Spaces:
Runtime error
Runtime error
Michael-Geis
commited on
Commit
•
c77644c
1
Parent(s):
fcfd917
cosmetic change
Browse files- data_storage.py +0 -11
data_storage.py
CHANGED
@@ -34,17 +34,6 @@ class ArXivData:
|
|
34 |
self.metadata = self._returned_metadata.drop(columns="arxiv_subjects")
|
35 |
self.arxiv_subjects = self.get_OHE_arxiv_subjects(self._returned_metadata)
|
36 |
|
37 |
-
def clean(self, dataset):
|
38 |
-
"""Constructs this dataset by cleaning another one.
|
39 |
-
|
40 |
-
Args:
|
41 |
-
dataset: An ArXivData object containing data to be cleaned.
|
42 |
-
"""
|
43 |
-
self.data = clean.clean(dataset)
|
44 |
-
self.query = dataset.query
|
45 |
-
self.raw = dataset.raw
|
46 |
-
self.categories = dataset.categories
|
47 |
-
|
48 |
def get_OHE_arxiv_subjects(self, returned_metadata):
|
49 |
mlb = MultiLabelBinarizer()
|
50 |
|
|
|
34 |
self.metadata = self._returned_metadata.drop(columns="arxiv_subjects")
|
35 |
self.arxiv_subjects = self.get_OHE_arxiv_subjects(self._returned_metadata)
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
def get_OHE_arxiv_subjects(self, returned_metadata):
|
38 |
mlb = MultiLabelBinarizer()
|
39 |
|