Skip to content
Riksdagen Records: OCR Quality Estimation

Fix speaker mapping #66

Sign in to view logs

Fix speaker mapping

Fix speaker mapping #66

Workflow file for this run

.github/workflows/qe_ocr-estimate.yml at a7cf8b2
name: "Riksdagen Records: OCR Quality Estimation"
on:
pull_request:
branches:
- 'dev'
paths:
- data/**
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.job }}-artifacts-${{ github.ref }}
cancel-in-progress: false
jobs:
decade-1860:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1860 --lev-only
- name: Cache result 1860s
uses: actions/upload-artifact@v4
with:
name: lev_1860
path: quality/estimates/ocr-estimation/lev-by-decade/1860_mpl_lev.tsv
decade-1870:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1880 --lev-only
- name: Cache result 1870s
uses: actions/upload-artifact@v4
with:
name: lev_1870
path: quality/estimates/ocr-estimation/lev-by-decade/1870_mpl_lev.tsv
decade-1880:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1880 --lev-only
- name: Cache result 1880s
uses: actions/upload-artifact@v4
with:
name: lev_1880
path: quality/estimates/ocr-estimation/lev-by-decade/1880_mpl_lev.tsv
decade-1890:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1890 --lev-only
- name: Cache result 1880s
uses: actions/upload-artifact@v4
with:
name: lev_1890
path: quality/estimates/ocr-estimation/lev-by-decade/1890_mpl_lev.tsv
decade-1900:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1900 --lev-only
- name: Cache result 1900s
uses: actions/upload-artifact@v4
with:
name: lev_1900
path: quality/estimates/ocr-estimation/lev-by-decade/1900_mpl_lev.tsv
decade-1910:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1910 --lev-only
- name: Cache result 1910s
uses: actions/upload-artifact@v4
with:
name: lev_1910
path: quality/estimates/ocr-estimation/lev-by-decade/1910_mpl_lev.tsv
decade-1920:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1920 --lev-only
- name: Cache result 1920s
uses: actions/upload-artifact@v4
with:
name: lev_1920
path: quality/estimates/ocr-estimation/lev-by-decade/1920_mpl_lev.tsv
decade-1930:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1930 --lev-only
- name: Cache result 1930s
uses: actions/upload-artifact@v4
with:
name: lev_1930
path: quality/estimates/ocr-estimation/lev-by-decade/1930_mpl_lev.tsv
decade-1940:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1940 --lev-only
- name: Cache result 1940s
uses: actions/upload-artifact@v4
with:
name: lev_1940
path: quality/estimates/ocr-estimation/lev-by-decade/1940_mpl_lev.tsv
decade-1950:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1950 --lev-only
- name: Cache result 1950s
uses: actions/upload-artifact@v4
with:
name: lev_1950
path: quality/estimates/ocr-estimation/lev-by-decade/1950_mpl_lev.tsv
decade-1960:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1960 --lev-only
- name: Cache result 1960s
uses: actions/upload-artifact@v4
with:
name: lev_1960
path: quality/estimates/ocr-estimation/lev-by-decade/1960_mpl_lev.tsv
decade-1970:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1970 --lev-only
- name: Cache result 1970s
uses: actions/upload-artifact@v4
with:
name: lev_1970
path: quality/estimates/ocr-estimation/lev-by-decade/1970_mpl_lev.tsv
decade-1980:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Estimate OCR Quality
run: |
python quality/qe_ocr-estimation.py -D 1980 --lev-only
- name: Cache result 1980s
uses: actions/upload-artifact@v4
with:
name: lev_1980
path: quality/estimates/ocr-estimation/lev-by-decade/1980_mpl_lev.tsv
summarize-decadewize-reults:
needs: [decade-1860, decade-1870, decade-1880, decade-1890, decade-1900, decade-1910, decade-1920, decade-1930, decade-1940, decade-1950, decade-1960, decade-1970, decade-1980]
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
steps:
- uses: actions/checkout@v4
- uses: ./.github/actions/checkout
- uses: ./.github/actions/setup-python
with:
python-version: ${{ matrix.python-version }}
- uses: ./.github/actions/free-up-space
- uses: ./.github/actions/install-dependencies
- name: Install extra dependencies
run: |
pip install nltk
- name: Download artifacts from decade jobs
uses: actions/download-artifact@v4
with:
path: quality/estimates/ocr-estimation/lev-by-decade
merge-multiple: true
- name: Summarize results
run: |
python quality/qe_ocr-estimation.py --read-lev --concat-lev
- name: Add and commit changes
run: |
git config --local user.email "41898282+github-actions[bot]@users.noreply.github.com"
git config --local user.name "github-actions[bot]"
if [[ `git status quality/estimates/ocr-estimation/ --porcelain --untracked-files=no` ]]; then
git add quality/estimates/ocr-estimation
git commit -m "chore (workflow): run OCR quality estimation"
else
echo "::warning:: WARNING!! No changes detected in the quality/estimates/ocr-estimation folder"
git commit --allow-empty -m "chore (workflow): no changes to OCR quality estimation"
fi
- uses: ./.github/actions/pull-push
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
branch: ${{ github.head_ref }}