Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
D
dh-stuff
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Henrik Schönemann
dh-stuff
Commits
b77c9c13
Commit
b77c9c13
authored
3 months ago
by
Schoeneh
Browse files
Options
Downloads
Patches
Plain Diff
fixed download
parent
474e421c
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
ue-llms/gensim_Spiegel.ipynb
+198
-2
198 additions, 2 deletions
ue-llms/gensim_Spiegel.ipynb
with
198 additions
and
2 deletions
ue-llms/gensim_Spiegel.ipynb
+
198
−
2
View file @
b77c9c13
...
...
@@ -10,7 +10,7 @@
},
{
"cell_type": "code",
"execution_count":
2
,
"execution_count":
null
,
"metadata": {},
"outputs": [
{
...
...
@@ -37,7 +37,7 @@
" with open(f'{file}.zip', 'wb') as fd:\n",
" for chunk in r.iter_content(chunk_size=128):\n",
" fd.write(chunk)\n",
"
print(\"File downloaded\")\n",
" print(\"File downloaded\")\n",
"else: print(\"File already downloaded.\")\n",
"\n",
"\n",
...
...
@@ -176,6 +176,202 @@
"source": [
"spiegel_fasttext.wv.most_similar(\"Trump\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('buchenwald', 0.8792651891708374),\n",
" ('dachau', 0.8258079290390015),\n",
" ('auschwitz', 0.8050574064254761),\n",
" ('mauthausen', 0.7775819897651672),\n",
" ('sachsenhausen', 0.765381395816803),\n",
" ('buchenwalder', 0.7609554529190063),\n",
" ('theresienstadt', 0.754604697227478),\n",
" ('häftlinge', 0.7309788465499878),\n",
" ('häftling', 0.7256706357002258),\n",
" ('gaskammern', 0.7118412256240845),\n",
" ('ns', 0.697554349899292),\n",
" ('nazi', 0.6951879858970642),\n",
" ('häftlings', 0.6949462890625),\n",
" ('auschwitzer', 0.6874114274978638),\n",
" ('lagerkommandant', 0.6857143044471741),\n",
" ('treblinka', 0.6774755120277405),\n",
" ('nazis', 0.6764761209487915),\n",
" ('ss', 0.6742820739746094),\n",
" ('zwangsarbeiter', 0.6706141233444214),\n",
" ('mitgefangene', 0.6703796982765198),\n",
" ('natzweiler', 0.6701797246932983),\n",
" ('häftlingsarzt', 0.6700323820114136),\n",
" ('gestapo', 0.6683216094970703),\n",
" ('gaskammer', 0.666691243648529),\n",
" ('häftlingen', 0.6666845679283142),\n",
" ('neuengamme', 0.665062665939331),\n",
" ('flossenbürg', 0.6631953120231628),\n",
" ('halbjuden', 0.6626685857772827),\n",
" ('ravensbrück', 0.6606388688087463),\n",
" ('euthanasie', 0.6560691595077515)]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"spiegel_fasttext.wv.most_similar(\"kz\", topn=30)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('suezkanal', 0.8312360644340515),\n",
" ('suezkanals', 0.7922067642211914),\n",
" ('akaba', 0.709147572517395),\n",
" ('said', 0.698356032371521),\n",
" ('anglo', 0.696181058883667),\n",
" ('ismailia', 0.6857931613922119),\n",
" ('kanals', 0.6778820157051086),\n",
" ('abadan', 0.6718226671218872),\n",
" ('israelisch', 0.6687085628509521),\n",
" ('ägyptisch', 0.6670056581497192),\n",
" ('ägypten', 0.6517369151115417),\n",
" ('nahost', 0.6489949822425842),\n",
" ('ägyptens', 0.6461713910102844),\n",
" ('biserta', 0.6436704993247986),\n",
" ('nassers', 0.6390738487243652),\n",
" ('kanal', 0.6378217339515686),\n",
" ('transarabische', 0.6368891000747681),\n",
" ('britisch', 0.6345162391662598),\n",
" ('jordanien', 0.6323387622833252),\n",
" ('arabien', 0.6312205195426941),\n",
" ('jordaniens', 0.6304064989089966),\n",
" ('sinai', 0.6302697658538818),\n",
" ('libanon', 0.6274277567863464),\n",
" ('nasser', 0.6264342069625854),\n",
" ('tiran', 0.6263170838356018),\n",
" ('sudan', 0.623646080493927),\n",
" ('irak', 0.6217209696769714),\n",
" ('port', 0.621683657169342),\n",
" ('transjordaniens', 0.6210361123085022),\n",
