Skip to content
Snippets Groups Projects
Commit effb699f authored by Luis Salamanca's avatar Luis Salamanca
Browse files

Solved conflict

parents c9999211 daec0a8a
No related branches found
No related tags found
No related merge requests found
Expand all Hide whitespace changes
Inline Side-by-side
Showing
with 717 additions and 4120 deletions
.gitattributes
+ 5
− 0
View file @ effb699f
......@@ -240,6 +240,8 @@ data/AB/1992/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1993/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1994/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1995/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
data/politicians/MPs_after1890.csv filter=lfs diff=lfs merge=lfs -text
data/politicians/lastnames/** filter=lfs diff=lfs merge=lfs -text
data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1975/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1976/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
......@@ -251,7 +253,10 @@ data/AB/1982/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1983/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1991/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1991/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/lists/dict_overlaps.pickle filter=lfs diff=lfs merge=lfs -text
data/lists/all_titles.csv filter=lfs diff=lfs merge=lfs -text
data/AB/1978/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1979/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1976/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1977/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
.gitignore
+ 4
− 0
View file @ effb699f
......@@ -282,3 +282,7 @@ Pipfile.lock
# NER training files
data/train_NER/1[0-9][0-9][0-9]_20[0-9][0-9][0-9][0-9][0-9][0-9].txt
data/train_NER/1[0-9][0-9][0-9]_20[0-9][0-9][0-9][0-9][0-9][0-9]_french.txt
# notunique files
data/lists/notunique_*.txt
.gitlab-ci.yml
+ 1
− 1
View file @ effb699f
......@@ -24,7 +24,7 @@ image_build:
dot:
stage: build
image: renku/renku-python:v0.3.3
image: renku/singleuser:latest
script:
- renku log --format dot $(git ls-files --no-empty-directory --recurse-submodules) > graph.dot
artifacts:
......
.renku/workflow/10b7585b16dd4fee9980bb3c8070d31f_python.cwl 0 → 100644
+ 68
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/extractMPs.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: File
path: ../../data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: File
input_3:
default:
class: File
path: ../../data/politicians/MPs_additionalInfo.csv
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: File
input_4:
default: data/politicians/MPs_after1890.csv
inputBinding:
position: 4
separate: true
shellQuote: true
streamable: false
type: string
input_5:
default: data/politicians/lastnames
inputBinding:
position: 5
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_4)
streamable: false
type: File
output_1:
outputBinding:
glob: $(inputs.input_5)
streamable: false
type: Directory
permanentFailCodes: []
requirements: []
successCodes: []
temporaryFailCodes: []
.renku/workflow/254ef26485a346aea2735e444fd037e0_python.cwl 0 → 100644
+ 51
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/run_correctxml.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: File
path: ../../data/AB/1975/02_extractedxml.tar.gz
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: File
input_3:
default: data/AB/1975/04_correctedxml.tar.gz
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_3)
streamable: false
type: File
permanentFailCodes: []
requirements:
- class: InlineJavascriptRequirement
- class: InitialWorkDirRequirement
listing:
- entry: '$({"listing": [], "class": "Directory"})'
entryname: data/AB/1975
writable: true
successCodes: []
temporaryFailCodes: []
.renku/workflow/37d3814894c7426fa0e5a6b0211ad38b_python.cwl 0 → 100644
+ 68
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/extractMPs.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: File
path: ../../data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: File
input_3:
default:
class: File
path: ../../data/politicians/MPs_additionalInfo.csv
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: File
input_4:
