From e6f380dc5f26b66a2fab09f94bb63f804ce763df Mon Sep 17 00:00:00 2001 From: Alejandro Moreo Date: Thu, 18 Apr 2024 09:38:33 +0200 Subject: [PATCH] update changelog --- CHANGE_LOG.txt | 7 +++++++ quapy/data/datasets.py | 7 +++++-- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/CHANGE_LOG.txt b/CHANGE_LOG.txt index e218b10..0dd3d0c 100644 --- a/CHANGE_LOG.txt +++ b/CHANGE_LOG.txt @@ -1,10 +1,17 @@ Change Log 0.1.9 ---------------- +- Added Continuous Integration with GitHub Actions (thanks to Mirko Bunse!) - Added Bayesian CC method (thanks to Pawel Czyz!). The method is described in detail in the paper Ziegler, Albert, and Paweł Czyż. "Bayesian Quantification with Black-Box Estimators." arXiv preprint arXiv:2302.09159 (2023). +- Removed binary UCI datasets {acute.a, acute.b, balance.2} from the list qp.data.datasets.UCI_BINARY_DATASETS + (the datasets are still loadable from the fetch_UCIBinaryLabelledCollection and fetch_UCIBinaryDataset + functions, though). The reason is that these datasets tend to yield results (for all methods) that are + one or two orders of magnitude greater than for other datasets, and this has a disproportionate impact in + methods average (I suspect there is something wrong in those datasets). + Change Log 0.1.8 ---------------- diff --git a/quapy/data/datasets.py b/quapy/data/datasets.py index 0f732e8..8e1c406 100644 --- a/quapy/data/datasets.py +++ b/quapy/data/datasets.py @@ -20,8 +20,11 @@ TWITTER_SENTIMENT_DATASETS_TEST = ['gasp', 'hcr', 'omd', 'sanders', TWITTER_SENTIMENT_DATASETS_TRAIN = ['gasp', 'hcr', 'omd', 'sanders', 'semeval', 'semeval16', 'sst', 'wa', 'wb'] -UCI_BINARY_DATASETS = ['acute.a', 'acute.b', - 'balance.1', 'balance.2', 'balance.3', +UCI_BINARY_DATASETS = [ + #'acute.a', 'acute.b', + 'balance.1', + #'balance.2', + 'balance.3', 'breast-cancer', 'cmc.1', 'cmc.2', 'cmc.3', 'ctg.1', 'ctg.2', 'ctg.3',