spacy named entities app

space_dependency_parse.py

from dash import Dash, dcc, html, Input, Output
import dash_bootstrap_components as dbc
import spacy
from spacy import displacy
import base64

nlp = spacy.load("en_core_web_sm")

initial_text = "I went to Seattle"
#initial_text = """In ancient Rome, some neighbors live in three adjacent houses. In the center is the house of Senex, who lives there with wife Domina, son Hero, and several slaves, including head slave Hysterium and the musical's main character Pseudolus. A slave belonging to Hero, Pseudolus wishes to buy, win, or steal his freedom. One of the neighboring houses is owned by Marcus Lycus, who is a buyer and seller of beautiful women; the other belongs to the ancient Erronius, who is abroad searching for his long-lost children (stolen in infancy by pirates). One day, Senex and Domina go on a trip and leave Pseudolus in charge of Hero. Hero confides in Pseudolus that he is in love with the lovely Philia, one of the courtesans in the House of Lycus (albeit still a virgin)."""

app = Dash(__name__, external_stylesheets=[dbc.themes.SPACELAB])


def get_svg(svg: str, style: str = ""):
    """Convert an SVG to a base64-encoded image."""
    b64 = base64.b64encode(svg.encode("utf-8")).decode("utf-8")
    html = f'<img src="data:image/svg+xml;base64,{b64}" style="{style}"/>'
    return  html


app.layout = dbc.Container(
    [
        html.H3(
            "Natural Language Processing with spaCy",
            className="text-center bg-primary text-white p-4 mb-4",
        ),
        html.Div("Enter text to analyze"),
        dcc.Textarea(value=initial_text, id="user-input", className="w-100 mb-4"),
        html.H4("Dependency Parse and Part of Speech Tags"),
        dbc.Card(
            dcc.Markdown(id="html", dangerously_allow_html=True),
            body=True,
            className="mb-5",
        ),

    ],
)


@app.callback(
    Output("html", "children"),  Input("user-input", "value")
)
def display(text):
    if text is None:
        return None, None

    # new lines mess up the displacy renderer
    text = text.replace("\n", " ")
    doc = nlp(text)
    sentence_spans = list(doc.sents)
    for sent in sentence_spans:
        html = displacy.render(
            sent, style="dep",
        )
        return get_svg(html)


if __name__ == "__main__":
    app.run_server(debug=True)

space_named_entities_multiple_textareas.py

import dash
from dash import Dash, dcc, html, Input, Output, State, MATCH

import dash_bootstrap_components as dbc
import spacy
from spacy import displacy

nlp = spacy.load("en_core_web_sm")

app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])

app.layout = dbc.Container(
    dbc.Row(
        dbc.Col(
            [
                html.H3(
                    "Natural Language Processing with spaCy",
                    className="text-center bg-primary text-white p-2 mb-4",
                ),
                dbc.Button(
                    "Add Text Input area",
                    id="pattern-match-add-card",
                    n_clicks=0,
                    className="mb-3",
                ),
                html.Div(id="pattern-match-container", children=[], className="mt-4"),
            ]
        )
    ),
    fluid=True,
)


def get_entities(input_text):
    # new lines mess up the displacy renderer
    input_text = input_text.replace("\n", " ")

    doc = nlp(input_text)
    return displacy.render(doc.ents, style="ent")


def make_card(n_clicks):
    return dbc.Card(
        [
            dbc.CardHeader(
                [
                    f"Text Input {n_clicks + 1} ",
                    html.Div(
                        dbc.Button(
                            "X",
                            id={"type": "delete-card", "index": n_clicks},
                            n_clicks=0,
                            color="secondary",
                        ),
                        className="ms-auto",
                    ),
                ],
                className="hstack",
            ),
            dbc.Row(
                [
                    dbc.Col(
                        dcc.Textarea(
                            id={"type": "text-input", "index": n_clicks},
                            className="w-100",

                        ),
                    ),
                    dbc.Col(
                        dcc.Markdown(
                            id={"type": "entities", "index": n_clicks},
                            dangerously_allow_html=True,
                        ),
                    ),
                ]
            ),
        ],
        className="m-1",
        id={"type": "card", "index": n_clicks},
    )