default: data/politicians/MPs_after1890.csv
inputBinding:
position: 4
separate: true
shellQuote: true
streamable: false
type: string
input_5:
default: data/politicians/lastnames
inputBinding:
position: 5
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_4)
streamable: false
type: File
output_1:
outputBinding:
glob: $(inputs.input_5)
streamable: false
type: Directory
permanentFailCodes: []
requirements: []
successCodes: []
temporaryFailCodes: []
.renku/workflow/4f646bc63f1d48be8e5091b18d0999fa_python.cwl 0 → 100644
+ 74
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/extractMPs.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: File
path: ../../data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: File
input_3:
default:
class: File
path: ../../data/politicians/MPs_additionalInfo.csv
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: File
input_4:
default: data/politicians/MPs_after1890.csv
inputBinding:
position: 4
separate: true
shellQuote: true
streamable: false
type: string
input_5:
default: data/politicians/lastnames
inputBinding:
position: 5
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_4)
streamable: false
type: File
output_1:
outputBinding:
glob: $(inputs.input_5)
streamable: false
type: Directory
permanentFailCodes: []
requirements:
- class: InlineJavascriptRequirement
- class: InitialWorkDirRequirement
listing:
- entry: '$({"listing": [], "class": "Directory"})'
entryname: data/politicians/lastnames
writable: true
successCodes: []
temporaryFailCodes: []
.renku/workflow/cef5b5b724be465ba21cb133160ea7d5_python.cwl 0 → 100644
+ 68
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/extractMPs.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: File
path: ../../data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: File
input_3:
default:
class: File
path: ../../data/politicians/MPs_additionalInfo.csv
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: File
input_4:
default: data/politicians/MPs_after1890.csv
inputBinding:
position: 4
separate: true
shellQuote: true
streamable: false
type: string
input_5:
default: data/politicians/lastnames
inputBinding:
position: 5
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_4)
streamable: false
type: File
output_1:
outputBinding:
glob: $(inputs.input_5)
streamable: false
type: Directory
permanentFailCodes: []
requirements: []
successCodes: []
temporaryFailCodes: []
.renku/workflow/d7f5834807064a1f8ed8026be247a3be_python.cwl 0 → 100644
+ 60
− 0
View file @ effb699f
arguments: []
baseCommand:
- python
class: CommandLineTool
cwlVersion: v1.0
hints: []
inputs:
input_1:
default:
class: File
path: ../../src/python/extract_document_titles.py
inputBinding:
position: 1
separate: true
shellQuote: true
streamable: false
type: File
input_2:
default:
class: Directory
listing: []
path: ../../data/AB
inputBinding:
position: 2
separate: true
shellQuote: true
streamable: false
type: Directory
input_3:
default: 03_correctedmeta
inputBinding:
position: 3
separate: true
shellQuote: true
streamable: false
type: string
input_4:
default: data/lists/all_titles.csv
inputBinding:
position: 4
separate: true
shellQuote: true
streamable: false
type: string
outputs:
output_0:
outputBinding:
glob: $(inputs.input_4)
streamable: false
type: File
permanentFailCodes: []
requirements:
- class: InlineJavascriptRequirement
- class: InitialWorkDirRequirement
listing:
- entry: '$({"listing": [], "class": "Directory"})'
entryname: data/lists
writable: true
successCodes: []
temporaryFailCodes: []
Dockerfile
+ 4
− 1
View file @ effb699f
......@@ -16,4 +16,7 @@ RUN sudo apt-get install -y vim
# install spacy models
RUN python -m spacy download de_core_news_sm
RUN python -m spacy download fr_core_news_sm
RUN python -m spacy download xx_ent_wiki_sm
\ No newline at end of file
RUN python -m spacy download xx_ent_wiki_sm
# install nltk stopwords and punkt
RUN python -m nltk.downloader punkt && python -m nltk.downloader stopwords
\ No newline at end of file
data/AB/1975/04_correctedxml.tar.gz 0 → 100644 LFS
+ 3
− 0
View file @ effb699f
File added
data/lists/all_titles.csv 0 → 100644 LFS
+ 3
− 0
View file @ effb699f
source diff could not be displayed: it is stored in LFS. Options to address this: view the blob.
