rnsrk/goodByeHida
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

full import scripts

Browse source
This commit is contained in:
rnsrk 2025-02-21 22:26:38 +01:00
parent 4d74913447
commit 34c9b1c0a9
136 changed files with 289629 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

17
dataWrangler.py Normal file
View file

@ -0,0 +1,17 @@
import pandas as pd
from initDb import initDb
processedRows = pd.read_csv(f'processedRows.csv')
for indexRow, row in processedRows.iterrows():
for indexCol, value in row.items():
processedRows.loc[indexRow, indexCol] = value.replace('[', '').replace(']', '').replace('\'', '')
print('Initializing the database...')
engine, metadata = initDb(True, './schemas/')
objects = pd.read_sql_table('c__obj', con=engine)
processedRows = pd.merge(processedRows, objects[['f__5000_obj_dok_nr_', 'f__uuid']].rename(columns={'f__uuid': 'uuid'}), how='left', left_on='objectId', right_on='f__5000_obj_dok_nr_')
processedRows = processedRows.drop('f__5000_obj_dok_nr_', axis=1)
processedRows.to_csv(f'cleanedProcessedRows.csv', index=False)
print('finish')