step3.py updated

This commit is contained in:
Patrick
2024-03-03 22:01:21 +01:00
parent a5348abe89
commit b0067ae057
3 changed files with 31 additions and 15 deletions

View File

@@ -2,10 +2,12 @@ import pandas as pd
from Levenshtein import distance
def compare_data(new, sys, bool_class):
def compare_data(new, sys):
print(f"\nEinträge in Import Liste: {len(new)}")
print(f"Einträge in System Liste: {len(sys)}")
bool_class = 'klasse' in new.columns
if bool_class:
if 'index' in new.columns:
new = new.drop('index', axis=1)
@@ -35,9 +37,10 @@ def search_typos(new, sys):
for idx1, row1 in new.iterrows():
for idx2, row2 in sys.iterrows():
if distance(row1[col1], row2[col1]) <= 2 and distance(row1[col2], row2[col2]) <= 2:
typos.append((row1[col1], row1[col2], row2[col1], row2[col2]))
if len(typos) > 0:
print('Mögliche Tippfehler:', len(typos), '\n', typos)
typos.append(([row1[col1], row1[col2]], [row2[col1], row2[col2]]))
typo_df = pd.DataFrame(typos, columns=['Import', 'System'])
if len(typo_df) > 0:
print('Mögliche Tippfehler:', len(typo_df), '\n', typo_df)
else:
print('Mögliche Tippfehler: keine Fehler gefunden!')