diff --git a/hospital-affiliations/.gitignore b/hospital-affiliations/.gitignore
new file mode 100644
index 0000000..ad72c46
--- /dev/null
+++ b/hospital-affiliations/.gitignore
@@ -0,0 +1,2 @@
+# virtual environment
+env/
\ No newline at end of file
diff --git a/hospital-affiliations/aff_hosp.py b/hospital-affiliations/aff_hosp.py
new file mode 100755
index 0000000..81dd3af
--- /dev/null
+++ b/hospital-affiliations/aff_hosp.py
@@ -0,0 +1,110 @@
+from numpy import column_stack
+import pandas as pd
+pd.options.mode.chained_assignment = None  
+from nltk.tokenize import word_tokenize
+from fuzzywuzzy import fuzz
+#from fuzzywuzzy import process
+import sys
+import json
+
+## MODIFICATION DU FICHIER EXCEL
+# On regarde si la liste des termes acronymes choisis est présente dans les affiliations
+def terme_aff(texte, liste=None) :
+    for aff in liste :
+        if aff in texte.lower() :
+            return True
+    return False
+# Il faut également que l'affiliation qu'on veut homogénéiser ait un terme de la liste
+
+
+#Correction des villes
+def correction(texte) :
+    sep = ' -'
+    stripped = texte.split(sep, 1)[0]
+    stripped = stripped.replace("-"," ")
+    stripped = stripped.replace("ç","c")
+    stripped = stripped.replace("Saint","St")
+    stripped = stripped.replace("é","e")
+    stripped = stripped.replace("è","e")
+    stripped = stripped.replace("É","E")
+    stripped = stripped.replace("â","a")
+    stripped = stripped.replace("ê","e")
+    stripped = stripped.replace("î","i")
+    stripped = stripped.replace("à","a")
+
+    return stripped
+
+# On repère/marque les lignes dont l'affiliation contient la ville
+def aff_ville(ville,texte):
+    if ville.lower() in texte.lower() :
+        return True
+    return False
+
+def fuzzywuzzy(affiliation,text = None):
+    return fuzz.ratio(affiliation,text)
+
+def base(texte,df):
+    acro = ["chr","ghu","chu ","chu,","chru","ap hp","ap hm","aphp","aphm","hosp","hop ","hop,"," serv","clcc","ctr lutte canc","antoine lacassagne","eugene marquis","baclesse",
+    "georges françois leclerc","gf leclerc","jf leclerc","henri becquerel","h becquerel","jean perrin","leon berard","ctr oscar lambret",
+    "oscar lambret comprehens","oscar lambret canc","clcc oscar lambret","ctr lutte canc oscar lambret","gustave roussy","bergonie",
+    "inst curie","curie inst","rene gauducheau","inst cancerol ouest","inst cancerol lorraine","alexis vautrin","inst reg canc montpellier",
+    "icans","paul strauss","paul str","paoli calmettes","inst j paoli i calmettes","claudius regaud","claudius rigaud","inst univ canc toulouse oncopole",
+    "inst univ cancerol oncopole","iuct oncopole","ctr lutte contre canc","ico canc","icm, montpellier canc inst","univ inst canc toulouse oncopole","rothschild"]
+    
+    Orga = ""
+    for ac in acro:
+        if ac in texte.lower():
+            # APPEL DES FONCTIONS
+            df['Terme Affiliation'] = df["Affiliation"].apply(terme_aff,liste=acro)
+            df['Ville_canonique_Dpt'] = df['Ville_canonique_Dpt'].apply(correction)
+            if len(df[df['Terme Affiliation'] == True]) != 0:
+                df2 = df[df['Terme Affiliation'] == True]
+                df2["Ville_présente"] = df2['Ville_canonique_Dpt'].apply(aff_ville,texte=texte)
