How makshobela/linearalgebraproject works
This command-line application prepares Swiss German sentence data, trains one custom linear SVM per dialect, reports validation accuracy and errors, and can classify user-entered sentences. Its main workflow is orchestrated by main.py; preparation writes per-dialect feature files and a held-out test set, which training and validation use. The README also documents configurable training parameters and four target dialects. The graph follows the shown calls and file operations; it does not assume details of unsampled code.
Main entry points: main.py CLI orchestrator · prepare_data.py Dataset preparation · train_data.py Training coordinator · error_report.py Validation report
Components 11
Data preparation
- Dataset preparation
src/prepare_data.py - Dialect feature files
src/prepare_data.py - Held-out test set
src/prepare_data.py
Dialect models
- Training coordinator
src/train_data.py - Manual linear SVM
src/train_data.py - Trained dialect models
src/train_data.py
Prediction and validation
- Dialect prediction
src/inference.py - Validation report
src/error_report.py
Other components
- CLI user
- CLI orchestrator
main.py - Swiss dialect corpus
Connections 16
- CLI user → CLI orchestrator: sets options
main.py - CLI orchestrator → Dataset preparation: prepares data
main.py - Swiss dialect corpus → Dataset preparation: provides parquet
- Dataset preparation → Dialect feature files: writes features
src/prepare_data.py - Dataset preparation → Held-out test set: writes split
src/prepare_data.py - CLI orchestrator → Training coordinator: starts training
main.py - Dialect feature files → Training coordinator: supplies matrices
src/train_data.py - Training coordinator → Manual linear SVM: trains each dialect
src/train_data.py - Training coordinator → Trained dialect models: returns models
src/train_data.py - CLI orchestrator → Validation report: runs validation
main.py - Trained dialect models → Validation report: supplies classifiers
main.py - Held-out test set → Validation report: provides examples
src/error_report.py - Validation report → Dialect prediction: predicts test rows
src/error_report.py - CLI user → CLI orchestrator: enters sentences
main.py - CLI orchestrator → Dialect prediction: requests prediction
main.py - Trained dialect models → Dialect prediction: supplies classifiers
main.py