Some prettyfication on iswc folder

dbpedia · May 6, 2022 · 2c9b7df · 2c9b7df
1 parent d12b84c
commit 2c9b7df
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 6 deletions.
diff --git a/iswc2022/README.md b/iswc2022/README.md
@@ -5,7 +5,7 @@
 - [Table of all outages](https://docs.google.com/spreadsheets/d/1bL0cnzxPP2y46Z-byf56oHNwREnid1cG0affctbD9fI/edit#gid=281687190)
 - [Outage per crawl](https://docs.google.com/spreadsheets/d/1bL0cnzxPP2y46Z-byf56oHNwREnid1cG0affctbD9fI/edit#gid=694221323)
 - [Outage per ontology](https://docs.google.com/spreadsheets/d/1bL0cnzxPP2y46Z-byf56oHNwREnid1cG0affctbD9fI/edit#gid=1207680809)
-- [Evaluation functions for generating the data](/archivo/iswc_eval.py)
+- [Evaluation functions for generating the data](/iswc2022/archivo_data/iswc_eval.py)
 
 ## Archivo Source Evaluation
 - [Ontology by source and addition](https://databus.dbpedia.org/ontologies/archivo-indices/ontologies/2021.11.21-220000/ontologies_type=official.csv)
@@ -45,7 +45,7 @@ https://databus.dbpedia.org/ontologies/collections/archivo-reproducibility-analy
 
 ## Unknown Terms of Archivo 
 
-The data can be found [here](unknown_terms_crawl) and contains the following
+The data can be found [here](unknown_terms_crawl/term_count_reason_mapping.csv) and contains the following
 * A table with mappings from terms to occurrence count in LOD cloud to the reason for not being able to be added to Archivo
 * A json file with mappings from term to reason for not being added
 * the script used to generate the stats
diff --git a/archivo/iswc_eval.py → iswc2022/archivo_data/iswc_eval.py b/archivo/iswc_eval.py → iswc2022/archivo_data/iswc_eval.py
diff --git a/iswc2022/unknown_terms_crawl/crawl_analysis.py b/iswc2022/unknown_terms_crawl/crawl_analysis.py
@@ -196,15 +196,13 @@ def generate_term_count_reasoning_mapping(output_filepath: str, write_files: boo
 
 def main():
     print("Loading data...")
-    covered_by_archivo = load_first_column_csv("/home/denis/Workspace/Job/archivo_iswc_2022/archivo-analysis/new_all_archivo_classes.csv")
-
-    # covered_by_archivo = covered_by_archivo + load_first_column_csv("/home/denis/Workspace/Job/archivo_iswc_2022/archivo-analysis/new_all_archivo_classes.csv")
+    covered_by_archivo = load_first_column_csv("all_archivo_classes.csv")
 
     covered_by_archivo = set(covered_by_archivo)
 
     print("Reading the file and filter it...")
 
-    term_count_reason_list = generate_term_count_reasoning_mapping("class_count_reason_mapping.csv", stopset=covered_by_archivo, write_files=True) 
+    term_count_reason_list = generate_term_count_reasoning_mapping("term_count_reason_mapping.csv", stopset=covered_by_archivo, write_files=True) 
 
     num_terms_not_in_archivo = len(term_count_reason_list)
 

diff --git a/...erms_crawl/class_count_reason_mapping.csv → ...terms_crawl/term_count_reason_mapping.csv b/...erms_crawl/class_count_reason_mapping.csv → ...terms_crawl/term_count_reason_mapping.csv