'use strict';
import { Templater, handleResponse, convertNumber } from './util.js';
/**
* Chart.js defaults
*/
Chart.defaults.global.legend.position = 'bottom';
Chart.defaults.global.defaultFontFamily = "-apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol'";
const CHART_COLORS = { model1: '#09a3d5', model2: '#066B8C' };
/**
* Formatters for model details.
* @property {function} author – Format model author with optional link.
* @property {function} license - Format model license with optional link.
* @property {function} sources - Format training data sources (list or string).
* @property {function} pipeline - Format list of pipeline components.
* @property {function} vectors - Format vector data (entries and dimensions).
* @property {function} version - Format model version number.
*/
export const formats = {
author: (author, url) => url ? `${author}` : author,
license: (license, url) => url ? `${license}` : license,
sources: sources => (sources instanceof Array) ? sources.join(', ') : sources,
pipeline: pipes => (pipes && pipes.length) ? pipes.map(p => `${p}
`).join(', ') : '-',
vectors: vec => vec ? `${convertNumber(vec.entries)} (${vec.width} dimensions)` : 'n/a',
version: version => `v${version}
`
};
/**
* Find the latest version of a model in a compatibility table.
* @param {string} model - The model name.
* @param {Object} compat - Compatibility table, keyed by spaCy version.
*/
export const getLatestVersion = (model, compat = {}) => {
for (let [spacy_v, models] of Object.entries(compat)) {
if (models[model]) return models[model][0];
}
};
export class ModelLoader {
/**
* Load model meta from GitHub and update model details on site. Uses the
* Templater mini template engine to update DOM.
* @param {string} repo - Path tp GitHub repository containing releases.
* @param {Array} models - List of model IDs, e.g. "en_core_web_sm".
* @param {Object} licenses - License IDs mapped to URLs.
* @param {Object} benchmarkKeys - Objects of available keys by type, e.g.
* 'parser', 'ner', 'speed', mapped to labels.
*/
constructor(repo, models = [], licenses = {}, benchmarkKeys = {}) {
this.url = `https://raw.githubusercontent.com/${repo}/master`;
this.repo = `https://github.com/${repo}`;
this.modelIds = models;
this.licenses = licenses;
this.benchKeys = benchmarkKeys;
this.init();
}
init() {
this.modelIds.forEach(modelId =>
new Templater(modelId).get('table').setAttribute('data-loading', ''));
this.fetch(`${this.url}/compatibility.json`)
.then(json => this.getModels(json.spacy))
.catch(_ => this.modelIds.forEach(modelId => this.showError(modelId)));
// make sure scroll positions for progress bar etc. are recalculated
window.dispatchEvent(new Event('resize'));
}
fetch(url) {
return new Promise((resolve, reject) =>
fetch(url).then(res => handleResponse(res))
.then(json => json.ok ? resolve(json) : reject()))
}
getModels(compat) {
this.compat = compat;
for (let modelId of this.modelIds) {
const version = getLatestVersion(modelId, compat);
if (version) this.fetch(`${this.url}/meta/${modelId}-${version}.json`)
.then(json => this.render(json))
.catch(_ => this.showError(modelId))
else this.showError(modelId);
}
}
showError(modelId) {
const tpl = new Templater(modelId);
tpl.get('table').removeAttribute('data-loading');
tpl.get('error').style.display = 'block';
for (let key of ['sources', 'pipeline', 'vectors', 'author', 'license']) {
tpl.get(key).parentElement.parentElement.style.display = 'none';
}
}
/**
* Update model details in tables. Currently quite hacky :(
*/
render(data) {
const modelId = `${data.lang}_${data.name}`;
const model = `${modelId}-${data.version}`;
const tpl = new Templater(modelId);
this.renderDetails(tpl, data)
this.renderBenchmarks(tpl, data.accuracy, data.speed);
this.renderCompat(tpl, modelId);
tpl.get('download').setAttribute('href', `${this.repo}/releases/tag/${model}`);
tpl.get('table').removeAttribute('data-loading');
}
renderDetails(tpl, { version, size, description, notes, author, url,
license, sources, vectors, pipeline }) {
const basics = { version, size, description, notes }
for (let [key, value] of Object.entries(basics)) {
if (value) tpl.fill(key, value);
}
if (author) tpl.fill('author', formats.author(author, url), true);
if (license) tpl.fill('license', formats.license(license, this.licenses[license]), true);
if (sources) tpl.fill('sources', formats.sources(sources));
if (vectors) tpl.fill('vectors', formats.vectors(vectors));
else tpl.get('vectors').parentElement.parentElement.style.display = 'none';
if (pipeline && pipeline.length) tpl.fill('pipeline', formats.pipeline(pipeline), true);
else tpl.get('pipeline').parentElement.parentElement.style.display = 'none';
}
renderBenchmarks(tpl, accuracy = {}, speed = {}) {
if (!accuracy && !speed) return;
this.renderTable(tpl, 'parser', accuracy, val => val.toFixed(2));
this.renderTable(tpl, 'ner', accuracy, val => val.toFixed(2));
this.renderTable(tpl, 'speed', speed, Math.round);
tpl.get('benchmarks').style.display = 'block';
}
renderTable(tpl, id, benchmarks, converter = val => val) {
if (!this.benchKeys[id] || !Object.keys(this.benchKeys[id]).some(key => benchmarks[key])) return;
for (let key of Object.keys(this.benchKeys[id])) {
if (benchmarks[key]) tpl
.fill(key, convertNumber(converter(benchmarks[key])))
.parentElement.style.display = 'table-row';
}
tpl.get(id).style.display = 'block';
}
renderCompat(tpl, modelId) {
tpl.get('compat-wrapper').style.display = 'table-row';
const header = '';
const options = Object.keys(this.compat)
.map(v => ``)
.join('');
tpl
.fill('compat', header + options, true)
.addEventListener('change', ({ target: { value }}) =>
tpl.fill('compat-versions', this.getCompat(value, modelId), true))
}
getCompat(version, model) {
const res = this.compat[version][model];
return res ? `${model}-${res[0]}
` : 'not compatible';
}
}
export class ModelComparer {
/**
* Compare to model meta files and render chart and comparison table.
