Upload folder using huggingface_hub
Browse files- .dvc/.gitignore +3 -0
- .dvc/config +6 -0
- .dvcignore +3 -0
- .github/workflows/huggingfacehub-sync.yml +31 -0
- .gitignore +2 -0
- LICENSE +121 -0
- README.md +38 -0
- corpora/.gitignore +2 -0
- corpora/finna/.gitignore +1 -0
- corpora/finna/kauno-finna-fin.tsv.gz.dvc +10 -0
- corpora/kauno-skos-reduced.ttl.dvc +11 -0
- corpora/kirjasampo/.gitignore +3 -0
- corpora/kirjasampo/kirjasampo-kauno-test.tsv.dvc +11 -0
- corpora/kirjasampo/kirjasampo-kauno-train.tsv.dvc +11 -0
- corpora/kirjasampo/kirjasampo-kauno-validate.tsv.dvc +11 -0
- data/projects/.gitignore +8 -0
- data/vocabs/.gitignore +1 -0
- dvc.lock +542 -0
- dvc.yaml +76 -0
- projects.d/2-projects-kauno.toml +44 -0
- projects.toml +44 -0
- reports/kauno-fi.json +5 -0
- reports/kauno-finna-bonsai-fi.json +5 -0
- reports/kauno-ks-bonsai-fi.json +5 -0
- reports/kauno-mllm-fi.json +5 -0
- requirements.txt +1 -0
- sync-model-data-ocp.sh +32 -0
.dvc/.gitignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/config.local
|
| 2 |
+
/tmp
|
| 3 |
+
/cache
|
.dvc/config
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[cache]
|
| 2 |
+
dir = /data/dvc-cache/FintoAI-data-KAUNO
|
| 3 |
+
shared = group
|
| 4 |
+
type = symlink
|
| 5 |
+
[core]
|
| 6 |
+
autostage = true
|
.dvcignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Add patterns of files dvc should ignore, which could improve
|
| 2 |
+
# the performance. Learn more at
|
| 3 |
+
# https://dvc.org/doc/user-guide/dvcignore
|
.github/workflows/huggingfacehub-sync.yml
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
name: Sync with Hugging Face Hub
|
| 2 |
+
on:
|
| 3 |
+
#push:
|
| 4 |
+
# branches:
|
| 5 |
+
# - main
|
| 6 |
+
workflow_dispatch
|
| 7 |
+
jobs:
|
| 8 |
+
sync-to-hfhub:
|
| 9 |
+
name: Sync to Hugging Face Hub
|
| 10 |
+
runs-on: ubuntu-latest
|
| 11 |
+
steps:
|
| 12 |
+
- name: Sync to Hugging Face Hub
|
| 13 |
+
uses: juhoinkinen/huggingface-sync-action@v0.0.10
|
| 14 |
+
with:
|
| 15 |
+
# The Hugging Face repo id you want to sync to. (ex. 'username/reponame')
|
| 16 |
+
# A repo with this name will be created if it doesn't exist. Required.
|
| 17 |
+
huggingface_repo_id: 'juhoinkinen/FintoAI-data-KAUNO-3'
|
| 18 |
+
|
| 19 |
+
# Hugging Face token with write access. Required.
|
| 20 |
+
# Here, we provide a token that we called `HF_TOKEN` when we added the secret to our GitHub repo.
|
| 21 |
+
hf_token: ${{ secrets.HF_TOKEN }}
|
| 22 |
+
|
| 23 |
+
# The type of repo you are syncing to: model, dataset, or space.
|
| 24 |
+
# Defaults to space.
|
| 25 |
+
repo_type: 'model'
|
| 26 |
+
|
| 27 |
+
# If true and the Hugging Face repo doesn't already exist, it will be created
|
| 28 |
+
# as a private repo.
|
| 29 |
+
#
|
| 30 |
+
# Note: this param has no effect if the repo already exists.
|
| 31 |
+
private: true
|
.gitignore
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
venv
|
| 2 |
+
venv-installed
|
LICENSE
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Creative Commons Legal Code
|
| 2 |
+
|
| 3 |
+
CC0 1.0 Universal
|
| 4 |
+
|
| 5 |
+
CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
|
| 6 |
+
LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
|
| 7 |
+
ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
|
| 8 |
+
INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
|
| 9 |
+
REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
|
| 10 |
+
PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
|
| 11 |
+
THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
|
| 12 |
+
HEREUNDER.
|
| 13 |
+
|
| 14 |
+
Statement of Purpose
|
| 15 |
+
|
| 16 |
+
The laws of most jurisdictions throughout the world automatically confer
|
| 17 |
+
exclusive Copyright and Related Rights (defined below) upon the creator
|
| 18 |
+
and subsequent owner(s) (each and all, an "owner") of an original work of
|
| 19 |
+
authorship and/or a database (each, a "Work").
|
| 20 |
+
|
| 21 |
+
Certain owners wish to permanently relinquish those rights to a Work for
|
| 22 |
+
the purpose of contributing to a commons of creative, cultural and
|
| 23 |
+
scientific works ("Commons") that the public can reliably and without fear
|
| 24 |
+
of later claims of infringement build upon, modify, incorporate in other
|
| 25 |
+
works, reuse and redistribute as freely as possible in any form whatsoever
|
| 26 |
+
and for any purposes, including without limitation commercial purposes.
|
| 27 |
+
These owners may contribute to the Commons to promote the ideal of a free
|
| 28 |
+
culture and the further production of creative, cultural and scientific
|
| 29 |
+
works, or to gain reputation or greater distribution for their Work in
|
| 30 |
+
part through the use and efforts of others.
|
| 31 |
+
|
| 32 |
+
For these and/or other purposes and motivations, and without any
|
| 33 |
+
expectation of additional consideration or compensation, the person
|
| 34 |
+
associating CC0 with a Work (the "Affirmer"), to the extent that he or she
|
| 35 |
+
is an owner of Copyright and Related Rights in the Work, voluntarily
|
| 36 |
+
elects to apply CC0 to the Work and publicly distribute the Work under its
|
| 37 |
+
terms, with knowledge of his or her Copyright and Related Rights in the
|
| 38 |
+
Work and the meaning and intended legal effect of CC0 on those rights.
|
| 39 |
+
|
| 40 |
+
1. Copyright and Related Rights. A Work made available under CC0 may be
|
| 41 |
+
protected by copyright and related or neighboring rights ("Copyright and
|
| 42 |
+
Related Rights"). Copyright and Related Rights include, but are not
|
| 43 |
+
limited to, the following:
|
| 44 |
+
|
| 45 |
+
i. the right to reproduce, adapt, distribute, perform, display,
|
| 46 |
+
communicate, and translate a Work;
|
| 47 |
+
ii. moral rights retained by the original author(s) and/or performer(s);
|
| 48 |
+
iii. publicity and privacy rights pertaining to a person's image or
|
| 49 |
+
likeness depicted in a Work;
|
| 50 |
+
iv. rights protecting against unfair competition in regards to a Work,
|
| 51 |
+
subject to the limitations in paragraph 4(a), below;
|
| 52 |
+
v. rights protecting the extraction, dissemination, use and reuse of data
|
| 53 |
+
in a Work;
|
| 54 |
+
vi. database rights (such as those arising under Directive 96/9/EC of the
|
| 55 |
+
European Parliament and of the Council of 11 March 1996 on the legal
|
| 56 |
+
protection of databases, and under any national implementation
|
| 57 |
+
thereof, including any amended or successor version of such
|
| 58 |
+
directive); and
|
| 59 |
+
vii. other similar, equivalent or corresponding rights throughout the
|
| 60 |
+
world based on applicable law or treaty, and any national
|
| 61 |
+
implementations thereof.
