5 examples of 'df.drop_duplicates' in Python

49
def remove_duplicates(df_or_series):
50
    """ Remove duplicate rows or values by keeping the first of each duplicate.
51
52
    Parameters
53
    ----------
54
    df_or_series : :any:`pandas.DataFrame` or :any:`pandas.Series`
55
        Pandas object from which to drop duplicate index values.
56
57
    Returns
58
    -------
59
    deduplicated : :any:`pandas.DataFrame` or :any:`pandas.Series`
60
        The deduplicated pandas object.
61
    """
62
    # CalTrack 2.3.2.2
63
    return df_or_series[~df_or_series.index.duplicated(keep="first")]

673
def _unique(df, columns=None):
674
    if isinstance(columns, str):
675
        columns = [columns]
676
    if not columns:
677
        columns = df.columns.tolist()
678
    info = {}
679
    for col in columns:
680
        values = df[col].dropna().values
681
        uniques = np.unique(list(_flatten_list(values))).tolist()
682
        info[col] = {'count': len(uniques), 'values': uniques}
683
    return info

14
def drop_duplicate_events(df):
15
    """
16
    Function to group dataframe, use all new information from the latest row
17
    but keep the ``event_index`` from the first one
18
    """
19
    df = df.sort_values('event_index', na_position='last')
20
    event_index = df.event_index.iloc[0]
21
    r = df.iloc[-1].to_dict()
22
    r['event_index'] = event_index
23
    return r

39
def _drop_col(self, df):
40
    '''
41
    Drops last column, which was added in the parsing procedure due to a
42
    trailing white space for each sample in the text file
43
    Arguments:
44
        df: pandas dataframe
45
    Return:
46
        df: original df with last column dropped
47
    '''
48
    return df.drop(df.columns[-1], axis=1)

259
def drop_some(df_: pd.DataFrame, thresh: int) -> pd.DataFrame:
260
    # thresh is the minimum number of NA, the 1 indicates that columns should be dropped not rows
261
    return df_.dropna(1, thresh=thresh)