" ('aden', 0.6208665370941162)]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"spiegel_fasttext.wv.most_similar(\"suez\", topn=30)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('ostafrikaner', 0.8676508069038391),\n",
" ('ostafrikas', 0.842673659324646),\n",
" ('ostafrikanische', 0.8248769640922546),\n",
" ('westafrika', 0.8198734521865845),\n",
" ('kenia', 0.8148528337478638),\n",
" ('afrika', 0.7896697521209717),\n",
" ('tanganjika', 0.7732571363449097),\n",
" ('tansania', 0.7536317706108093),\n",
" ('nigeria', 0.7515606880187988),\n",
" ('westafrikas', 0.7401487231254578),\n",
" ('togo', 0.7241421937942505),\n",
" ('kamerun', 0.7232619524002075),\n",
" ('uganda', 0.722804069519043),\n",
" ('ghana', 0.7129299640655518),\n",
" ('guinea', 0.7060198783874512),\n",
" ('nyassaland', 0.7059506773948669),\n",
" ('kolonie', 0.7057479023933411),\n",
" ('sambia', 0.7054694890975952),\n",
" ('südafrika', 0.696257472038269),\n",
" ('sudan', 0.6920241117477417),\n",
" ('niger', 0.6908750534057617),\n",
" ('safari', 0.689552366733551),\n",
" ('niederländisch', 0.6891322731971741),\n",
" ('afrikas', 0.6875596642494202),\n",
" ('südwestafrikas', 0.6868376731872559),\n",
" ('senegal', 0.6863754391670227),\n",
" ('daressalam', 0.6860796213150024),\n",
" ('afrikanischen', 0.6859438419342041),\n",
" ('indien', 0.6857169270515442),\n",
" ('äthiopien', 0.6830366253852844)]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"spiegel_fasttext.wv.most_similar(\"ostafrika\", topn=30)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('volkspolens', 0.9186643362045288),\n",
" ('volkspolnischen', 0.8382866978645325),\n",
" ('westpolen', 0.6901859641075134),\n",
" ('gomulkas', 0.6826123595237732),\n",
" ('gomulka', 0.6729230284690857),\n",
" ('polens', 0.6660183072090149),\n",
" ('ostdeutschland', 0.6637937426567078),\n",
" ('sed', 0.6632714867591858),\n",
" ('sowjetzone', 0.6624323725700378),\n",
" ('ostdeutschlands', 0.6607036590576172),\n",
" ('vorkriegspolen', 0.6591367125511169),\n",
" ('ostdeutsch', 0.6585639715194702),\n",
" ('warschau', 0.6509412527084351),\n",
" ('ulbrichts', 0.6508803963661194),\n",
" ('cyrankiewicz', 0.6478868126869202),\n",
" ('ddr', 0.645229160785675),\n",
" ('ostdeutschen', 0.6429562568664551),\n",
" ('ostberlin', 0.6405128836631775),\n",
" ('ulbricht', 0.6396167278289795),\n",
" ('ostpolnischen', 0.6330234408378601),\n",
" ('honecker', 0.632041335105896),\n",
" ('polen', 0.6277611255645752),\n",
" ('rumänien', 0.624265193939209),\n",
" ('gierek', 0.6231211423873901),\n",
" ('ostpolen', 0.6198691129684448),\n",
" ('cssr', 0.6192417144775391),\n",
" ('prag', 0.6176929473876953),\n",
" ('komsomolzen', 0.6167832612991333),\n",
" ('bulgarien', 0.6152984499931335),\n",
" ('ostdeutsche', 0.6143065690994263)]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"spiegel_fasttext.wv.most_similar(\"volkspolen\", topn=30)"
]
}
],
"metadata": {
...
...
%% Cell type:markdown id: tags:
# Testing gensim
See https://radimrehurek.com/gensim/
%% Cell type:code id: tags:
```
python
import
gensim
import
requests
,
zipfile
,
io
,
os
from
os.path
import
exists
# Downloading data & reading csv as pandas DataFrame
file
=
'
spiegel_1948-1979_embeddings_fasttext_50epochs_2
'
link
=
'
https://box.hu-berlin.de/f/19c5aa45779a461499d0/?dl=1
'
model
=
'
fasttext_model_spiegel_corpus_neu_50epochs_2
'
if
exists
(
f
'
{
file
}
.zip
'
)
==
False
:
r
=
requests
.
get
(
link
,
stream
=
True
)
with
open
(
f
'
{
file
}
.zip
'
,
'
wb
'
)
as
fd
:
for
chunk
in
r
.
iter_content
(
chunk_size
=
128
):
fd
.
write
(
chunk
)
print
(
"
File downloaded
"
)
print
(
"
File downloaded
"
)
else
:
print
(
"
File already downloaded.
