VANA/VANA-python/subtitles_processing
Giò Diani 44df18fcfb search 2025-01-26 23:26:55 +01:00
..
src/subtitles_processing search 2025-01-26 23:26:55 +01:00
.gitattributes improvement topic modelling 2025-01-16 22:18:12 +01:00
.gitignore improvement topic modelling 2025-01-16 22:18:12 +01:00
README.md sentiments colors, topics in dashboard 2025-01-17 08:54:42 +01:00
pixi.lock improvement topic modelling 2025-01-16 22:18:12 +01:00
pyproject.toml improvement topic modelling 2025-01-16 22:18:12 +01:00

README.md

subtitles_processing

Paket zur Aufbereitung der Untertitel.

subtitles-processing.py

Normalisiert die Untertitel einer Episode. Die timecodes werden umgespeichert, damit immer ganze Sätze pro Zeile vorhanden sind.

python src/normalize_subtitles/subtitles-processing.py -a <"normalize"> -ep <int>

count_words.py

Zählt die Wortanzahl pro Satz.

python src/normalize_subtitles/count_words.py -ep <int>

sentence_sentiment.py

Rechnet die Sentimente pro Satz.

python src/normalize_subtitles/sentence_sentiment.py -ep <int>

topics.py

Generiert Topics mittels LDA.

python src/normalize_subtitles/topics.py -ep <int>