chore(script): Include superseded in duplicate count

Included studies marked as 'out::superseded' in the duplication removal step.
This commit is contained in:
Marty Oehme 2023-12-13 14:42:34 +01:00
parent c35b205345
commit 8c2c83cd9a
Signed by: Marty
GPG key ID: EDBF2ED917B2EF6A

View file

@ -429,6 +429,7 @@ nr_out_duplicates = FULL_RAW_SAMPLE_NOTHING_REMOVED - len(bib_sample.entries)
nr_other_sources = (len(bib_sample.entries) + nr_out_duplicates) - nr_database_query_raw nr_other_sources = (len(bib_sample.entries) + nr_out_duplicates) - nr_database_query_raw
all_keywords = [entry["keywords"] for entry in bib_sample.entries if "keywords" in entry.fields_dict.keys()] all_keywords = [entry["keywords"] for entry in bib_sample.entries if "keywords" in entry.fields_dict.keys()]
nr_out_superseded = len([1 for kw in all_keywords if "out::superseded" in kw])
nr_out_title = len([1 for kw in all_keywords if "out::title" in kw]) nr_out_title = len([1 for kw in all_keywords if "out::title" in kw])
nr_out_abstract = len([1 for kw in all_keywords if "out::abstract" in kw]) nr_out_abstract = len([1 for kw in all_keywords if "out::abstract" in kw])
nr_out_fulltext = len([1 for kw in all_keywords if "out::full-text" in kw]) nr_out_fulltext = len([1 for kw in all_keywords if "out::full-text" in kw])
@ -447,7 +448,7 @@ flowchart TD;
search_db["Records identified through database searching (n={nr_database_query_raw})"] --> starting_sample; search_db["Records identified through database searching (n={nr_database_query_raw})"] --> starting_sample;
search_prev["Records identified through other sources (n={nr_other_sources})"] --> starting_sample["Starting sample (n={FULL_RAW_SAMPLE_NOTHING_REMOVED})"]; search_prev["Records identified through other sources (n={nr_other_sources})"] --> starting_sample["Starting sample (n={FULL_RAW_SAMPLE_NOTHING_REMOVED})"];
starting_sample -- "Duplicate removal ({nr_out_duplicates} removed) "--> dedup["Records after duplicates removed (n={len(bib_sample.entries)})"]; starting_sample -- "Duplicate removal ({nr_out_duplicates+nr_out_superseded} removed) "--> dedup["Records after duplicates removed (n={len(bib_sample.entries)})"];
dedup -- "Title screening ({nr_out_title} excluded)" --> title_screened["Records after titles screened (n={len(bib_sample.entries) - nr_out_title})"]; dedup -- "Title screening ({nr_out_title} excluded)" --> title_screened["Records after titles screened (n={len(bib_sample.entries) - nr_out_title})"];