data/lists/dict_overlaps.pickle 0 → 100644 LFS
+ 3
− 0
View file @ effb699f
File added
data/lists/metadata.yml 0 → 100644
+ 31
− 0
View file @ effb699f
'@context':
added: http://schema.org/dateCreated
affiliation: scoro:affiliate
authors:
'@container': '@list'
created: http://schema.org/dateCreated
dcterms: http://purl.org/dc/terms/
dctypes: http://purl.org/dc/dcmitypes/
email: dcterms:email
files:
'@container': '@index'
foaf: http://xmlns.com/foaf/0.1/
identifier:
'@id': dctypes:Dataset
'@type': '@id'
name: dcterms:name
prov: http://www.w3.org/ns/prov#
scoro: http://purl.org/spar/scoro/
url: http://schema.org/url
'@type': dctypes:Dataset
authors: []
created: 2019-02-05 12:19:12.309142
files:
dict_overlaps.pickle:
'@type': http://schema.org/DigitalDocument
added: 2019-02-05 12:19:12.416049
authors: []
path: dict_overlaps.pickle
url: ../data_from_nlp-democracy/results_overlap/dict_overlaps.pickle
identifier: 2b13b133-de16-4322-b120-72993d08ce89
name: lists
data/lists/not_names.txt
+ 35
− 0
View file @ effb699f
Abs
Alinea
Alter
Ari
Art
ausser
besser
bietet
darin
drehen
eher
Erster
ess
Fällen
fasse
Ferner
ferner
findet
Gallen
gehen
Gründe
hausen
Herren
Herr
Hunger
immer
Kasse
Kollege
Kollega
komme
Kosten
lassen
Leider
leider
lieber
Lieber
liegen
Masse
Minister
neben
nehmen
nen
neu
nicht
Rath
Recht
Schrit
Seite
selber
sicher
Sinne
später
Ständer
Steuer
StGallen
Stimmen
Stimme
stimmt
Studien
tischen
Tunnel
Ueber
Hans
Walter
Wegen
Werner
Weitere
weiterer
Welt
Wer
wissen
Wort
Worten
Ziel
Zuerst
Zusatz
allemand
autre
Berne
Biffer
biffer
cerner
......@@ -54,6 +84,9 @@ comme
force
cause
dernier
durant
grande
Nicolas
ouvert
peu
pilier
......@@ -61,6 +94,8 @@ poser
projet
Rédiger
rédiger
sais
tirer
vote
delle
tener
data/lists/wrongly_identified_speakers.txt
+ 165
− 41
View file @ effb699f
also check for council:
-----------------------
1925/20029870 and several more: Baumann, Berichterstatter --> not uniquely identified but there is only one SR Baumann
1925/20029937: Schneider, Berichterstatter --> NR, not SR
one MP not active in whole year, leads to other not uniquely identified
-----------------------------------------------------------------------
1925/20029860ff: Keller-Aargau (in March, there is only one Keller-Aargau, in June, another one joins --> finds two!)
1925/20029967: Seiler (in December, the second Seiler already left) --> finds two!)
1925/20029967: Huber (in December, the second Huber already left) --> finds two!)
1925/20029882: Naine (in June, there is only one Naine, in December, another one joins --> finds two!) also in ...96, ...97, etc.
identified as speech start but is in text:
speaker not identifiable:
-------------------------
1891/20026455: Dufour (CANTON MISSING) [1420, 1421] 1891-06-22 15:00 7 twice in same document
1891/20026465: Zweifel one time not identified --> is it a different one (not the Landammann) or was he already mentioned before?
1925/20029836,37,87: Seiler (CANTON MISSING) Berichterstatter [4810, 4815] 1925-03-28 00:00 9
1925/20029943: Welti (CANTON MISSING) [5655, 5656] 1925-09-29 00:00 6
1971/20000592: ['M', 'Simon', 'Kohler', 'rassorteur', 'de', 'la', 'majorité'] 7
1951/20034994: found a name: Studer ['Studer'] 0 Studer (CANTON MISSING) [5130, 5141]
found a name: Kunz ['Kunz'] 0 Kunz (CANTON MISSING) [3017, 3019]
1951/20034996: found a name: Studer ['Studer'] 0 Studer (CANTON MISSING) [5130, 5141]
1951/20035991: Dietschi (CANTON MISSING) Berichterstatter [1350, 1351] 1951-10-02 00:00 9 ['Dietschi', 'Berichterstatter']
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']
1952/20035320: Bühler (CANTON MISSING) reporter [811, 816] 1952-09-17 00:00 7 ['Bühler', 'Berichterstatter']
1952/20035322: Albrecht (CANTON MISSING) reporter [76, 78] 1952-09-17 00:00 2 ['Albrecht', 'Berichterstatter']
1948/20034218: Bringolf (CANTON MISSING) [707, 706] 1948-03-11 00:00 2 ['Bringolf']
1948/20034315: Roth (CANTON MISSING) [4354, 4364] 1948-09-23 00:00 9 ['Rot']
1948/20034328,29: Bucher (CANTON MISSING) [778, 779] 1948-10-07 00:00 1 ['Bucher'] (there is an Antrag Bucher-Zürich)
1944/20033495: Perrin (CANTON MISSING) reporter majority [3935, 3939] 1944-03-21 00:00 24 ['Perrin', 'rapporteur', 'majorité']
1944/20033504,28: Schnyder (CANTON MISSING) [4712, 4716] 1944-03-29 00:00 19 ['Schnyder']
1936/20031982: Bossi (CANTON MISSING) [632, 634] 1936-01-07 00:00 26 ['Bossi']
1936/2003198x: Keller, Berichterstatter
1936/20032003: Widmer (CANTON MISSING) [5696, 5703] 1936-01-22 00:00 0 ['Widmer']
1936/20032132: Huber (CANTON MISSING) [2591, 2599] 1936-09-23 00:00 9 ['Huber']
1936/20032149: Odermatt (CANTON MISSING) [3818, 3819] 1936-10-06 00:00 10 ['Odermatt']
speaker not uniquely identified when he spoke the second time:
--------------------------------------------------------------
1925/20029924: Keller-Aargau Berichterstatter (first time), Keller Berichterstatter (after)
1925/20029928,29: Keller Berichterstatter (also first time), maybe check title of document...
