diff --git a/pandas/core/frame.py b/pandas/core/frame.py index 71b755bbf9665..1f73efed82cb9 100644 --- a/pandas/core/frame.py +++ b/pandas/core/frame.py @@ -4673,6 +4673,47 @@ def drop_duplicates( See Also -------- DataFrame.value_counts: Count unique combinations of columns. + + Examples + -------- + Consider dataset containing ramen rating. + + >>> df = pd.DataFrame({ + ... 'brand': ['Yum Yum', 'Yum Yum', 'Indomie', 'Indomie', 'Indomie'], + ... 'style': ['cup', 'cup', 'cup', 'pack', 'pack'], + ... 'rating': [4, 4, 3.5, 15, 5] + ... }) + >>> df + brand style rating + 0 Yum Yum cup 4.0 + 1 Yum Yum cup 4.0 + 2 Indomie cup 3.5 + 3 Indomie pack 15.0 + 4 Indomie pack 5.0 + + By default, it removes duplicate rows based on all columns. + + >>> df.drop_duplicates() + brand style rating + 0 Yum Yum cup 4.0 + 2 Indomie cup 3.5 + 3 Indomie pack 15.0 + 4 Indomie pack 5.0 + + To remove duplicates on specific column(s), use ``subset``. + + >>> df.drop_duplicates(subset=['brand']) + brand style rating + 0 Yum Yum cup 4.0 + 2 Indomie cup 3.5 + + To remove duplicates and keep last occurences, use ``keep``. + + >>> df.drop_duplicates(subset=['brand', 'style'], keep='last') + brand style rating + 1 Yum Yum cup 4.0 + 2 Indomie cup 3.5 + 4 Indomie pack 5.0 """ if self.empty: return self.copy()