Reset repo before projects upload with Annif

.dvc/.gitignore

@@ -1,3 +0,0 @@
-/config.local
-/tmp
-/cache

.dvc/config

@@ -1,6 +0,0 @@
-[cache]
-    dir = /data/dvc-cache/FintoAI-data-YKL
-    shared = group
-    type = symlink
-[core]
-    autostage = true

.dvcignore

@@ -1,3 +0,0 @@
-# Add patterns of files dvc should ignore, which could improve
-# the performance. Learn more at
-# https://dvc.org/doc/user-guide/dvcignore

.gitattributes

@@ -1,43 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree0.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree1.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree2.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-bonsai-fi/vectorizer filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree0.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree1.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree2.cbor filter=lfs diff=lfs merge=lfs -text
-data/projects/ykl-omikuji-parabel-fi/vectorizer filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,2 +0,0 @@
-venv
-venv-installed

LICENSE

@@ -1,121 +0,0 @@
-Creative Commons Legal Code
-
-CC0 1.0 Universal
-
-    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
-    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
-    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
-    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
-    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
-    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
-    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
-    HEREUNDER.
-
-Statement of Purpose
-
-The laws of most jurisdictions throughout the world automatically confer
-exclusive Copyright and Related Rights (defined below) upon the creator
-and subsequent owner(s) (each and all, an "owner") of an original work of
-authorship and/or a database (each, a "Work").
-
-Certain owners wish to permanently relinquish those rights to a Work for
-the purpose of contributing to a commons of creative, cultural and
-scientific works ("Commons") that the public can reliably and without fear
-of later claims of infringement build upon, modify, incorporate in other
-works, reuse and redistribute as freely as possible in any form whatsoever
-and for any purposes, including without limitation commercial purposes.
-These owners may contribute to the Commons to promote the ideal of a free
-culture and the further production of creative, cultural and scientific
-works, or to gain reputation or greater distribution for their Work in
-part through the use and efforts of others.
-
-For these and/or other purposes and motivations, and without any
-expectation of additional consideration or compensation, the person
-associating CC0 with a Work (the "Affirmer"), to the extent that he or she
-is an owner of Copyright and Related Rights in the Work, voluntarily
-elects to apply CC0 to the Work and publicly distribute the Work under its
-terms, with knowledge of his or her Copyright and Related Rights in the
-Work and the meaning and intended legal effect of CC0 on those rights.
-
-1. Copyright and Related Rights. A Work made available under CC0 may be
-protected by copyright and related or neighboring rights ("Copyright and
-Related Rights"). Copyright and Related Rights include, but are not
-limited to, the following:
-
-  i. the right to reproduce, adapt, distribute, perform, display,
-     communicate, and translate a Work;
- ii. moral rights retained by the original author(s) and/or performer(s);
-iii. publicity and privacy rights pertaining to a person's image or
-     likeness depicted in a Work;
- iv. rights protecting against unfair competition in regards to a Work,
-     subject to the limitations in paragraph 4(a), below;
-  v. rights protecting the extraction, dissemination, use and reuse of data
-     in a Work;
- vi. database rights (such as those arising under Directive 96/9/EC of the
-     European Parliament and of the Council of 11 March 1996 on the legal
-     protection of databases, and under any national implementation
-     thereof, including any amended or successor version of such
-     directive); and
-vii. other similar, equivalent or corresponding rights throughout the
-     world based on applicable law or treaty, and any national
-     implementations thereof.
-
-2. Waiver. To the greatest extent permitted by, but not in contravention
-of, applicable law, Affirmer hereby overtly, fully, permanently,
-irrevocably and unconditionally waives, abandons, and surrenders all of
-Affirmer's Copyright and Related Rights and associated claims and causes
-of action, whether now known or unknown (including existing as well as
-future claims and causes of action), in the Work (i) in all territories
-worldwide, (ii) for the maximum duration provided by applicable law or
-treaty (including future time extensions), (iii) in any current or future
-medium and for any number of copies, and (iv) for any purpose whatsoever,
-including without limitation commercial, advertising or promotional
-purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
-member of the public at large and to the detriment of Affirmer's heirs and
-successors, fully intending that such Waiver shall not be subject to
-revocation, rescission, cancellation, termination, or any other legal or
-equitable action to disrupt the quiet enjoyment of the Work by the public
-as contemplated by Affirmer's express Statement of Purpose.
-
-3. Public License Fallback. Should any part of the Waiver for any reason
-be judged legally invalid or ineffective under applicable law, then the
-Waiver shall be preserved to the maximum extent permitted taking into
-account Affirmer's express Statement of Purpose. In addition, to the
-extent the Waiver is so judged Affirmer hereby grants to each affected
-person a royalty-free, non transferable, non sublicensable, non exclusive,
-irrevocable and unconditional license to exercise Affirmer's Copyright and
-Related Rights in the Work (i) in all territories worldwide, (ii) for the
-maximum duration provided by applicable law or treaty (including future
-time extensions), (iii) in any current or future medium and for any number
-of copies, and (iv) for any purpose whatsoever, including without
-limitation commercial, advertising or promotional purposes (the
-"License"). The License shall be deemed effective as of the date CC0 was
-applied by Affirmer to the Work. Should any part of the License for any
-reason be judged legally invalid or ineffective under applicable law, such
-partial invalidity or ineffectiveness shall not invalidate the remainder
-of the License, and in such case Affirmer hereby affirms that he or she
-will not (i) exercise any of his or her remaining Copyright and Related
-Rights in the Work or (ii) assert any associated claims and causes of
-action with respect to the Work, in either case contrary to Affirmer's
-express Statement of Purpose.
-
-4. Limitations and Disclaimers.
-
- a. No trademark or patent rights held by Affirmer are waived, abandoned,
-    surrendered, licensed or otherwise affected by this document.
- b. Affirmer offers the Work as-is and makes no representations or
-    warranties of any kind concerning the Work, express, implied,
-    statutory or otherwise, including without limitation warranties of
-    title, merchantability, fitness for a particular purpose, non
-    infringement, or the absence of latent or other defects, accuracy, or
-    the present or absence of errors, whether or not discoverable, all to
-    the greatest extent permissible under applicable law.
- c. Affirmer disclaims responsibility for clearing rights of other persons
-    that may apply to the Work or any use thereof, including without
-    limitation any person's Copyright and Related Rights in the Work.
-    Further, Affirmer disclaims responsibility for obtaining any necessary
-    consents, permissions or other rights required for any use of the
-    Work.
- d. Affirmer understands and acknowledges that Creative Commons is not a
-    party to this document and has no duty or obligation with respect to
-    this CC0 or use of the Work.

