Add nan manage to arff datasets

This commit is contained in:
2022-10-25 00:56:37 +02:00
parent 8001c7f2eb
commit 2362f66c7a

View File

@@ -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