{"entities":{"Q116403":{"pageid":117878,"ns":120,"title":"Item:Q116403","lastrevid":105447125,"modified":"2026-10-09T15:10:53Z","type":"item","id":"Q116403","labels":{"en":{"language":"en","value":"dataprep"}},"descriptions":{"en":{"language":"en","value":"Fast, Efficient, and Versatile Data Preprocessing and Reshaping with 'C++', 'OpenMP' & 'SIMD'"}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"438d0eef0223375d3a92def8ffc6a10a8bf1ca95","datavalue":{"value":{"entity-type":"item","numeric-id":57080,"id":"Q57080"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$2F8FB5F4-1385-4428-86A9-2698DDEDF958","rank":"normal"}],"P132":[{"mainsnak":{"snaktype":"value","property":"P132","hash":"e6a6d44e87193de89fc34899b7ebb3eae2f84381","datavalue":{"value":"0.1.5","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"f29f1a5023def8b2009d8a676328d002fb0c80b6","datavalue":{"value":{"time":"+2022-01-15T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$7B7C3851-ACAB-40F3-8129-D8AD89E0E14B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"b542975f358e64266fc8bf3287bc018a1e05a763","datavalue":{"value":"PACKAGES.rds","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"1800a222e902962cc1db4ed590279fc261a09159","datavalue":{"value":{"time":"+2026-10-01T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$9FD024E9-4806-4F14-8D75-4F7700F0CA9B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"10edd141e119b3c38cc2aa087b8fe5922cd0eea3","datavalue":{"value":"0.1.0","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"794125f171c90da9b4a55338e6ac3623e89afeea","datavalue":{"value":{"time":"+2021-01-11T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$A212BE3D-36F2-4533-8661-177D60E6A1B1","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"dd764dabaf036ec40584882b7f9127cdfd73d125","datavalue":{"value":"0.1.1","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"42453767723d1600848a9984bd07197242b7153d","datavalue":{"value":{"time":"+2021-04-04T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$1A1AAE8B-5B64-4016-8F62-6326BAC13064","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"8e566d59c9c8e44ecba7cb45a73aaa454a64a603","datavalue":{"value":"0.1.2","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"00ffa60ea309af725dad80fc9f6348e56a9ea74b","datavalue":{"value":{"time":"+2021-05-25T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$85C7395B-FE97-4EA5-B64B-C745BB7F3073","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"954d5354d497f63bbdb6d95ed05a0ef7b6accda0","datavalue":{"value":"0.1.3","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"b7114c8a48eab6b2cffa75bb0f06d1b4842c227e","datavalue":{"value":{"time":"+2021-05-28T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$E442F1A4-9738-46F6-A204-43C5E8564247","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"c4c531ad1b89c5ba6464b86c76e97622abb245ef","datavalue":{"value":"0.1.4","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"88de36560b45b94d6377eabcf4eff43910d99d5f","datavalue":{"value":{"time":"+2021-07-04T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$9B1121AC-176C-4E48-9B81-2BBC550D934B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"f5397d88140cff34334efa224b068189fcd702a4","datavalue":{"value":"0.1.8","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"1800a222e902962cc1db4ed590279fc261a09159","datavalue":{"value":{"time":"+2026-10-01T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q116403$F0B6B387-2F38-4BDB-B579-BFD67AD45175","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"8603616e142412e841d233ddd7290d7bb1237b0e","datavalue":{"value":{"entity-type":"item","numeric-id":116395,"id":"Q116395"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$866E3B5B-9CA5-4C8D-AD57-083F51C85919","rank":"normal"}],"P19":[{"mainsnak":{"snaktype":"value","property":"P19","hash":"997b9a8934a2bafe643fccc7ccb403f7109d9997","datavalue":{"value":{"entity