Alejandro Moreo Fernandez
|
505d2de823
|
elm examples
|
2023-02-13 12:01:52 +01:00 |
Alejandro Moreo Fernandez
|
4c74ff02a3
|
svmperf in one-vs-all bugfix
|
2023-02-11 10:47:27 +01:00 |
Alejandro Moreo Fernandez
|
7b2d3cb7f1
|
example using svmperf
|
2023-02-11 10:08:31 +01:00 |
Alejandro Moreo Fernandez
|
952cf5e767
|
fixing bugs in one-vs-all
|
2023-02-10 19:02:17 +01:00 |
Alejandro Moreo Fernandez
|
33a21db52c
|
more examples, one-vs-all fixed
|
2023-02-09 19:43:24 +01:00 |
Alejandro Moreo Fernandez
|
9584e5152e
|
more examples, one-vs-all fixed
|
2023-02-09 19:39:39 +01:00 |
Alejandro Moreo Fernandez
|
e28abfc362
|
more examples, one-vs-all fixed
|
2023-02-09 19:39:16 +01:00 |
Alejandro Moreo Fernandez
|
2485117f05
|
adding documentation and adding one new example
|
2023-02-08 19:06:53 +01:00 |
Alejandro Moreo Fernandez
|
ceb88792c5
|
added DistributionMatching method, a generic model for distribution matching for multiclass quantification problems that takes the divergence and number of bins as hyperparameters
|
2023-01-31 15:08:58 +01:00 |
Alejandro Moreo Fernandez
|
f9a199d859
|
fixing hyperparameters with prefixes, and replacing learner with classifier in aggregative quantifiers
|
2023-01-27 18:13:23 +01:00 |
Alejandro Moreo Fernandez
|
3c48841480
|
Merge branch 'protocols' of github.com:HLT-ISTI/QuaPy into protocols
|
2023-01-18 19:46:31 +01:00 |
Alejandro Moreo Fernandez
|
09abcfc935
|
adding calibration methods from the abstension package to quapy
|
2023-01-18 19:46:19 +01:00 |
Pablo González
|
38aa42e4c5
|
fixing a bug
|
2023-01-18 16:44:56 +01:00 |
Pablo González
|
8da4b4c5f3
|
placing the legend
|
2023-01-18 16:12:38 +01:00 |
Pablo González
|
7ed7c9b2e9
|
changing the logaritmic scale
|
2023-01-18 16:05:40 +01:00 |
Alejandro Moreo Fernandez
|
1d4fa40f3e
|
Merge branch 'protocols' of github.com:HLT-ISTI/QuaPy into protocols
|
2023-01-18 15:19:57 +01:00 |
Pablo González
|
f10a3139d9
|
changes to plots again
|
2023-01-18 14:53:46 +01:00 |
Pablo González
|
50d886bffe
|
testing log scale
|
2023-01-18 13:06:38 +01:00 |
Alejandro Moreo Fernandez
|
6e910075ab
|
adding calibration methods from abstension package
|
2023-01-17 13:53:48 +01:00 |
Pablo González
|
c888346fcf
|
solving a bug in show_legend
|
2023-01-17 11:03:52 +01:00 |
Pablo González
|
7bcf8b24e9
|
fixing bug
|
2023-01-16 17:17:02 +01:00 |
Pablo González
|
948f63fade
|
updating plot to center it better
|
2023-01-16 17:00:24 +01:00 |
Alejandro Moreo Fernandez
|
8b0b9f522a
|
some bugfixes, unittest and minor changes
|
2023-01-16 13:51:29 +01:00 |
Alejandro Moreo Fernandez
|
bb7a77c7c0
|
missing param in documentation of some protocols
|
2022-12-13 16:57:11 +01:00 |
Alejandro Moreo Fernandez
|
c20d9d5ea4
|
the heuristic exact_train_prev is performed via kFCV, using a new function qp.model_selection.cross_val_predict
|
2022-12-12 17:32:30 +01:00 |
Alejandro Moreo Fernandez
|
eb860e9678
|
