Spaces:
Build error
Build error
File size: 3,622 Bytes
7a7a355 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
import streamlit as st
import pandas as pd
import numpy as np
from math import ceil
from collections import Counter
from string import punctuation
import spacy
from spacy import displacy
import en_ner_bc5cdr_md
# Store the initial value of widgets in session state
if "visibility" not in st.session_state:
st.session_state.visibility = "visible"
st.session_state.disabled = False
#nlp = en_core_web_lg.load()
nlp = spacy.load("en_ner_bc5cdr_md")
st.set_page_config(layout='wide')
st.title('Clinical Note Summarization')
st.sidebar.markdown('Using transformer model')
## Loading in dataset
#df = pd.read_csv('mtsamples_small.csv',index_col=0)
df = pd.read_csv('shpi_w_rouge21Nov.csv')
#Renaming column
df.rename(columns={'SUBJECT_ID':'Patient_ID',
'HADM_ID':'Admission_ID',
'hpi_input_text':'Original_Text',
'hpi_reference_summary':'Reference_text'}, inplace = True)
#data.rename(columns={'gdp':'log(gdp)'}, inplace=True)
#Filter selection
st.sidebar.header("Search for Patient:")
patientid = df['Patient_ID']
patient = st.sidebar.selectbox('Select Patient ID:', patientid)
admissionid = df['Admission_ID'].loc[df['Patient_ID'] == patient]
HospitalAdmission = st.sidebar.selectbox('', admissionid)
# List of Model available
model = st.sidebar.selectbox('Select Model', ('BertSummarizer','BertGPT2','t5seq2eq','t5','gensim','pysummarizer'))
col3,col4 = st.columns(2)
patientid = col3.write(f"Patient ID: {patient} ")
admissionid =col4.write(f"Admission ID: {HospitalAdmission} ")
col1, col2 = st.columns(2)
#_min_length = col1.number_input("Minimum Length", value=_min_length)
#_max_length = col2.number_input("Maximun Length", value=_max_length)
##_early_stopping = col3.number_input("early_stopping", value=_early_stopping)
#text = st.text_area('Input Clinical Note here')
# Query out relevant Clinical notes
original_text = df.query(
"Patient_ID == @patient & Admission_ID == @HospitalAdmission"
)
original_text2 = original_text['Original_Text'].values
runtext =st.text_area('Input Clinical Note here:', str(original_text2), height=300)
reference_text = original_text['Reference_text'].values
def run_model(input_text):
if model == "BertSummarizer":
output = original_text['BertSummarizer'].values
st.write('Summary')
st.success(output[0])
elif model == "BertGPT2":
output = original_text['BertGPT2'].values
st.write('Summary')
st.success(output[0])
elif model == "t5seq2eq":
output = original_text['t5seq2eq'].values
st.write('Summary')
st.success(output)
elif model == "t5":
output = original_text['t5'].values
st.write('Summary')
st.success(output)
elif model == "gensim":
output = original_text['gensim'].values
st.write('Summary')
st.success(output)
elif model == "pysummarizer":
output = original_text['pysummarizer'].values
st.write('Summary')
st.success(output)
col1, col2 = st.columns([1,1])
with col1:
st.button('Summarize')
run_model(runtext)
sentences=runtext.split('.')
st.text_area('Reference text', str(reference_text),label_visibility="hidden")
with col2:
st.button('NER')
doc = nlp(str(original_text2))
colors = { "DISEASE": "pink","CHEMICAL": "orange"}
options = {"ents": [ "DISEASE", "CHEMICAL"],"colors": colors}
ent_html = displacy.render(doc, style="ent", options=options)
st.markdown(ent_html, unsafe_allow_html=True)
|