Built-in datasets¶

Amazon Clothing¶

This data is built based on the Amazon datasets provided by Julian McAuley @ http://jmcauley.ucsd.edu/data/amazon/. We make sure all items having three types of auxiliary data: text, image, and context (items appearing together).

cornac.datasets.amazon_clothing.load_context(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the item-item interactions

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (item, item, 1).
Return type:	array-like

cornac.datasets.amazon_clothing.load_image()[source]¶

Load the item image in the form of visual features (extracted from pre-trained CNN)

Returns:	features (numpy.ndarray) – Feature matrix with shape (n, 4096) with n is the number of items. item_ids (List) – List of item ids aligned with indices in features.

cornac.datasets.amazon_clothing.load_rating(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the user-item ratings

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, rating).
Return type:	array-like

cornac.datasets.amazon_clothing.load_text()[source]¶

Load the item text descriptions

Returns:	texts (List) – List of text documents, one per item. ids (List) – List of item ids aligned with indices in texts.

Amazon Office¶

This data is built based on the Amazon datasets provided by Julian McAuley at: http://jmcauley.ucsd.edu/data/amazon/

cornac.datasets.amazon_office.load_context(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the item-item interactions

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (item, item, 1).
Return type:	array-like

cornac.datasets.amazon_office.load_rating(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the user-item ratings

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, rating).
Return type:	array-like

Amazon Toys and Games¶

This data is built based on the Amazon datasets provided by Julian McAuley at: http://jmcauley.ucsd.edu/data/amazon/

cornac.datasets.amazon_toy.load_rating(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the user-item ratings

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, rating).
Return type:	array-like

cornac.datasets.amazon_toy.load_sentiment(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the user-item-sentiments The dataset was constructed by the method described in the reference paper.

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, [(aspect, opinion, sentiment), (aspect, opinion, sentiment), …]).
Return type:	array-like

References

Gao, J., Wang, X., Wang, Y., & Xie, X. (2019). Explainable Recommendation Through Attentive Multi-View Learning. AAAI.

CiteULike¶

This dataset is mostly from the paper ‘Collaborative topic modeling for recommending scientific articles’ [Wang and Blei - KDD 2011]. It was further collected, named citeulike-a, and used in the paper ‘Collaborative Topic Regression with Social Regularization’ [Wang, Chen and Li - IJCAI 2013].

Link to the data: http://www.wanghao.in/CDL.htm

cornac.datasets.citeulike.load_data(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the implicit feedback between users and items

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, 1).
Return type:	array-like

cornac.datasets.citeulike.load_text()[source]¶

Load item texts including tile and abstract joined together into one document per item.

Returns:	texts (List) – List of text documents, one per item. ids (List) – List of item ids aligned with indices in texts.

Epinions¶

Link to the dataset: http://www.trustlet.org/downloaded_epinions.html

cornac.datasets.epinions.load_data(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the rating feedback

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, rating).
Return type:	array-like

cornac.datasets.epinions.load_trust(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the trust data

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (source_user, target_item, trust_value).
Return type:	array-like

MovieLens¶

Link to the data: https://grouplens.org/datasets/movielens/

cornac.datasets.movielens.load_100k(fmt='UIR', reader=None)[source]¶

Load the MovieLens 100K dataset

Parameters:	fmt (str, default: 'UIR') – Data format to be returned.
Returns:	data – Data in the form of a list of tuples depending on the given data format.
Return type:	array-like

cornac.datasets.movielens.load_1m(fmt='UIR', reader: cornac.data.reader.Reader = None) → List[source]¶

Load the MovieLens 1M dataset

Parameters:	fmt (str, default: 'UIR') – Data format to be returned. reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples depending on the given data format.
Return type:	array-like

cornac.datasets.movielens.load_plot()[source]¶

Load the plots of movies provided @ http://dm.postech.ac.kr/~cartopy/ConvMF/

Returns:	texts (List) – List of text documents, one per item. ids (List) – List of item ids aligned with indices in texts.

Netflix¶

Link to the data: https://www.kaggle.com/netflix-inc/netflix-prize-data/

cornac.datasets.netflix.load_data(fmt='UIR', reader: cornac.data.reader.Reader = None) → List[source]¶

Load the Netflix entire dataset - Number of ratings: 100,480,507 - Number of users: 480,189 - Number of items: 17,770

Parameters:	fmt (str, default: 'UIR') – Data format to be returned. reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples depending on the given data format.
Return type:	array-like

cornac.datasets.netflix.load_data_small(fmt='UIR', reader: cornac.data.reader.Reader = None) → List[source]¶

Load a small subset of the Netflix dataset. We draw this subsample such that every user has at least 10 items and each item has at least 10 users. - Number of ratings: 607,803 - Number of users: 10,000 - Number of items: 5,000

Parameters:	fmt (str, default: 'UIR') – Data format to be returned. reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples depending on the given data format.
Return type:	array-like

Tradesy¶

Link to the data: http://jmcauley.ucsd.edu/data/tradesy/ This data is used in the VBPR paper. After cleaning the data, we have: - Number of feedback: 394,421 (410,186 is reported but there are duplicates) - Number of users: 19,243 (19,823 is reported due to duplicates) - Number of items: 165,906 (166,521 is reported due to duplicates)

cornac.datasets.tradesy.load_data(reader: cornac.data.reader.Reader = None) → List[source]¶

Load the feedback observations

Parameters:	reader (obj:cornac.data.Reader, default: None) – Reader object used to read the data.
Returns:	data – Data in the form of a list of tuples (user, item, 1).
Return type:	array-like

cornac.datasets.tradesy.load_feature()[source]¶

Load the item visual feature

Returns:	features (numpy.ndarray) – Feature matrix with shape (n, 4096) with n is the number of items. item_ids (List) – List of item ids aligned with indices in features.