|
| 62 |
+
|
| 63 |
+
2. Waiver. To the greatest extent permitted by, but not in contravention
|
| 64 |
+
of, applicable law, Affirmer hereby overtly, fully, permanently,
|
| 65 |
+
irrevocably and unconditionally waives, abandons, and surrenders all of
|
| 66 |
+
Affirmer's Copyright and Related Rights and associated claims and causes
|
| 67 |
+
of action, whether now known or unknown (including existing as well as
|
| 68 |
+
future claims and causes of action), in the Work (i) in all territories
|
| 69 |
+
worldwide, (ii) for the maximum duration provided by applicable law or
|
| 70 |
+
treaty (including future time extensions), (iii) in any current or future
|
| 71 |
+
medium and for any number of copies, and (iv) for any purpose whatsoever,
|
| 72 |
+
including without limitation commercial, advertising or promotional
|
| 73 |
+
purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
|
| 74 |
+
member of the public at large and to the detriment of Affirmer's heirs and
|
| 75 |
+
successors, fully intending that such Waiver shall not be subject to
|
| 76 |
+
revocation, rescission, cancellation, termination, or any other legal or
|
| 77 |
+
equitable action to disrupt the quiet enjoyment of the Work by the public
|
| 78 |
+
as contemplated by Affirmer's express Statement of Purpose.
|
| 79 |
+
|
| 80 |
+
3. Public License Fallback. Should any part of the Waiver for any reason
|
| 81 |
+
be judged legally invalid or ineffective under applicable law, then the
|
| 82 |
+
Waiver shall be preserved to the maximum extent permitted taking into
|
| 83 |
+
account Affirmer's express Statement of Purpose. In addition, to the
|
| 84 |
+
extent the Waiver is so judged Affirmer hereby grants to each affected
|
| 85 |
+
person a royalty-free, non transferable, non sublicensable, non exclusive,
|
| 86 |
+
irrevocable and unconditional license to exercise Affirmer's Copyright and
|
| 87 |
+
Related Rights in the Work (i) in all territories worldwide, (ii) for the
|
| 88 |
+
maximum duration provided by applicable law or treaty (including future
|
| 89 |
+
time extensions), (iii) in any current or future medium and for any number
|
| 90 |
+
of copies, and (iv) for any purpose whatsoever, including without
|
| 91 |
+
limitation commercial, advertising or promotional purposes (the
|
| 92 |
+
"License"). The License shall be deemed effective as of the date CC0 was
|
| 93 |
+
applied by Affirmer to the Work. Should any part of the License for any
|
| 94 |
+
reason be judged legally invalid or ineffective under applicable law, such
|
| 95 |
+
partial invalidity or ineffectiveness shall not invalidate the remainder
|
| 96 |
+
of the License, and in such case Affirmer hereby affirms that he or she
|
| 97 |
+
will not (i) exercise any of his or her remaining Copyright and Related
|
| 98 |
+
Rights in the Work or (ii) assert any associated claims and causes of
|
| 99 |
+
action with respect to the Work, in either case contrary to Affirmer's
|
| 100 |
+
express Statement of Purpose.
|
| 101 |
+
|
| 102 |
+
4. Limitations and Disclaimers.
|
| 103 |
+
|
| 104 |
+
a. No trademark or patent rights held by Affirmer are waived, abandoned,
|
| 105 |
+
surrendered, licensed or otherwise affected by this document.
|
| 106 |
+
b. Affirmer offers the Work as-is and makes no representations or
|
| 107 |
+
warranties of any kind concerning the Work, express, implied,
|
| 108 |
+
statutory or otherwise, including without limitation warranties of
|
| 109 |
+
title, merchantability, fitness for a particular purpose, non
|
| 110 |
+
infringement, or the absence of latent or other defects, accuracy, or
|
| 111 |
+
the present or absence of errors, whether or not discoverable, all to
|
| 112 |
+
the greatest extent permissible under applicable law.
|
| 113 |
+
c. Affirmer disclaims responsibility for clearing rights of other persons
|
| 114 |
+
that may apply to the Work or any use thereof, including without
|
| 115 |
+
limitation any person's Copyright and Related Rights in the Work.
|
| 116 |
+
Further, Affirmer disclaims responsibility for obtaining any necessary
|
| 117 |
+
consents, permissions or other rights required for any use of the
|
| 118 |
+
Work.
|
| 119 |
+
d. Affirmer understands and acknowledges that Creative Commons is not a
|
| 120 |
+
party to this document and has no duty or obligation with respect to
|
| 121 |
+
this CC0 or use of the Work.
|
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc0-1.0
|
| 3 |
+
language:
|
| 4 |
+
- fi
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
thumbnail: https://raw.githubusercontent.com/NatLibFi/FintoAI/main/ai.finto.fi/static/img/finto-ai-social.png
|
| 7 |
+
tags:
|
| 8 |
+
- glam
|
| 9 |
+
- lam
|
| 10 |
+
- subject indexing
|
| 11 |
+
- annif
|
| 12 |
+
---
|
| 13 |
+
# FintoAI-data-KAUNO
|
| 14 |
+
The Annif projects with KAUNO vocabulary used at the [Finto AI service](https://ai.finto.fi/).
|
| 15 |
+
|
| 16 |
+
This repository is mirrored from GitHub to the 🤗 Hugging Face Hub;
|
| 17 |
+
the GitHub repository does not contain the model files, but only the configurations for maintaining the projects, see below.
|
| 18 |
+
|
| 19 |
+
## Models
|
| 20 |
+
The data files for projects and vocabularies are stored in the
|
| 21 |
+
[`/data`](https://huggingface.co/juhoinkinen/FintoAI-data-KAUNO/tree/main/data)
|
| 22 |
+
directory of this repository in the 🤗 Hugging Face Hub.
|
| 23 |
+
|
| 24 |
+
## DVC pipeline
|
| 25 |
+
The projects are trained and evaluated using a [DVC (Data Version Control) pipeline](https://dvc.org/doc/start/data-management/data-pipelines) defined in [dvc.yaml](./dvc.yaml).
|
| 26 |
+
|
| 27 |
+
The pipeline takes care of
|
| 28 |
+
|
| 29 |
+
1. installing Annif in a venv,
|
| 30 |
+
2. loading the vocabulary,
|
| 31 |
+
3. training the projects,
|
| 32 |
+
4. evaluating the projects.
|
| 33 |
+
|
| 34 |
+
When the necessary vocabulary and training corpora are in place the pipeline can be run using the command
|
| 35 |
+
|
| 36 |
+
dvc repro
|
| 37 |
+
|
| 38 |
+
For more information about using DVC with Annif projects see the [DVC exercise of Annif tutorial](https://github.com/NatLibFi/Annif-tutorial/blob/master/exercises/OPT_dvc.md).
