How wooseok-shin/hscode_identification works
This repository is a research prototype for identifying Harmonized System codes from trade-item names. Its workflow cleans labeled product-name data, builds Word2Vec-based inputs, trains a classifier for either two- or four-digit codes, and predicts ranked classes for new names; the README describes expanding predictions to six digits by cosine similarity. The six scripts combine these stages rather than calling a shared training pipeline, and import helpers from modules.py. The excerpts show preprocessing, model construction and prediction, but not the full training or similarity-expansion implementation.
Main entry points: modules.py Cleaning and metrics · CNN_2digits.py CNN 2-digit · CNN_4digits.py CNN 4-digit · FCN_2digits.py FCN 2-digit
Components 11
Shared preparation
- Cleaning and metrics
modules.py
CNN classifiers
- CNN 2-digit
CNN_2digits.py - CNN 4-digit
CNN_4digits.py
FCN classifiers
- FCN 2-digit
FCN_2digits.py - FCN 4-digit
FCN_4digits.py
LSTM classifiers
- LSTM 2-digit
LSTM_2digits.py - LSTM 4-digit
LSTM_4digits.py
Other components
- Trade user
- Labeled names
- Ranked code predictions
- Six-digit expansion
Connections 25
- Trade user → CNN 2-digit: runs prediction
README.md - Trade user → CNN 4-digit: runs prediction
README.md - Trade user → FCN 2-digit: runs prediction
README.md - Trade user → FCN 4-digit: runs prediction
README.md - Trade user → LSTM 2-digit: runs prediction
README.md - Trade user → LSTM 4-digit: runs prediction
README.md - Labeled names → CNN 2-digit: reads labels
CNN_2digits.py - Labeled names → CNN 4-digit: reads labels
CNN_4digits.py - Labeled names → FCN 2-digit: reads labels
FCN_2digits.py - Labeled names → FCN 4-digit: reads labels
FCN_4digits.py - Labeled names → LSTM 2-digit: reads labels
LSTM_2digits.py - Labeled names → LSTM 4-digit: reads labels
LSTM_4digits.py - CNN 2-digit → Cleaning and metrics: imports helpers
CNN_2digits.py - CNN 4-digit → Cleaning and metrics: imports helpers
CNN_4digits.py - FCN 2-digit → Cleaning and metrics: imports helpers
FCN_2digits.py - FCN 4-digit → Cleaning and metrics: imports helpers
FCN_4digits.py - LSTM 2-digit → Cleaning and metrics: imports helpers
LSTM_2digits.py - LSTM 4-digit → Cleaning and metrics: imports helpers
LSTM_4digits.py - CNN 2-digit → Ranked code predictions: prints predictions
CNN_2digits.py - CNN 4-digit → Ranked code predictions: prints predictions
CNN_4digits.py - FCN 2-digit → Ranked code predictions: prints predictions
FCN_2digits.py - FCN 4-digit → Ranked code predictions: prints predictions
FCN_4digits.py - LSTM 2-digit → Ranked code predictions: prints predictions
LSTM_2digits.py - LSTM 4-digit → Ranked code predictions: prints predictions
LSTM_4digits.py - Ranked code predictions → Six-digit expansion: expands by similarity
README.md