diff --git a/hospital-affiliations/aff_hosp.py b/hospital-affiliations/aff_hosp.py index 695089e..5c24ffb 100755 --- a/hospital-affiliations/aff_hosp.py +++ b/hospital-affiliations/aff_hosp.py @@ -38,8 +38,8 @@ def is_city_in_affiliation(city,affiliation): return city.lower() in affiliation.lower() -def fuzzywuzzy(affiliation,text = None): - return fuzz.ratio(affiliation,text) +def affiliations_match_ratio(first_affiliation,second_affiliation): + return fuzz.ratio(first_affiliation,second_affiliation) def base(texte,df): acronyms = ["chr","chr ","chu ","chu,","chru","ap hp","ap hm","aphp","aphm","hosp","hop ","hop,"," serv","clcc","ctr lutte canc","antoine lacassagne","eugene marquis","baclesse", @@ -61,7 +61,7 @@ df2["Ville_présente"] = df2['Ville_canonique_Dpt'].apply(is_city_in_affiliation,affiliation=texte) if len(df2[df2["Ville_présente"] == True]) != 0: df3 = df2[df2["Ville_présente"] == True] - df3["ratio"] = df3["Affiliation"].apply(fuzzywuzzy,text=texte) + df3["ratio"] = df3["Affiliation"].apply(affiliations_match_ratio,second_affiliation=texte) Orga = df3["Orga NonCnrs Acorriger"][df3["ratio"].idxmax()] else: Orga = "N.C"