import pandas as pd # Sample DataFrame data = { "some_id": ["xxx"] * 6, "some_email": ["abc.xyz@somedomain.com"] * 6, "This is Sample": [ {"a": "22", "b": "Y", "c": "33", "d": "x"}, {"a": "44", "b": "N", "c": "55", "d": "Y"}, {"a": "22", "b": "Y", "c": "33", "d": "x"}, {"a": "44", "b": "N", "c": "55", "d": "Y"}, {"a": "22", "b": "Y", "c": "33", "d": "x"}, {"a": "44", "b": "N", "c": "55", "d": "Y"}, ] } df = pd.DataFrame(data) # Convert dicts to strings df["dict_str"] = df["This is Sample"].apply(lambda x: str(sorted(x.items()))) # Drop duplicates based on the string version df_unique = df.drop_duplicates(subset="dict_str").drop(columns="dict_str") # Result print(df_unique)
Loading...