Function clear_known_categories

dask/dataframe/utils.py:220–258

Set categories to be unknown. Parameters ---------- x : DataFrame, Series, Index cols : iterable, optional If x is a DataFrame, set only categoricals in these columns to unknown. By default, all categorical columns are set to unknown categoricals index : bool, op

(x, cols=None, index=True, dtype_backend=None)

def clear_known_categories(x, cols=None, index=True, dtype_backend=None):
    """Set categories to be unknown.

    Parameters
    ----------
    x : DataFrame, Series, Index
    cols : iterable, optional
        If x is a DataFrame, set only categoricals in these columns to unknown.
        By default, all categorical columns are set to unknown categoricals
    index : bool, optional
        If True and x is a Series or DataFrame, set the clear known categories
        in the index as well.
    dtype_backend : string, optional
        If set to PyArrow, the categorical dtype is implemented as a PyArrow
        dictionary
    """
    if dtype_backend == "pyarrow":
        # Right now Categorical with PyArrow is implemented as dictionary and
        # categorical accessor is not yet available
        return x

    if not is_index_like(x):
        x = x.copy()
        if is_dataframe_like(x):
            mask = x.dtypes == "category"
            if cols is None:
                cols = mask[mask].index
            elif not mask.loc[cols].all():
                raise ValueError("Not all columns are categoricals")
            for c in cols:
                x[c] = x[c].cat.set_categories([UNKNOWN_CATEGORIES])
        elif is_series_like(x):
            if is_categorical_dtype_dispatch(x.dtype):
                x = x.cat.set_categories([UNKNOWN_CATEGORIES])
        if index and is_categorical_dtype_dispatch(x.index.dtype):
            x.index = x.index.set_categories([UNKNOWN_CATEGORIES])
    elif is_categorical_dtype_dispatch(x.dtype):
        x = x.set_categories([UNKNOWN_CATEGORIES])
    return x


def _empty_series(name, dtype, index=None):