"
)
if
exists
(
f
'
./
{
file
}
'
)
==
False
:
os
.
mkdir
(
f
'
./
{
file
}
'
)
with
zipfile
.
ZipFile
(
f
'
{
file
}
.zip
'
)
as
zf
:
zf
.
extractall
(
path
=
f
'
./
{
file
}
'
)
print
(
"
File unzipped.
"
)
else
:
print
(
"
File already unzipped.
"
)
```
%% Output
File already downloaded.
File already unzipped.
%% Cell type:code id: tags:
```
python
spiegel_fasttext
=
gensim
.
models
.
FastText
.
load
(
f
'
/
{
file
}
/
{
model
}
.model
'
)
#spiegel_1948-1979_embeddings_fasttext_50epochs_2
#ue-llms\spiegel_1948-1979_embeddings_fasttext_50epochs_2\fasttext_model_spiegel_corpus_neu_50epochs_2.model
#ue-llms\spiegel_1948-1979_embeddings_fasttext_50epochs_2\fasttext_model_spiegel_corpus_neu_50epochs_2.model
```
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
Kolonie
"
)
```
%% Output
[('kolonie', 0.7393254637718201),
('exkolonie', 0.6531060338020325),
('kolonialreiche', 0.652650773525238),
('kolonien', 0.6513134837150574),
('musterkolonie', 0.6470878720283508),
('kolonialreiches', 0.6406031250953674),
('nachbarprovinz', 0.6389856338500977),
('kolonialreichs', 0.6318897008895874),
('kolonialreich', 0.6315282583236694),
('ferienkolonie', 0.6258662343025208)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
Kolonialismus
"
)
```
%% Output
[('kolonialismus', 0.9018982648849487),
('kolonialist', 0.8311547040939331),
('kolonialisten', 0.7932776212692261),
('nachkolonialen', 0.7744893431663513),
('antikolonialen', 0.7676698565483093),
('kolonialpolitik', 0.7602006793022156),
('nachkoloniale', 0.7534233331680298),
('nationalismus', 0.7524922490119934),
('kolonialen', 0.7517328858375549),
('antikoloniale', 0.7438010573387146)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
nazi
"
)
```
%% Output
[('nazis', 0.8403863310813904),
('ns', 0.8173379898071289),
('nazistischer', 0.7557086944580078),
('nazistischen', 0.750986635684967),
('nazistische', 0.7342256903648376),
('nazistisch', 0.726861298084259),
('großdeutscher', 0.7023860216140747),
('nazismus', 0.7022897601127625),
('antisemitischer', 0.696376383304596),
('kz', 0.6951879262924194)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
Trump
"
)
```
%% Output
[('krump', 0.735675036907196),
('registrier', 0.5744073987007141),
('neuerkrankungen', 0.57392418384552),
('gemeldete', 0.5610890984535217),
('pressebericht', 0.5544757843017578),
('verlustanzeige', 0.5432375073432922),
('anmeldungen', 0.5428926348686218),
('aufgeflogene', 0.5423745512962341),
('alarmnachricht', 0.5374037623405457),
('alarmierende', 0.5313758254051208)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
kz
"
,
topn
=
30
)
```
%% Output
[('buchenwald', 0.8792651891708374),
('dachau', 0.8258079290390015),
('auschwitz', 0.8050574064254761),
('mauthausen', 0.7775819897651672),
('sachsenhausen', 0.765381395816803),
('buchenwalder', 0.7609554529190063),
('theresienstadt', 0.754604697227478),
('häftlinge', 0.7309788465499878),
('häftling', 0.7256706357002258),
('gaskammern', 0.7118412256240845),
('ns', 0.697554349899292),
('nazi', 0.6951879858970642),
('häftlings', 0.6949462890625),
('auschwitzer', 0.6874114274978638),
('lagerkommandant', 0.6857143044471741),
('treblinka', 0.6774755120277405),
('nazis', 0.6764761209487915),
('ss', 0.6742820739746094),
('zwangsarbeiter', 0.6706141233444214),
('mitgefangene', 0.6703796982765198),
('natzweiler', 0.6701797246932983),
('häftlingsarzt', 0.6700323820114136),
('gestapo', 0.6683216094970703),
('gaskammer', 0.666691243648529),
('häftlingen', 0.6666845679283142),
('neuengamme', 0.665062665939331),
('flossenbürg', 0.6631953120231628),
