Beispiel #1
0
 def apply_func(obj_index: tp.Index) -> tp.Index:
     return index_fns.drop_duplicate_levels(obj_index, keep=keep)
Beispiel #2
0
def broadcast_index(args,
                    to_shape,
                    index_from=None,
                    axis=0,
                    ignore_single='default',
                    drop_duplicates='default',
                    keep='default'):
    """Produce a broadcasted index/columns.

    Args:
        *args (array_like): Array-like objects.
        to_shape (tuple): Target shape.
        index_from (None, int, str or array_like): Broadcasting rule for this index/these columns.

            Accepts the following values:

            * `'default'` - take the value from `vectorbt.defaults.broadcasting`
            * `None` - use the original index/columns of the objects in `args`
            * `int` - use the index/columns of the i-nth object in `args`
            * `'strict'` - ensure that all pandas objects have the same index/columns
            * `'stack'` - stack different indexes/columns using `vectorbt.base.index_fns.stack_indexes`
            * everything else will be converted to `pd.Index`

        axis (int): Set to 0 for index and 1 for columns.
        ignore_single (bool): If `True`, won't consider index/columns with a single value.
        drop_duplicates (bool): See `vectorbt.base.index_fns.drop_duplicate_levels`.
        keep (bool): See `vectorbt.base.index_fns.drop_duplicate_levels`.

    For defaults, see `vectorbt.defaults.broadcasting`.
    """

    if ignore_single == 'default':
        ignore_single = defaults.broadcasting['ignore_single']
    if drop_duplicates == 'default':
        drop_duplicates = defaults.broadcasting['drop_duplicates']
    if keep == 'default':
        keep = defaults.broadcasting['keep']
    index_str = 'columns' if axis == 1 else 'index'
    new_index = None
    if axis == 1 and len(to_shape) == 1:
        to_shape = (to_shape[0], 1)
    maxlen = to_shape[1] if axis == 1 else to_shape[0]

    if index_from is not None:
        if isinstance(index_from, int):
            # Take index/columns of the object indexed by index_from
            if not checks.is_pandas(args[index_from]):
                raise TypeError(
                    f"Argument under index {index_from} must be a pandas object"
                )
            new_index = index_fns.get_index(args[index_from], axis)
        elif isinstance(index_from, str):
            if index_from in ('stack', 'strict'):
                # If pandas objects have different index/columns, stack them together
                # maxlen stores the length of the longest index
                for arg in args:
                    if checks.is_pandas(arg):
                        index = index_fns.get_index(arg, axis)
                        if pd.Index.equals(
                                index,
                                pd.RangeIndex(start=0, stop=len(index),
                                              step=1)):
                            # ignore simple ranges without name
                            continue
                        if new_index is None:
                            new_index = index
                        else:
                            if index_from == 'strict':
                                # If pandas objects have different index/columns, raise an exception
                                if not pd.Index.equals(index, new_index):
                                    raise ValueError(
                                        f"Broadcasting {index_str} is not allowed for {index_str}_from=strict"
                                    )
                            # Broadcasting index must follow the rules of a regular broadcasting operation
                            # https://docs.scipy.org/doc/numpy/user/basics.broadcasting.html#general-broadcasting-rules
                            # 1. rule: if indexes are of the same length, they are simply stacked
                            # 2. rule: if index has one element, it gets repeated and then stacked

                            if pd.Index.equals(index, new_index):
                                continue
                            if len(index) != len(new_index):
                                if len(index) > 1 and len(new_index) > 1:
                                    raise ValueError(
                                        "Indexes could not be broadcast together"
                                    )
                                if ignore_single:
                                    # Columns of length 1 should be ignored
                                    if len(index) > len(new_index):
                                        new_index = index
                                    continue
                                else:
                                    if len(index) > len(new_index):
                                        new_index = index_fns.repeat_index(
                                            new_index, len(index))
                                    elif len(index) < len(new_index):
                                        index = index_fns.repeat_index(
                                            index, len(new_index))
                            new_index = index_fns.stack_indexes(
                                new_index, index)
            else:
                raise ValueError(
                    f"Invalid value {index_from} for {'columns' if axis == 1 else 'index'}_from"
                )
        else:
            new_index = index_from
        if new_index is not None:
            if maxlen > len(new_index):
                if index_from == 'strict':
                    raise ValueError(
                        f"Broadcasting {index_str} is not allowed for {index_str}_from=strict"
                    )
                # This happens only when some numpy object is longer than the new pandas index
                # In this case, new pandas index (one element) should be repeated to match this length.
                if maxlen > 1 and len(new_index) > 1:
                    raise ValueError("Indexes could not be broadcast together")
                new_index = index_fns.repeat_index(new_index, maxlen)
            if drop_duplicates:
                new_index = index_fns.drop_duplicate_levels(new_index,
                                                            keep=keep)
    return new_index