chore(code): Rename prisma calculation variables

Renamed intermediate calculation vars from long and redundant names to
slightly shorter and more coherent versions.

manuscript/article.qmd

@@ -160,12 +160,23 @@ The results to be identified in the matrix include a study's: i) key outcome mea
 
 ```{python}
 from src.model import prisma
-nr = prisma.PrismaNumbers()
+p = prisma.PrismaNumbers()
 ```
 
-The query execution results in an initial sample of `{python} nr.nr_database_query_raw` potential studies identified from the database search as well as `{python} nr.nr_snowballing_raw` potential studies from other sources, leading to a total initial number of `{python} nr.FULL_RAW_SAMPLE_NOTHING_REMOVED`.
+The query execution results in an initial sample of
+`{python} p.raw_db`
+potential studies identified from the database search as well as
+`{python} p.raw_snowball`
+potential studies from other sources,
+leading to a total initial number of
+`{python} p.raw_full`.
 This accounts for all identified studies without duplicate removal, without controlling for literature that has been superseded or applying any other screening criteria.
-Of these, `{python} nr.FULL_SAMPLE_DUPLICATES_REMOVED-nr.nr_out_title-nr.nr_out_abstract-nr.nr_out_language` have been identified as potentially relevant studies for the purposes of this scoping review and selected for a full text review,
+Of these,
+`{python} p.dedup_full - p.out_title - p.out_abstract - p.out_language`
+have been identified as potentially relevant studies for the purposes of this scoping review and selected for a full text review,
+from which in turn
+`{python} p.final_extracted`
+have ultimately been extracted.
 
 @fig-intervention-types shows the predominant interventions contained in the reviewed literature.
 Overall, there is a focus on measures of minimum wage, subsidisation, considerations of trade liberalisation and collective bargaining, education and training.

manuscript/scoping_review.qmd

@@ -403,13 +403,23 @@ For a full list of validity ranks, see @apptbl-validity-external and @apptbl-val
 
 ```{python}
 from src.model import prisma
-nr = prisma.PrismaNumbers()
+p = prisma.PrismaNumbers()
 ```
 
-The query execution results in an initial sample of `{python} nr.nr_database_query_raw` potential studies identified from the database search as well as `{python} nr.nr_snowballing_raw` potential studies from other sources, leading to a total initial number of `{python} nr.FULL_RAW_SAMPLE_NOTHING_REMOVED`.
+The query execution results in an initial sample of
+`{python} p.raw_db`
+potential studies identified from the database search as well as
+`{python} p.raw_snowball`
+potential studies from other sources,
+leading to a total initial number of
+`{python} p.raw_full`.
 This accounts for all identified studies without duplicate removal, without controlling for literature that has been superseded or applying any other screening criteria.
-Of these, `{python} nr.FULL_SAMPLE_DUPLICATES_REMOVED-nr.nr_out_title-nr.nr_out_abstract-nr.nr_out_language` have been identified as potentially relevant studies for the purposes of this scoping review and selected for a full text review,
-from which in turn `{python} nr.nr_extraction_done` have ultimately been extracted.
+Of these,
+`{python} p.dedup_full - p.out_title - p.out_abstract - p.out_language`
+have been identified as potentially relevant studies for the purposes of this scoping review and selected for a full text review,
+from which in turn
+`{python} p.final_extracted`
+have ultimately been extracted.
 
 The currently identified literature rises somewhat in volume over time,
 with first larger outputs identified from 2014,

src/model/prisma.py

@@ -1,48 +1,67 @@
-from src.process.generate_dataframes import bib_sample_raw_db, bib_sample
+from src.process.generate_dataframes import bib_sample, bib_sample_raw_db
+
 
 class PrismaNumbers:
-    nr_database_query_raw = len(bib_sample_raw_db.entries)
-    nr_snowballing_raw = 2240
+    raw_db = len(bib_sample_raw_db.entries)
+    raw_snowball = 2240
 
-    all_keywords = [entry["keywords"] for entry in bib_sample.entries if "keywords" in entry.fields_dict.keys()]
-    nr_database_deduplicated = len([1 for kw in all_keywords if "sample::database" in kw])
-    nr_snowballing_deduplicated = len([1 for kw in all_keywords if "sample::snowballing" in kw])
-    nr_out_superseded = len([1 for kw in all_keywords if "out::superseded" in kw])
+    # list of all keywords (semicolon-delimited string) for each entry in sample
+    all_kw = [
+        entry["keywords"]
+        for entry in bib_sample.entries
+        if "keywords" in entry.fields_dict.keys()
+    ]
 
-    FULL_RAW_SAMPLE_NOTHING_REMOVED = nr_database_query_raw + nr_snowballing_raw
-    FULL_SAMPLE_DUPLICATES_REMOVED = nr_database_deduplicated + nr_snowballing_deduplicated + nr_out_superseded
+    # calculate deduplicated and superseded amounts
+    dedup_db = len([1 for kw in all_kw if "sample::database" in kw])
+    dedup_snowball = len([1 for kw in all_kw if "sample::snowballing" in kw])
+    out_superseded = len([1 for kw in all_kw if "out::superseded" in kw])
 
