diff --git a/data/lists/wrongly_identified_speakers.txt b/data/lists/wrongly_identified_speakers.txt
index b47fdb664c6e0019bb9e3a2b8dac434b96962196..d28e5208b2a30624df07801a66463da0ac6d9919 100644
--- a/data/lists/wrongly_identified_speakers.txt
+++ b/data/lists/wrongly_identified_speakers.txt
@@ -12,6 +12,7 @@ speaker not identifiable:
1951/20035171: Perrin (CANTON MISSING) rapporteur [3935, 3939] 1951-12-07 00:00 0 ['Perrin', 'rapporteur']
1931/20031058: Pfister (CANTON MISSING) [3980, 3981, 3984] 1931-09-25 00:00 4 ['Pfister']
1961/20037310: Berger (CANTON MISSING) rapporteur [368, 373, 375] 1961-09-21 00:00 1 ['Berger', 'rapporteur']
+1956/20036009: Steiner (CANTON MISSING) [5049, 5054] 1956-03-07 00:00 5 ['Steiner']
speaker not uniquely identified when he spoke the second time:
@@ -31,6 +32,7 @@ identifier is split into two words
1971/20000498: ['M', 'Muf', 'ny', 'rapporteur', 'de', 'la', 'majorité'] 7 --> finds Muff but is Mugny
1951/20034978,79,94: found a name: Bringolf- Schaff hausen ['Bringolf', 'Schaff', 'hausen'] 0 Bringolf (CANTON MISSING) [707, 706] --> solved by adding Schaff as additional Info
1941/ : Müller Aarb erg
+1956/20036201: Berger (CANTON MISSING) reporter [368, 373, 375] 1956-12-10 00:00 1 ['Berger', 'Neuch', 'Ã tei', 'rapporteur']
identified as speech start but is in text:
@@ -74,8 +76,9 @@ weird layout:
bad OCR:
--------
-1941/20033146: MüHer instead of Müller is not discovered
+1941/20033146: MüHer --> Müller is not discovered
1911/20027998: ['UsterijBericbterstatter', 'Kommission'] 2 --> Usteri not found
+1956/20036007: reporter [] 1956-03-06 00:00 1 ['Gtliliand', 'rapporteur'] --> Guinand not found
not sure about place:
@@ -105,12 +108,13 @@ person has been elected but not yet officially started (presumably):
1921/20029265: one Huber starts 5.12.21, discussion is on 6.12.21 --> finds two
-Firstname before LastName
+Firstname before LastName --> solved (but not for misspelled firstnames)
-------------------------
1971/20000592: Simon Kohler rapporteur
1911/20028008: Frey (CANTON MISSING) [1816, 1828] 1911-06-13 08:00 2 ['Alfred', 'Frey']
1911/20028010: Eugster (CANTON MISSING) [1571, 1572] 1911-06-22 08:00 15 ['Arthur', 'Eugster']
1961/20037222: Borel (CANTON MISSING) [590, 591] 1961-03-15 00:00 6 ['Georges', 'Borei']
+1956/20036021,22,23: Borel (CANTON MISSING) reporter [590, 591] 1956-03-16 00:00 1 ['Alfred', 'Borei', 'rapporteur']
two people with same last name and same citizenship
diff --git a/data/politicians/MPs_additionalInfo.csv b/data/politicians/MPs_additionalInfo.csv
index b76f6c08b99b3ba5795f7743bce0ad2071651bab..feb0543aa4b8ab46ffbf558d614d0068b526da1f 100644
--- a/data/politicians/MPs_additionalInfo.csv
+++ b/data/politicians/MPs_additionalInfo.csv
@@ -50,3 +50,6 @@ Sonderegger,Johann Jakob,AR,Ausserrhoden
Sonderegger,Karl Justin,IR,Innerrhoden
Müller,Emil,BL,Baselland
König,Walter,BE,Biel
+Meier,Ernst,AG,Baden
+Gfeller,Hans,BE,Oppligen
+Berger,Clause,NE,Neuchâtel
diff --git a/data/politicians/Ratsmitglieder_1848_DE_corr.xlsx b/data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
index 88627f969d79b2c9c2142c021a01499dd42ba57f..5a23edca35923db696ac475e8601b36687bed29f 100644
Binary files a/data/politicians/Ratsmitglieder_1848_DE_corr.xlsx and b/data/politicians/Ratsmitglieder_1848_DE_corr.xlsx differ
diff --git a/src/python/utils_annot.py b/src/python/utils_annot.py
index c7eb9619e697784b4719599bb8b42087ab81ab56..299ff5782a40da408132ed0b20f3028000d85dbf 100644
--- a/src/python/utils_annot.py
+++ b/src/python/utils_annot.py
@@ -574,16 +574,16 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
list_uniqueID = []
str_canton = ''
name_type = ''
- str_council_federal = ''
+ str_firstname = ''
- # extract list and array of last names
+ # extract lists and arrays of names
list_all_names = list(df_names['shortName'])
array_all_names = np.array(df_names['shortName'])
+ list_all_firstnames = list(df_names['FirstName'])
# for every term
for term in list_oi:
- #list_roles_ext = ['Mehrheit', 'Minderheit', 'majorité', 'minorité', 'deutscher', 'deutsche', 'français', 'française', 'Kommission', 'commission']
if term in list_roles:
# update str_role
# TODO: also look for similar terms (misspellings)
@@ -625,7 +625,7 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
# cannot happen for the first term in list_oi
elif name_type == 'canton':
- list_cantons = get_list_cantons(df_names, str_name.split(' ')[0], str_council)
+ list_cantons = get_list_cantons(df_names, str_name.split(' ')[0], str_council, str_firstname)
canton_type = ''
for list_, type_ in list_cantons:
