Quality estimation documentation #11
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "Riksdagen Records: OCR Quality Estimation" | |
on: | |
pull_request: | |
branches: | |
- 'dev' | |
jobs: | |
decade-1860: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1860 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1860* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1860s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1870: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1870 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1870* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1870s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1880: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1880 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1880* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1880s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1890: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1890 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1890* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1890s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1900: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1900 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1900* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1900s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1910: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1910 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1910* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1910s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1920: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1920 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1920* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1920s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1930: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1930 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1930* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1930s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1940: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1940 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1940* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1940s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1950: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1950 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1950* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1950" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1960: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1960 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1960* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1960s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1970: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1970 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1970* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1970s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
decade-1980: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
python-version: [3.8] | |
steps: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Estimate OCR Quality | |
run: | | |
python quality/qe_ocr-estimation.py -D 1980 --lev-only | |
- 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]" | |
git add quality/estimates/ocr-estimation/lev-by-decade/1980* | |
git commit -m "chore (workflow): find MPL and calculate lev for 1980s" | |
git pull origin ${{ github.head_ref }} | |
- name: Push changes | |
uses: ad-m/github-push-action@master | |
with: | |
github_token: ${{ secrets.GITHUB_TOKEN }} | |
branch: ${{ github.head_ref }} | |
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: | |
- name: Checkout PR source branch | |
uses: actions/checkout@v4 | |
with: | |
ref: ${{ github.head_ref }} | |
- name: Set up Python ${{ matrix.python-version }} | |
uses: actions/setup-python@v5 | |
with: | |
python-version: ${{ matrix.python-version }} | |
- name: Install dependencies | |
run: | | |
python -m pip install --upgrade pip | |
pip install pyriksdagen | |
pip install torchmetrics | |
pip install nltk | |
- name: Summarize results | |
run: | | |
python quality/qe_ocr-estimation.py --read-lev --concat-lev |