PubMedTM / pages /03_Explore_Documents.py
Array3022
2024-02-14 Release Updates
d62ad66
Raw History Blame Contribute Delete
3.25 kB
import streamlit as st
import pandas as pd
from top2vec import Top2Vec
# def append_dict(data):
# # Create df with author info
# author_df = pd.DataFrame(columns=['Name', 'Affiliation'])
# for i, item in enumerate(data):
# author_df.at[i, 'Name'] = item['name']
# if item['affiliation'] is not None:
# author_df.at[i, 'Affiliation'] = item['affiliation']
# else:
# author_df.at[i, 'Affiliation'] = ''
# # Find longest affiliation string
# max_affiliation = 0
# for item in author_df['Affiliation']:
# if len(item) > max_affiliation:
# max_affiliation = len(item)
# # Add space to affiliation strings to match longest string
# for i, item in enumerate(author_df['Affiliation']):
# author_df.at[i, 'Affiliation'] = item + ' ' * (max_affiliation - len(item))
# # Change index to start at 1
# author_df.index = author_df.index + 1
# return author_df
@st.cache_resource
def load_model():
name = '2024-02-14_22_19_09_reduced__model_medline0[test,mincount_250,topicmergedelta_0.15,ngram_True,ngramvocab_args_250_.4_80M_npmi_connector].json'
with open(name, 'rb') as f:
return Top2Vec.load(f)
@st.cache_data
def load_data():
df = pd.read_pickle('medline_0_df_nlp.pkl.bz2', compression='bz2')
return df
# Notification of loading
start_container = st.empty()
if 'first' not in st.session_state:
st.session_state['first'] = True
if st.session_state['first'] == True:
start_container.text('Loading model and data... This may take two to three minutes on the initial run.')
st.session_state['first'] = False
# Load the model and data
model = load_model()
df = load_data()
# Remove loading notification
start_container.empty()
# User interface
with st.sidebar.form('Explore Documents', clear_on_submit=False):
st.write('Input a search term(s) separated by a space and receive the documents that are most semantical similar.')
txt_ed = st.text_area('Keyword(s) or Phrase(s)')
num_ed = st.number_input('Number of documents to return',
min_value=1,
max_value=50,
value=10) # Default value is 10
submitted_ed = st.form_submit_button("Submit")
if submitted_ed:
txt_ed_list = txt_ed.split()
doc_scores, doc_ids = model.search_documents_by_keywords(txt_ed_list, num_docs=num_ed)
for i, doc in enumerate(doc_ids):
st.header(f'{df.at[doc, "TI"]}')
with st.expander('See more'):
# st.write('Authors:', f'{df.at[doc, "AU"]}')
st.write('Authors:', ','.join(df.at[doc, "AU"]).replace(',', ', '))
# st.dataframe(append_dict(df.iat[doc, 5]))
st.write('Year:', f'{df.at[doc, "DP"]}')
st.markdown(f'PMUID: [{df.at[doc, "PMID"]}](https://pubmed.ncbi.nlm.nih.gov/{df.at[doc, "PMID"]})')
st.write('Journal:', f'*{df.at[doc, "JT"]}*')
st.write('Journal Location:', f'{df.at[doc, "PL"]}')
st.write('Cosine Similarity:', str(doc_scores[i]))
st.write('Abstract:', f'{df.at[doc,"AB"]}')
st.write('Keywords:', '|'.join(df.at[doc, "MH"]).replace('|', ' | '))