# read a dataset of movie reviewers into a DataFrame user_cols = ['user_id', 'age', 'gender', 'occupation', 'zip_code'] users = pd.read_table('http://bit.ly/movieusers', sep='|', header=None, names=user_cols, index_col='user_id') users.head()

users.shape

users.zip_code.duplicated().sum() # Numbers of duplicated zip code

users.duplicated().sum()

users.loc[users.duplicated(keep='first'),:] # keep only the first rows in the duplication

users.loc[users.duplicated(keep='last'),:] # keep only the last rows in the duplication

users.loc[users.duplicated(keep=False),:] #Shows all the duplicated rows

users.drop_duplicates(keep='first').shape # drop 7 rows but keep the first version of the duplicate

users.duplicated(subset=['age','zip_code']).sum()

users.loc[users.duplicated(subset=['age','zip_code'],keep=False),:].sort_values('zip_code')