sarcasm-project.yml

title: "Demo Textcat (Text Classification)"
description: "A minimal demo textcat project for spaCy v3."
# Variables can be referenced across the project.yml using ${vars.var_name}
vars:
  name: "textcat_sarcasm"
  # Supported languages: all except ja, ko, th, vi, and zh, which would require
  # custom tokenizer settings in config.cfg
  lang: "en"
  # Set your GPU ID, -1 is CPU
  gpu_id: -1
  version: "0.0.0"
  train: "data.train.jsonl"
  dev: "data.valid.jsonl"
  config: "config.conf"

# These are the directories that the project needs. The project CLI will make
# sure that they always exist.
directories: ["assets", "corpus", "configs", "training", "scripts", "packages"]

# Assets that should be downloaded or available in the directory. We're shipping
# them with the project, so they won't have to be downloaded.
assets:
  - dest: "assets/${vars.train}"
    description: "Demo training data"
  - dest: "assets/${vars.dev}"
    description: "Demo development data"

# Workflows are sequences of commands (see below) executed in order. You can
# run them via "spacy project run [workflow]". If a commands's inputs/outputs
# haven't changed, it won't be re-run.
workflows:
  all:
    - convert
    - train
    - evaluate
    - package

# Project commands, specified in a style similar to CI config files (e.g. Azure
# pipelines). The name is the command name that lets you trigger the command
# via "spacy project run [command] [path]". The help message is optional and
# shown when executing "spacy project run [optional command] [path] --help".
commands:
  - name: "convert"
    help: "Convert the data to spaCy's binary format"
    script:
      - "python scripts/convert.py ${vars.lang} assets/${vars.train} corpus/train.spacy"
      - "python scripts/convert.py ${vars.lang} assets/${vars.dev} corpus/dev.spacy"
    deps:
      - "assets/${vars.train}"
      - "assets/${vars.dev}"
      - "scripts/convert.py"
    outputs:
      - "corpus/train.spacy"
      - "corpus/dev.spacy"

  - name: "train"
    help: "Train the textcat model"
    script:
      - "python -m spacy train configs/${vars.config} --output training/ --paths.train corpus/train.spacy --paths.dev corpus/dev.spacy --nlp.lang ${vars.lang} --gpu-id ${vars.gpu_id}"
    deps:
      - "configs/${vars.config}"
      - "corpus/train.spacy"
      - "corpus/dev.spacy"
    outputs:
      - "training/model-best"

  - name: "evaluate"
    help: "Evaluate the model and export metrics"
    script:
      - "python -m spacy evaluate training/model-best corpus/dev.spacy --output training/metrics.json"
    deps:
      - "corpus/dev.spacy"
      - "training/model-best"
    outputs:
      - "training/metrics.json"

  - name: package
    help: "Package the trained model as a pip package"
    script:
      - "python -m spacy package training/model-best packages --name ${vars.name} --version ${vars.version} --force"
    deps:
      - "training/model-best"
    outputs_no_cache:
      - "packages/${vars.lang}_${vars.name}-${vars.version}/dist/${vars.lang}_${vars.name}-${vars.version}.tar.gz"

  - name: visualize-model
    help: Visualize the model's output interactively using Streamlit
    script:
      - "streamlit run scripts/visualize_model.py training/model-best \"provision Portland K8s cluster\""
    deps:
      - "scripts/visualize_model.py"
      - "training/model-best"