🪐 spaCy Project: Demo spancat in a new pipeline (Span Categorization)
A minimal demo spancat project for spaCy v3
📋 project.yml
The project.yml
defines the data assets required by the
project, as well as the available commands and workflows. For details, see the
spaCy projects documentation.
⏯ Commands
The following commands are defined by the project. They
can be executed using spacy project run [name]
.
Commands are only re-run if their inputs have changed.
Command | Description |
---|---|
download |
Download a spaCy model with pretrained vectors |
convert |
Convert the data to spaCy's binary format |
create-config |
Create a new config with a spancat pipeline component |
train |
Train the spancat model |
train-with-vectors |
Train the spancat model with vectors |
evaluate |
Evaluate the model and export metrics |
package |
Package the trained model as a pip package |
clean |
Remove intermediary directories |
⏭ Workflows
The following workflows are defined by the project. They
can be executed using spacy project run [name]
and will run the specified commands in order. Commands are only re-run if their
inputs have changed.
Workflow | Steps |
---|---|
all |
convert → create-config → train → evaluate |
all-vectors |
download → convert → create-config → train-with-vectors → evaluate |
🗂 Assets
The following assets are defined by the project. They can
be fetched by running spacy project assets
in the project directory.
File | Source | Description |
---|---|---|
assets/train.json |
Local | Demo training data adapted from the ner_demo project |
assets/dev.json |
Local | Demo development data |