+                if len(df2[df2["Ville_présente"] == True]) != 0:
+                    df3 = df2[df2["Ville_présente"] == True]
+                    df3["ratio"] = df3["Affiliation"].apply(fuzzywuzzy,text=texte)
+                    Orga = df3["Orga NonCnrs Acorriger"][df3["ratio"].idxmax()]
+                else:
+                    Orga = "N.C"
+            else:
+                Orga = "N.C"
+            break
+    if Orga == "":
+        Orga = "N.C"
+    return Orga
+
+df = pd.read_excel ('hospital_affiliations.xlsx')
+
+
+for line in sys.stdin:
+    data = json.loads(line)
+    texte=data['value']
+    data['value']=base(texte,df)
+    sys.stdout.write(json.dumps(data))
+    sys.stdout.write('\n')
+
+## TEST 
+#{"id": "1","value": "CHRU Hautepierre Strasbourg, Lab Anat Pathol, 1 Ave Moliere, F-67098 Strasbourg, France"},
+# {"id" :"2","value": "AP HP, Paris Ctr Necker Cochin, Clin Res Unit, Paris, France"},
+# {"id" :"3","value": "Hop La Pitie Salpetriere, AP HP, Serv Med Interne, Ctr Natl Reference Histiocytoses, Paris, France"},
+# {"id" :"4","value": "Hop Necker Enfants Malad, Gen Pediat Dept, Paris, France"},
+# {"id" :"5","value": "Bergonie Inst, Dept Radiat Oncol, Bordeaux, France"}
+#{"id" :"6","value": "CHU Besancon, Serv Neurol, 2 Blvd Fleming, F-25030 Besancon, France"}
+#{"id" :"7","value": "Univ Bordeaux, INCIA, CNRS UMR 5287, Equipe Neuropsychopharmacol Addict, BP31,146 Rue Leo Saignat, F-33076 Bordeaux, France"}
+
+"""
+lines = json.loads(json.dumps([
+{"id" :"5","value": "Hop Charpennes, 27 Rue G Peri, F-69100 Villeurbanne, France"},
+{"id" :"6","value": "Fdn Ophtalmol Rothschild, ERT TREAT Vis, 25 Rue Manin, F-75019 Paris, France"},
+{"id" :"7","value": "Ctr Hosp, Mt De Marsan, France"},
+{"id": "8", "value":"CHU Pointe A Pitre, Serv Gynecol Obstet, F-97159 Pointe A Pitre, Guadeloupe, France"},
+]))
+
+for line in lines:
+    data = line
+    texte=data['value']
+    data['value']=base(texte,df)
+    sys.stdout.write(json.dumps(data))
+    sys.stdout.write('\n')
+""" 
+
diff --git a/hospital-affiliations/hospital_affiliations.xlsx b/hospital-affiliations/hospital_affiliations.xlsx
new file mode 100755
index 0000000..f1906ec
--- /dev/null
+++ b/hospital-affiliations/hospital_affiliations.xlsx
Binary files differ
diff --git a/hospital-affiliations/input_data.txt b/hospital-affiliations/input_data.txt
new file mode 100644
index 0000000..e375b72
--- /dev/null
+++ b/hospital-affiliations/input_data.txt
@@ -0,0 +1,5 @@
+{"id" :"3","value": "Hop La Pitie Salpetriere, AP HP, Serv Med Interne, Ctr Natl Reference Histiocytoses, Paris, France"}
+{"id" :"4","value": "Hop Necker Enfants Malad, Gen Pediat Dept, Paris, France"}
+{"id" :"5","value": "Bergonie Inst, Dept Radiat Oncol, Bordeaux, France"}
+{"id" :"6","value": "CHU Besancon, Serv Neurol, 2 Blvd Fleming, F-25030 Besancon, France"}
+{"id" :"7","value": "Univ Bordeaux, INCIA, CNRS UMR 5287, Equipe Neuropsychopharmacol Addict, BP31,146 Rue Leo Saignat, F-33076 Bordeaux, France"}
\ No newline at end of file
diff --git a/hospital-affiliations/requirements.txt b/hospital-affiliations/requirements.txt
new file mode 100755
index 0000000..4669346
--- /dev/null
+++ b/hospital-affiliations/requirements.txt
@@ -0,0 +1,5 @@
+fuzzywuzzy
+numpy
+pandas
+nltk
+openpyxl