How syedanazish-debug/verifier_model works
Verifier Lense is a Flask-based fake/real news text classifier. The main user flow is submitting article text in the web form, vectorizing it with the saved TF-IDF artifact, classifying it with the saved model, and displaying a label and confidence. Separate scripts prepare labeled data and train or evaluate models. The README mentions broader real-time verification and APIs, but the sampled runtime shows no such integration; the graph reflects the implemented workflow and documented capabilities only where supported. Training-script links are limited to relationships visible in the excerpts.
Main entry points: app.py Prediction route · dataset_process.py Dataset preparation · index.html News form · News _dataset Combined labeled data
Components 14
Web classification
- Prediction route
app.py - News form
templates/index.html
Inference artifacts
- Saved classifier
model/VERIFIER LENSE MODEL.pkl - Saved TF-IDF
model/TF-IDF_VECTORIZIER.pkl
Dataset preparation
- Fake articles
News _dataset/Fake.csv - Real articles
News _dataset/True.csv - Dataset preparation
dataset_process.py - Data diagnostics
dignostics.py - Combined labeled data
News _dataset
Model development
- Baseline training
baseline_modf.py - Grouped split
basetrain_modf.py - Refined text model
control_ref_mod.py - Title classifier
verifer_model.py
Other components
- News submitter
Connections 13
- News submitter → News form: enters text
- News form → Prediction route: posts text
app.py - Prediction route → Saved TF-IDF: vectorizes with
app.py - Prediction route → Saved classifier: predicts with
app.py - Prediction route → News form: renders result
app.py - Dataset preparation → Fake articles: reads
dataset_process.py - Dataset preparation → Real articles: reads
dataset_process.py - Dataset preparation → Combined labeled data: writes combined data
dataset_process.py - Data diagnostics → Fake articles: inspects
dignostics.py - Data diagnostics → Real articles: inspects
dignostics.py - Baseline training → Combined labeled data: loads data
baseline_modf.py - Grouped split → Combined labeled data: loads data
basetrain_modf.py - Refined text model → Baseline training: uses training split
control_ref_mod.py