Spaces:
Sleeping
Sleeping
File size: 2,125 Bytes
0d77127 dc4a88c 0d77127 3ffb3f2 0d77127 3ffb3f2 0d77127 3ffb3f2 dc4a88c 3ffb3f2 6940aac 0d77127 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import spacy
import json
from datetime import datetime
import streamlit as st
import pandas as pd
nlp = spacy.load('la_core_web_lg')
def tokenize_with_spacy(text):
doc = nlp(text)
return [token.text for token in doc]
def annotate_text(segmented_text):
annotated_tokens = []
for token in segmented_text:
doc = nlp(token)
annotated_token = {
'token': token,
'pos': str(doc[0].pos_),
'lemma': str(doc[0].lemma_),
'aspect': ', '.join(doc[0].morph.get("Aspect", default=[""])),
'tense': ', '.join(doc[0].morph.get("Tense", default=[""])),
'verbForm': ', '.join(doc[0].morph.get("VerbForm", default=[""])),
'voice': ', '.join(doc[0].morph.get("Voice", default=[""])),
'mood': ', '.join(doc[0].morph.get("Mood", default=[""])),
'number': ', '.join(doc[0].morph.get("Number", default=[""])),
'person': ', '.join(doc[0].morph.get("Person", default=[""])),
'case': ', '.join(doc[0].morph.get("Case", default=[""])),
'gender': ', '.join(doc[0].morph.get("Gender", default=[""]))
}
annotated_tokens.append(annotated_token)
return annotated_tokens
def save_annotations_as_json(annotated_text, filename):
with open(filename, 'w', encoding='utf-8') as json_file:
json.dump(annotated_text, json_file, ensure_ascii=False, indent=4)
st.title("Annotation Tool")
text = st.text_area("Text")
if st.button("Annotate"):
if text:
segmented_text = tokenize_with_spacy(text)
annotated_text = annotate_text(segmented_text)
st.subheader("Segmented Text:")
st.write(segmented_text)
st.subheader("Annotated Text:")
# Create a DataFrame from the annotated text
df = pd.DataFrame(annotated_text)
st.dataframe(df)
if st.button("Save Modifications as JSON"):
save_annotations_as_json(df.to_dict(orient='records'), 'annotations.json')
st.success("Annotations saved as annotations.json")
else:
st.warning("Please enter some text.")
|