1951/20034982: Perrin-Corcelles rapporteur (first time), after: found a name: M. Pétrin, rapporteur ['Pétrin', 'rapporteur'] 0 Perrin (CANTON MISSING) rapporteur [3935, 3939]
1951/20034995: after: Kunz (CANTON MISSING) [3017, 3019] 1951-04-03 00:00 21 ['Kunz']
1951/20034996: Studer
1931/20031095: Pfister (CANTON MISSING) Berichterstatter [3980, 3981, 3984] 1931-12-10 00:00 3 ['Pf', 'ister', 'Berichterstatter']
1921/20029087: Müller (CANTON MISSING) [3663, 3695] 1921-01-20 00:00 6 ['Müller']
1952/20025282,5330: Dietschi (CANTON MISSING) reporter majority [1350, 1351] 1952-06-18 00:00 19 ['Dietschi', 'Berichterstatter', 'Mehrheit']
1940/20033001: Keller (CANTON MISSING) reporter majority [2868, 2871, 2890] 1940-03-27 00:00 16 ['Keller', 'Berichterstatter', 'Mehrheit']
identifier is split into two words --> partly solved by adding more additional info columns to csv
----------------------------------
1971/20000498: ['M', 'Muf', 'ny', 'rapporteur', 'de', 'la', 'majorité'] 7 --> finds Muff but is Mugny
1936/20031984: Keller (CANTON MISSING) reporter majority [2868, 2871, 2890] 1936-01-08 00:00 10 ['Keller', 'Aar', 'Berichterstatter', 'Mehrheit'] Aarau split in Aar au
identified as speech start but is in text: --> some of these might be solved by only looking at list_oi with less than 9 elements
------------------------------------------
do I really need to look on the first two lines? maybe one is sufficient?
look for typical terms such as gestellt, gesagt, etc.
1891/20026455: Ein weiterer Antrag ist derjenige des Hrn. Dufour. Herr Dufour hat den Antrag gestellt:
1891/20026465: Wir haben nun aber, dem Gedankengang des Hrn. Bühler folgend, die Erklärung gewählt:
1891/20026489: Um jeden Zweifel zu heben, beantrage ich Ihnen folgende Redaktion des Art. 2 :
1894/20026607: Müller gegenüber drei anderen durchgedrungen, welche lautete:
1925/20029903: Nun hat Herr Nationalrat Huber schon am 5. De-zember 1924 folgende Kleine Anfrage gestellt:
1925/20029863: ganz gut gehen. Es ist ja wahr, was Herr Brügger gesagt hat: --> finds Lanz and Brügger
1925/20029917: Mögen Sie nun aber denken wie Herr Oberst Brügger oder mögen Sie denken wie ich: --> identified as speech start but is in text
1925/20029917: Herr Hauser sagt:
1925/20029978: Das ist, was Herr Charles Naine gesagt hat. Herr Hugglersagt:
1925/20029978: Das ist, was Herr Charles Naine gesagt hat. Herr Hugglersagt: and a second time in the same document with Naine
1925/20029981: Brügger möchte ich sagen:
1971/20000663: de MM. Knüsel et Leu (there must be more speech starts, this is from a list of cantons and people inside a speech, !!! Layout)
1971/20000007: La seconde réaction qu'a suscité chez moi l'intervention de M. Weber est le doute:
1971/20000007: Herr Kollega Gut hat es gesagt:
1971/20000007: Noch eine Antwort an Kollege Clottu
1971/20000010: Nun noch etwas zu Richard Müller. Erstens
1971/20000010,11: Nun noch etwas zu Richard Müller. Erstens
1971/20000024: Noch ein Wort zu Herrn Ständerat Wenk
1971/20000024: Herr Kollege Heimann stellt sich schliesslich gegen einen Finanzausgleich mit dem Hinweis
1971/20000093: Meine erste Frage an den Bundesrat lautet
