Function groupby_reduce_majority

python/pathway/stdlib/utils/col.py:309–350

Finds a majority in column_val for every group in column_group. Workaround for missing majority reducer. Example: >>> import pathway as pw >>> table = pw.debug.table_from_markdown( ... ''' ... | group | vote ... 0 | 1 | pizza ... 1 | 1 | pizza ... 2 |

(
    column_group: pw.ColumnReference, column_val: pw.ColumnReference
)

@check_arg_types
@trace_user_frame
def groupby_reduce_majority(
    column_group: pw.ColumnReference, column_val: pw.ColumnReference
):
    """Finds a majority in column_val for every group in column_group.

    Workaround for missing majority reducer.

    Example:

    >>> import pathway as pw
    >>> table = pw.debug.table_from_markdown(
    ... '''
    ...   | group | vote
    ... 0 | 1     | pizza
    ... 1 | 1     | pizza
    ... 2 | 1     | hotdog
    ... 3 | 2     | hotdog
    ... 4 | 2     | pasta
    ... 5 | 2     | pasta
    ... 6 | 2     | pasta
    ... ''')
    >>> result = pw.utils.col.groupby_reduce_majority(table.group, table.vote)
    >>> pw.debug.compute_and_print(result, include_id=False)
    group | majority
    1     | pizza
    2     | pasta
    """
    table = column_group.table
    column_val = table[column_val]  # in case its pw.this reference
    column_val_name = column_val.name
    column_group_name = column_group.name
    counts = table.groupby(column_group, column_val).reduce(
        column_group, column_val, _pw_special_count=pw.reducers.count()
    )
    res = counts.groupby(counts[column_group_name]).reduce(
        counts[column_group_name],
        majority=counts.ix(
            pw.reducers.argmax(counts._pw_special_count), context=pw.this
        )[column_val_name],
    )

    return res