+    raw_full = raw_db + raw_snowball
+    dedup_full = dedup_db + dedup_snowball + out_superseded
+
+    # additional non-captured numbers
     NON_ZOTERO_CAPTURE_TITLE_REMOVAL = 1150
     NON_ZOTERO_CAPTURE_ABSTRACT_REMOVAL = 727
     NON_ZOTERO_CAPTURE_FULLTEXT_REMOVAL = 348
 
-    nr_out_duplicates = FULL_RAW_SAMPLE_NOTHING_REMOVED - FULL_SAMPLE_DUPLICATES_REMOVED
-    nr_out_title = len([1 for kw in all_keywords if "out::title" in kw]) + NON_ZOTERO_CAPTURE_TITLE_REMOVAL
-    nr_out_abstract = len([1 for kw in all_keywords if "out::abstract" in kw]) + NON_ZOTERO_CAPTURE_ABSTRACT_REMOVAL
-    nr_out_fulltext = len([1 for kw in all_keywords if "out::full-text" in kw]) + NON_ZOTERO_CAPTURE_FULLTEXT_REMOVAL
-    nr_out_language = len([1 for kw in all_keywords if "out::language" in kw])
-    nr_extraction_done = len([1 for kw in all_keywords if "done::extracted" in kw])
+    out_duplicates = raw_full - dedup_full
+    out_title = (
+        len([1 for kw in all_kw if "out::title" in kw])
+        + NON_ZOTERO_CAPTURE_TITLE_REMOVAL
+    )
+    out_abstract = (
+        len([1 for kw in all_kw if "out::abstract" in kw])
+        + NON_ZOTERO_CAPTURE_ABSTRACT_REMOVAL
+    )
+    out_fulltext = (
+        len([1 for kw in all_kw if "out::full-text" in kw])
+        + NON_ZOTERO_CAPTURE_FULLTEXT_REMOVAL
+    )
+    out_language = len([1 for kw in all_kw if "out::language" in kw])
+
+    final_extracted = len([1 for kw in all_kw if "done::extracted" in kw])
 
 
 del bib_sample, bib_sample_raw_db
 
 if __name__ == "__main__":
-    nr = PrismaNumbers()
+    prisma = PrismaNumbers()
 
     # FIXME use data/supplementary undeduplciated counts to get database starting and snowballing counts
     outp = f"""
     flowchart TD;
-        search_db["Records identified through database searching (n={nr.nr_database_query_raw})"] --> starting_sample;
-        search_prev["Records identified through other sources (n={nr.nr_snowballing_raw})"] --> starting_sample["Starting sample (n={nr.FULL_RAW_SAMPLE_NOTHING_REMOVED})"];
+        search_db["Records identified through database searching (n={prisma.raw_db})"] --> starting_sample;
+        search_prev["Records identified through other sources (n={prisma.raw_snowball})"] --> starting_sample["Starting sample (n={prisma.raw_full})"];
 
-        starting_sample -- "Duplicate removal ({nr.nr_out_duplicates+nr.nr_out_superseded} removed) "--> dedup["Records after duplicates removed (n={nr.FULL_SAMPLE_DUPLICATES_REMOVED})"];
+        starting_sample -- "Duplicate removal ({prisma.out_duplicates+prisma.out_superseded} removed) "--> dedup["Records after duplicates removed (n={prisma.dedup_full})"];
 
-        dedup -- "Title screening ({nr.nr_out_title} excluded)" --> title_screened["Records after titles screened (n={nr.FULL_SAMPLE_DUPLICATES_REMOVED - nr.nr_out_title})"];
+        dedup -- "Title screening ({prisma.out_title} excluded)" --> title_screened["Records after titles screened (n={prisma.dedup_full - prisma.out_title})"];
 
-        title_screened -- "Abstract screening ({nr.nr_out_abstract} excluded)"--> abstract_screened["Records after abstracts screened (n={nr.FULL_SAMPLE_DUPLICATES_REMOVED-nr.nr_out_title-nr.nr_out_abstract})"];
+        title_screened -- "Abstract screening ({prisma.out_abstract} excluded)"--> abstract_screened["Records after abstracts screened (n={prisma.dedup_full-prisma.out_title-prisma.out_abstract})"];
 
-        abstract_screened -- "  Language screening ({nr.nr_out_language} excluded)  "--> language_screened["Records after language screened (n={nr.FULL_SAMPLE_DUPLICATES_REMOVED-nr.nr_out_title-nr.nr_out_abstract-nr.nr_out_language})"];
+        abstract_screened -- "  Language screening ({prisma.out_language} excluded)  "--> language_screened["Records after language screened (n={prisma.dedup_full-prisma.out_title-prisma.out_abstract-prisma.out_language})"];
 
-        language_screened -- "  Full-text screening ({nr.nr_out_fulltext} excluded)  "--> full-text_screened["Full-text articles assessed for eligibility (n={nr.nr_extraction_done})"];
+        language_screened -- "  Full-text screening ({prisma.out_fulltext} excluded)  "--> full-text_screened["Full-text articles assessed for eligibility (n={prisma.final_extracted})"];
     """
     print(outp)