[{"_1":2,"_119":-5,"_120":-5},"loaderData",{"_3":4,"_13":14},"root",{"_5":6,"_7":8,"_9":10,"_11":12},"isProduction",true,"domain","cran-e.com","version","2.10.1","nonce","NjZlNzBlNWYtM2E3MS00MzViLWJjODQtODZmNWE2YjQ4Njg2","routes/_page.author.$authorName",{"_15":16,"_17":18,"_47":48,"_28":118},"authorName","Sebastiano Vigna","packages",[19,33,40],{"_20":21,"_30":31},"package",{"_22":23,"_24":25,"_26":27,"_28":29},"id",8358,"name","cmfrec","title","Collective Matrix Factorization for Recommender Systems","description","Collective matrix factorization (a.k.a. multi-view or multi-way factorization,\n\tSingh, Gordon, (2008) <[doi:10.1145/1401890.1401969](https://doi.org/10.1145%2F1401890.1401969)> tries to approximate a (potentially very sparse\n\tor having many missing values) matrix 'X' as the product of two low-dimensional matrices,\n\toptionally aided with secondary information matrices about rows and/or columns of 'X',\n\twhich are also factorized using the same latent components.\n\tThe intended usage is for recommender systems, dimensionality reduction, and missing value imputation.\n\tImplements extensions of the original model (Cortes, (2018) <[doi:10.48550/arXiv.1809.00366](https://doi.org/10.48550/arXiv.1809.00366)>) and can produce\n\tdifferent factorizations such as the weighted 'implicit-feedback' model (Hu, Koren, Volinsky,\n\t(2008) <[doi:10.1109/ICDM.2008.22](https://doi.org/10.1109%2FICDM.2008.22)>), the 'weighted-lambda-regularization' model,\n\t(Zhou, Wilkinson, Schreiber, Pan, (2008) <[doi:10.1007/978-3-540-68880-8_32](https://doi.org/10.1007%2F978-3-540-68880-8_32)>),\n\tor the enhanced model with 'implicit features' (Rendle, Zhang,\n\tKoren, (2019) <[doi:10.48550/arXiv.1905.01395](https://doi.org/10.48550/arXiv.1905.01395)>), with or without side information. Can use gradient-based\n\tprocedures or alternating-least squares procedures (Koren, Bell, Volinsky, (2009)\n\t<[doi:10.1109/MC.2009.263](https://doi.org/10.1109%2FMC.2009.263)>), with either a Cholesky solver, a faster conjugate gradient solver\n\t(Takacs, Pilaszy, Tikk, (2011) <[doi:10.1145/2043932.2043987](https://doi.org/10.1145%2F2043932.2043987)>), or a non-negative\n\tcoordinate descent solver (Franc, Hlavac, Navara, (2005) <[doi:10.1007/11556121_50](https://doi.org/10.1007%2F11556121_50)>),\n\tproviding efficient methods for sparse and dense data, and mixtures thereof.\n\tSupports L1 and L2 regularization in the main models,\n\toffers alternative most-popular and content-based models, and implements functionality\n\tfor cold-start recommendations and imputation of 2D data.","roles",[32],"cph",{"_20":34,"_30":39},{"_22":35,"_24":36,"_26":37,"_28":38},9680,"dqrng","Fast Pseudo Random Number Generators","Several fast random number generators are provided as C++ header only libraries: The PCG family by O'Neill (2014 [https://www.cs.hmc.edu/tr/hmc-cs-2014-0905.pdf](https://www.cs.hmc.edu/tr/hmc-cs-2014-0905.pdf)) as well as the Xoroshiro / Xoshiro family by Blackman and Vigna (2021 [doi:10.1145/3460772](https://doi.org/10.1145%2F3460772)). In addition fast functions for generating random numbers according to a uniform, normal and exponential distribution are included. The latter two use the Ziggurat algorithm originally proposed by Marsaglia and Tsang (2000, [doi:10.18637/jss.v005.i08](https://doi.org/10.18637%2Fjss.v005.i08)). The fast sampling methods support unweighted sampling both with and without replacement. These functions are exported to R and as a C++ interface and are enabled for use with the default 64 bit generator from the PCG family, Xoroshiro128+/++/** and Xoshiro256+/++/** as well as the 64 bit version of the 20 rounds Threefry engine (Salmon et al., 2011, [doi:10.1145/2063384.2063405](https://doi.org/10.1145%2F2063384.2063405)) as provided by the package 'sitmo'.",[32],{"_20":41,"_30":46},{"_22":42,"_24":43,"_26":44,"_28":45},12910,"isotree","Isolation-Based Outlier Detection","Fast and multi-threaded implementation of isolation forest (Liu, Ting, Zhou (2008) <[doi:10.1109/ICDM.2008.17](https://doi.org/10.1109%2FICDM.2008.17)>), extended isolation forest (Hariri, Kind, Brunner (2018) <[doi:10.48550/arXiv.1811.02141](https://doi.org/10.48550/arXiv.1811.02141)>), SCiForest (Liu, Ting, Zhou (2010) <[doi:10.1007/978-3-642-15883-4_18](https://doi.org/10.1007%2F978-3-642-15883-4_18)>), fair-cut forest (Cortes (2021) ), robust random-cut forest (Guha, Mishra, Roy, Schrijvers (2016) <[http://proceedings.mlr.press/v48/guha16.html](http://proceedings.mlr.press/v48/guha16.html)>), and customizable variations of them, for isolation-based outlier detection, clustered outlier detection, distance or similarity approximation (Cortes (2019) <[doi:10.48550/arXiv.1910.12362](https://doi.org/10.48550/arXiv.1910.12362)>), isolation kernel calculation (Ting, Zhu, Zhou (2018) <[doi:10.1145/3219819.3219990](https://doi.org/10.1145%2F3219819.3219990)>), and imputation of missing values (Cortes (2019) <[doi:10.48550/arXiv.1911.06646](https://doi.org/10.48550/arXiv.1911.06646)>), based on random or guided decision tree splitting, and providing different metrics for scoring anomalies based on isolation depth or density (Cortes (2021) <[doi:10.48550/arXiv.2111.11639](https://doi.org/10.48550/arXiv.2111.11639)>). Provides simple heuristics for fitting the model to categorical columns and handling missing data, and offers options for varying between random and guided splits, and for using different splitting criteria.",[32],"otherAuthors",[49,64,68,71,75,78,82,86,89,93,97,101,104,108,111,115],{"_22":50,"_24":51,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":58,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":58},2620,"David Cortes","email","extra","orc_id","orc_link","github_id","created_at","2024-11-24T20:49:21.105835+00:00","github_link","unknown_link","website_link","linkedin_link","_last_scraped_at",{"_22":65,"_24":66,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":67,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":67},11968,"Jorge Nocedal","2024-11-24T20:49:28.107185+00:00",{"_22":69,"_24":70,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":67,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":67},11969,"Naoaki Okazaki",{"_22":72,"_24":73,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":74,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":74},21552,"David Blackman","2024-11-24T20:49:35.03944+00:00",{"_22":76,"_24":77,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":74,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":74},21554,"NumPy Developers",{"_22":79,"_24":80,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":81,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":81},3947,"Philippe Grosjean","2024-11-24T20:49:22.430757+00:00",{"_22":83,"_24":84,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":85,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":85},6269,"Kyle Butts","2024-11-24T20:49:24.319227+00:00",{"_22":87,"_24":88,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":85,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":85},6407,"Ralf Stubner",{"_22":90,"_24":91,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":92,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":92},12213,"Melissa O'Neill","2024-11-24T20:49:28.440999+00:00",{"_22":94,"_24":95,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":96,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":96},17772,"Aaron Lun","2024-11-24T20:49:32.134397+00:00",{"_22":98,"_24":99,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":100,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":100},22772,"daqana GmbH","2024-11-24T20:49:35.748403+00:00",{"_22":102,"_24":103,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":100,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":100},22773,"Henrik Sloot",{"_22":105,"_24":106,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":107,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":107},15764,"Stephen Moshier","2024-11-24T20:49:30.777716+00:00",{"_22":109,"_24":110,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":107,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":107},15792,"Thibaut Goetghebuer-Planchon",{"_22":112,"_24":113,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":114,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":114},25692,"SciPy Developers","2024-11-24T20:49:37.942926+00:00",{"_22":116,"_24":117,"_52":-5,"_53":-5,"_54":-5,"_55":-5,"_56":-5,"_57":114,"_59":-5,"_60":-5,"_61":-5,"_62":-5,"_63":114},25693,"Enthought Inc","Sebastiano Vigna has worked on 3 packages. Three's a charm, and it seems like Sebastiano Vigna is finding their stride! With 16 collaborators, Sebastiano Vigna was part of a truly massive undertaking. It takes a village to code something great!","actionData","errors"]

Sebastiano Vigna

3 Packages

Team