last name which is both canton and double now also finds person which is...

last name which is both canton and double now also finds person which is double (Schmid-Ruedin Philipp, 1951)

data/lists/not_names.txt

@@ -51,6 +51,7 @@ StGallen
 Stimmen
 Stimme
 stimmt
+Studien
 tischen
 Tunnel
 Ueber

data/lists/wrongly_identified_speakers.txt

@@ -68,6 +68,7 @@ term very similar to one name is actually another name
 ------------------------------------------------------
 1925/20029863: ganz --> finds Lanz, there is a Ganz
 1971/20000630 and others: Schweizer --> finds Schneider, there is a Schweizer
+1951/20035112: Schweizer --> finds Schwizer
 
 
 term is a name
@@ -89,6 +90,10 @@ person has entry date 29.11.71 but is not yet active (presumably):
 1971/20000726: one Muheim starts 29.11.71, discussion is on 8.12.71 --> finds two!
 
 
+Firstname before LastName
+-------------------------
+1971/20000592: Simon Kohler rapporteur
+
 two people with same last name and same citizenship
 ---------------------------------------------------
 1951/20034993: Eggenberger Grabs

src/python/utils_annot.py

@@ -467,7 +467,7 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
 
         # TODO: how to handle for people mentioned in text???
         elif name_type in ['canton']:
-            list_temp = list(df_names.loc[(df_names['nameType']==name_type) & (df_names['shortName']==term)].iloc[:, df_names.columns.get_loc('uniqueIndex')])
+            list_temp = list(df_names.loc[(df_names['shortName']==term)].iloc[:, df_names.columns.get_loc('uniqueIndex')])
             str_completeName = term + ' (CANTON MISSING)'
 
         print(list_temp, str_completeName)
@@ -598,8 +598,8 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
             # if person was not uniquely identified, check for misspellings
             if not canton_type:
                 # look for similar names based on (normalized) Damerau-Levenshtein distance
-                # only look at cantonname, citizenship and additionalinfo
-                list_cantons_approx = [list_cantons[i] for i in (0, 2, 4)]
+                # only look at cantonname, citizenship, firstname and additionalinfo
+                list_cantons_approx = [list_cantons[i] for i in (0, 2, 3, 4)]
                 for list_, type_ in list_cantons_approx:
                     term_approx = get_approximate_term(term, np.array(list_))
                     if term_approx:
@@ -613,7 +613,7 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
                 # get rid of CANTON MISSING
                 str_name = str_name.split(' ')[0]
 
-                df_temp = get_df_temp_canton(df_names, str_name, str_council)
+                df_temp = get_df_temp(df_names, str_name, str_council)
                 # extract uniqueID
                 # if Citizenship, get list of cities and compare each to term
                 if canton_type == 'Citizenship':
@@ -622,20 +622,20 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
                     str_citizenship = ''
                     if len(list_cities) == 1:
                         str_citizenship = list_cities[0]
-                        list_temp = list(df_temp.loc[(df_temp['nameType']==name_type) & (df_temp['shortName']==str_name) & (df_temp[canton_type]==str_citizenship)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
-                        str_completeName = df_temp['completeName'].loc[(df_temp['nameType']==name_type) & (df_temp['shortName']==str_name) & (df_temp[canton_type]==str_citizenship)].iloc[0]
+                        list_temp = list(df_temp.loc[(df_temp['shortName']==str_name) & (df_temp[canton_type]==str_citizenship)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
+                        str_completeName = df_temp['completeName'].loc[(df_temp['shortName']==str_name) & (df_temp[canton_type]==str_citizenship)].iloc[0]
                     elif len(list_cities) > 1:
                         print('found more than one person with citizenship', str_canton, str_name, list_cities)
                         # TODO what happens with these:?
-                        list_temp = list(df_names.loc[(df_names['nameType']==name_type) & (df_names['shortName']==str_name)].iloc[:, df_names.columns.get_loc('uniqueIndex')])
+                        list_temp = list(df_names.loc[(df_names['shortName']==str_name)].iloc[:, df_names.columns.get_loc('uniqueIndex')])
                         str_completeName = str_name + ' (CANTON MISSING)'
                     else:
                         print('found no person with citizenship', str_canton, str_name, list_cities)
 
 
                 else:
-                    list_temp = list(df_temp.loc[(df_temp['nameType']==name_type) & (df_temp['shortName']==str_name) & (df_temp[canton_type]==str_canton)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
-                    str_completeName = df_temp['completeName'].loc[(df_temp['nameType']==name_type) & (df_temp['shortName']==str_name) & (df_temp[canton_type]==str_canton)].iloc[0]
+                    list_temp = list(df_temp.loc[(df_temp['shortName']==str_name) & (df_temp[canton_type]==str_canton)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
+                    str_completeName = df_temp['completeName'].loc[(df_temp['shortName']==str_name) & (df_temp[canton_type]==str_canton)].iloc[0]
 
                 print(list_temp, list_uniqueID, str_completeName)
 
@@ -799,12 +799,12 @@ def label_language(XML_new, ind_p, ind_t, aux_dict_l):
 def get_cities(list_citizenship):
     return [city[:-5] for item in list_citizenship for city in item.split(',')]
 
-def get_df_temp_canton(df_names, str_name, str_council):
+def get_df_temp(df_names, str_name, str_council):
 
     if str_council in ['Nationalrat', 'Ständerat']:
-        df_temp = df_names.loc[(df_names['nameType']=='canton') & (df_names['shortName']==str_name) & (df_names['CouncilName']==str_council)]
+        df_temp = df_names.loc[(df_names['shortName']==str_name) & (df_names['CouncilName']==str_council)]
     else:
-        df_temp = df_names.loc[(df_names['nameType']=='canton') & (df_names['shortName']==str_name)]
+        df_temp = df_names.loc[(df_names['shortName']==str_name)]
 
     return df_temp
 
@@ -819,7 +819,7 @@ def get_list_cantons(df_names, str_name, str_council = ''):
     str_additionalInfo = 'additionalInfo'
 
     # get dataframe
-    df_temp = get_df_temp_canton(df_names, str_name, str_council)
+    df_temp = get_df_temp(df_names, str_name, str_council)
 
     # list of cantons
     list_cantonname = list(df_temp[str_CantonName])