mkallipo
/
affRo
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases 1 Wiki Activity

updates -openorgs

This commit is contained in:
mkallipo 2024-11-21 12:39:26 +01:00
parent 415b45e3ca
commit ba98a16bcb
13 changed files with 92 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
__pycache__/affro_cluster.cpython-311.pyc
View File

Binary file not shown.

BIN
__pycache__/functions_cluster.cpython-311.pyc
View File

Binary file not shown.

BIN
__pycache__/matching_cluster.cpython-311.pyc
View File

Binary file not shown.

48
affro_cluster.py
View File

@ -9,19 +9,49 @@ dix_org = load_json('dictionaries/dix_acad.json')
dix_mult = load_json('dictionaries/dix_mult.json')
dix_city = load_json('dictionaries/dix_city.json')
dix_country = load_json('dictionaries/dix_country.json')
dix_org_oaire = load_json('dictionaries/dix_acad_oaire.json')
dix_mult_oaire = load_json('dictionaries/dix_mult_oaire.json')
dix_country_oaire = load_json('dictionaries/dix_country_oaire.json')
dix_status = load_json('dictionaries/dix_status.json')
def find_ror(input, simU, simG):
result = Aff_Ids(input, dix_org, dix_mult, dix_city, dix_country, simU, simG)
result_oaire = Aff_Ids(input, dix_org_oaire, dix_mult_oaire, dix_country_oaire, dix_country_oaire, simU, simG)
results_upd = []
for r in result:
if dix_status[r[2]][0] == 'active':
results_upd.append([r[1], 'ROR', r[2], 'active'])
else:
if dix_status[r[2]][1] == '':
results_upd.append([r[1], 'ROR', r[2], dix_status[r[2]][0]])
else:
results_upd.append([r[1], 'ROR', r[2], dix_status[r[2]][0]])
results_upd.append([r[1], 'ROR', dix_status[r[2]][1], 'active'])
for r in result_oaire:
results_upd.append([r[1],'OpenOrgs', r[2], None])
if len(results_upd)>0:
result_dict = [{'Provenance': 'AffRo', 'PID':'ROR', 'Value':x[2], 'Confidence':x[0], 'Status':x[3]} if x[1] == 'ROR' else {'Provenance': 'AffRo', 'PID':'OpenOrgs', 'Value':x[2], 'Confidence':x[0], 'Status': 'active'} for x in results_upd]
else:
result_dict = []
return result_dict
def affro(raw_aff_string):
try:
result = Aff_Ids(create_df_algorithm(raw_aff_string), dix_org, dix_mult, dix_city, dix_country, 0.65, 0.82)
if len(result)>0:
# result_dict = [json.dumps({'Origin': 'AffRo', 'PID':x[2], 'Confidence':x[1], 'Status':x[3]}) for x in result]
result_dict = [{'Provenance': 'AffRo', 'PID':x[2], 'Value':x[3], 'Confidence':x[1], 'Status':x[4]} for x in result]
else:
result_dict = []
return result_dict
result = find_ror(create_df_algorithm(raw_aff_string), 0.65, 0.82)
return result
except Exception as e:
# Return some indication of an error, or log the row
print(f"Error: {str(e)}")

