In [1]:
import pandas as pd
import numpy as np
import json
In [7]:
df=pd.read_csv('C:/Users/Peter/Documents/atlas/atlasdata/obs_types/analysisNEW.csv')
df['dupe'] = df['sampleID'].duplicated(keep=False) #boolean for duplicate in column
dupes = df[df['dupe']==True]
dupes.to_csv('C:/Users/Peter/Documents/atlas/atlasdata/obs_types/analysisDUPES.csv')