Commit Graph

194 Commits

Author SHA1 Message Date
Alejandro Moreo Fernandez 1d89301089 more uci datasets, plots improved (higher fonts), and evaluation script that shows numerical results in command line 2021-01-27 22:49:54 +01:00
Alejandro Moreo Fernandez e609c262b4 parallel functionality added to quapy in order to allow for multiprocess parallelization (and not threading) handling quapy's environment variables 2021-01-27 09:54:41 +01:00
Alejandro Moreo Fernandez 301e8b9088 adding uci ml datasets 2021-01-25 18:38:56 +01:00
Alejandro Moreo Fernandez 8a53cfe677 parallel in threading mode (another) 2021-01-25 16:46:59 +01:00
Alejandro Moreo Fernandez 2fda46fc13 qp.environment was not reachable within Parallel processes; changing backend to threading 2021-01-25 09:58:39 +01:00
Alejandro Moreo Fernandez e7527bd7ed bugfix 2021-01-25 09:02:11 +01:00
Alejandro Moreo Fernandez 2001c6d852 running ensembles 2021-01-25 08:54:10 +01:00
Alejandro Moreo Fernandez 03cf73aff6 refactor: methods requiring a val_split can now declare a default value in the __init__ method that will be used in case the fit method is called without specifying the val_split, which now is by default None in the fit, i.e., by default takes the value of the init, that is generally set to 0.4; some uci datasets added; ensembles can now be optimized for quantification, and can be trained on samples of smaller size 2021-01-22 18:01:51 +01:00
Alejandro Moreo Fernandez 54dc2980e6 creating checkpointdir in fit 2021-01-22 10:03:08 +01:00
Alejandro Moreo Fernandez bf1cc74ba1 quapy fixed 2021-01-22 09:58:12 +01:00
Alejandro Moreo Fernandez 1ba0748b59 experimental method ave-pool, not working due to the fact that onevsall is aggregative and ave-pool is not 2021-01-20 17:03:12 +01:00
Alejandro Moreo Fernandez 99132c8166 fixing quanet 2021-01-20 12:35:14 +01:00
Alejandro Moreo Fernandez f69eb59eb8 launching quanet 2021-01-20 09:01:04 +01:00
Alejandro Moreo Fernandez 482e4453a8 refactor of ensembles, launching EPACC with Ptr policy 2021-01-19 18:26:40 +01:00
Alejandro Moreo Fernandez 1399125fb8 adding QuaNet to experiments of Twitter; trying new stuff in 'NewMethods' 2021-01-18 19:14:04 +01:00
Alejandro Moreo Fernandez b30c40b7a0 some refactor made in order to accomodate OneVsAll to operate with aggregative probabilistic quantifiers; launching OneVsAll(HDy) 2021-01-18 16:52:19 +01:00
Alejandro Moreo Fernandez 8ef9e6a633 bugfix 2021-01-18 10:53:22 +01:00
Alejandro Moreo Fernandez 5e64d2588a import fixes 2021-01-15 18:32:32 +01:00
Alejandro Moreo Fernandez 9c7c017acd import fix 2021-01-15 17:47:55 +01:00
Alejandro Moreo Fernandez 27c688eb2e import fix 2021-01-15 17:44:28 +01:00
Alejandro Moreo Fernandez 865dafaefc setting a timeout for model_selection combinations in order to prevent some combinations to stuck the model selection 2021-01-15 17:42:19 +01:00
Alejandro Moreo Fernandez c5ae2f8b1f adding table manager 2021-01-15 08:33:39 +01:00
Alejandro Moreo Fernandez 3c5a53bdec testing quapy via replicating Tweet Quantification experiments 2021-01-12 17:39:00 +01:00
Alejandro Moreo Fernandez 3e07feda3c import bug fixed 2021-01-12 09:35:49 +01:00
Alejandro Moreo Fernandez 2ec3400d15 adding tweet sent quant experiments 2021-01-11 18:31:12 +01:00
Alejandro Moreo Fernandez 41347b50f9 cleaning and adding some uci datasets 2021-01-11 12:55:06 +01:00
Alejandro Moreo Fernandez d1b449d2e9 plot functionality added 2021-01-07 17:58:48 +01:00
Alejandro Moreo Fernandez 5894d46b31 cleaning 2021-01-06 15:00:48 +01:00
Alejandro Moreo Fernandez 326a8ab803 added Ensemble methods (methods ALL, ACC, Ptr, DS from Pérez-Gallego et al 2017 and 2019) and some UCI ML datasets used in those articles (only 5 datasets out of 32 they used) 2021-01-06 14:58:29 +01:00
Alejandro Moreo Fernandez d8e2f7556e QuaNet added, two examples of TextClassifiers added (CNN, LSTM) 2020-12-29 20:33:59 +01:00
Alejandro Moreo Fernandez 3ec711c96e model selection for quantification added 2020-12-23 11:14:35 +01:00
Alejandro Moreo Fernandez 7bed93dcbf added model selection for quantification 2020-12-22 17:43:23 +01:00
Alejandro Moreo Fernandez 7d6f523e4b uniform sampling added if *prevs is empty 2020-12-17 18:17:17 +01:00
Alejandro Moreo Fernandez 71949e9a03 cleaning 2020-12-15 15:20:35 +01:00
Alejandro Moreo Fernandez 649d412389 dataset fetch for polarity reviews (hp, kindle, imdb) and twitter sentiment (11 datasets) added 2020-12-14 18:36:19 +01:00
Alejandro Moreo Fernandez c8a1a70c8a refactoring aggregative methods as methods that not only implement 'classify' and 'quantify', but that also implement 'aggregate' and that, by default, have a default implementation of 'quantify' as a pipeline of 'classify' and 'aggregate'; this helps speeding up evaluations A LOT, since the documents can be pre-classified and the samples are carried out across pre-classified values (labels, or posterior probabilities), and thus only aggregate is called many times within the artificial sampling protocol 2020-12-11 19:28:17 +01:00
Alejandro Moreo Fernandez e55caf82fd merged 2020-12-10 19:08:22 +01:00
Alejandro Moreo Fernandez 9bc3a9f28a evaluation by artificial prevalence sampling added. New methods added. New util functions added to quapy.functional and quapy.utils 2020-12-10 19:04:33 +01:00
Alejandro Moreo Fernandez 2361186a01 aggregation methods updated 2020-12-09 12:46:50 +01:00
Alejandro Moreo Fernandez 9c8d29156c aggregative methods adapted. Explicit loss minimization methods (SVMQ, SVMKLD, ...) added and with support to binary or single-label. HDy added 2020-12-04 19:32:08 +01:00
Alejandro Moreo Fernandez a882424eeb many aggregative methods added 2020-12-03 18:12:28 +01:00
Alejandro Moreo Fernandez 78988c87f9 svmperf wrapper added 2020-12-03 16:59:13 +01:00
Alejandro Moreo Fernandez e81009e665 fixing dataset loading 2020-12-03 16:36:54 +01:00
Alejandro Moreo Fernandez b6820e8dba data loading 2020-12-03 16:24:21 +01:00