adding the possibility to estimate the training prevalence, instead of using the true training prevalence, as a starting point in emq
|
2022-12-12 09:34:09 +01:00 |
Alejandro Moreo Fernandez
|
643a19228b
|
data reader for lequa 2022 competition
|
2022-11-28 12:02:08 +01:00 |
Alejandro Moreo Fernandez
|
fb79a29204
|
todos and change log
|
2022-11-08 16:36:52 +01:00 |
Alejandro Moreo Fernandez
|
d75b777a13
|
Merge branch 'protocols' of github.com:HLT-ISTI/QuaPy into protocols
|
2022-11-04 15:04:50 +01:00 |
Alejandro Moreo Fernandez
|
f2550fdb82
|
full example of training, model selection, and evaluation using the lequa2022 dataset with the new protocols
|
2022-11-04 15:04:36 +01:00 |
Alejandro Moreo Fernandez
|
a4c33a8e4d
|
import fix
|
2022-10-04 17:44:16 +02:00 |
Alejandro Moreo Fernandez
|
e40c409609
|
bugfix in NeuralClassifierTrainer; it was only configured to work well in binary problems
|
2022-10-04 11:03:08 +02:00 |
Alejandro Moreo Fernandez
|
3af7c70a53
|
restoring the default legend in diag plot
|
2022-10-04 09:12:51 +02:00 |
Alejandro Moreo Fernandez
|
543003f914
|
Merge pull request #13 from pglez82/dys_implementation
Dys implementation
|
2022-07-12 13:05:35 +02:00 |
Pablo González
|
a4584b79db
|
changing gridsearchQ to ensure reproducibility
|
2022-07-11 16:27:02 +02:00 |
Pablo González
|
c91961cff5
|
adding to __init__.py
|
2022-07-11 14:10:04 +02:00 |
Pablo González
|
428f10fb2d
|
adding SMM
|
2022-07-11 14:06:14 +02:00 |
Alejandro Moreo Fernandez
|
ecd0ad7ec7
|
unit test for replicability based on qp.util.temp_seed
|
2022-07-11 14:00:25 +02:00 |
Pablo González
|
46e294002f
|
dys implementation
|
2022-07-11 12:21:49 +02:00 |
Pablo González
|
750814ef2a
|
fixing bug in ACC when using cross validation
|
2022-06-24 14:20:08 +02:00 |
Pablo González
|
02dd2846ff
|
changing app to use prevalence_linspace function with smooth limits
|
2022-06-24 14:05:47 +02:00 |
Pablo González
|
cf7d37c793
|
removing log message
|
2022-06-21 11:07:00 +02:00 |
Alejandro Moreo Fernandez
|
8f6aa629b8
|
param seed changed to random_state
|
2022-06-21 10:49:30 +02:00 |
Alejandro Moreo Fernandez
|
cef20d8b32
|
Merge branch 'protocols' of github.com:HLT-ISTI/QuaPy into protocols
|
2022-06-21 10:27:12 +02:00 |
Alejandro Moreo Fernandez
|
f4a2a94ba5
|
fixing random_state in base and in protocols
|
2022-06-21 10:27:06 +02:00 |
Alejandro Moreo Fernandez
|
cf0bd14cf1
|
bug fix in covariate shift protocol
|
2022-06-17 12:51:52 +02:00 |
Alejandro Moreo Fernandez
|
c0c37f0a17
|
return type in covariate protocol
|
2022-06-16 16:54:15 +02:00 |
Alejandro Moreo Fernandez
|
a7c768bb40
|
param fix
|
2022-06-16 16:38:34 +02:00 |
Alejandro Moreo Fernandez
|
c795404e7f
|
import fix
|
2022-06-15 16:54:42 +02:00 |
Alejandro Moreo Fernandez
|
789b9d5fbc
|
pathfix in lequa2022 datasets
|
2022-06-15 14:36:02 +02:00 |
Alejandro Moreo Fernandez
|
2cc7db60cc
|