README.md

@@ -1,64 +0,0 @@
----
-license: cc0-1.0
-language:
-- fi
-- sv
-- en
-pipeline_tag: text-classification
-thumbnail: https://raw.githubusercontent.com/NatLibFi/FintoAI/main/ai.finto.fi/static/img/finto-ai-social.png
-tags:
-- glam
-- lam
-- subject indexing
-- annif
----
-# FintoAI-data-YKL
-This repository is for the Annif projects with the
-[YKL vocabulary](https://finto.fi/ykl)
-used at the [Finto AI service](https://ai.finto.fi/).
-The current models were published there 2023-12-04.
-The models have been trained on Python 3.8.10 with [Annif](https://annif.org) version 1.0.0.
-See [projects.toml](projects.toml) for the configurations of the models.
-
-This repository is mirrored from GitHub to the 🤗 Hugging Face Hub;
-the GitHub repository does not contain the model files, but only the configurations for the projects and the DVC pipeline, see below.
-
-The training corpora that are public can be found from the [Annif-corpora repository](https://github.com/NatLibFi/Annif-corpora/).
-
-## Models
-The downloadable directories for projects and vocabularies are stored in the
-[`/data`](https://huggingface.co/juhoinkinen/FintoAI-data-YKL/tree/main/data)
-directory of this repository in the 🤗 Hugging Face Hub.
-
-## DVC pipeline
-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).
-
-The pipeline takes care of
-
-1. installing Annif in a venv,
-2. loading the vocabulary,
-3. training the projects,
-4. evaluating the projects.
-
-When the necessary vocabulary and training corpora are in place the pipeline can be run using the command
-
-    dvc repro
-
-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).
-
-Configurations for maintaining the Annif projects with YKL vocabulary used at [Finto AI service](ai.finto.fi/).
-
-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).
-
-The pipeline takes care of 
-
-1. installing Annif in a venv,
-2. loading the vocabulary,
-3. training the projects,
-4. evaluating the projects.
-
-When the necessary vocabulary and training corpora are in place the pipeline can be run using the command
-
-    dvc repro
-    
-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

