extract

extract(__data, col, into, regex='(\\w+)', remove=True, convert=False, flags=0)

Pull out len(into) fields from character strings.

Returns a DataFrame with a column added for each piece.

Parameters:

Name	Type	Description	Default
__data		a DataFrame	required
col		name of column to split (either string, or siu expression).	required
into		names of resulting columns holding each entry in pulled out fields.	required
regex		regular expression used to extract field. Passed to col.str.extract method.	'(\\w+)'
remove		whether to remove col from the returned DataFrame.	True
convert		whether to attempt to convert the split columns to numerics.	False
flags		flags from the re module, passed to col.str.extract.	0

Source code in siuba/dply/verbs.py

@singledispatch2(pd.DataFrame)
def extract(
        __data, col, into, regex = r"(\w+)",
        remove = True, convert = False,
        flags = 0
        ):
    """Pull out len(into) fields from character strings. 

    Returns a DataFrame with a column added for each piece.

    Parameters
    ----------
    __data:
        a DataFrame
    col:
        name of column to split (either string, or siu expression).
    into:
        names of resulting columns holding each entry in pulled out fields.
    regex:
        regular expression used to extract field. Passed to col.str.extract method.
    remove:
        whether to remove col from the returned DataFrame.
    convert:
        whether to attempt to convert the split columns to numerics.
    flags:
        flags from the re module, passed to col.str.extract.

    """

    col_name = simple_varname(col)
    n_into = len(into)

    all_splits = __data[col_name].str.extract(regex, flags)
    n_split_cols = len(all_splits.columns)

    if n_split_cols != n_into:
        raise ValueError("Split into %s pieces, but expected %s" % (n_split_cols, n_into))

    # attempt to convert columns to numeric ----
    if convert:
        # TODO: better strategy here? 
        for k in all_splits:
            try:
                all_splits[k] = pd.to_numeric(all_splits[k])
            except ValueError:
                pass

    out = __data.copy()
    for ii, name in enumerate(into):
        out[name] = all_splits.iloc[:, ii]

    if remove:
        return out.drop(columns = col_name)

    return out