df_loader.py

Browse Source
This commit is contained in:
Aleksey Filippov 2023-06-06 17:59:37 +04:00
parent ae87945f46
commit f4a32bf57f
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/main/df_loader.py
View File

@ -2,6 +2,7 @@ from datetime import date
import numpy as np import numpy as np
import pandas as pd import pandas as pd
from numpy import ndarray
from pandas import DataFrame from pandas import DataFrame
from src.main.constants import Constants as const from src.main.constants import Constants as const
@ -73,8 +74,8 @@ class DfLoader:
self.__df['location-lo'] = self.__df.loc[:, 'location'] \ self.__df['location-lo'] = self.__df.loc[:, 'location'] \
.apply(lambda val: 0 if Utils.is_empty_collection(val) else val[1]) .apply(lambda val: 0 if Utils.is_empty_collection(val) else val[1])
def get_clustering_data(self) -> DataFrame: def get_data(self) -> ndarray:
columns: [] = ['location-la', 'location-lo', columns: [] = ['location-la', 'location-lo',
'sex', 'age', 'is_university', 'is_work', 'is_student', 'is_schoolboy'] 'sex', 'age', 'is_university', 'is_work', 'is_student', 'is_schoolboy']
df = self.__df df = self.__df
return df[columns] return df[columns].to_numpy()