1971/20000093: found a name: In zwei wesentlichen Punkten bin ich mit Herrn Kollega Biel absolut einverstanden ['zwei', 'wesentlichen', 'Punkten', 'Kollega', 'Biel', 'absolut', 'einverstanden'] 1 Biel Walter (Zürich ZH) [426]
1971/20000614: Zu Herrn Fischer
1951/20035112: Schmid (CANTON MISSING) [4639, 4646, 4660] 1951-09-26 00:00 27 ['Antrag', 'Schmid']
1932/20031152: Je comprends M. Bossi Bossi (CANTON MISSING) [632, 634] 1932-03-16 00:00 13 ['comprends', 'Bossi']
wrongly spelled city
--------------------
1925/20029963: Jenny Ennend (instead of Ennenda)
1925/20029995,96: Keller Zurich (instead of Zürich)
1971/? : Berne instead of Bern
list of people in a minority are recognized as speech starts:
-------------------------------------------------------------
1936/20031980,85,many more: Schmid (CANTON MISSING) [4639, 4660, 4672] 1936-01-06 00:00 0 ['Schmid', 'Schneider']
Schmid (CANTON MISSING) [4639, 4660, 4672] 1936-01-06 00:00 0 ['Schmid', 'Soleure', 'Schneider']
1936/20031990: many, e.g. Widmer (CANTON MISSING) [5696, 5703] 1936-01-14 00:00 0 ['Walter', 'Olten', 'Widmer', 'Rossi']
misspelled role:
----------------
1936/20031986: Meyer (CANTON MISSING) [3482, 3483, 3488, 3490] 1936-01-09 00:00 14 ['Rundespräsident', 'Meyer'] ---> solved
1936/20031992: Meyer (CANTON MISSING) [3482, 3483, 3488, 3490] 1936-01-15 00:00 10 ['ßundespräsident', 'Meyer']
1932/20031299: Häberlin (CANTON MISSING) [2290, 2287] 1932-09-21 00:00 6 ['Bimdesrat', 'Häberlin'] --> solved
doubled double names:
weird layout:
-------------
1971/20000663: de MM. Knüsel et Leu (there must be more speech starts, this is from a list of cantons and people inside a speech, !!! Layout)
bad OCR:
--------
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
1952/20035242, and some others: reporter [] 1952-03-25 00:00 9 ['Spanier', 'Berichterstatter'] --> Spühler not found
1948/20034315: reporter [] 1948-09-23 00:00 5 ['Statili', 'Berichterstatter'] --> Stähli not found
1936/20032015: reporter majority [] 1936-01-30 00:00 2 ['Statili', 'Berichterstatter', 'Mehrheit'] --> Stähli not found
1936/20032189: page 4 ['Bundesrat', 'Bautltann'] 1936-12-17 00:00 --> Baumann not found
1936/20031985: page 1 ['DollîUS', 'rapporteur'] 1936-01-09 00:00 --> Dollfus not found
not sure about place:
---------------------
1971/20000010: Meyer-Boller
1921/20029090: Seiler (CANTON MISSING) [4810, 4815] 1921-02-24 00:00 5 ['Seiler', 'Sitten'] found no connection between Seiler Hermann and Sitten
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
1921/20029145: Seiler (CANTON MISSING) [4810, 4815] 1921-04-13 00:00 10 ['Nationalrat', 'Speiser', 'sagte'] finds Seiler for Speiser
term is a name
--------------
1891/20026489: Um jeden Zweifel zu heben, beantrage ich Ihnen folgende Redaktion des Art. 2 --> finds Zweifel
1971/20000010: Ganz wenige Einzelfragen --> finds Ganz
1971/20000024: Politisch gesehen ist es doch ganz einfach so --> finds Ganz
French name with special characters
-----------------------------------
1971/20000055: Debétaz
person has been elected but not yet officially started (presumably):
------------------------------------------------------------------
1971/20000587: Tanner Paul starts officiall on 29.11.71, discussion is on 30.11.71 --> finds two!