@@ -1,2 +0,0 @@
-/ykl-classes.tsv
-/ykl-skos.ttl

corpora/kirjaesittelyt2021/.gitignore

@@ -1,9 +0,0 @@
-/kvesit-ykl-fin-train.tsv
-/kvesit-ykl-fin-validate.tsv
-/kvesit-ykl-fin-test.tsv
-/kvesit-ykl-eng-train.tsv
-/kvesit-ykl-eng-validate.tsv
-/kvesit-ykl-eng-test.tsv
-/kvesit-ykl-swe-train.tsv
-/kvesit-ykl-swe-validate.tsv
-/kvesit-ykl-swe-test.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-eng-test.tsv.dvc

@@ -1,10 +0,0 @@
-md5: d0048a06955ce66d56224834e8f6ef9c
-deps:
-- md5: bc7f924d84a20e9ab91e2600fd2415ec
-  size: 210866
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-eng-test.tsv
-  hash: md5
-outs:
-- md5: bc7f924d84a20e9ab91e2600fd2415ec
-  size: 210866
-  path: kvesit-ykl-eng-test.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-eng-train.tsv.dvc

@@ -1,10 +0,0 @@
-md5: fbe7fe15b03297c612dd0e436c9f63af
-deps:
-- md5: 87548d6f8f9a8185dc870e8112668c87
-  size: 1730632
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-eng-train.tsv
-  hash: md5
-outs:
-- md5: 87548d6f8f9a8185dc870e8112668c87
-  size: 1730632
-  path: kvesit-ykl-eng-train.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-eng-validate.tsv.dvc

@@ -1,9 +0,0 @@
-md5: da25cc54ab5e66d5e2ec5c21edc76796
-deps:
-- md5: c1706bb4102fa4799492fd653acc97a2
-  size: 218773
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-eng-validate.tsv
-outs:
-- md5: c1706bb4102fa4799492fd653acc97a2
-  size: 218773
-  path: kvesit-ykl-eng-validate.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-fin-test.tsv.dvc

@@ -1,10 +0,0 @@
-md5: e41640988a93564680ee91b589667028
-deps:
-- md5: 9f8d094ae71ec68c5d40dde46d991e1f
-  size: 4534782
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-fin-test.tsv
-  hash: md5
-outs:
-- md5: 9f8d094ae71ec68c5d40dde46d991e1f
-  size: 4534782
-  path: kvesit-ykl-fin-test.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-fin-train.tsv.dvc

@@ -1,10 +0,0 @@
-md5: d86b6c73a936179a8f4b069e5ac90322
-deps:
-- md5: cc52c6a5c21d799aad3fb73a889cd90e
-  size: 36684502
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-fin-train.tsv
-  hash: md5
-outs:
-- md5: cc52c6a5c21d799aad3fb73a889cd90e
-  size: 36684502
-  path: kvesit-ykl-fin-train.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-fin-validate.tsv.dvc

@@ -1,9 +0,0 @@
-md5: c11ba98458f2295383418b1fd8142813
-deps:
-- md5: 88d1c1d133953681474207186f0408e1
-  size: 4575927
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-fin-validate.tsv
-outs:
-- md5: 88d1c1d133953681474207186f0408e1
-  size: 4575927
-  path: kvesit-ykl-fin-validate.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-swe-test.tsv.dvc

@@ -1,10 +0,0 @@
-md5: 72edc7073e64d873fe62c73201c13965
-deps:
-- md5: a9177ace2f0d1dffa6a424fccdf04b37
-  size: 287821
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-swe-test.tsv
-  hash: md5
-outs:
-- md5: a9177ace2f0d1dffa6a424fccdf04b37
-  size: 287821
-  path: kvesit-ykl-swe-test.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-swe-train.tsv.dvc