updating parallel policy to take n_jobs from environment (not yet tested)
|
2022-06-14 09:35:39 +02:00 |
Alejandro Moreo Fernandez
|
82a01478ec
|
collator functions in protocols for preparing the outputs
|
2022-06-03 18:02:52 +02:00 |
Alejandro Moreo Fernandez
|
bfe4b8b51a
|
updating properties of labelled collection
|
2022-06-03 13:51:22 +02:00 |
Alejandro Moreo Fernandez
|
45642ad778
|
lequa as dataset
|
2022-06-01 18:28:59 +02:00 |
Alejandro Moreo Fernandez
|
eba6fd8123
|
optimization conditional in the prediction function
|
2022-05-26 17:59:23 +02:00 |
Alejandro Moreo Fernandez
|
4bc9d19635
|
many changes, see change log
|
2022-05-25 19:14:33 +02:00 |
Alejandro Moreo Fernandez
|
46e3632200
|
ongoing protocols
|
2022-05-23 00:20:08 +02:00 |
Alejandro Moreo Fernandez
|
b453c8fcbc
|
first commit protocols
|
2022-05-20 16:48:46 +02:00 |
Alejandro Moreo Fernandez
|
cbe3f410ed
|
updating diagonal plot legend
|
2022-05-20 11:52:59 +02:00 |
Alejandro Moreo Fernandez
|
6a5c528154
|
Merge branch 'master' of github.com:HLT-ISTI/QuaPy
|
2022-05-19 13:43:57 +02:00 |
Alejandro Moreo Fernandez
|
fd339839a5
|
removing redundant code
|
2022-05-19 13:43:32 +02:00 |
Alejandro Moreo Fernandez
|
9f4a9cb3fd
|
Merge branch 'master' of github.com:HLT-ISTI/QuaPy
|
2022-04-12 17:23:39 +02:00 |
Alejandro Moreo Fernandez
|
524ec37f83
|
sample_size can now be set to None to indicate that the value has to be resolved by inspecting the environment variable SAMPLE_SIZE
|
2022-04-12 17:13:38 +02:00 |
Alejandro Moreo Fernandez
|
fa577abdd2
|
merging from pool request and adding documentation
|
2022-03-15 14:16:37 +01:00 |
Alejandro Moreo Fernandez
|
de9d5aaf5b
|
Merge branch 'master' of github.com:HLT-ISTI/QuaPy
|
2022-03-14 16:43:03 +01:00 |
Alejandro Moreo Fernandez
|
8ee5e499f5
|
bugfix when the number of positive elemnts for one of the classes is 0
|
2022-03-14 16:42:41 +01:00 |
Pablo González
|
2fde7921d4
|
updating comments
I think this comments are not correct. Changing them
|
2022-02-11 14:33:00 +01:00 |
Alejandro Moreo Fernandez
|
ba18d00334
|
trying to figure out how to refactor protocols meaninguflly
|
2021-12-20 11:39:44 +01:00 |
Alejandro Moreo Fernandez
|
164f7d8d5c
|
documenting quanet
|
2021-12-15 16:39:57 +01:00 |
Alejandro Moreo Fernandez
|
9cf9c73824
|
adding documentation for ensembles
|
2021-12-15 15:46:15 +01:00 |
Alejandro Moreo Fernandez
|
3835f89e9d
|
adding documentation
|
2021-12-15 15:27:43 +01:00 |
Alejandro Moreo Fernandez
|
5deb92b457
|
update doc
|
2021-12-07 17:16:39 +01:00 |
Alejandro Moreo Fernandez
|
2bd47f0841
|
updating the documentation
|
2021-12-06 18:25:47 +01:00 |
Alejandro Moreo Fernandez
|
4da1233b46
|
adapting everything to the new file format
|
2021-11-30 11:36:23 +01:00 |
Alejandro Moreo Fernandez
|
8368c467dc
|
adapting new format
|
2021-11-26 10:57:49 +01:00 |
Alejandro Moreo Fernandez
|
7468519495
|
testing baselines for lequa
|
2021-11-24 11:20:42 +01:00 |
