%reload_ext autoreload
%autoreload 2

import pandas as pd

import os

import context

from edsnlp.utils.brat import BratConnector

import spacy

data_dir = '../../data/section_dataset/'

brat = BratConnector(data_dir)

texts, annotations = brat.get_brat()

texts

nlp = spacy.blank('fr')

nlp.add_pipe('normaliser')
nlp.add_pipe('sections')

df = texts.copy()

df['doc'] = df.note_text.apply(nlp)

def assign_id(row):
    row.doc._.note_id = row.note_id

df.apply(assign_id, axis=1);

df['matches'] = df.doc.apply(lambda d: [dict(
    lexical_variant=s.text,
    label=s.label_,
    start=s.start_char,
    end=s.end_char
) for s in d._.section_titles])

df = df[['note_text', 'note_id', 'matches']].explode('matches')

df = df.dropna()

df[['lexical_variant', 'label', 'start', 'end']] = df.matches.apply(pd.Series)

df = df.drop('matches', axis=1)

df.head(20)

df = df.rename(columns={'start': 'offset_begin', 'end': 'offset_end', 'label': 'label_value'})

df['label_name'] = df.label_value

df['modifier_type'] = ''
df['modifier_result'] = ''

from ipywidgets import Output, Button, VBox, Layout, Text, HTML
from IPython.display import display
from labeltool.labelling import GlobalLabels, Labels, Labelling

out = Output()

labels = Labels()

for label in df.label_value.unique():
    labels.add(name = label,
               color = 'green',
               selection_type = 'button')

labeller = Labelling(
    df,
    save_path='testing.pickle',
    labels_dict=labels.dict,
    from_save=True,
    out=out,
    display=display,
)

labeller.run()
out