1971/20000588: one Kohler starts 29.11.71, discussion is on 30.11.71 --> finds two!
1971/20000726: one Muheim starts 29.11.71, discussion is on 8.12.71 --> finds two!
1921/20029265: one Huber starts 5.12.21, discussion is on 6.12.21 --> finds two
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
---------------------------------------------------
1951/20034993: Eggenberger Grabs
Appenzeller
......@@ -72,7 +142,61 @@ Appenzeller
1894/20026618: Sonderegger
some other persons wrongly identified as MP
-------------------------------------------
1925/20029833: Sauser-Hall (not a MP)--> Hauser
1941/20033145: Prof. Böhler erklärt --> finds Bühler
======================================================================================
solved: also check for council:
-----------------------
1925/20029870 and several more: Baumann, Berichterstatter --> not uniquely identified but there is only one SR Baumann --> solved!
1925/20029937: Schneider, Berichterstatter --> NR, not SR --> solved!
solved: one MP not active in whole year, leads to other not uniquely identified
-----------------------------------------------------------------------
1925/20029860ff: Keller-Aargau (in March, there is only one Keller-Aargau, in June, another one joins --> finds two!) --> solved!
1925/20029967: Seiler (in December, the second Seiler already left) --> finds two!) --> solved!
1925/20029967: Huber (in December, the second Huber already left) --> finds two!) --> solved because only NR!
1925/20029882: Naine (in June, there is only one Naine, in December, another one joins --> finds two!) also in ...96, ...97, etc. --> solved!
solved: doubled double names:
---------------------
1971/20000010: Meyer-Boller --> solved!
solved: wrongly spelled city
--------------------
1925/20029963: Jenny Ennend (instead of Ennenda) --> solved!
1925/20029995,96: Keller Zurich (instead of Zürich) --> solved!
1971/? : Berne instead of Bern --> solved with using get_approximate_term for cantons
solved: Bundesrat not found:
--------------------
1951/20035017,26: Petitpierre (CANTON MISSING) [3955, 3956] 1951-04-03 00:00 8 ['Petitpierre', 'conseiller', 'fédéral'] --> solved!
1951/20035018,20,77,83: Rubattel (CANTON MISSING) [4381, 4382] 1951-04-03 00:00 6 ['Rubattel', 'conseiller', 'fédéral'] --> solved!
1931/20031089: Meyer (CANTON MISSING) Bundesrat [3482, 3483, 3490, 3495] 1931-12-08 00:00 1 ['Meyer', 'Bundesrat'] --> solved!
1931/20030968: Häberlin (CANTON MISSING) [2290, 2287] 1931-03-24 00:00 6 ['Bundespräsident', 'Häberlin'] --> solved!
1911/20027998: Forrer (CANTON MISSING) Bundesrat [1771, 1773] 1911-03-30 09:00 2 ['Bundesrat', 'Forrer'] --> solved
1911/20028039: Müller (CANTON MISSING) Bundesrat [3642, 3653, 3663, 3683] 1911-10-05 08:30 11 ['Bundesrat', 'Müller'] --> solved!
