Update table

chr-werner · Apr 17, 2024 · fe4ed5b · fe4ed5b
1 parent 27d774e
commit fe4ed5b
Show file tree

Hide file tree

Showing 3 changed files with 415 additions and 335 deletions.
diff --git a/README.md b/README.md
@@ -6,19 +6,15 @@ This repo contains the notebooks used for sourcing data for `A Corpus of Biblica
 
 ```text
 data/                             General directory for downloaded and generated data
-  |-- publish/                    Directory of cleaned up lists
-  |   |-- manuscripts.csv
-  |   |-- names.csv
-  |   |-- occurrences.csv
-  |   |-- verses.csv
+  |-- publish/                    Directory of cleaned up lists (will be generated by 05_pub_prep.ipynb)
   |-- tables/                     Directory containing manually curated lists
   |   `-- names.csv               List of manually curated names
   |-- transcriptions/             Directory of transcripts (will be created during download)
   |-- manuscripts/                Directory of manuscript metadata (will be created during download)
-  |-- manuscripts.csv             Processed list of manuscripts
-  |-- names.csv                   Processed list of names
-  |-- occurrences.csv             Processed list of occurrences of names
-  `-- verses.csv                  Processed list of verses in manuscripts
+  |-- manuscripts.csv             Processed list of manuscripts (will be generated by 03_*.ipynb)
+  |-- names.csv                   Processed list of names (will be generated by 02_get_words.ipynb)
+  |-- occurrences.csv             Processed list of occurrences of names (will be generated by 04_search.ipynb)
+  `-- verses.csv                  Processed list of verses in manuscripts  (will be generated by 03_*.ipynb)
 notebooks/                        Directory of notebooks used
   |-- 01_download.ipynb           Download files from the IGNTP and NTVMR (TEI files and JSON files)
   |-- 02_get_words.ipynb          Preprocess manual curated list of names for later search
@@ -58,7 +54,7 @@ WHERE {
   ?Person wdt:P2 wd:Q8811.
   ?Person wdt:P143 ?noted.
   ?noted wdt:P8 ?book.
-  
+
   FILTER (?book IN (wd:Q74942, wd:Q74943, wd:Q74944, wd:Q74945, wd:Q74946, wd:Q74947, wd:Q74948, wd:Q74949, wd:Q74950, wd:Q74951, wd:Q74952, wd:Q74953, wd:Q74954, wd:Q74955, wd:Q74956, wd:Q74957, wd:Q74958, wd:Q74959, wd:Q74960,  wd:Q74961, wd:Q74962, wd:Q74963, wd:Q74964, wd:Q74965, wd:Q74966, wd:Q74967, wd:Q74968)) 
   
   OPTIONAL { ?Person wdt:P154 ?Gender. }