7-3 データの重複を検出する
7-3-1 マスターデータの重複を検出する
import pandas as pd
import numpy as np
import psycopg2
conn = psycopg2.connect("dbname=BigData host=localhost user=testuser")
mst_categories = pd.read_sql("SELECT * FROM mst_categories", conn)
print(mst_categories)
mst_categories.duplicated('id')
print(mst_categories[mst_categories.duplicated('id')])