|
corpora/.gitignore
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/kauno-skos.ttl
|
| 2 |
+
/kauno-skos-reduced.ttl
|
corpora/finna/.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
/kauno-finna-fin.tsv.gz
|
corpora/finna/kauno-finna-fin.tsv.gz.dvc
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
md5: dae92ef1d2bed2a3c21e7631b6cdcb5e
|
| 2 |
+
deps:
|
| 3 |
+
- md5: ae570f73cbc72bd952efebd67575cda4
|
| 4 |
+
size: 63666506
|
| 5 |
+
path: /data/Annif-corpora/training/kauno-finna-fin.tsv.gz
|
| 6 |
+
hash: md5
|
| 7 |
+
outs:
|
| 8 |
+
- md5: ae570f73cbc72bd952efebd67575cda4
|
| 9 |
+
size: 63666506
|
| 10 |
+
path: kauno-finna-fin.tsv.gz
|
corpora/kauno-skos-reduced.ttl.dvc
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
md5: 4d29a28b7156dd12c51a8626e9f882bf
|
| 2 |
+
deps:
|
| 3 |
+
- md5: 6ca997fbaed020b9bfa867c991b19739
|
| 4 |
+
size: 17501880
|
| 5 |
+
path: /data/Annif-corpora-restricted/kirjasampo/kauno-skos-reduced.ttl
|
| 6 |
+
hash: md5
|
| 7 |
+
outs:
|
| 8 |
+
- md5: 6ca997fbaed020b9bfa867c991b19739
|
| 9 |
+
size: 17501880
|
| 10 |
+
path: kauno-skos-reduced.ttl
|
| 11 |
+
hash: md5
|
corpora/kirjasampo/.gitignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/kirjasampo-kauno-train.tsv
|
| 2 |
+
/kirjasampo-kauno-validate.tsv
|
| 3 |
+
/kirjasampo-kauno-test.tsv
|
corpora/kirjasampo/kirjasampo-kauno-test.tsv.dvc
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
md5: cca190c38bb6b6fbdeb2c4ca5c85abd9
|
| 2 |
+
deps:
|
| 3 |
+
- md5: 2a491f3d2b35df602a3730db99f7605c
|
| 4 |
+
size: 1502390
|
| 5 |
+
path: /data/Annif-corpora-restricted/kirjasampo/kirjasampo-kauno-test.tsv
|
| 6 |
+
hash: md5
|
| 7 |
+
outs:
|
| 8 |
+
- md5: 2a491f3d2b35df602a3730db99f7605c
|
| 9 |
+
size: 1502390
|
| 10 |
+
path: kirjasampo-kauno-test.tsv
|
| 11 |
+
hash: md5
|
corpora/kirjasampo/kirjasampo-kauno-train.tsv.dvc
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
md5: a59acca5aa93619ecdebc3083d0377a4
|
| 2 |
+
deps:
|
| 3 |
+
- md5: 77c01592d2c7c34f04bbee75b6584ec8
|
| 4 |
+
size: 58959362
|
| 5 |
+
path: /data/Annif-corpora-restricted/kirjasampo/kirjasampo-kauno-train.tsv
|
| 6 |
+
hash: md5
|
| 7 |
+
outs:
|
| 8 |
+
- md5: 77c01592d2c7c34f04bbee75b6584ec8
|
| 9 |
+
size: 58959362
|
| 10 |
+
path: kirjasampo-kauno-train.tsv
|
| 11 |
+
hash: md5
|
corpora/kirjasampo/kirjasampo-kauno-validate.tsv.dvc
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
md5: 54798c42f7f1117903899095aa02821e
|
| 2 |
+
deps:
|
| 3 |
+
- md5: 6dbd774820c16dbd440da71151e36079
|
| 4 |
+
size: 2455221
|
| 5 |
+
path: /data/Annif-corpora-restricted/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 6 |
+
hash: md5
|
| 7 |
+
outs:
|
| 8 |
+
- md5: 6dbd774820c16dbd440da71151e36079
|
| 9 |
+
size: 2455221
|
| 10 |
+
path: kirjasampo-kauno-validate.tsv
|
| 11 |
+
hash: md5
|
data/projects/.gitignore
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
/kauno-mllm-fi
|
| 2 |
+
/kauno-parabel-fi
|
| 3 |
+
/kauno-bonsai-fi
|
| 4 |
+
/kauno-ks-parabel-fi
|
| 5 |
+
/kauno-finna-bonsai-fi
|
| 6 |
+
/kauno-finna-parabel-fi
|
| 7 |
+
/kauno-ks-bonsai-fi
|
| 8 |
+
/kauno-fi
|
data/vocabs/.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
/kauno
|
dvc.lock
ADDED
|
@@ -0,0 +1,542 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
schema: '2.0'
|
| 2 |
+
stages:
|
| 3 |
+
install:
|
| 4 |
+
cmd:
|
| 5 |
+
- python3 -m venv venv
|
| 6 |
+
- . venv/bin/activate && pip install -U pip wheel setuptools && pip install -r
|
| 7 |
+
requirements.txt
|
| 8 |
+
- cp requirements.txt venv-installed
|
| 9 |
+
deps:
|
| 10 |
+
- path: requirements.txt
|
| 11 |
+
hash: md5
|
| 12 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 13 |
+
size: 41
|
| 14 |
+
outs:
|
| 15 |
+
- path: venv-installed
|
| 16 |
+
hash: md5
|
| 17 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 18 |
+
size: 41
|
| 19 |
+
loadvoc:
|
| 20 |
+
cmd: venv/bin/annif load-vocab --force kauno corpora/kauno-skos-reduced.ttl
|
| 21 |
+
deps:
|
| 22 |
+
- path: corpora/kauno-skos-reduced.ttl
|
| 23 |
+
hash: md5
|
| 24 |
+
md5: 6ca997fbaed020b9bfa867c991b19739
|
| 25 |
+
size: 17501880
|
| 26 |
+
- path: venv-installed
|
| 27 |
+
hash: md5
|
| 28 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 29 |
+
size: 41
|
| 30 |
+
outs:
|
| 31 |
+
- path: data/vocabs/kauno
|
| 32 |
+
hash: md5
|
| 33 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 34 |
+
size: 34076325
|
| 35 |
+
nfiles: 3
|
| 36 |
+
train-mllm:
|
| 37 |
+
cmd: venv/bin/annif train kauno-mllm-fi -j 8 -d 2000 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 38 |
+
deps:
|
| 39 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 40 |
+
hash: md5
|
| 41 |
+
md5: 77c01592d2c7c34f04bbee75b6584ec8
|
| 42 |
+
size: 58959362
|
| 43 |
+
- path: data/vocabs/kauno
|
| 44 |
+
hash: md5
|
| 45 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 46 |
+
size: 34076325
|
| 47 |
+
nfiles: 3
|
| 48 |
+
- path: venv-installed
|
| 49 |
+
hash: md5
|
| 50 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 51 |
+
size: 41
|
| 52 |
+
outs:
|
| 53 |
+
- path: data/projects/kauno-mllm-fi
|
| 54 |
+
hash: md5
|
| 55 |
+
md5: 23c57a221af59d0d2541a7df9e37ad7c.dir
|
| 56 |
+
size: 2261733
|
| 57 |
+
nfiles: 2
|
| 58 |
+
train-omikuji@parabel:
|
| 59 |
+