* @param {string} repo - Path tp GitHub repository containing releases.
* @param {Object} licenses - License IDs mapped to URLs.
* @param {Object} benchmarkKeys - Objects of available keys by type, e.g.
* 'parser', 'ner', 'speed', mapped to labels.
* @param {Object} languages - Available languages, ID mapped to name.
* @param {Object} defaultModels - Models to compare on load, 'model1' and
* 'model2' mapped to model names.
*/
constructor(repo, licenses = {}, benchmarkKeys = {}, languages = {}, labels = {}, defaultModels) {
this.url = `https://raw.githubusercontent.com/${repo}/master`;
this.repo = `https://github.com/${repo}`;
this.tpl = new Templater('compare');
this.benchKeys = benchmarkKeys;
this.licenses = licenses;
this.languages = languages;
this.labels = labels;
this.models = {};
this.colors = CHART_COLORS;
this.defaultModels = defaultModels;
this.fetchCompat()
.then(compat => this.init(compat))
.catch(this.showError.bind(this))
}
init(compat) {
this.compat = compat;
const selectA = this.tpl.get('model1');
const selectB = this.tpl.get('model2');
selectA.addEventListener('change', this.onSelect.bind(this));
selectB.addEventListener('change', this.onSelect.bind(this));
this.chart = new Chart('chart_compare_accuracy', { type: 'bar',
options: { responsive: true, scales: {
yAxes: [{ label: 'Accuracy', ticks: { min: 70 }}],
xAxes: [{ barPercentage: 0.75 }]
}}
});
if (this.defaultModels) {
selectA.value = this.defaultModels.model1;
selectB.value = this.defaultModels.model2;
this.getModels(this.defaultModels);
}
}
fetchCompat() {
return new Promise((resolve, reject) =>
fetch(`${this.url}/compatibility.json`)
.then(res => handleResponse(res))
.then(json => json.ok ? resolve(json.spacy) : reject()))
}
fetchModel(name) {
const version = getLatestVersion(name, this.compat);
const modelName = `${name}-${version}`;
return new Promise((resolve, reject) => {
// resolve immediately if model already loaded, e.g. in this.models
if (this.models[name]) resolve(this.models[name]);
else fetch(`${this.url}/meta/${modelName}.json`)
.then(res => handleResponse(res))
.then(json => json.ok ? resolve(this.saveModel(name, json)) : reject())
})
}
/**
* "Save" meta to this.models so it only has to be fetched from GitHub once.
* @param {string} name - The model name.
* @param {Object} data - The model meta data.
*/
saveModel(name, data) {
this.models[name] = data;
return data;
}
showError() {
this.tpl.get('result').style.display = 'none';
this.tpl.get('error').style.display = 'block';
}
onSelect(ev) {
const modelId = ev.target.value;
const otherId = (ev.target.id == 'model1') ? 'model2' : 'model1';
const otherVal = this.tpl.get(otherId);
const otherModel = otherVal.options[otherVal.selectedIndex].value;
if (otherModel != '') this.getModels({
[ev.target.id]: modelId,
[otherId]: otherModel
})
}
getModels({ model1, model2 }) {
this.tpl.get('result').setAttribute('data-loading', '');
this.fetchModel(model1)
.then(data1 => this.fetchModel(model2)
.then(data2 => this.render({ model1: data1, model2: data2 })))
.catch(this.showError.bind(this))
}
/**
* Render two models, and populate the chart and table. Currently quite hacky :(
* @param {Object} models - The models to render.
* @param {Object} models.model1 - The first model (via first