Spaces:
Runtime error
Runtime error
File size: 4,689 Bytes
cd32a73 7970241 cd32a73 6f6f507 cd32a73 |
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 |
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer, DebertaV2Tokenizer, DebertaV2Model
import sentencepiece
import streamlit as st
import pandas as pd
import spacy
example_list = [
"The primary outcome was overall survival (OS).",
"Overall survival was not significantly different between the groups (hazard ratio [HR], 0.87; 95% CI, 0.66-1.16; P = .34).",
"Afatinib-an oral irreversible ErbB family blocker-improves progression-free survival compared with pemetrexed and cisplatin for first-line treatment of patients with EGFR mutation-positive advanced non-small-cell lung cancer (NSCLC)."
]
st.set_page_config(layout="wide")
st.title("Demo for EIC NER")
model_list = ['akdeniz27/bert-base-turkish-cased-ner',
'akdeniz27/convbert-base-turkish-cased-ner',
'akdeniz27/xlm-roberta-base-turkish-ner',
'xlm-roberta-large-finetuned-conll03-english']
st.sidebar.header("Select NER Model")
model_checkpoint = st.sidebar.radio("", model_list)
st.sidebar.write("For details of models: 'https://huggingface.co/akdeniz27/")
st.sidebar.write("")
xlm_agg_strategy_info = "'aggregation_strategy' can be selected as 'simple' or 'none' for 'xlm-roberta' because of the RoBERTa model's tokenization approach."
st.sidebar.header("Select Aggregation Strategy Type")
if model_checkpoint == "akdeniz27/xlm-roberta-base-turkish-ner":
aggregation = st.sidebar.radio("", ('simple', 'none'))
st.sidebar.write(xlm_agg_strategy_info)
elif model_checkpoint == "xlm-roberta-large-finetuned-conll03-english":
aggregation = st.sidebar.radio("", ('simple', 'none'))
st.sidebar.write(xlm_agg_strategy_info)
st.sidebar.write("")
st.sidebar.write("This English NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta.")
else:
aggregation = st.sidebar.radio("", ('first', 'simple', 'average', 'max', 'none'))
st.sidebar.write("Please refer 'https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html' for entity grouping with aggregation_strategy parameter.")
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(model_checkpoint, aggregation):
model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
return pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy=aggregation)
@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_pipeline = setModel(model_checkpoint, aggregation)
output = ner_pipeline(input_text)
df = pd.DataFrame.from_dict(output)
if aggregation != "none":
cols_to_keep = ['word','entity_group','score','start','end']
else:
cols_to_keep = ['word','entity','score','start','end']
df_final = df[cols_to_keep]
st.subheader("Recognized Entities")
st.dataframe(df_final)
st.subheader("Spacy Style Display")
spacy_display = {}
spacy_display["ents"] = []
spacy_display["text"] = input_text
spacy_display["title"] = None
for entity in output:
if aggregation != "none":
spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity_group"]})
else:
spacy_display["ents"].append({"start": entity["start"], "end": entity["end"], "label": entity["entity"]})
entity_list = ["PER", "LOC", "ORG", "MISC"]
colors = {'PER': '#85DCDF', 'LOC': '#DF85DC', 'ORG': '#DCDF85', 'MISC': '#85ABDF',}
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) |