cblearn.datasets.fetch_similarity_matrix#

cblearn.datasets.fetch_similarity_matrix(name, data_home=None, download_if_missing=True)[source]#

Load human similarity judgements, aggregated to a similarity matrix.

This function provides access to the following similarity matrices: fruit2_romney, nonsense_romney, furniture_romney, kinship_kimrosenberg, rectangle_kruschke, vegetables2_romney, animalpictures5, auditory, druguse, faces11, fruits, dotpatterns, furniture2_romney, bodies_viken, textures, sport_romney, bankwiring, morsenumbers, faces_busey, letters, vehicles_romney, vehicles2_romney, birds_romney, fruit_romney, risks, morseall, texturemit_heaps, cartoonfaces, country_robinsonhefner, congress, phonemes, toys_romney, colour, countriessim, faces5, tools_romney, lines_cohen, abstractnumbers, countriesdis, animalnames11, faces_steyvers, weapons2_romney, texturebrodatz_heaps, fish_romney, flowerpots, sizeangle_treat, clothing2_romney, weapons_romney, clothing_romney, animalnames5, vegetables_romney, animalpictures11.

See Similarity Judgement Matrix datasets for a detailed description.

>>> dataset = fetch_similarity_matrix('colour')  
>>> dataset.labels[:2].tolist()  
['434', '445']
>>> dataset.similarity.shape  
(14, 14)

Parameters:

name (str) – Name of the similarity dataset
data_home (PathLike | None) – optional, default: None Specify another download and cache folder for the datasets. By default all scikit-learn data is stored in ‘~/scikit_learn_data’ subfolders.
download_if_missing (bool) – optional, default=True

Returns:

Bunch

Dictionary-like object, with the following attributes.

similarityndarray, shape (n_objects, n_objects): Symmetric matrix of normalized object similarities. None for some datasets.
proximityndarray, shape (n_objects, n_objects): Symmetric matrix of normalized pairwise proximities. None for some datasets.
n_objects: int: Number of objects
labels(n_objects,): Single word describing each object
sigma: float: Uncertainty of the similarity values. Not available for all datasets.
DESCRstring: Description of the dataset.

Return type:

dataset

Raises:

IOError – If the data is not locally available, but download_if_missing=False