def load_dexter():
"""Load the dexter data set.
.. note:: Deprecated in hub-toolbox 2.3
Will be removed in hub-toolbox 3.0.
Please use IO.load_dexter() instead.
"""
return IO.load_dexter()
def __init__(self, D:np.ndarray=None, classes:np.ndarray=None,
vectors:np.ndarray=None, metric:str='distance'):
"""Initialize a quick hubness analysis.
Parameters
----------
D : ndarray, optional (default: None)
The n x n symmetric distance (similarity) matrix.
Default: load example dataset (dexter).
classes : ndarray, optional (default: None)
The 1 x n class labels. Required for k-NN, GK.
vectors : ndarray, optional (default: None)
The m x n vector data. Required for IntrDim estimation.
metric : {'distance', 'similarity'}
Define whether `D` is a distance or similarity matrix.
"""
self.has_class_data, self.has_vector_data = False, False
if D is None:
print('\n'
'NO PARAMETERS GIVEN! Loading & evaluating DEXTER data set.'
'\n'
'DEXTER is a text classification problem in a bag-of-word \n'
'representation. This is a two-class classification problem\n'
'with sparse continuous input variables. \n'
'This dataset is one of five datasets of the NIPS 2003\n'
'feature selection challenge.\n'
'http://archive.ics.uci.edu/ml/datasets/Dexter\n')
self.D, self.classes, self.vectors = IO.load_dexter()
self.has_class_data, self.has_vector_data = True, True
self.metric = 'distance'
else:
# copy data and ensure correct type (not int16 etc.)
self.D = np.copy(D).astype(np.float64)
if classes is None:
self.classes = None
else:
self.classes = np.copy(classes).astype(np.float64)
self.has_class_data = True
if vectors is None:
self.vectors = None
else:
self.vectors = np.copy(vectors).astype(np.float64)
self.has_vector_data = True
self.metric = metric
self.n = len(self.D)
self.experiments = []
