def _normalize_tabular_data()

in rlkit/core/tabulate.py [0:0]

• 38 lines of code
• 26 McCabe index (conditional complexity)

def _normalize_tabular_data(tabular_data, headers):
    """Transform a supported data type to a list of lists, and a list of headers.

    Supported tabular data types:

    * list-of-lists or another iterable of iterables

    * list of named tuples (usually used with headers="keys")

    * 2D NumPy arrays

    * NumPy record arrays (usually used with headers="keys")

    * dict of iterables (usually used with headers="keys")

    * pandas.DataFrame (usually used with headers="keys")

    The first row can be used as headers if headers="firstrow",
    column indices can be used as headers if headers="keys".

    """

    if hasattr(tabular_data, "keys") and hasattr(tabular_data, "values"):
        # dict-like and pandas.DataFrame?
        if hasattr(tabular_data.values, "__call__"):
            # likely a conventional dict
            keys = list(tabular_data.keys())
            rows = list(zip_longest(*list(tabular_data.values())))  # columns have to be transposed
        elif hasattr(tabular_data, "index"):
            # values is a property, has .index => it's likely a pandas.DataFrame (pandas 0.11.0)
            keys = list(tabular_data.keys())
            vals = tabular_data.values  # values matrix doesn't need to be transposed
            names = tabular_data.index
            rows = [[v]+list(row) for v,row in zip(names, vals)]
        else:
            raise ValueError("tabular data doesn't appear to be a dict or a DataFrame")

        if headers == "keys":
            headers = list(map(_text_type,keys))  # headers should be strings

    else:  # it's a usual an iterable of iterables, or a NumPy array
        rows = list(tabular_data)

        if (headers == "keys" and
            hasattr(tabular_data, "dtype") and
            getattr(tabular_data.dtype, "names")):
            # numpy record array
            headers = tabular_data.dtype.names
        elif (headers == "keys"
              and len(rows) > 0
              and isinstance(rows[0], tuple)
              and hasattr(rows[0], "_fields")): # namedtuple
            headers = list(map(_text_type, rows[0]._fields))
        elif headers == "keys" and len(rows) > 0:  # keys are column indices
            headers = list(map(_text_type, list(range(len(rows[0])))))

    # take headers from the first row if necessary
    if headers == "firstrow" and len(rows) > 0:
        headers = list(map(_text_type, rows[0])) # headers should be strings
        rows = rows[1:]

    headers = list(headers)
    rows = list(map(list,rows))

    # pad with empty headers for initial columns if necessary
    if headers and len(rows) > 0:
       nhs = len(headers)
       ncols = len(rows[0])
       if nhs < ncols:
           headers = [""]*(ncols - nhs) + headers

    return rows, headers