@app.callback(
    Output("pattern-match-container", "children"),
    Input("pattern-match-add-card", "n_clicks"),
    State("pattern-match-container", "children"),
)
def add_card(
    n_clicks,
    cards,
):
    new_card = make_card(n_clicks)
    cards.append(new_card)
    return cards


@app.callback(
    Output({"type": "card", "index": MATCH}, "style"),
    Input({"type": "delete-card", "index": MATCH}, "n_clicks"),
    prevent_initial_call=True,
)
def remove_card(_):
    return {"display": "none"}


@app.callback(
    Output({"type": "entities", "index": MATCH}, "children"),
    Input({"type": "text-input", "index": MATCH}, "value"),
)
def update_figure(text_input):
    if text_input is None:
        return dash.no_update
    return get_entities(text_input)


if __name__ == "__main__":
    app.run_server(debug=True)

spacy_ent_label_dropdown.py

from dash import Dash, dash_table, dcc, html, Input, Output
import dash_bootstrap_components as dbc
import spacy
from spacy import displacy
import pandas as pd
from spacy.displacy.render import DEFAULT_LABEL_COLORS

nlp = spacy.load("en_core_web_sm")


app = Dash(__name__, external_stylesheets=[dbc.themes.SPACELAB])

options = [
    {
        "label": html.Div(
            [label],
            style={
                "background-color": color,
                "font-weight": "bold",
                "padding": 5,
                "border-radius": "0.35em",
            },
        ),
        "value": label,
    }
    for label, color in DEFAULT_LABEL_COLORS.items()
]


label_dropdown = dbc.InputGroup(
    [
        dcc.Dropdown(options, multi=True, id="label-dropdown", style={"width": 400}),
        dbc.Button("Select All", id="all"),
    ]
)

app.layout = dbc.Container(label_dropdown)


@app.callback(
    Output("label-dropdown", "value"),
    Input("all", "n_clicks"),
)
def select_all_labels(_):
    return list(DEFAULT_LABEL_COLORS.keys())


if __name__ == "__main__":
    app.run_server(debug=True)

spacy_named_entities.py

from dash import Dash, dash_table, dcc, html, Input, Output
import dash_bootstrap_components as dbc
import spacy
from spacy import displacy
import pandas as pd

nlp = spacy.load("en_core_web_sm")

initial_text = "I went to Seattle"
NER_ATTRS = ["text",  "start_char", "end_char", "label_",]


app = Dash(__name__, external_stylesheets=[dbc.themes.SPACELAB])

table = dash_table.DataTable(
    id="table",
    columns=[{"name": c, "id": c} for c in NER_ATTRS + ["description"]],
    filter_action="native",
    sort_action="native",
    page_size=10,
    style_table={"overflowX": "auto"},
)

app.layout = dbc.Container(
    [
        html.H3(
            "Natural Language Processing with spaCy",
            className="text-center bg-primary text-white p-4 mb-4",
        ),
        html.Div("Enter text to analyze"),
        dcc.Textarea(value=initial_text, id="user-input", className="w-100 mb-4"),
        html.H4("Named Entities"),
        dbc.Card(
            dcc.Markdown(id="html", dangerously_allow_html=True),
            body=True,
            className="mb-5",
        ),
        html.Div(table),
    ],
)


@app.callback(
    Output("html", "children"), Output("table", "data"), Input("user-input", "value")
)
def display(text):
    if text is None:
        return None, None

    # new lines mess up the displacy renderer
    text = text.replace("\n", " ")

    doc = nlp(text)
    html = displacy.render(doc, style="ent")

   # if doc.ents:
    table_data = [
        [str(getattr(ent, attr)) for attr in NER_ATTRS]
        for ent in doc.ents
        # if ent.label_ in label_select
    ]

    if table_data:
        dff = pd.DataFrame(table_data, columns=NER_ATTRS)
        dff["description"] = dff["label_"].apply(lambda x: spacy.explain(x))
        return html, dff.to_dict("records")
    return html, None


if __name__ == "__main__":
    app.run_server(debug=True)

dependency parse

---

---

named entities

---

---

ent label dropdown

---

---

---

---

---