app.py

import spacy
from spacy import displacy
import random
from spacy.tokens import Span
import gradio as gr
import pandas as pd

DEFAULT_MODEL = "en_core_web"
DEFAULT_TEXT = "Apple is looking at buying U.K. startup for $1 billion."
DEFAULT_TOK_ATTR = ['idx', 'text', 'pos_', 'lemma_', 'shape_', 'dep_']
DEFAULT_ENTS = ['CARDINAL', 'DATE', 'EVENT', 'FAC', 'GPE', 'LANGUAGE', 'LAW', 'LOC', 'MONEY',
                'NORP', 'ORDINAL', 'ORG', 'PERCENT', 'PERSON', 'PRODUCT', 'QUANTITY', 'TIME', 'WORK_OF_ART']

texts = {"en": DEFAULT_TEXT, "ca": "Apple està buscant comprar una startup del Regne Unit per mil milions de dòlars", "da": "Apple overvejer at købe et britisk startup for 1 milliard dollar.", "de": "Die ganze Stadt ist ein Startup: Shenzhen ist das Silicon Valley für Hardware-Firmen",
         "el": "Η άνιση κατανομή του πλούτου και του εισοδήματος, η οποία έχει λάβει τρομερές διαστάσεις, δεν δείχνει τάσεις βελτίωσης.", "es": "Apple está buscando comprar una startup del Reino Unido por mil millones de dólares.", "fi": "Itseajavat autot siirtävät vakuutusvastuun autojen valmistajille", "fr": "Apple cherche à acheter une start-up anglaise pour 1 milliard de dollars", "it": "Apple vuole comprare una startup del Regno Unito per un miliardo di dollari",
         "ja": "アップルがイギリスの新興企業を１０億ドルで購入を検討", "ko": "애플이 영국의 스타트업을 10억 달러에 인수하는 것을 알아보고 있다.", "lt": "Jaunikis pirmąją vestuvinę naktį iškeitė į areštinės gultą", "nb": "Apple vurderer å kjøpe britisk oppstartfirma for en milliard dollar.", "nl": "Apple overweegt om voor 1 miljard een U.K. startup te kopen",
         "pl": "Poczuł przyjemną woń mocnej kawy.", "pt": "Apple está querendo comprar uma startup do Reino Unido por 100 milhões de dólares", "ro": "Apple plănuiește să cumpere o companie britanică pentru un miliard de dolari", "ru": "Apple рассматривает возможность покупки стартапа из Соединённого Королевства за $1 млрд", "sv": "Apple överväger att köpa brittisk startup för 1 miljard dollar.", "zh": "作为语言而言，为世界使用人数最多的语言，目前世界有五分之一人口做为母语。"}


def get_all_models():
    with open("requirements.txt") as f:
        content = f.readlines()
        models = []
        for line in content:
            if "huggingface.co" in line:
                model = "_".join(line.split("/")[4].split("_")[:3])
                if model not in models:
                    models.append(model)
        return models


models = get_all_models()


def dependency(text, col_punct, col_phrase, compact, model):
    nlp = spacy.load(model + "_sm")
    doc = nlp(text)
    options = {"compact": compact, "collapse_phrases": col_phrase,
               "collapse_punct": col_punct}
    html = displacy.render(doc, style="dep", options=options)
    return html


def entity(text, ents, model):
    nlp = spacy.load(model + "_sm")
    doc = nlp(text)
    options = {"ents": ents}
    html = displacy.render(doc, style="ent", options=options)
    return html


def token(text, attributes, model):
    nlp = spacy.load(model + "_sm")
    data = []
    doc = nlp(text)
    for tok in doc:
        tok_data = []
        for attr in attributes:
            tok_data.append(getattr(tok, attr))
        data.append(tok_data)
    data = pd.DataFrame(data, columns=attributes)
    return data


def random_vectors(text, model):
    nlp = spacy.load(model + "_md")
    doc = nlp(text)
    n_chunks = [chunk for chunk in doc.noun_chunks if doc.noun_chunks]
    words = [tok for tok in doc if not tok.is_stop and tok.pos_ not in [
        'PUNCT', "PROPN"]]
    str_list = n_chunks + words
    choice = random.choices(str_list, k=2)
    return round(choice[0].similarity(choice[1]), 2), choice[0].text, choice[1].text


def vectors(input1, input2, model):
    nlp = spacy.load(model + "_md")
    return round(nlp(input1).similarity(nlp(input2)), 2)


def span(text, span1, span2, label1, label2, model):
    nlp = spacy.load(model + "_sm")
    doc = nlp(text)
    if span1:
        idx1_1 = 0
        idx1_2 = 0
        idx2_1 = 0
        idx2_2 = 0

