version 0.9 and adding diff to v0.8

openrefine/v0.9/create_diff_v0.9_v0.8.py

@@ -0,0 +1,14 @@
+import os
+import pandas as pd
+
+# make sure the working directory when running this file is the project root of the git repository
+os.chdir('../../')
+
+old = pd.read_csv('openrefine/v0.8/IHEC_metadata_harmonization.v0.8.csv')
+old.index = old.EpiRR
+new = pd.read_csv('openrefine/v0.9/IHEC_metadata_harmonization.v0.9.csv')
+new.index = new.EpiRR
+
+diff_tbl = old.compare(new)
+diff_tbl.rename(columns={'self': 'v0.8', 'other': 'v0.9'}, inplace=True)
+diff_tbl.apply(lambda x: [x.dropna()], axis=1).to_json('openrefine/v0.9/diff_v0.8_v0.9.json', indent=True)

openrefine/v0.9/create_v0.9.py

@@ -1,16 +1,16 @@
-import json
 import os.path
 import warnings
+import xml.etree.ElementTree as et
+from collections import defaultdict
 from subprocess import run
+from typing import Dict, List, Tuple
+
 import pandas as pd
-from collections import defaultdict
 
 # make sure the working directory when running this file is the project root of the git project
 os.chdir('../../')
 
 # first get the ncit thesaurus
-from typing import Dict, List, Tuple
-import xml.etree.ElementTree as et
 
 tree = et.parse('ontologies/Thesaurus.owl')
 root = tree.getroot()