-type":"item","numeric-id":116395,"id":"Q116395"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$7E9A0BD6-310E-4FF6-8BE1-029094BC8ABC","rank":"normal"}],"P163":[{"mainsnak":{"snaktype":"value","property":"P163","hash":"caec58e2e2e3256bca461f95da85075ecd3567cd","datavalue":{"value":{"entity-type":"item","numeric-id":56623,"id":"Q56623"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$064EC682-1CC9-44F0-9B95-5B1C1E9CD98F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P163","hash":"8576d3d16efe97b9b62facebe80c3ed9e3b6aae2","datavalue":{"value":{"entity-type":"item","numeric-id":56621,"id":"Q56621"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P232":[{"snaktype":"value","property":"P232","hash":"06f074efd5e7d7d06d7477e8ca68e18601234f9f","datavalue":{"value":{"text":"expanded from: GPL (\u2265 2)","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"}]},"qualifiers-order":["P232"],"id":"Q116403$A84C9ADB-1F4B-414B-B5B0-003FAD4AF943","rank":"normal"}],"P585":[{"mainsnak":{"snaktype":"value","property":"P585","hash":"377927ca9faccb74fb3425e77d43b739b674c2ef","datavalue":{"value":{"entity-type":"item","numeric-id":57344,"id":"Q57344"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$FEC5F406-ED5E-4EFB-AD7E-AA5ABD46E4A5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P585","hash":"d595b9251c15d55b682bbb22e27ac12f91c3ba38","datavalue":{"value":{"entity-type":"item","numeric-id":20394,"id":"Q20394"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P132":[{"snaktype":"value","property":"P132","hash":"ec19bbe64cf6edf549d31f1ca2c95abf9a1fc7bb","datavalue":{"value":"\u2265 1.0.10","type":"string"},"datatype":"string"}]},"qualifiers-order":["P132"],"id":"Q116403$321025D6-ABEC-4A89-B75C-652ED3365A62","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P585","hash":"24c3e3d95d6aceb19323da214a060d1bb0535ab2","datavalue":{"value":{"entity-type":"item","numeric-id":57178,"id":"Q57178"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$895E9C8C-4ED3-47F6-9872-781537507F52","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P585","hash":"181574dfe61d92a30914c897a5022337ec55662b","datavalue":{"value":{"entity-type":"item","numeric-id":57412,"id":"Q57412"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$CFD4929C-BBBB-4434-A785-754597A196EB","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"4c17e6c930edf4029fbb132cba0c002cd0103dc5","datavalue":{"value":{"entity-type":"item","numeric-id":116402,"id":"Q116402"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$AA405403-97C7-489C-97B9-777D8DEB7F49","rank":"normal"}],"P229":[{"mainsnak":{"snaktype":"value","property":"P229","hash":"abdd555638599dfd0de782d753f0e0bea7b47c3e","datavalue":{"value":"dataprep","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q116403$FC4355A9-550A-41E9-8EE5-031372760141","rank":"normal"}],"P114":[{"mainsnak":{"snaktype":"value","property":"P114","hash":"251fd109c2cd8c1ee39b48cd109c9f4b1c9fcf5c","datavalue":{"value":{"entity-type":"item","numeric-id":13519,"id":"Q13519"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$3927C64C-EC59-492F-9714-64EBC37CE62B","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"908c3454b3659c4b140ccce33c5aee31081edc8d","datavalue":{"value":{"entity-type":"item","numeric-id":5976450,"id":"Q5976450"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q116403$8184839F-74EA-4230-BAC3-F7E9CE56329B","rank":"normal"}],"P170":[{"mainsnak":{"snaktype":"value","property":"P170","hash":"ced4ce7aefb07268536f795953664e46da7126ee","datavalue":{"value":{"time":"+2026-10-01T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q116403$7C515F8F-37D6-4861-85B9-5E0BAD7FA5C7","rank":"normal"}],"P342":[{"mainsnak":{"snaktype":"value","property":"P342","hash":"a0beaece152e3d4cfe5f01b8a4c02caff7e1e6cc","datavalue":{"value":{"entity-type":"item","numeric-id":56774,"id":"Q56774"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P132":[{"snaktype":"value","property":"P132","hash":"a386f688c4ec865eedc0ad4e580a57cc00116cf9","datavalue":{"value":"\u2265 