stephbuon/hansard-speakers
A data processing pipeline to disambiguate speakers in the 19th-century British Parliamentary debates.
PythonMIT
Issues
- 0
- 0
- 0
Fill In Numbers for Article
#189 opened - 0
- 0
- 0
go over rest of names with sir
#186 opened - 0
Fix the top errorful fuzzy_matched speakers
#185 opened - 1
- 0
Algorithm is ignoring less rows -- why?
#183 opened - 0
Fix Sample Numbers
#182 opened - 4
Debug Fuzzy Match: Mr. C. ANSTEY
#181 opened - 0
Aren't these fixed with edit distance?
#180 opened - 0
Ask about punctuation in ignored files
#179 opened - 0
- 0
ask about these
#177 opened - 1
Reopen these files:
#176 opened - 0
New folder: hansard speakers
#175 opened - 3
Data expansion guidelines
#174 opened - 1
Fix the peerage titles spreadsheet
#173 opened - 0
- 0
ask about chancellor of the exchqeque
#171 opened - 1
make data sets pretty
#170 opened - 0
names
#169 opened - 1
make sure non-mps say non_mp in cell
#168 opened - 3
Speaker Name Output
#167 opened - 0
- 3
speakers_terms
#165 opened - 0
Change col names
#164 opened - 0
Fix Office Holdings CSV
#163 opened - 0
Evaluate the Addition of "Lord"
#162 opened - 0
Fix Dates in Incorrect Order
#161 opened - 0
download military-titles
#160 opened - 0
check member id
#159 opened - 0
peerage titles -- many dates are backwards
#158 opened - 1
Add Lord as an alternative to Mr
#157 opened - 0
why are speakers and speakers terms separate?
#156 opened - 0
ask about added speakers
#155 opened - 0
in hansard speakers get rid of dob dod?
#154 opened - 2
Edit the speakers_terms CSV File
#153 opened - 1
- 0
- 0
fix office numbers
#150 opened - 0
Ive renamed member_id to correponding_id
#149 opened - 2
do we need "alias_type"
#148 opened - 0
office holdings has "oh_id" what is that?
#147 opened - 1
Do we need hansard_titles.csv?
#146 opened - 0
download make sure
#145 opened - 0
results for fuzzy match office titles
#144 opened - 1
Consider middle names after all
#143 opened - 0
Lets keep the office holdings csv
#142 opened