2
dictionaries/dix_acad.json
View File

File diff suppressed because one or more lines are too long

1
dictionaries/dix_acad_oaire.json Normal file
View File

File diff suppressed because one or more lines are too long

2
dictionaries/dix_city.json
View File

File diff suppressed because one or more lines are too long

2
dictionaries/dix_country.json
View File

File diff suppressed because one or more lines are too long

1
dictionaries/dix_country_oaire.json Normal file
View File

File diff suppressed because one or more lines are too long

2
dictionaries/dix_mult.json
View File

File diff suppressed because one or more lines are too long

1
dictionaries/dix_mult_oaire.json Normal file
View File

File diff suppressed because one or more lines are too long

65
functions_cluster.py
View File

@ -181,44 +181,45 @@ protected_phrases1 = [
replacements = {'saint' : 'st',
replacements = {'czechoslovak':'czech',
'saint' : 'st',
'aghia' : 'agia',
'universitatsklinikum' : 'universi hospital',
'universitetshospital' : 'universi hospital',
'universitatskinderklinik' : 'universi childrens hospital',
'universitatskliniken': 'universi hospital',
'Universitätsklinik': 'universi hospital',
'universitatsmedizin': 'universi medicine',
'universitatskliniken' : 'universi hospital',
'Universitätsklinik' : 'universi hospital',
'universitatsmedizin' : 'universi medicine',
'universitatsbibliothek' : 'universi library',
'nat.':'national',
'uni versity':'university',
'unive rsity': 'university',
'univ ersity': 'university',
'inst ':'institute ',
'adv ':'advanced ',
'univ ':'university ',
'stud ': 'studies ',
'inst.':'institute',
'adv.':'advanced',
'univ.':'university',
'stud.': 'studies',
'univercity':'university',
'univerisity':'university',
'universtiy':'university',
'univeristy':'university',
'universirty':'university',
'universiti':'university',
'universitiy':'university',
'universty' :'university',
'nat.' : 'national',
'uni versity' : 'university',
'unive rsity' : 'university',
'univ ersity' : 'university',
'inst ' : 'institute ',
'adv ' : 'advanced ',
'univ ' : 'university ',
'stud ' : 'studies ',
'inst.' : 'institute',
'adv.' : 'advanced',
'univ.' : 'university',
'stud.' : 'studies',
'univercity' : 'university',
'univerisity' : 'university',
'universtiy' : 'university',
'univeristy' : 'university',
'universirty' : 'university',
'universiti' : 'university',
'universitiy' : 'university',
'universty' : 'university',
'techniche' : 'technological',
'univ col': 'university colege',
'univ. col.': 'university colege',
'univ. coll.': 'university colege',
'col.':'colege',
'univ col' : 'university colege',
'univ. col.' : 'university colege',
'univ. coll.' : 'university colege',
'col.' : 'colege',
'hipokration' : 'hipocration',
'belfield, dublin': 'dublin',
'balsbridge, dublin': 'dublin', #ballsbridge
'earlsfort terrace, dublin': 'dublin',
'belfield, dublin' : 'dublin',
'balsbridge, dublin' : 'dublin', #ballsbridge
'earlsfort terrace, dublin' : 'dublin',
'bon secours hospital, cork' : 'bon secours hospital cork',
'bon secours hospital, dublin' : 'bon secours hospital dublin',
'bon secours hospital, galway' : 'bon secours hospital galway',
@ -231,7 +232,7 @@ replacements = {'saint' : 'st',
'royal holoway, university london' : 'royal holoway universi london', #holloway
'city, university london' : 'city universi london',
'city university, london' : 'city universi london',
'aeginition':'eginition',
'aeginition' : 'eginition',
'national technical university, athens' : 'national technical university athens'
# 'harvard medical school' : 'harvard university'

27
matching_cluster.py
View File

@ -9,8 +9,7 @@ from sklearn.metrics.pairwise import cosine_similarity
from functions_cluster import *
from create_input_cluster import *
with open('dix_status.json', 'rb') as f:
dix_status = json.load(f)
specific = [k for k in categ_dicts if categ_dicts[k] == 'Specific']
@ -334,19 +333,19 @@ def Aff_Ids(input, dix_org, dix_mult, dix_city_ror, dix_country_ror, simU, simG)
results = [[x[0],x[1], ids[i]] for i,x in enumerate(best)]
results_upd = []
# results_upd = []
for r in results:
if 'ror.org' in r[2]:
if dix_status[r[2]][0] == 'active':
results_upd.append([r[0],r[1], 'ROR', r[2], 'active'])
else:
if dix_status[r[2]][1] == '':
results_upd.append([r[0],r[1], 'ROR', r[2], dix_status[r[2]][0]])
else:
# for r in results:
# if 'ror.org' in r[2]:
# if dix_status[r[2]][0] == 'active':
# results_upd.append([r[0],r[1], 'ROR', r[2], 'active'])
# else:
# if dix_status[r[2]][1] == '':
# results_upd.append([r[0],r[1], 'ROR', r[2], dix_status[r[2]][0]])
# else:
results_upd.append([r[0],r[1], 'ROR', r[2], dix_status[r[2]][0]])
# results_upd.append([r[0],r[1], 'ROR', r[2], dix_status[r[2]][0]])
results_upd.append([r[0],r[1], 'ROR', dix_status[r[2]][1], 'active'])
# results_upd.append([r[0],r[1], 'ROR', dix_status[r[2]][1], 'active'])
return results_upd
return results