@@ -1,10 +0,0 @@
-md5: b1f96f9bf1677ae056540572f3968311
-deps:
-- md5: fa74f039e20594e212d2429eb3e74c13
-  size: 2367569
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-swe-train.tsv
-  hash: md5
-outs:
-- md5: fa74f039e20594e212d2429eb3e74c13
-  size: 2367569
-  path: kvesit-ykl-swe-train.tsv

corpora/kirjaesittelyt2021/kvesit-ykl-swe-validate.tsv.dvc

@@ -1,9 +0,0 @@
-md5: 896803dc4e4492ea12625b363ef21007
-deps:
-- md5: 6ae75a57ef7c1107f55978d759796c94
-  size: 294875
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/kvesit-ykl-swe-validate.tsv
-outs:
-- md5: 6ae75a57ef7c1107f55978d759796c94
-  size: 294875
-  path: kvesit-ykl-swe-validate.tsv

corpora/ykl-classes.tsv.dvc

@@ -1,9 +0,0 @@
-md5: c0b12e0a05399ad397f12e30d4bef364
-deps:
-- md5: b2f29070ccedefda72994b8db324e371
-  size: 187637
-  path: /data/Annif-corpora-restricted/kirjaesittelyt2021/ykl/ykl-classes.tsv
-outs:
-- md5: b2f29070ccedefda72994b8db324e371
-  size: 187637
-  path: ykl-classes.tsv

corpora/ykl-skos.ttl.dvc

@@ -1,10 +0,0 @@
-md5: 7f7e7284f20b95f4d8717a955778e726
-deps:
-- md5: fea11c863134c9e8379ea52e0f31e28a
-  size: 3901929
-  path: /data/Annif-corpora/vocab/ykl-skos.ttl
-  hash: md5
-outs:
-- md5: fea11c863134c9e8379ea52e0f31e28a
-  size: 3901929
-  path: ykl-skos.ttl

data/projects/.gitignore

@@ -1,6 +0,0 @@
-/ykl-omikuji-parabel-fi
-/ykl-omikuji-bonsai-fi
-/ykl-omikuji-bonsai-sv
-/ykl-omikuji-bonsai-en
-/ykl-omikuji-parabel-sv
-/ykl-omikuji-parabel-en

data/projects/ykl-omikuji-bonsai-en/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 12977,
-  "classifier_loss_type": "Hinge"
-}

data/projects/ykl-omikuji-bonsai-fi/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 183181,
-  "classifier_loss_type": "Hinge"
-}

data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree0.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0ecb457f9bf9c5140e70e8e0199019c6a51b75ef76c07f2b51fd1f0a405a13a1
-size 11502388

data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree1.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10c53c4109bc48439bdc987aae2b65ac5a38e4fad527b1a7801a01e6c6db14e2
-size 10790296

data/projects/ykl-omikuji-bonsai-fi/omikuji-model/tree2.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe8a116a2833ce3506044a98e6d0c7fa0b2ebf24a8bb245d025458f2ef276ade
-size 11139212

data/projects/ykl-omikuji-bonsai-fi/vectorizer

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64c591e7f3f33ace9e16502861b00bc2ab771aa2cf1b6ec38cacd60665808fea
-size 6499579

data/projects/ykl-omikuji-bonsai-sv/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 25365,
-  "classifier_loss_type": "Hinge"
-}

data/projects/ykl-omikuji-parabel-en/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 12977,
-  "classifier_loss_type": "Hinge"
-}

data/projects/ykl-omikuji-parabel-fi/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 183181,
-  "classifier_loss_type": "Hinge"
-}

data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree0.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0a2f3add2bd8edea4384ae4ae090f83b036c75761c46883fbc69114109cc25d
-size 12343749

data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree1.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eeec5a04d38a50cc1a3510c5e9f8e51f1c4cf09b0b1ef09f58b45f193fdd0ff1
-size 12255077

data/projects/ykl-omikuji-parabel-fi/omikuji-model/tree2.cbor

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3c3afa19fcc917f642ec84ebaf1a5028ef4b671f791039cfe9cd521cbbcf6c8
-size 12598645

data/projects/ykl-omikuji-parabel-fi/vectorizer

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:64c591e7f3f33ace9e16502861b00bc2ab771aa2cf1b6ec38cacd60665808fea
-size 6499579

data/projects/ykl-omikuji-parabel-sv/omikuji-model/settings.json

@@ -1,4 +0,0 @@
-{
-  "n_features": 25365,
-  "classifier_loss_type": "Hinge"
-}