cmd: venv/bin/annif train kauno-parabel-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 60 |
+
deps:
|
| 61 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 62 |
+
md5: 6200fab3e9179186787cd49dbcaa587a
|
| 63 |
+
size: 39921230
|
| 64 |
+
- path: data/vocabs/kauno
|
| 65 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 66 |
+
size: 33952771
|
| 67 |
+
nfiles: 3
|
| 68 |
+
- path: venv-installed
|
| 69 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 70 |
+
size: 42
|
| 71 |
+
outs:
|
| 72 |
+
- path: data/projects/kauno-parabel-fi
|
| 73 |
+
md5: ba358be8ebda5347eba4825fcebcf43a.dir
|
| 74 |
+
size: 327572347
|
| 75 |
+
nfiles: 6
|
| 76 |
+
train-omikuji@bonsai:
|
| 77 |
+
cmd: venv/bin/annif train kauno-bonsai-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 78 |
+
deps:
|
| 79 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 80 |
+
md5: 6200fab3e9179186787cd49dbcaa587a
|
| 81 |
+
size: 39921230
|
| 82 |
+
- path: data/vocabs/kauno
|
| 83 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 84 |
+
size: 33952771
|
| 85 |
+
nfiles: 3
|
| 86 |
+
- path: venv-installed
|
| 87 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 88 |
+
size: 42
|
| 89 |
+
outs:
|
| 90 |
+
- path: data/projects/kauno-bonsai-fi
|
| 91 |
+
md5: 93b109deb653d12ea6137f3f67742934.dir
|
| 92 |
+
size: 428545588
|
| 93 |
+
nfiles: 6
|
| 94 |
+
eval@bonsai:
|
| 95 |
+
cmd:
|
| 96 |
+
- venv/bin/annif eval kauno-bonsai-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-bonsai-fi.json
|
| 97 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 98 |
+
deps:
|
| 99 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 100 |
+
md5: 48611b60c8006116b9c8686456dcfbf6
|
| 101 |
+
size: 1535757
|
| 102 |
+
- path: data/projects/kauno-bonsai-fi
|
| 103 |
+
md5: 93b109deb653d12ea6137f3f67742934.dir
|
| 104 |
+
size: 428545588
|
| 105 |
+
nfiles: 6
|
| 106 |
+
- path: venv-installed
|
| 107 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 108 |
+
size: 42
|
| 109 |
+
outs:
|
| 110 |
+
- path: reports/kauno-bonsai-fi.json
|
| 111 |
+
md5: 0cb706d29e2c34c41292f422c0d71dd6
|
| 112 |
+
size: 93
|
| 113 |
+
eval@mllm:
|
| 114 |
+
cmd:
|
| 115 |
+
- venv/bin/annif eval kauno-mllm-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-mllm-fi.json
|
| 116 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 117 |
+
deps:
|
| 118 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 119 |
+
hash: md5
|
| 120 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 121 |
+
size: 1502390
|
| 122 |
+
- path: data/projects/kauno-mllm-fi
|
| 123 |
+
hash: md5
|
| 124 |
+
md5: 23c57a221af59d0d2541a7df9e37ad7c.dir
|
| 125 |
+
size: 2261733
|
| 126 |
+
nfiles: 2
|
| 127 |
+
- path: venv-installed
|
| 128 |
+
hash: md5
|
| 129 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 130 |
+
size: 41
|
| 131 |
+
outs:
|
| 132 |
+
- path: reports/kauno-mllm-fi.json
|
| 133 |
+
hash: md5
|
| 134 |
+
md5: 9b94207439de0dee3c8efb58eaf23bdb
|
| 135 |
+
size: 95
|
| 136 |
+
eval@parabel:
|
| 137 |
+
cmd:
|
| 138 |
+
- venv/bin/annif eval kauno-parabel-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-parabel-fi.json
|
| 139 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 140 |
+
deps:
|
| 141 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 142 |
+
md5: 48611b60c8006116b9c8686456dcfbf6
|
| 143 |
+
size: 1535757
|
| 144 |
+
- path: data/projects/kauno-parabel-fi
|
| 145 |
+
md5: ba358be8ebda5347eba4825fcebcf43a.dir
|
| 146 |
+
size: 327572347
|
| 147 |
+
nfiles: 6
|
| 148 |
+
- path: venv-installed
|
| 149 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 150 |
+
size: 42
|
| 151 |
+
outs:
|
| 152 |
+
- path: reports/kauno-parabel-fi.json
|
| 153 |
+
md5: 56697a462498d0fc1b0dbe0f39dce592
|
| 154 |
+
size: 94
|
| 155 |
+
eval@ensemble:
|
| 156 |
+
cmd:
|
| 157 |
+
- venv/bin/annif eval kauno-ensemble-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-ensemble-fi.json
|
| 158 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 159 |
+
deps:
|
| 160 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 161 |
+
hash: md5
|
| 162 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 163 |
+
size: 1502390
|
| 164 |
+
- path: data/projects/kauno-ensemble-fi
|
| 165 |
+
hash: md5
|
| 166 |
+
md5: 3c5b9e385b3d59c658f823a92dfd34f6.dir
|
| 167 |
+
size: 1223621179
|
| 168 |
+
nfiles: 3
|
| 169 |
+
- path: venv-installed
|
| 170 |
+
hash: md5
|
| 171 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 172 |
+
size: 41
|
| 173 |
+
outs:
|
| 174 |
+
- path: reports/kauno-ensemble-fi.json
|
| 175 |
+
hash: md5
|
| 176 |
+
md5: bc2d8f32c841e8941bba9fcd88a92896
|
| 177 |
+
size: 94
|
| 178 |
+
train-omikuji-ks@parabel:
|
| 179 |
+
cmd: venv/bin/annif train kauno-ks-parabel-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 180 |
+
deps:
|
| 181 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 182 |
+
md5: 6200fab3e9179186787cd49dbcaa587a
|
| 183 |
+
size: 39921230
|
| 184 |
+
- path: data/vocabs/kauno
|
| 185 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 186 |
+
size: 33952771
|
| 187 |
+
nfiles: 3
|
| 188 |
+
- path: venv-installed
|
| 189 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 190 |
+
size: 42
|
| 191 |
+
outs:
|
| 192 |
+
- path: data/projects/kauno-ks-parabel-fi
|
| 193 |
+
md5: d24263f3ad1b5c3373ba6b1b86a4a222.dir
|
| 194 |
+
