import streamlit as st
import json
import pandas as pd
import streamlit.components.v1 as components
# Function to load JSONL file into a DataFrame
def load_jsonl(file_path):
data = []
with open(file_path, 'r') as f:
for line in f:
data.append(json.loads(line))
return pd.DataFrame(data)
# Function to filter DataFrame by keyword
def filter_by_keyword(df, keyword):
return df[df.apply(lambda row: row.astype(str).str.contains(keyword).any(), axis=1)]
# Function to generate HTML with textarea
def generate_html_with_textarea(text_to_speak):
return f'''
Read It Aloud
🔊 Read It Aloud
'''
# Streamlit App 🚀
st.title("USMLE Medical Questions Explorer with Speech Synthesis 🎙")
# Dropdown for file selection
file_option = st.selectbox("Select file:", ["usmle_16.2MB.jsonl", "usmle_2.08MB.jsonl"])
st.write(f"You selected: {file_option}")
# Load data
large_data = load_jsonl("usmle_16.2MB.jsonl")
small_data = load_jsonl("usmle_2.08MB.jsonl")
data = small_data if file_option == "usmle_16.2MB.jsonl" else small_data
# Top 20 healthcare terms for USMLE
top_20_terms = ['Heart', 'Lung', 'Pain', 'Memory', 'Kidney', 'Diabetes', 'Cancer', 'Infection', 'Virus', 'Bacteria', 'Neurology', 'Psychiatry', 'Gastrointestinal', 'Pediatrics', 'Oncology', 'Skin', 'Blood', 'Surgery', 'Epidemiology', 'Genetics']
# Create Expander and Columns UI for terms
with st.expander("Search by Common Terms 📚"):
cols = st.columns(4)
for term in top_20_terms:
with cols[top_20_terms.index(term) % 4]:
if st.button(f"{term}"):
filtered_data = filter_by_keyword(data, term)
st.write(f"Filtered Dataset by '{term}' 📊")
st.dataframe(filtered_data)
# Text input for search keyword
search_keyword = st.text_input("Or, enter a keyword to filter data:")
if st.button("Search 🕵️♀️"):
filtered_data = filter_by_keyword(data, search_keyword)
st.write(f"Filtered Dataset by '{search_keyword}' 📊")
st.dataframe(filtered_data)
# Button to read all filtered rows
if st.button("Read All Rows 📖"):
if not filtered_data.empty:
html_blocks = []
for idx, row in filtered_data.iterrows():
question_text = row.get("question", "No question field")
documentHTML5 = generate_html_with_textarea(question_text)
html_blocks.append(documentHTML5)
all_html = ''.join(html_blocks)
components.html(all_html, width=1280, height=1024)
else:
st.warning("No rows to read. 🚨")