Spaces:
Runtime error
Runtime error
File size: 3,800 Bytes
ba99ac9 4d544f0 ba99ac9 4d544f0 ba99ac9 ff08140 ba99ac9 ff08140 ba99ac9 f3f70d0 ba99ac9 f3f70d0 ff08140 f3f70d0 ff08140 f3f70d0 ba99ac9 f3f70d0 ba99ac9 f3f70d0 ba99ac9 f3f70d0 ff08140 ba99ac9 ff08140 f3f70d0 ba99ac9 f3f70d0 |
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 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import sentencepiece
import streamlit as st
import pandas as pd
import spacy
import roner
example_list = [
"Ana merge în București.",
"""Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București. Ana merge în București."""
]
st.set_page_config(layout="wide")
st.title("Demo for Romanian NER")
model_list = ['dumitrescustefan/bert-base-romanian-ner']
st.sidebar.header("Select NER Model")
model_checkpoint = st.sidebar.radio("", model_list)
st.sidebar.write("This demo is based on RoNER: 'https://github.com/dumitrescustefan/roner'")
st.sidebar.write("")
st.sidebar.header("Select type of PERSON detection")
named_persons_only = st.sidebar.radio("", ('Proper nouns only', 'All nouns'))
st.sidebar.write("Types of entities detected: 'PERSON', 'ORG', 'GPE', 'LOC', 'NAT_REL_POL', 'EVENT', 'LANGUAGE', 'WORK_OF_ART', 'DATETIME', 'PERIOD', 'MONEY', 'QUANTITY', 'NUMERIC', 'ORDINAL', 'FACILITY'")
st.subheader("Select Text Input Method")
input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text'))
if input_method == 'Select from Examples':
selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
st.subheader("Text to Run")
input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
elif input_method == "Write or Paste New Text":
st.subheader("Text to Run")
input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
@st.cache(allow_output_mutation=True)
def setModel(named_persons_only):
ner = roner.NER(named_persons_only=named_persons_only)
return ner
@st.cache(allow_output_mutation=True)
def get_html(html: str):
WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
html = html.replace("\n", " ")
return WRAPPER.format(html)
Run_Button = st.button("Run", key=None)
if Run_Button == True:
ner = setModel(named_persons_only = False)
output = ner(input_text)[0] # only one sentence
# tabular form
data = []
for word in output["words"]:
if word["tag"]!="O":
data.append({
"word": word["text"],
"entity": word["tag"],
"start_char": word["start_char"],
"end_char": word["end_char"]
})
df = pd.DataFrame.from_dict(data)
st.subheader("Recognized Entities")
st.dataframe(df)
st.subheader("Spacy Style Display")
spacy_display = {}
spacy_display["ents"] = []
spacy_display["text"] = output["text"]
spacy_display["title"] = None
for word in output["words"]:
if word["tag"]!="O":
spacy_display["ents"].append({"start": word["start_char"], "end": word["end_char"], "label": word["tag"]})
entity_list = ['PERSON', 'ORG', 'GPE', 'LOC', 'NAT_REL_POL',
'EVENT', 'LANGUAGE', 'WORK_OF_ART', 'DATETIME',
'PERIOD', 'MONEY', 'QUANTITY', 'NUMERIC',
'ORDINAL', 'FACILITY']
colors = {
'PERSON': '#F00',
'ORG': '#F00',
'GPE': '#F00',
'LOC': '#F00',
'NAT_REL_POL': '#F00',
'EVENT': '#F00',
'LANGUAGE': '#F00',
'WORK_OF_ART': '#F00',
'DATETIME': '#F00',
'PERIOD': '#F00',
'MONEY': '#F00',
'QUANTITY': '#F00',
'NUMERIC': '#F00',
'ORDINAL': '#F00',
'FACILITY': '#F00',
}
html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": entity_list, "colors": colors})
style = "<style>mark.entity { display: inline-block }</style>"
st.write(f"{style}{get_html(html)}", unsafe_allow_html=True) |