Alejandro Moreo Fernandez
|
1a3755eb58
|
adding documentation, adding brokenbar plots, merging plots from tweetsent with density
|
2021-11-22 18:10:48 +01:00 |
Alejandro Moreo Fernandez
|
b78c8268fd
|
update qp.error documentation
|
2021-11-12 15:37:31 +01:00 |
Alejandro Moreo Fernandez
|
3eb760901f
|
doc update, official baselines for T1A and T1B refactored
|
2021-11-12 14:30:02 +01:00 |
Alejandro Moreo Fernandez
|
611d080ca6
|
format fix
|
2021-11-09 15:44:57 +01:00 |
Alejandro Moreo Fernandez
|
238a30520c
|
adapting everything to the new format
|
2021-11-08 18:01:49 +01:00 |
Alejandro Moreo Fernandez
|
a7e87e41f8
|
GridSearchQ adapted to work with generator functions and integrated for the baselines of LeQua2022; some tests with SVD
|
2021-10-26 18:41:10 +02:00 |
Alejandro Moreo Fernandez
|
9a08125e7e
|
evaluation script and format checker added
|
2021-10-25 13:37:22 +02:00 |
Alejandro Moreo Fernandez
|
5f15b365fe
|
result file format check, read, load, and evaluation with pandas
|
2021-10-22 19:03:15 +02:00 |
Alejandro Moreo Fernandez
|
65b2c2ce74
|
setting baseline experiments with data format
|
2021-10-21 17:14:40 +02:00 |
Alejandro Moreo Fernandez
|
4284f1daa3
|
branch for LeQua2022 - first commit
|
2021-10-13 20:36:53 +02:00 |
Alejandro Moreo Fernandez
|
537a95fa18
|
Merge branch 'crosslingual' of gitea-s2i2s.isti.cnr.it:moreo/QuaPy
|
2021-07-02 13:51:52 +02:00 |
Alejandro Moreo Fernandez
|
a091b2af82
|
update to 0.1.6
|
2021-07-02 11:09:43 +02:00 |
Alejandro Moreo Fernandez
|
f9b80ae437
|
bugfix in quanet
|
2021-07-02 10:20:42 +02:00 |
Alejandro Moreo Fernandez
|
ce908573e7
|
adding features for cross-lingual
|
2021-07-01 18:34:24 +02:00 |
Alejandro Moreo Fernandez
|
986e61620c
|
cleaning data base
|
2021-06-21 12:57:44 +02:00 |
Alejandro Moreo Fernandez
|
b4aeaa97b7
|
fixing issue regarding fit_learner=False in QuaNetTrainer
|
2021-06-21 12:55:39 +02:00 |
Alejandro Moreo Fernandez
|
f33abb5319
|
Merge branch 'master' of https://github.com/HLT-ISTI/QuaPy
|
2021-06-21 11:13:38 +02:00 |
Alejandro Moreo Fernandez
|
a1cdc9ef43
|
fixing fit_learner=False case in QuaNet
|
2021-06-21 11:13:14 +02:00 |
Alejandro Moreo Fernandez
|
8cc11c0276
|
Merge pull request #6 from pglez82/master
fixing two problems with parameters: hidden_size and lstm_nlayers
|
2021-06-21 10:32:58 +02:00 |
Alejandro Moreo Fernandez
|
8239947746
|
refit=True default value in GridSearchQ
|
2021-06-16 13:53:54 +02:00 |
Alejandro Moreo Fernandez
|
294e251450
|
bugfix when refit=False in model selection
|
2021-06-16 13:23:44 +02:00 |
Alejandro Moreo Fernandez
|
4f07680381
|
adding Forman's methods
|
2021-06-16 12:03:37 +02:00 |
Alejandro Moreo Fernandez
|
be2f54de9c
|
renaming functions to match the app and npp nomenclature; adding npp as an option for GridSearchQ
|
2021-06-16 11:45:40 +02:00 |
Alejandro Moreo Fernandez
|
f28a84242f
|
adding more colors to plots
|
2021-06-16 09:38:13 +02:00 |