size: 327667525
|
| 195 |
+
nfiles: 6
|
| 196 |
+
train-omikuji-finna@bonsai:
|
| 197 |
+
cmd: venv/bin/annif train kauno-finna-bonsai-fi -j 8 corpora/finna/kauno-finna-fin.tsv.gz
|
| 198 |
+
deps:
|
| 199 |
+
- path: corpora/finna/kauno-finna-fin.tsv.gz
|
| 200 |
+
md5: ae570f73cbc72bd952efebd67575cda4
|
| 201 |
+
size: 63666506
|
| 202 |
+
- path: data/vocabs/kauno
|
| 203 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 204 |
+
size: 33952771
|
| 205 |
+
nfiles: 3
|
| 206 |
+
- path: venv-installed
|
| 207 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 208 |
+
size: 42
|
| 209 |
+
outs:
|
| 210 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 211 |
+
md5: 16418f34c02a34155b9db383138a8d87.dir
|
| 212 |
+
size: 546792457
|
| 213 |
+
nfiles: 6
|
| 214 |
+
train-omikuji-finna@parabel:
|
| 215 |
+
cmd: venv/bin/annif train kauno-finna-parabel-fi -j 8 corpora/finna/kauno-finna-fin.tsv.gz
|
| 216 |
+
deps:
|
| 217 |
+
- path: corpora/finna/kauno-finna-fin.tsv.gz
|
| 218 |
+
md5: ae570f73cbc72bd952efebd67575cda4
|
| 219 |
+
size: 63666506
|
| 220 |
+
- path: data/vocabs/kauno
|
| 221 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 222 |
+
size: 33952771
|
| 223 |
+
nfiles: 3
|
| 224 |
+
- path: venv-installed
|
| 225 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 226 |
+
size: 42
|
| 227 |
+
outs:
|
| 228 |
+
- path: data/projects/kauno-finna-parabel-fi
|
| 229 |
+
md5: f952af490b34403547b9dd3204d63e15.dir
|
| 230 |
+
size: 379427399
|
| 231 |
+
nfiles: 6
|
| 232 |
+
eval@finna-bonsai:
|
| 233 |
+
cmd:
|
| 234 |
+
- venv/bin/annif eval kauno-finna-bonsai-fi -j 8 -m F1@5 -m NDCG --metrics-file
|
| 235 |
+
reports/kauno-finna-bonsai-fi.json corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 236 |
+
deps:
|
| 237 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 238 |
+
hash: md5
|
| 239 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 240 |
+
size: 1502390
|
| 241 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 242 |
+
hash: md5
|
| 243 |
+
md5: eb1d5d6d196c0237832da37d53680b78.dir
|
| 244 |
+
size: 542003428
|
| 245 |
+
nfiles: 6
|
| 246 |
+
- path: venv-installed
|
| 247 |
+
hash: md5
|
| 248 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 249 |
+
size: 41
|
| 250 |
+
outs:
|
| 251 |
+
- path: reports/kauno-finna-bonsai-fi.json
|
| 252 |
+
hash: md5
|
| 253 |
+
md5: fe5bc33b1f952c4d330ee1a12613fd9c
|
| 254 |
+
size: 94
|
| 255 |
+
eval@finna-parabel:
|
| 256 |
+
cmd:
|
| 257 |
+
- venv/bin/annif eval kauno-finna-parabel-fi -j 8 -m F1@5 -m NDCG --metrics-file
|
| 258 |
+
reports/kauno-finna-parabel-fi.json corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 259 |
+
deps:
|
| 260 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 261 |
+
md5: 48611b60c8006116b9c8686456dcfbf6
|
| 262 |
+
size: 1535757
|
| 263 |
+
- path: data/projects/kauno-finna-parabel-fi
|
| 264 |
+
md5: f952af490b34403547b9dd3204d63e15.dir
|
| 265 |
+
size: 379427399
|
| 266 |
+
nfiles: 6
|
| 267 |
+
- path: venv-installed
|
| 268 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 269 |
+
size: 42
|
| 270 |
+
outs:
|
| 271 |
+
- path: reports/kauno-finna-parabel-fi.json
|
| 272 |
+
md5: e037704630021469933d06952c18d27e
|
| 273 |
+
size: 95
|
| 274 |
+
eval@ks-parabel:
|
| 275 |
+
cmd:
|
| 276 |
+
- venv/bin/annif eval kauno-ks-parabel-fi -j 8 -m F1@5 -m NDCG --metrics-file
|
| 277 |
+
reports/kauno-ks-parabel-fi.json corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 278 |
+
deps:
|
| 279 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 280 |
+
md5: 48611b60c8006116b9c8686456dcfbf6
|
| 281 |
+
size: 1535757
|
| 282 |
+
- path: data/projects/kauno-ks-parabel-fi
|
| 283 |
+
md5: d24263f3ad1b5c3373ba6b1b86a4a222.dir
|
| 284 |
+
size: 327667525
|
| 285 |
+
nfiles: 6
|
| 286 |
+
- path: venv-installed
|
| 287 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 288 |
+
size: 42
|
| 289 |
+
outs:
|
| 290 |
+
- path: reports/kauno-ks-parabel-fi.json
|
| 291 |
+
md5: 5615be39b149e641186f32916d80b0a5
|
| 292 |
+
size: 94
|
| 293 |
+
train-omikuji-ks@bonsai:
|
| 294 |
+
cmd: venv/bin/annif train kauno-ks-bonsai-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 295 |
+
deps:
|
| 296 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 297 |
+
md5: 6200fab3e9179186787cd49dbcaa587a
|
| 298 |
+
size: 39921230
|
| 299 |
+
- path: data/vocabs/kauno
|
| 300 |
+
md5: 43f49eabb66648de35d01d57d196e196.dir
|
| 301 |
+
size: 33952771
|
| 302 |
+
nfiles: 3
|
| 303 |
+
- path: venv-installed
|
| 304 |
+
md5: b1b83339d2df42e93f3df0e83b1e85ab
|
| 305 |
+
size: 42
|
| 306 |
+
outs:
|
| 307 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 308 |
+
md5: 3130bd53059af8c55630d94116657d4f.dir
|
| 309 |
+
size: 426174615
|
| 310 |
+
nfiles: 6
|
| 311 |
+
eval@ks-bonsai:
|
| 312 |
+
cmd:
|
| 313 |
+
- venv/bin/annif eval kauno-ks-bonsai-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-ks-bonsai-fi.json
|
| 314 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 315 |
+
deps:
|
| 316 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 317 |
+
hash: md5
|
| 318 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 319 |
+
size: 1502390
|
| 320 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 321 |
+
hash: md5
|
| 322 |
+
md5: 7f3dae80e066dae4428a86bba7eea413.dir
|
| 323 |
+