('halbjuden', 0.6626685857772827),
('ravensbrück', 0.6606388688087463),
('euthanasie', 0.6560691595077515)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
suez
"
,
topn
=
30
)
```
%% Output
[('suezkanal', 0.8312360644340515),
('suezkanals', 0.7922067642211914),
('akaba', 0.709147572517395),
('said', 0.698356032371521),
('anglo', 0.696181058883667),
('ismailia', 0.6857931613922119),
('kanals', 0.6778820157051086),
('abadan', 0.6718226671218872),
('israelisch', 0.6687085628509521),
('ägyptisch', 0.6670056581497192),
('ägypten', 0.6517369151115417),
('nahost', 0.6489949822425842),
('ägyptens', 0.6461713910102844),
('biserta', 0.6436704993247986),
('nassers', 0.6390738487243652),
('kanal', 0.6378217339515686),
('transarabische', 0.6368891000747681),
('britisch', 0.6345162391662598),
('jordanien', 0.6323387622833252),
('arabien', 0.6312205195426941),
('jordaniens', 0.6304064989089966),
('sinai', 0.6302697658538818),
('libanon', 0.6274277567863464),
('nasser', 0.6264342069625854),
('tiran', 0.6263170838356018),
('sudan', 0.623646080493927),
('irak', 0.6217209696769714),
('port', 0.621683657169342),
('transjordaniens', 0.6210361123085022),
('aden', 0.6208665370941162)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
ostafrika
"
,
topn
=
30
)
```
%% Output
[('ostafrikaner', 0.8676508069038391),
('ostafrikas', 0.842673659324646),
('ostafrikanische', 0.8248769640922546),
('westafrika', 0.8198734521865845),
('kenia', 0.8148528337478638),
('afrika', 0.7896697521209717),
('tanganjika', 0.7732571363449097),
('tansania', 0.7536317706108093),
('nigeria', 0.7515606880187988),
('westafrikas', 0.7401487231254578),
('togo', 0.7241421937942505),
('kamerun', 0.7232619524002075),
('uganda', 0.722804069519043),
('ghana', 0.7129299640655518),
('guinea', 0.7060198783874512),
('nyassaland', 0.7059506773948669),
('kolonie', 0.7057479023933411),
('sambia', 0.7054694890975952),
('südafrika', 0.696257472038269),
('sudan', 0.6920241117477417),
('niger', 0.6908750534057617),
('safari', 0.689552366733551),
('niederländisch', 0.6891322731971741),
('afrikas', 0.6875596642494202),
('südwestafrikas', 0.6868376731872559),
('senegal', 0.6863754391670227),
('daressalam', 0.6860796213150024),
('afrikanischen', 0.6859438419342041),
('indien', 0.6857169270515442),
('äthiopien', 0.6830366253852844)]
%% Cell type:code id: tags:
```
python
spiegel_fasttext
.
wv
.
most_similar
(
"
volkspolen
"
,
topn
=
30
)
```
%% Output
[('volkspolens', 0.9186643362045288),
('volkspolnischen', 0.8382866978645325),
('westpolen', 0.6901859641075134),
('gomulkas', 0.6826123595237732),
('gomulka', 0.6729230284690857),
('polens', 0.6660183072090149),
('ostdeutschland', 0.6637937426567078),
('sed', 0.6632714867591858),
('sowjetzone', 0.6624323725700378),
('ostdeutschlands', 0.6607036590576172),
('vorkriegspolen', 0.6591367125511169),
('ostdeutsch', 0.6585639715194702),
('warschau', 0.6509412527084351),
('ulbrichts', 0.6508803963661194),
('cyrankiewicz', 0.6478868126869202),
('ddr', 0.645229160785675),
('ostdeutschen', 0.6429562568664551),
('ostberlin', 0.6405128836631775),
('ulbricht', 0.6396167278289795),
('ostpolnischen', 0.6330234408378601),
('honecker', 0.632041335105896),
('polen', 0.6277611255645752),
('rumänien', 0.624265193939209),
('gierek', 0.6231211423873901),
('ostpolen', 0.6198691129684448),
('cssr', 0.6192417144775391),
('prag', 0.6176929473876953),
('komsomolzen', 0.6167832612991333),
('bulgarien', 0.6152984499931335),
('ostdeutsche', 0.6143065690994263)]
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment