Prodigy hierarchical text classification (testing)

custom.js

function toggle(id) {
    var x = document.getElementById(id);
    if (id == "a"){
        reset("b")
    }else{
        reset("a")
    }
    if (x.style.display === "none") {
    x.style.display = "block";
    } else {
    x.style.display = "none";
    }
}

function reset(id){
    var x = document.getElementById(id);
    x.style.display = "none"
    var checkboxes = document.getElementsByClassName("checkbox");
    for(let elem in checkboxes){
        checkboxes[elem].checked = false;
    }
}

function update(){
    var checkboxes = document.getElementsByClassName("checkbox");

    var results = [];
    for(let elem in checkboxes){
        if(checkboxes[elem].checked){
            results.push(checkboxes[elem].id)
        }
    }
    prodigy.update({
        selected: results
    })
}

document.addEventListener('prodigyanswer', event => {
    reset("a")
    reset("b")
})

labels.jsonl

{"a": ["sub-option a1","sub-option a2"], "b": ["sub-option b1","sub-option b2"]}

my_recipe2.py

import jinja2
from typing import Union
from pathlib import Path

import srsly
import prodigy
from prodigy.util import msg
from prodigy import set_hashes, get_stream


def load_template(path: Union[str, Path]) -> jinja2.Template:
    if not isinstance(path, Path):
        path = Path(path)
    if not path.suffix == ".jinja2":
        msg.fail(
            "Must supply jinja2 file.",
            exits=1,
        )
    with path.open("r", encoding="utf8") as file_:
        text = file_.read()
    return jinja2.Template(text, undefined=jinja2.DebugUndefined)


@prodigy.recipe(
        "textcat.hierarchical",
        dataset=("The dataset to save to", "positional", None, str),
        source=("The source data as a JSONL file", "positional", None, str),
        labels=("The label hierarchy as a JSONL file", "positional", None, str),
)
def textcat_hierarchical(
    dataset: str, 
    source: str,
    labels: str,
):

    options = list(srsly.read_jsonl(labels))[0]
    stream = get_stream(source, rehash=True, dedup=True)
    template = load_template("template.jinja2")

    def add_template(stream):
        for ex in stream:
            ex['html'] = template.render(options=options)
            yield set_hashes(ex)

    custom_js = Path("custom.js").read_text() 
    
    def before_db(examples):
        for ex in examples:
            del ex['html']
        print(examples)
        return examples

    blocks = [
        {"view_id": "text"},
        {"view_id": "html"},
    ]

    return {
        "view_id": "blocks",         
        "dataset": dataset,   # Name of dataset to save annotations       
        "stream": add_template(stream),  # Incoming stream of examples          
        "config": {
            "blocks": blocks,      
            "javascript": custom_js,
        },
        "before_db": before_db
    }

news_headlines.jsonl

{"text":"Uber\u2019s Lesson: Silicon Valley\u2019s Start-Up Machine Needs Fixing","meta":{"source":"The New York Times"}}
{"text":"Pearl Automation, Founded by Apple Veterans, Shuts Down","meta":{"source":"The New York Times"}}
{"text":"How Silicon Valley Pushed Coding Into American Classrooms","meta":{"source":"The New York Times"}}
{"text":"Women in Tech Speak Frankly on Culture of Harassment","meta":{"source":"The New York Times"}}
{"text":"Silicon Valley Investors Flexed Their Muscles in Uber Fight","meta":{"source":"The New York Times"}}
{"text":"Uber is a Creature of an Industry Struggling to Grow Up","meta":{"source":"The New York Times"}}
{"text":"\u2018The Internet Is Broken\u2019: @ev Is Trying to Salvage It","meta":{"source":"The New York Times"}}
{"text":"The South Park Commons Fills a Hole in the Tech Landscape","meta":{"source":"The New York Times"}}
{"text":"The Closing of the Republican Mind","meta":{"source":"The New York Times"}}
{"text":"Writers From the Right and Left on Trump Jr., the Future of the F.B.I., Health Care and More","meta":{"source":"The New York Times"}}
{"text":"Daily Report: From Lean to Fat Start-Ups","meta":{"source":"The New York Times"}}
{"text":"How Uber\u2019s Chief Is Gaining Even More Clout in the Company","meta":{"source":"The New York Times"}}
{"text":"As New Zealand Courts Tech Talent, Isolation Becomes a Draw","meta":{"source":"The New York Times"}}
{"text":"One Thing Silicon Valley Can\u2019t Seem to Fix","meta":{"source":"The New York Times"}}
{"text":"In Silicon Valley, a Voice of Caution Guides a High-Flying Uber","meta":{"source":"The New York Times"}}
{"text":"Silicon Valley Writes a Protest Letter Against Trump","meta":{"source":"The New York Times"}}
{"text":"Warriors, Tech\u2019s Team, Are Soaring Out of Reach","meta":{"source":"The New York Times"}}
{"text":"Silicon Valley\u2019s Most Elusive Beast","meta":{"source":"The New York Times"}}
{"text":"Wall Street and Silicon Valley Form an Uneasy Alliance","meta":{"source":"The New York Times"}}
{"text":"Tim O'Reilly Explains the Internet of Things","meta":{"source":"The New York Times"}}
{"text":"Alibaba I.P.O. May Unleash Global Fight Over Users","meta":{"source":"The New York Times"}}
{"text":"Disruptions: Looking Beyond Silicon Valley's Bubble","meta":{"source":"The New York Times"}}
{"text":"Twitter Outages Linked to Glitches and Site Upgrade","meta":{"source":"The New York Times"}}
{"text":"Out of the Loop in Silicon Valley","meta":{"source":"The New York Times"}}
{"text":"A Determined Outpost of Tiny Technology","meta":{"source":"The New York Times"}}

template.jinja2

<button onclick="toggle('a')">Option A</button>
<div id="a" style="display: none;">
    <form style="display: block;">
    {%- for reason in options["a"] -%}
        <input type="checkbox" class="checkbox" id="{{reason}}" name="{{reason}}" onchange="update()" style="margin: 0.4rem;"><label for="{{reason}}">{{reason}}</label><br>
    {%- endfor -%}
    </form>
</div>
<button onclick="toggle('b')">Option B</button>
<div id="b" style="display: none;">
<form style="display: block;">
    {%- for reason in options["b"] -%}
        <input type="checkbox" class="checkbox" id="{{reason}}" name="{{reason}}" onchange="update()" style="margin: 0.4rem;"><label for="{{reason}}">{{reason}}</label><br>
    {%- endfor -%}
    </form>
</div>

python -m prodigy textcat.hierarchical news-hier ./data/news_headlines.jsonl ./data/labels.jsonl -F my_recipe2.py