“Teilen Sie die Pandas in mehrere Reihen auf” Code-Antworten

Teilen Sie die Pandas in mehrere Reihen auf

def split_dataframe_rows(df,column_selectors):
    # we need to keep track of the ordering of the columns
    def _split_list_to_rows(row,row_accumulator,column_selector):
        split_rows = {}
        max_split = 0
        for column_selector in column_selectors:
            split_row = row[column_selector]
            split_rows[column_selector] = split_row
            if len(split_row) > max_split:
                max_split = len(split_row)
            
        for i in range(max_split):
            new_row = row.to_dict()
            for column_selector in column_selectors:
                try:
                    new_row[column_selector] = split_rows[column_selector].pop(0)
                except IndexError:
                    new_row[column_selector] = ''
            row_accumulator.append(new_row)

    new_rows = []
    df.apply(_split_list_to_rows,axis=1,args = (new_rows,column_selectors))
    new_df = pd.DataFrame(new_rows, columns=df.columns)
    return new_df
Saiful Islam

Erweitern Sie Pandas DataFrame in separate Zeilen

def explode(df, lst_cols, fill_value='', preserve_index=False):
    # make sure `lst_cols` is list-alike
    if (lst_cols is not None
        and len(lst_cols) > 0
        and not isinstance(lst_cols, (list, tuple, np.ndarray, pd.Series))):
        lst_cols = [lst_cols]
    # all columns except `lst_cols`
    idx_cols = df.columns.difference(lst_cols)
    # calculate lengths of lists
    lens = df[lst_cols[0]].str.len()
    # preserve original index values    
    idx = np.repeat(df.index.values, lens)
    # create "exploded" DF
    res = (pd.DataFrame({
                col:np.repeat(df[col].values, lens)
                for col in idx_cols},
                index=idx)
             .assign(**{col:np.concatenate(df.loc[lens>0, col].values)
                            for col in lst_cols}))
    # append those rows that have empty lists
    if (lens == 0).any():
        # at least one list in cells is empty
        res = (res.append(df.loc[lens==0, idx_cols], sort=False)
                  .fillna(fill_value))
    # revert the original index order
    res = res.sort_index()
    # reset index if requested
    if not preserve_index:        
        res = res.reset_index(drop=True)
    return res
Busy Boar

Ähnliche Antworten wie “Teilen Sie die Pandas in mehrere Reihen auf”

Fragen ähnlich wie “Teilen Sie die Pandas in mehrere Reihen auf”

Weitere verwandte Antworten zu “Teilen Sie die Pandas in mehrere Reihen auf” auf Python

Durchsuchen Sie beliebte Code-Antworten nach Sprache

Durchsuchen Sie andere Codesprachen