diff options
| author | adamjanovsky | 2023-09-21 14:43:10 +0200 |
|---|---|---|
| committer | adamjanovsky | 2023-09-21 14:43:10 +0200 |
| commit | e159e9cd4fcd6d4270eaabdce875138cfdee87ca (patch) | |
| tree | 94fa068b234fac5cde48ed9c691b0bd3c8df7a15 /src | |
| parent | 7c1c355daa0c066c901fa20914ebde1174849aca (diff) | |
| download | sec-certs-e159e9cd4fcd6d4270eaabdce875138cfdee87ca.tar.gz sec-certs-e159e9cd4fcd6d4270eaabdce875138cfdee87ca.tar.zst sec-certs-e159e9cd4fcd6d4270eaabdce875138cfdee87ca.zip | |
clean labels when loading dataframes
Diffstat (limited to 'src')
| -rw-r--r-- | src/sec_certs/model/references/segment_extractor.py | 2 |
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), |