-
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
2 changed files
with
187 additions
and
0 deletions.
There are no files selected for viewing
43 changes: 43 additions & 0 deletions
43
machine-learn/scrape_data/level0/Gemini-synthetic-v2/0-create-yml-list.py
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,43 @@ | ||
def generate_jobs(start, end, step, output_file): | ||
job_template = """ process_songs_{start}-{end}: | ||
runs-on: ubuntu-latest | ||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
- name: Run Python Script for lines {start}-{end} | ||
env: | ||
GEMINI_API_KEY: ${{{{ secrets.GEMINI_API_KEY }}}} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py {start} {end} | ||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-{start}-{end} | ||
path: tagged_songs.json | ||
""" | ||
|
||
jobs = [] | ||
|
||
for i in range(start, end, step): | ||
job_start = i | ||
job_end = i + step - 1 | ||
jobs.append(job_template.format(start=job_start, end=job_end)) | ||
|
||
with open(output_file, 'w') as f: | ||
f.write("\n".join(jobs)) | ||
|
||
# Generate jobs for ranges 1000 to 5000 with a step of 1000 | ||
generate_jobs(0, 10000, 2000, 'jobs_output.txt') |
144 changes: 144 additions & 0 deletions
144
machine-learn/scrape_data/level0/Gemini-synthetic-v2/jobs_output.txt
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,144 @@ | ||
process_songs_0-1999: | ||
runs-on: ubuntu-latest | ||
|
||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
|
||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
|
||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
|
||
- name: Run Python Script for lines 0-1999 | ||
env: | ||
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py 0 1999 | ||
|
||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-0-1999 | ||
path: tagged_songs.json | ||
|
||
process_songs_2000-3999: | ||
runs-on: ubuntu-latest | ||
|
||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
|
||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
|
||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
|
||
- name: Run Python Script for lines 2000-3999 | ||
env: | ||
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py 2000 3999 | ||
|
||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-2000-3999 | ||
path: tagged_songs.json | ||
|
||
process_songs_4000-5999: | ||
runs-on: ubuntu-latest | ||
|
||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
|
||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
|
||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
|
||
- name: Run Python Script for lines 4000-5999 | ||
env: | ||
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py 4000 5999 | ||
|
||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-4000-5999 | ||
path: tagged_songs.json | ||
|
||
process_songs_6000-7999: | ||
runs-on: ubuntu-latest | ||
|
||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
|
||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
|
||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
|
||
- name: Run Python Script for lines 6000-7999 | ||
env: | ||
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py 6000 7999 | ||
|
||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-6000-7999 | ||
path: tagged_songs.json | ||
|
||
process_songs_8000-9999: | ||
runs-on: ubuntu-latest | ||
|
||
steps: | ||
- name: Checkout code | ||
uses: actions/checkout@v4 | ||
|
||
- name: Set up Python | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: '3.11' | ||
|
||
- name: Install dependencies | ||
run: | | ||
python -m pip install --upgrade pip | ||
pip install google-generativeai | ||
|
||
- name: Run Python Script for lines 8000-9999 | ||
env: | ||
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }} | ||
run: | | ||
python machine-learn/scrape_data/level0/Gemini-synthetic-v2/1-gemini_tagging-api.py 8000 9999 | ||
|
||
- name: Upload Artifact | ||
uses: actions/upload-artifact@v4 | ||
with: | ||
name: song-tags-output-8000-9999 | ||
path: tagged_songs.json |