solved: wrong entries in xlsx:
----------------------
1931/20030940,49: Scherer (CANTON MISSING) [4560, 4565] 1931-03-18 00:00 18 ['Scherer'] --> there are two entries for one person
1971/20000055: Debétaz, was not there as a NR
solved: identifier is split into two words
----------------------------------
1925/20029945, 1951/20035173: found a name: Schmid-Oberentf elden ['Schmid', 'Oberentf', 'elden'] 0 Schmid (CANTON MISSING) [4639, 4660]
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', 'àtei', 'rapporteur']
1936/20031998: Stähli (CANTON MISSING) [4967, 4964] 1936-01-17 00:00 13 ['Stähli', 'Sieb', 'nen']
1936/20032015: Müller (CANTON MISSING) [3638, 3645, 3652, 3654, 3658, 3659, 3662] 1936-01-30 00:00 6 ['Müller', 'Grosshöchste', 'tten']
data/politicians/MPs_additionalInfo.csv 0 → 100644
+ 68
− 0
View file @ effb699f
LastName,FirstName,CantonAbbreviation,Additional,Additional2,Additional3
Berger,Claude,NE,Neuchâtel,Neuch,
Blumer,Johannes,SG,Egloff,,
Bossi,Bixio,TI,Lugano,,
Bossi,Johann,GR,Chur,,
Bratschi,Peter,BE,Matten,,
Bringolf,Walther,SH,Schaff,,
Bringolf,Richard,VD,Peilz,,
Bühler,René,SG,Uzwil,,
Bühler,Peter Theophil,GR,Bünden,,
Bühler,Rolf Theodor,SG,Uzwil,,
Cottier,Henry,VD,Lausanne,,
Cottier,Fernand,GE,Genève,,
Cramer,Konrad H.,ZH,Frey,,
Eggenberger,Matthias,SG,Niederuzwil,,
Eugster,Howard,AR,Züst,,
Fischer,Hanspeter,TG,Weinfelden,,
Gfeller,Hans,BE,Oppligen,,
Gfeller,Arnold,BS,Basel,,
Hofer,Walther,BE,Flawil,,
Jenny,Johann,BE,Worblaufen,,
Jordan,Adolphe,VD,Martin,,
Kunz,Alois,LU,Hergiswil,,
Kunz,Paul,BE,Thun,,
König,Walter,BE,Biel,,
Meier,Christian,GL,Netstal,,
Meier,Ernst,AG,Baden,,
Moser,Arthur,SH,Schaff,,
Müller,Alfred,TG,Amriswil,,
Müller,Hans Gottfried,BE,Aarberg,Aarb,
Müller,Hans,BE,Grosshöchstetten,höchstetten,Grosshöchste
Müller,Alban,SO,Olten,,
Müller,Emil,BL,Baselland,,
Müller,Johannes,SG,Gallen,,
Naine,Charles-Théophile,VD,Préverenges,,
Naine,Charles-Théophile,NE,Préverenges,,
Odermatt,Gottfried,NW,Ennetbürgen,,
Perrin,Tell,NE,Chaux,,
Perrin,Paul,VD,Corcelles,,
Pfister,Bruno,SG,Gallen,,
Pfister,Eduard,TG,Frauenfeld,,
Roth,August,TG,Frauenfeld,Arbon,
Roth,Hans,BE,Interlaken,,
Rusca,Giovan-Battista,TI,Locarno,,
Schirmer,L. August,SG,Gallen,,
Schirmer,August,AG,Baden,,
Schmid,Jakob,LU,Ronca,,
Schmid,Arthur,AG,Oberentfelden,Oberentf,entfelden
Schmid,Jacques,SO,Olten,,
Schmid,Ernst,BE,Dieterswil,,
Schmid-Ruedin,Philipp,ZH,Philip,,
Seiler,Hermann,VS,Zermatt,,
Sigg,Jean-C.,GE,Genève,,
Sonderegger,Johann Jakob,AR,Ausserrhoden,,
Sonderegger,Karl Justin,IR,Innerrhoden,,
Stähli,Fritz,SZ,Siebnen,Sieb,
Steiner,Ferdinand,LU,Malters,,
Studer,Ernst,BE,Burgdorf,,
Sulzer,Eduard,ZH,Ziegler,,
Suter,Johannes,BL,Baselland,,
von Moos,Ludwig,OW,MOOS,,
Weber,Rolf,TG,Arbon,,
Weber,Jakob Rudolf,BE,Grasswil,,
Weber,Heinrich Otto,SG,Gallen,,
Welti,Franz,BS,Basel,,
Welti,Adolf,AG,Rheinfelden,,
Zweifel,Esaja,GL,Landammann,,
Zweifel,Peter,GL,Regierungsrath,,
data/politicians/MPs_after1890.csv LFS
+ 3
− 4077
View file @ effb699f
This diff is collapsed.
data/politicians/Ratsmitglieder_1848_DE_corr.xlsx
+ 0
− 0
View file @ effb699f
No preview for this file type
data/politicians/lastnames/1891_MPs.pickle 0 → 100644 LFS
+ 3
− 0
View file @ effb699f
File added
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment

This GitLab is a part of renkulab.io