size: 745367632
|
| 324 |
+
nfiles: 6
|
| 325 |
+
- path: venv-installed
|
| 326 |
+
hash: md5
|
| 327 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 328 |
+
size: 41
|
| 329 |
+
outs:
|
| 330 |
+
- path: reports/kauno-ks-bonsai-fi.json
|
| 331 |
+
hash: md5
|
| 332 |
+
md5: 9c16b8188723d2a92c8a4117e841fa83
|
| 333 |
+
size: 94
|
| 334 |
+
train-omikuji-ks:
|
| 335 |
+
cmd: venv/bin/annif train kauno-ks-bonsai-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 336 |
+
deps:
|
| 337 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 338 |
+
hash: md5
|
| 339 |
+
md5: 77c01592d2c7c34f04bbee75b6584ec8
|
| 340 |
+
size: 58959362
|
| 341 |
+
- path: data/vocabs/kauno
|
| 342 |
+
hash: md5
|
| 343 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 344 |
+
size: 34076325
|
| 345 |
+
nfiles: 3
|
| 346 |
+
- path: venv-installed
|
| 347 |
+
hash: md5
|
| 348 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 349 |
+
size: 41
|
| 350 |
+
outs:
|
| 351 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 352 |
+
hash: md5
|
| 353 |
+
md5: 7f3dae80e066dae4428a86bba7eea413.dir
|
| 354 |
+
size: 745367632
|
| 355 |
+
nfiles: 6
|
| 356 |
+
train-omikuji-finna:
|
| 357 |
+
cmd: venv/bin/annif train kauno-finna-bonsai-fi -j 8 corpora/finna/kauno-finna-fin.tsv.gz
|
| 358 |
+
deps:
|
| 359 |
+
- path: corpora/finna/kauno-finna-fin.tsv.gz
|
| 360 |
+
md5: ae570f73cbc72bd952efebd67575cda4
|
| 361 |
+
size: 63666506
|
| 362 |
+
- path: data/vocabs/kauno
|
| 363 |
+
hash: md5
|
| 364 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 365 |
+
size: 34076325
|
| 366 |
+
nfiles: 3
|
| 367 |
+
- path: venv-installed
|
| 368 |
+
hash: md5
|
| 369 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 370 |
+
size: 41
|
| 371 |
+
outs:
|
| 372 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 373 |
+
hash: md5
|
| 374 |
+
md5: eb1d5d6d196c0237832da37d53680b78.dir
|
| 375 |
+
size: 542003428
|
| 376 |
+
nfiles: 6
|
| 377 |
+
train-ensemble:
|
| 378 |
+
cmd: venv/bin/annif train -j 8 kauno-ensemble-fi corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 379 |
+
deps:
|
| 380 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 381 |
+
hash: md5
|
| 382 |
+
md5: 6dbd774820c16dbd440da71151e36079
|
| 383 |
+
size: 2455221
|
| 384 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 385 |
+
hash: md5
|
| 386 |
+
md5: eb1d5d6d196c0237832da37d53680b78.dir
|
| 387 |
+
size: 542003428
|
| 388 |
+
nfiles: 6
|
| 389 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 390 |
+
hash: md5
|
| 391 |
+
md5: 7f3dae80e066dae4428a86bba7eea413.dir
|
| 392 |
+
size: 745367632
|
| 393 |
+
nfiles: 6
|
| 394 |
+
- path: data/projects/kauno-mllm-fi
|
| 395 |
+
hash: md5
|
| 396 |
+
md5: 23c57a221af59d0d2541a7df9e37ad7c.dir
|
| 397 |
+
size: 2261733
|
| 398 |
+
nfiles: 2
|
| 399 |
+
- path: data/vocabs/kauno
|
| 400 |
+
hash: md5
|
| 401 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 402 |
+
size: 34076325
|
| 403 |
+
nfiles: 3
|
| 404 |
+
- path: venv-installed
|
| 405 |
+
hash: md5
|
| 406 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 407 |
+
size: 41
|
| 408 |
+
outs:
|
| 409 |
+
- path: data/projects/kauno-ensemble-fi
|
| 410 |
+
hash: md5
|
| 411 |
+
md5: 3c5b9e385b3d59c658f823a92dfd34f6.dir
|
| 412 |
+
size: 1223621179
|
| 413 |
+
nfiles: 3
|
| 414 |
+
train-nn-ensemble:
|
| 415 |
+
cmd: venv/bin/annif train -j 8 kauno-fi corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 416 |
+
deps:
|
| 417 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 418 |
+
hash: md5
|
| 419 |
+
md5: 6dbd774820c16dbd440da71151e36079
|
| 420 |
+
size: 2455221
|
| 421 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 422 |
+
hash: md5
|
| 423 |
+
md5: eb1d5d6d196c0237832da37d53680b78.dir
|
| 424 |
+
size: 542003428
|
| 425 |
+
nfiles: 6
|
| 426 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 427 |
+
hash: md5
|
| 428 |
+
md5: 7f3dae80e066dae4428a86bba7eea413.dir
|
| 429 |
+
size: 745367632
|
| 430 |
+
nfiles: 6
|
| 431 |
+
- path: data/projects/kauno-mllm-fi
|
| 432 |
+
hash: md5
|
| 433 |
+
md5: 23c57a221af59d0d2541a7df9e37ad7c.dir
|
| 434 |
+
size: 2261733
|
| 435 |
+
nfiles: 2
|
| 436 |
+
- path: data/vocabs/kauno
|
| 437 |
+
hash: md5
|
| 438 |
+
md5: 8d23b787082ad96201ffb484ec6fb681.dir
|
| 439 |
+
size: 34076325
|
| 440 |
+
nfiles: 3
|
| 441 |
+
- path: venv-installed
|
| 442 |
+
hash: md5
|
| 443 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 444 |
+
size: 41
|
| 445 |
+
outs:
|
| 446 |
+
- path: data/projects/kauno-fi
|
| 447 |
+
hash: md5
|
| 448 |
+
md5: ce989b5df6c6771b0e60aefb8a7d4ec9.dir
|
| 449 |
+
size: 1223621179
|
| 450 |
+
nfiles: 3
|
| 451 |
+
eval@mllm-fi:
|
| 452 |
+
cmd:
|
| 453 |
+
- venv/bin/annif eval kauno-mllm-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-mllm-fi.json
|
| 454 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 455 |
+
deps:
|
| 456 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 457 |
+
hash: md5
|
| 458 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 459 |
+
size: 1502390
|
| 460 |
+
- path: data/projects/kauno-mllm-fi
|
| 461 |
+
hash: md5
|
| 462 |
+
md5: 23c57a221af59d0d2541a7df9e37ad7c.dir
|
| 463 |
+
size: 2261733
|
| 464 |
+
nfiles: 2
|
| 465 |
+
- path: venv-installed
|
| 466 |
+
hash: md5
|
| 467 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 468 |