4.0.0","type":"string"},"datatype":"string"}]},"qualifiers-order":["P132"],"id":"Q116403$8585C3FB-1906-4459-852B-5AD5CB401E02","rank":"normal"}],"P1459":[{"mainsnak":{"snaktype":"value","property":"P1459","hash":"c62800e89193fb767e7a659ed2fddb033c47e4c2","datavalue":{"value":"Fast, efficient, and versatile preprocessing and reshaping of tabular    and time-series data. Most heavy routines are implemented in 'C++' via    'Rcpp', with optional 'OpenMP' parallelization and 'SIMD' acceleration    ('AVX2' / 'AVX-512') on supported hardware. The 0.1.8 release rewrites    the cleaning routines in 'C++' and delivers a 1.1\u20131146\u00d7 speedup over    0.1.5. The 'melt()' and 'dcast()' reshaping functions achieve a    0.6\u00d7\u20131628.9\u00d7 speedup for 'melt()' and a 1.9\u00d7\u2013799.8\u00d7 speedup for    'dcast()' relative to every one of the seven major alternatives in    the R and Python ecosystems, at every tested scale (from 1,000 to    100,000,000 rows), and produce output identical to 'reshape2',    'data.table', 'tidyr', 'pandas', 'polars', 'dask', and 'duckdb'.    Core preprocessing steps include variable deletion by missing    fraction, observation deletion by consecutive missing runs,    point-by-point weighted outlier removal via conditional extremum,    traditional percentile-based outlier removal, and linear    interpolation within short time periods. The package also provides    fast reshaping, descriptive statistics, missing-value diagnosis,    multiple imputation strategies, winsorization, several outlier    detection methods (IQR, MAD, percentile), data transformation and    standardization, categorical encoding, duplicate removal, data    validation, data quality reporting, and stratified sampling.    Feature-engineering helpers cover binning, high-correlation and    low-variance filtering, and string cleaning. Time-series tools    cover detrending, diurnal-cycle removal, rolling statistics, lag    creation, resampling, simple decomposition, day/night and season    flags, log returns, drift detection, and panel balancing.    Fit/transform-style machine-learning interfaces prevent data    leakage during preprocessing. Methods are based on, and improved    from: Liang, C.-S., Wu, H., Li, H.-Y., Zhang, Q., Li, Z. & He,    K.-B. (2020) <doi:10.1016/j.scitotenv.2020.140923>. This work    was supported by the National Natural Science Foundation of China    (No. 12301674).","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$748F1F47-272C-433E-8BBF-BC6F35E5B79A","rank":"normal"}],"P43":[{"mainsnak":{"snaktype":"value","property":"P43","hash":"71df0b6fd6776cef9d32e580ca6aefad944f79fb","datavalue":{"value":"Hao Wu","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$FB197240-D473-412C-8695-89D1C7632B75","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"d50d2cd5ec7aa845f4c9b8ca61cbb72f466b32ef","datavalue":{"value":"Hai-Yan Li","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$0E9333F2-B63D-431A-9000-6C656A803F19","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"ee4c7b64bdacfca2f8aa609d0c8043e06635dc28","datavalue":{"value":"Qiang Zhang","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$A5FC37E0-7666-4D95-B405-DFC708351E11","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"dc5028be3ff0bb731d4824949e9e2a24cdf3f80a","datavalue":{"value":"Zhanqing Li","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$CA715E5D-6FBF-4416-ADDC-2A6339B61566","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"5c10f3eae2e10b20739f5e799bbf0285becccde8","datavalue":{"value":"Ke-Bin He","type":"string"},"datatype":"string"},"type":"statement","id":"Q116403$49F3CE28-812D-4A66-A0B1-46D23ECD05FF","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Dataprep","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Dataprep"}}}}}