From 2362f66c7aaa056d6d30001e6cfaa2c8f1d36790 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Monta=C3=B1ana?= Date: Tue, 25 Oct 2022 00:56:37 +0200 Subject: [PATCH] Add nan manage to arff datasets --- benchmark/Datasets.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/benchmark/Datasets.py b/benchmark/Datasets.py index 0150623..8fb77b3 100644 --- a/benchmark/Datasets.py +++ b/benchmark/Datasets.py @@ -28,8 +28,9 @@ class DatasetsArff: file_name = os.path.join(self.folder(), self.dataset_names(name)) data = arff.loadarff(file_name) df = pd.DataFrame(data[0]) + df = df.dropna() X = df.drop(class_name, axis=1).to_numpy() - y = df[class_name].to_numpy() + y, _ = pd.factorize(df[class_name]) return X, y