+
size: 41
|
| 469 |
+
outs:
|
| 470 |
+
- path: reports/kauno-mllm-fi.json
|
| 471 |
+
hash: md5
|
| 472 |
+
md5: 9b94207439de0dee3c8efb58eaf23bdb
|
| 473 |
+
size: 95
|
| 474 |
+
eval@ks-bonsai-fi:
|
| 475 |
+
cmd:
|
| 476 |
+
- venv/bin/annif eval kauno-ks-bonsai-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-ks-bonsai-fi.json
|
| 477 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 478 |
+
deps:
|
| 479 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 480 |
+
hash: md5
|
| 481 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 482 |
+
size: 1502390
|
| 483 |
+
- path: data/projects/kauno-ks-bonsai-fi
|
| 484 |
+
hash: md5
|
| 485 |
+
md5: 7f3dae80e066dae4428a86bba7eea413.dir
|
| 486 |
+
size: 745367632
|
| 487 |
+
nfiles: 6
|
| 488 |
+
- path: venv-installed
|
| 489 |
+
hash: md5
|
| 490 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 491 |
+
size: 41
|
| 492 |
+
outs:
|
| 493 |
+
- path: reports/kauno-ks-bonsai-fi.json
|
| 494 |
+
hash: md5
|
| 495 |
+
md5: 9c16b8188723d2a92c8a4117e841fa83
|
| 496 |
+
size: 94
|
| 497 |
+
eval@finna-bonsai-fi:
|
| 498 |
+
cmd:
|
| 499 |
+
- venv/bin/annif eval kauno-finna-bonsai-fi -j 8 -m F1@5 -m NDCG --metrics-file
|
| 500 |
+
reports/kauno-finna-bonsai-fi.json corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 501 |
+
deps:
|
| 502 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 503 |
+
hash: md5
|
| 504 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 505 |
+
size: 1502390
|
| 506 |
+
- path: data/projects/kauno-finna-bonsai-fi
|
| 507 |
+
hash: md5
|
| 508 |
+
md5: eb1d5d6d196c0237832da37d53680b78.dir
|
| 509 |
+
size: 542003428
|
| 510 |
+
nfiles: 6
|
| 511 |
+
- path: venv-installed
|
| 512 |
+
hash: md5
|
| 513 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 514 |
+
size: 41
|
| 515 |
+
outs:
|
| 516 |
+
- path: reports/kauno-finna-bonsai-fi.json
|
| 517 |
+
hash: md5
|
| 518 |
+
md5: fe5bc33b1f952c4d330ee1a12613fd9c
|
| 519 |
+
size: 94
|
| 520 |
+
eval@fi:
|
| 521 |
+
cmd:
|
| 522 |
+
- venv/bin/annif eval kauno-fi -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-fi.json
|
| 523 |
+
corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 524 |
+
deps:
|
| 525 |
+
- path: corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 526 |
+
hash: md5
|
| 527 |
+
md5: 2a491f3d2b35df602a3730db99f7605c
|
| 528 |
+
size: 1502390
|
| 529 |
+
- path: data/projects/kauno-fi
|
| 530 |
+
hash: md5
|
| 531 |
+
md5: ce989b5df6c6771b0e60aefb8a7d4ec9.dir
|
| 532 |
+
size: 1223621179
|
| 533 |
+
nfiles: 3
|
| 534 |
+
- path: venv-installed
|
| 535 |
+
hash: md5
|
| 536 |
+
md5: f85f21b68735b126c2241fbff83fd0ef
|
| 537 |
+
size: 41
|
| 538 |
+
outs:
|
| 539 |
+
- path: reports/kauno-fi.json
|
| 540 |
+
hash: md5
|
| 541 |
+
md5: 500d93c3d47823dbef945b2efa8899e4
|
| 542 |
+
size: 93
|
dvc.yaml
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
stages:
|
| 2 |
+
# Ensure Annif is installed
|
| 3 |
+
install:
|
| 4 |
+
cmd:
|
| 5 |
+
- python3 -m venv venv
|
| 6 |
+
- . venv/bin/activate && pip install -U pip wheel setuptools && pip install -r requirements.txt
|
| 7 |
+
- cp requirements.txt venv-installed
|
| 8 |
+
deps:
|
| 9 |
+
- requirements.txt
|
| 10 |
+
outs:
|
| 11 |
+
- venv-installed:
|
| 12 |
+
cache: false
|
| 13 |
+
# Load KAUNO vocabulary
|
| 14 |
+
loadvoc:
|
| 15 |
+
cmd: venv/bin/annif load-vocab --force kauno corpora/kauno-skos-reduced.ttl
|
| 16 |
+
deps:
|
| 17 |
+
- venv-installed
|
| 18 |
+
- corpora/kauno-skos-reduced.ttl
|
| 19 |
+
outs:
|
| 20 |
+
- data/vocabs/kauno
|
| 21 |
+
# Train MLLM project
|
| 22 |
+
train-mllm:
|
| 23 |
+
cmd: venv/bin/annif train kauno-mllm-fi -j 8 -d 2000 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 24 |
+
deps:
|
| 25 |
+
- venv-installed
|
| 26 |
+
- corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 27 |
+
- data/vocabs/kauno
|
| 28 |
+
outs:
|
| 29 |
+
- data/projects/kauno-mllm-fi
|
| 30 |
+
# Train Omikuji project using Kirjasampo data
|
| 31 |
+
train-omikuji-ks:
|
| 32 |
+
cmd: venv/bin/annif train kauno-ks-bonsai-fi -j 8 corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 33 |
+
deps:
|
| 34 |
+
- venv-installed
|
| 35 |
+
- corpora/kirjasampo/kirjasampo-kauno-train.tsv
|
| 36 |
+
- data/vocabs/kauno
|
| 37 |
+
outs:
|
| 38 |
+
- data/projects/kauno-ks-bonsai-fi
|
| 39 |
+
# Train Omikuji project using Finna data
|
| 40 |
+
train-omikuji-finna:
|
| 41 |
+
cmd: venv/bin/annif train kauno-finna-bonsai-fi -j 8 corpora/finna/kauno-finna-fin.tsv.gz
|
| 42 |
+
deps:
|
| 43 |
+
- venv-installed
|
| 44 |
+
- corpora/finna/kauno-finna-fin.tsv.gz
|
| 45 |
+
- data/vocabs/kauno
|
| 46 |
+
outs:
|
| 47 |
+
- data/projects/kauno-finna-bonsai-fi
|
| 48 |
+
# Train NN ensemble
|
| 49 |
+
train-nn-ensemble:
|
| 50 |
+
cmd: venv/bin/annif train -j 8 kauno-fi corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 51 |
+
deps:
|
| 52 |
+
- venv-installed
|
| 53 |
+
- corpora/kirjasampo/kirjasampo-kauno-validate.tsv
|
| 54 |
+
- data/vocabs/kauno
|
| 55 |
+
- data/projects/kauno-mllm-fi
|
| 56 |
+
- data/projects/kauno-ks-bonsai-fi
|
| 57 |
+
- data/projects/kauno-finna-bonsai-fi
|
| 58 |
+
outs:
|
| 59 |
+
- data/projects/kauno-fi
|
| 60 |
+
# Evaluate projects
|
| 61 |
+
eval:
|
| 62 |
+
foreach:
|
| 63 |
+
- mllm-fi
|
| 64 |
+
