Repository files navigation

Available languages:English |Ελληνικά

This repository provides a lightweightdesktop GUI application for analyzing, extracting, and exporting linguistic information from plain-text files.

This repository contains:

• Talos_Text_Analyser.py — the complete source code (all-in-one Tkinter application)
• Talos_Text_Analyser_Documentation.pdf — installation & usage guide (Version 2.0)

TheTALOS Text File Analyser (TFA) is a cross-platformdesktop tool (Tkinter) forinteractive text analysis. It can:

• PerformWord frequency analysis
• ExtractNouns (POS-based)
• DetectPerson andLocation names (NER)
• RunLemmatization
• ExtractLexico-Syntactic Patterns (predefined & custom up to 5 tokens)
• Export results toExcel (.xlsx) andCSV

Designed forresearchers, educators, and developers, with special support forAncient Greek via Stanza andmodern languages via spaCy.

• Language detection (automatic) with tuned English/Greek heuristics; supports Ancient & Modern Greek distinctions.
• Six analysis modes: Words, Nouns, Person names, Location names, Lemmas, Pattern extraction.
• Custom pattern builder (POS templates, wildcard, up to 5 positions).
• Export to Excel (multi-sheet) and CSV.
• Multilingual NLP: spaCy models for modern languages; Stanza forAncient Greek (grc).
• Modern dark UI with progress bars and responsive feedback.

# 1) Ensure Python 3.8+ is installedpython --version# 2) Install core librariespip install pandas openpyxl spacy langdetect stanza# 3) Install spaCy language models (essential)python -m spacy download en_core_web_smpython -m spacy download el_core_news_sm# Greek# 4) Install Stanza Ancient Greek model (one-time)python -<< 'PY'import stanzastanza.download("grc")PY# 5) Launch the GUI applicationpython Talos_Text_Analyser.py

Prof. Christophe Roche — TALOS ERA Chair Holder — University of Crete

📧roche.university@gmail.com

🌐https://talos-ai4ssh.uoc.gr/

For general reference to the project:

Roche, C. (2025). TALOS Text File Analyser (Version 2.0).
TALOS AI4SSH Project, University of Crete.
https://talos-ai4ssh.uoc.gr/

All the code is distributed under theCreative Commons Attribution–NonCommercial (CC BY-NC 4.0) license.
You are free toshare and redistribute the material under the following conditions:

• BY: Credit must be given to the creator(s).
• NC: Only non-commercial uses are permitted.

More info:https://creativecommons.org/licenses/by-nc/4.0/

• TALOS Text File Analyser Website:talos-ai4ssh.eu/Text_Analyser
• TALOS Project Website:talos-ai4ssh.uoc.gr