aboutsummaryrefslogtreecommitdiffhomepage
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/sec_certs/model/references/segment_extractor.py2
1 files changed, 2 insertions, 0 deletions
diff --git a/src/sec_certs/model/references/segment_extractor.py b/src/sec_certs/model/references/segment_extractor.py
index bbb526b1..ffa576f2 100644
--- a/src/sec_certs/model/references/segment_extractor.py
+++ b/src/sec_certs/model/references/segment_extractor.py
@@ -276,6 +276,7 @@ class ReferenceSegmentExtractor:
return (
pd.read_csv(
pth,
+ na_values=["None"],
dtype={
"dgst": str,
"canonical_reference_keyword": str,
@@ -348,6 +349,7 @@ class ReferenceSegmentExtractor:
label=lambda df_: [
annotations_dict.get(x) for x in zip(df_["dgst"], df_["canonical_reference_keyword"])
],
+ actual_reference_keywords=lambda df_: df_.actual_reference_keywords.map(list),
cert_name=lambda df_: df_.dgst.map(dgst_to_cert_name),
referenced_cert_name=lambda df_: df_.canonical_reference_keyword.map(cert_id_to_cert_name),
cert_versions=lambda df_: df_.dgst.map(dgst_to_extracted_versions),