- ks-bonsai-fi
|
| 65 |
+
- finna-bonsai-fi
|
| 66 |
+
- fi
|
| 67 |
+
do:
|
| 68 |
+
cmd:
|
| 69 |
+
- venv/bin/annif eval kauno-${item} -j 8 -m F1@5 -m NDCG --metrics-file reports/kauno-${item}.json corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 70 |
+
deps:
|
| 71 |
+
- venv-installed
|
| 72 |
+
- corpora/kirjasampo/kirjasampo-kauno-test.tsv
|
| 73 |
+
- data/projects/kauno-${item}
|
| 74 |
+
metrics:
|
| 75 |
+
- reports/kauno-${item}.json:
|
| 76 |
+
cache: false
|
projects.d/2-projects-kauno.toml
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# KAUNO Finnish
|
| 2 |
+
|
| 3 |
+
[kauno-mllm-fi]
|
| 4 |
+
name="KAUNO MLLM Finnish"
|
| 5 |
+
language="fi"
|
| 6 |
+
backend="mllm"
|
| 7 |
+
analyzer="voikko(fi)"
|
| 8 |
+
vocab="kauno"
|
| 9 |
+
access="hidden"
|
| 10 |
+
|
| 11 |
+
[kauno-ks-bonsai-fi]
|
| 12 |
+
name="KAUNO KS Omikuji Bonsai Finnish"
|
| 13 |
+
language="fi"
|
| 14 |
+
backend="omikuji"
|
| 15 |
+
analyzer="voikko(fi)"
|
| 16 |
+
vocab="kauno"
|
| 17 |
+
cluster_balanced=false
|
| 18 |
+
cluster_k=100
|
| 19 |
+
max_depth=3
|
| 20 |
+
min_df=2
|
| 21 |
+
ngram=2
|
| 22 |
+
transform="limit(5000)"
|
| 23 |
+
access="hidden"
|
| 24 |
+
|
| 25 |
+
[kauno-finna-bonsai-fi]
|
| 26 |
+
name="KAUNO Finna Omikuji Bonsai Finnish"
|
| 27 |
+
language="fi"
|
| 28 |
+
backend="omikuji"
|
| 29 |
+
analyzer="voikko(fi)"
|
| 30 |
+
vocab="kauno"
|
| 31 |
+
cluster_balanced=false
|
| 32 |
+
cluster_k=100
|
| 33 |
+
max_depth=3
|
| 34 |
+
min_df=2
|
| 35 |
+
ngram=2
|
| 36 |
+
transform="limit(5000)"
|
| 37 |
+
access="hidden"
|
| 38 |
+
|
| 39 |
+
[kauno-fi]
|
| 40 |
+
name="KAUNO suomi"
|
| 41 |
+
language="fi"
|
| 42 |
+
backend="nn_ensemble"
|
| 43 |
+
sources="kauno-mllm-fi:0.1293,kauno-ks-bonsai-fi:0.5518,kauno-finna-bonsai-fi:0.3189"
|
| 44 |
+
vocab="kauno"
|
projects.toml
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# KAUNO Finnish
|
| 2 |
+
|
| 3 |
+
[kauno-mllm-fi]
|
| 4 |
+
name="KAUNO MLLM Finnish"
|
| 5 |
+
language="fi"
|
| 6 |
+
backend="mllm"
|
| 7 |
+
analyzer="voikko(fi)"
|
| 8 |
+
vocab="kauno"
|
| 9 |
+
access="hidden"
|
| 10 |
+
|
| 11 |
+
[kauno-ks-bonsai-fi]
|
| 12 |
+
name="KAUNO KS Omikuji Bonsai Finnish"
|
| 13 |
+
language="fi"
|
| 14 |
+
backend="omikuji"
|
| 15 |
+
analyzer="voikko(fi)"
|
| 16 |
+
vocab="kauno"
|
| 17 |
+
cluster_balanced=false
|
| 18 |
+
cluster_k=100
|
| 19 |
+
max_depth=3
|
| 20 |
+
min_df=2
|
| 21 |
+
ngram=2
|
| 22 |
+
transform="limit(5000)"
|
| 23 |
+
access="hidden"
|
| 24 |
+
|
| 25 |
+
[kauno-finna-bonsai-fi]
|
| 26 |
+
name="KAUNO Finna Omikuji Bonsai Finnish"
|
| 27 |
+
language="fi"
|
| 28 |
+
backend="omikuji"
|
| 29 |
+
analyzer="voikko(fi)"
|
| 30 |
+
vocab="kauno"
|
| 31 |
+
cluster_balanced=false
|
| 32 |
+
cluster_k=100
|
| 33 |
+
max_depth=3
|
| 34 |
+
min_df=2
|
| 35 |
+
ngram=2
|
| 36 |
+
transform="limit(5000)"
|
| 37 |
+
access="hidden"
|
| 38 |
+
|
| 39 |
+
[kauno-fi]
|
| 40 |
+
name="KAUNO suomi"
|
| 41 |
+
language="fi"
|
| 42 |
+
backend="nn_ensemble"
|
| 43 |
+
sources="kauno-mllm-fi:0.1293,kauno-ks-bonsai-fi:0.5518,kauno-finna-bonsai-fi:0.3189"
|
| 44 |
+
vocab="kauno"
|
reports/kauno-fi.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"F1@5": 0.4662634707739284,
|
| 3 |
+
"NDCG": 0.6133524179458618,
|
| 4 |
+
"Documents_evaluated": 1367
|
| 5 |
+
}
|
reports/kauno-finna-bonsai-fi.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"F1@5": 0.2873918358957718,
|
| 3 |
+
"NDCG": 0.38556820154190063,
|
| 4 |
+
"Documents_evaluated": 1367
|
| 5 |
+
}
|
reports/kauno-ks-bonsai-fi.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"F1@5": 0.39796013215991816,
|
| 3 |
+
"NDCG": 0.5301554799079895,
|
| 4 |
+
"Documents_evaluated": 1367
|
| 5 |
+
}
|
reports/kauno-mllm-fi.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"F1@5": 0.18675745352815562,
|
| 3 |
+
"NDCG": 0.24778875708580017,
|
| 4 |
+
"Documents_evaluated": 1367
|
| 5 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
annif[fasttext,omikuji,nn,voikko]==1.0.*
|
sync-model-data-ocp.sh
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
|
| 3 |
+
# Runs rsync to transfer model data from the current directory to an OpenShift volume
|
| 4 |
+
# that is attached to a pod which is running Annif. The instance
|
| 5 |
+
# {api-annif-org,ai-finto-fi, etc.} to transfer to is given as the argument.
|
| 6 |
+
# You need to be logged to the cluster with the oc tool.
|
| 7 |
+
|
| 8 |
+
set -e
|
| 9 |
+
|
| 10 |
+
if [ $# -ne 1 ]
|
| 11 |
+
then
|
| 12 |
+
echo "Not enough arguments; argument 1: destination_instance"
|
| 13 |
+
exit 1
|
| 14 |
+
fi
|
| 15 |
+
|
| 16 |
+
pod=$(oc get pods -l app.kubernetes.io/instance=$1,app.kubernetes.io/name=annif -o name)
|
| 17 |
+
|
| 18 |
+
if [[ $pod = *[[:space:]]* ]]
|
| 19 |
+
then
|
| 20 |
+
echo "Multiple pod exists; using first"
|
| 21 |
+
pod=(${pod//$'\n'/ })
|
| 22 |
+
fi
|
| 23 |
+
echo "Target is "$pod
|
| 24 |
+
pod=${pod#pod/}
|
| 25 |
+
if [ -z "${pod}" ]
|
| 26 |
+
then
|
| 27 |
+
echo "No target pod found"
|
| 28 |
+
exit 1
|
| 29 |
+
fi
|
| 30 |
+
|
| 31 |
+
rsync --rsh='oc rsh' -avrL --exclude="*train*" --exclude="*zip" --inplace projects.d $pod:/annif-projects
|
| 32 |
+
rsync --rsh='oc rsh' -avrL --exclude="*train*" --exclude="*zip" --inplace data/{projects,vocabs} $pod:/annif-projects/data
|