Exemple #1
0
def _normalize_data(data, index):
    """normalize the data to a dict with tuples of strings as keys
    right now it works with:

        0 - dictionary (or equivalent mappable)
        1 - pandas.Series with simple or hierarchical indexes
        2 - numpy.ndarrays
        3 - everything that can be converted to a numpy array
        4 - pandas.DataFrame (via the _normalize_dataframe function)
    """
    # if data is a dataframe we need to take a completely new road
    # before coming back here. Use the hasattr to avoid importing
    # pandas explicitly
    if hasattr(data, 'pivot') and hasattr(data, 'groupby'):
        data = _normalize_dataframe(data, index)
        index = None
    # can it be used as a dictionary?
    try:
        items = list(iteritems(data))
    except AttributeError:
        # ok, I cannot use the data as a dictionary
        # Try to convert it to a numpy array, or die trying
        data = np.asarray(data)
        temp = OrderedDict()
        for idx in np.ndindex(data.shape):
            name = tuple(i for i in idx)
            temp[name] = data[idx]
        data = temp
        items = list(iteritems(data))
    # make all the keys a tuple, even if simple numbers
    data = OrderedDict([_tuplify(k), v] for k, v in items)
    categories_levels = _categories_level(list(iterkeys(data)))
    # fill the void in the counting dictionary
    indexes = product(*categories_levels)
    contingency = OrderedDict([(k, data.get(k, 0)) for k in indexes])
    data = contingency
    # reorder the keys order according to the one specified by the user
    # or if the index is None convert it into a simple list
    # right now it doesn't do any check, but can be modified in the future
    index = lrange(len(categories_levels)) if index is None else index
    contingency = OrderedDict()
    for key, value in iteritems(data):
        new_key = tuple(key[i] for i in index)
        contingency[new_key] = value
    data = contingency
    return data
Exemple #2
0
def _normalize_data(data, index):
    """normalize the data to a dict with tuples of strings as keys
    right now it works with:

        0 - dictionary (or equivalent mappable)
        1 - pandas.Series with simple or hierarchical indexes
        2 - numpy.ndarrays
        3 - everything that can be converted to a numpy array
        4 - pandas.DataFrame (via the _normalize_dataframe function)
    """
    # if data is a dataframe we need to take a completely new road
    # before coming back here. Use the hasattr to avoid importing
    # pandas explicitly
    if hasattr(data, 'pivot') and hasattr(data, 'groupby'):
        data = _normalize_dataframe(data, index)
        index = None
    # can it be used as a dictionary?
    try:
        items = list(iteritems(data))
    except AttributeError:
        # ok, I cannot use the data as a dictionary
        # Try to convert it to a numpy array, or die trying
        data = np.asarray(data)
        temp = OrderedDict()
        for idx in np.ndindex(data.shape):
            name = tuple(i for i in idx)
            temp[name] = data[idx]
        data = temp
        items = list(iteritems(data))
    # make all the keys a tuple, even if simple numbers
    data = OrderedDict([_tuplify(k), v] for k, v in items)
    categories_levels = _categories_level(list(iterkeys(data)))
    # fill the void in the counting dictionary
    indexes = product(*categories_levels)
    contingency = OrderedDict([(k, data.get(k, 0)) for k in indexes])
    data = contingency
    # reorder the keys order according to the one specified by the user
    # or if the index is None convert it into a simple list
    # right now it doesn't do any check, but can be modified in the future
    index = lrange(len(categories_levels)) if index is None else index
    contingency = OrderedDict()
    for key, value in iteritems(data):
        new_key = tuple(key[i] for i in index)
        contingency[new_key] = value
    data = contingency
    return data