if term in list_:
@@ -691,6 +691,10 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
else:
print('could not be identified as a canton:', term, list_oi, str_name, str_role)
+ elif term in list_all_firstnames:
+ str_firstname = term
+ print('found a first name', str_firstname)
+
# if term is not easily mistaken as a name (avoid false positives)
elif term not in list_notnames:
@@ -716,11 +720,25 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
# initial checks for not uniquely identified peoples
# TODO check for false positives of these procedures
if name_type == 'canton':
+ # check if person can be identified from firstname
+ print(str_firstname)
+ if str_firstname:
+ df_temp = df_names.loc[(df_names['shortName']==str_name.split(' ')[0]) & (df_names['FirstName']==str_firstname)]
+ if df_temp.shape[0] == 1:
+ list_temp = list(df_temp.loc[(df_temp['shortName']==str_name.split(' ')[0]) & (df_temp['FirstName']==str_firstname)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
+ str_completeName = df_temp['completeName'].loc[(df_temp['shortName']==str_name.split(' ')[0]) & (df_temp['FirstName']==str_firstname)].iloc[0]
+
+ list_uniqueID = update_list_uniqueID(list_uniqueID, list_temp, name_type)
+ if str_completeName.split(' ')[0] == str_name.split(' ')[0] or str_completeName.split(' ')[1] == str_name.split(' ')[0]:
+ str_name = add_to_string('', str_completeName)
+ else:
+ str_name = add_to_string(str_name, str_completeName)
+
# check if person can be identified from council
df_temp = df_names.loc[(df_names['nameType']==name_type) & (df_names['shortName']==str_name.split(' ')[0]) & (df_names['CouncilName']==str_council)]
if df_temp.shape[0] == 1:
- list_temp = list(df_names.loc[(df_names['nameType']==name_type) & (df_names['shortName']==str_name.split(' ')[0]) & (df_names['CouncilName']==str_council)].iloc[:, df_names.columns.get_loc('uniqueIndex')])
- str_completeName = df_names['completeName'].loc[(df_names['nameType']==name_type) & (df_names['shortName']==str_name.split(' ')[0]) & (df_names['CouncilName']==str_council)].iloc[0]
+ list_temp = list(df_temp.loc[(df_temp['shortName']==str_name.split(' ')[0]) & (df_temp['CouncilName']==str_council)].iloc[:, df_temp.columns.get_loc('uniqueIndex')])
+ str_completeName = df_temp['completeName'].loc[(df_temp['shortName']==str_name.split(' ')[0]) & (df_temp['CouncilName']==str_council)].iloc[0]
list_uniqueID = update_list_uniqueID(list_uniqueID, list_temp, name_type)
if str_completeName.split(' ')[0] == str_name.split(' ')[0] or str_completeName.split(' ')[1] == str_name.split(' ')[0]:
@@ -759,6 +777,9 @@ def find_names(list_oi, list_roles, list_roles_ext, df_names, list_notnames, str
# TODO: function to update list unique ID and str_name
+
+
+
# if a federal council is referenced as "Name Bundesrat", it is not found by the existing procedure
if str_council == 'Bundesrat' and 'CANTON MISSING' in str_name:
# check if person can be identified from council
@@ -849,17 +870,23 @@ 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(df_names, str_name, str_council):
+def get_df_temp(df_names, str_name, str_council = '', str_firstname = ''):
- if str_council in ['Nationalrat', 'Ständerat', 'Bundesrat']:
- df_temp = df_names.loc[(df_names['shortName']==str_name) & (df_names['CouncilName']==str_council)]
+ if str_firstname:
+ if str_council in ['Nationalrat', 'Ständerat', 'Bundesrat']:
+ df_temp = df_names.loc[(df_names['shortName']==str_name) & (df_names['FirstName']==str_firstname) & (df_names['CouncilName']==str_council)]
+ else:
+ df_temp = df_names.loc[(df_names['shortName']==str_name) & (df_names['FirstName']==str_firstname)]
else:
- df_temp = df_names.loc[(df_names['shortName']==str_name)]
+ if str_council in ['Nationalrat', 'Ständerat', 'Bundesrat']:
+ df_temp = df_names.loc[(df_names['shortName']==str_name) & (df_names['CouncilName']==str_council)]
+ else:
+ df_temp = df_names.loc[(df_names['shortName']==str_name)]
return df_temp
# function to get list of places
-def get_list_cantons(df_names, str_name, str_council = ''):
+def get_list_cantons(df_names, str_name, str_council = '', str_firstname = ''):
# specify strings as they are used in Ratsmitglieder_1848_DE_corr.xlsx and therefore in df_names
str_CantonName = 'CantonName'
@@ -869,7 +896,7 @@ def get_list_cantons(df_names, str_name, str_council = ''):
str_additionalInfo = 'additionalInfo'
# get dataframe
- df_temp = get_df_temp(df_names, str_name, str_council)
+ df_temp = get_df_temp(df_names, str_name, str_council, str_firstname)
# list of cantons
list_cantonname = list(df_temp[str_CantonName])