Doctorado-ML/benchmark
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/benchmark.git synced 2025-08-18 17:05:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add nan manage to arff datasets

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2022-10-25 00:56:37 +02:00
parent 8001c7f2eb
commit 2362f66c7a
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
benchmark/Datasets.py
View File

@@ -28,8 +28,9 @@ class DatasetsArff:
file_name = os.path.join(self.folder(), self.dataset_names(name)) file_name = os.path.join(self.folder(), self.dataset_names(name))
data = arff.loadarff(file_name) data = arff.loadarff(file_name)
df = pd.DataFrame(data[0]) df = pd.DataFrame(data[0])
df = df.dropna()
X = df.drop(class_name, axis=1).to_numpy() X = df.drop(class_name, axis=1).to_numpy()
y = df[class_name].to_numpy() y, _ = pd.factorize(df[class_name])
return X, y return X, y