        span1 = [split for split in span1.split(" ") if split]
        span2 = [split for split in span2.split(" ") if split]

        for i in range(len(list(doc))):
            tok = list(doc)[i]
            if span1[0] == tok.text:
                idx1_1 = i
            if span1[-1] == tok.text:
                idx1_2 = i + 1
            if span2[0] == tok.text:
                idx2_1 = i
            if span2[-1] == tok.text:
                idx2_2 = i + 1

        doc.spans["sc"] = [
            Span(doc, idx1_1, idx1_2, label1),
            Span(doc, idx2_1, idx2_2, label2),
        ]
    else:
        idx1_1 = 0
        idx1_2 = round(len(list(doc)) / 2)
        idx2_1 = 0
        idx2_2 = 1

        doc.spans["sc"] = [
            Span(doc, idx1_1, idx1_2, label1),
            Span(doc, idx2_1, idx2_2, label2),
        ]

    html = displacy.render(doc, style="span")
    return html


def get_text(model):
    for i in range(len(models)):
        model = model.split("_")[0]
        new_text = texts[model]

    return new_text


demo = gr.Blocks()

with demo:
    model_input = gr.Dropdown(
        choices=models, value=DEFAULT_MODEL, interactive=True, label="Pretrained Pipelines")
    text_button = gr.Button("Get new text")
    text_input = gr.Textbox(
        value=DEFAULT_TEXT, interactive=True, label="Input Text")
    button = gr.Button("Generate")
    with gr.Tabs():
        with gr.TabItem("Dependency"):
            col_punct = gr.Checkbox(label="Collapse Punctuation", value=True)
            col_phrase = gr.Checkbox(label="Collapse Phrases", value=True)
            compact = gr.Checkbox(label="Compact", value=False)
            depen_output = gr.HTML()
            dep_button = gr.Button("Generate this tab")
        with gr.TabItem("Entity"):
            entity_input = gr.CheckboxGroup(DEFAULT_ENTS, value=DEFAULT_ENTS)
            entity_output = gr.HTML()
            ent_button = gr.Button("Generate this tab")
        with gr.TabItem("Tokens"):
            with gr.Column():
                tok_input = gr.CheckboxGroup(
                    DEFAULT_TOK_ATTR, value=DEFAULT_TOK_ATTR)
                tok_output = gr.Dataframe(
                    headers=DEFAULT_TOK_ATTR, overflow_row_behaviour="paginate")
            tok_button = gr.Button("Generate this tab")
        with gr.TabItem("Similarity"):
            with gr.Row():
                sim_text1 = gr.Textbox(
                    value="Apple", label="Chosen", interactive=True,)
                sim_text2 = gr.Textbox(
                    value="U.K. startup", label="Chosen", interactive=True,)
            sim_output = gr.Textbox(label="Similarity Score")
            sim_random_button = gr.Button("Generate random words")
            sim_button = gr.Button("Generate inputs")
        with gr.TabItem("Spans"):
            with gr.Column():
                with gr.Row():
                    span1 = gr.Textbox(
                        label="Span 1", value="U.K. startup", placeholder="Input a part of the sentence")
                    label1 = gr.Textbox(value="ORG",
                                        label="Label for Span 1")
                with gr.Row():
                    span2 = gr.Textbox(
                        label="Span 2", value="U.K.", placeholder="Input another part of the sentence")
                    label2 = gr.Textbox(value="GPE",
                                        label="Label for Span 2")
                span_output = gr.HTML()
                gr.Markdown(value="\n\n\n\n")
                gr.Markdown(value="\n\n\n\n")
                span_button = gr.Button("Generate this tab")
    text_button.click(get_text, inputs=[model_input], outputs=text_input)
    button.click(dependency, inputs=[
        text_input, col_punct, col_phrase, compact, model_input], outputs=depen_output)
    button.click(
        entity, inputs=[text_input, entity_input, model_input], outputs=entity_output)
    button.click(
        token, inputs=[text_input, tok_input, model_input], outputs=tok_output)
    button.click(vectors, inputs=[sim_text1,
                 sim_text2, model_input], outputs=sim_output)
    button.click(
        span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=span_output)
    dep_button.click(dependency, inputs=[
        text_input, col_punct, col_phrase, compact, model_input], outputs=depen_output)
    ent_button.click(
        entity, inputs=[text_input, entity_input, model_input], outputs=entity_output)
    tok_button.click(
        token, inputs=[text_input, tok_input, model_input], outputs=[tok_output])
    sim_button.click(vectors, inputs=[
                     sim_text1, sim_text2, model_input], outputs=sim_output)
    span_button.click(
        span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=span_output)
    sim_random_button.click(random_vectors, inputs=[text_input, model_input], outputs=[
                            sim_output, sim_text1, sim_text2])
demo.launch()