File size: 5,229 Bytes
ce2d794 4a66f10 ce2d794 0ac3298 ce2d794 4a66f10 ce2d794 4a66f10 ce2d794 8cebd63 4a66f10 0ac3298 4a66f10 0ac3298 ce2d794 0ac3298 ce2d794 4a66f10 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
import streamlit as st
import json
import pandas as pd
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt
import streamlit.components.v1 as components
# Global variable to hold selected row index
selected_row_index = None
# Initialize an empty DataFrame
filtered_data = pd.DataFrame()
# 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)]
# Streamlit App
st.title("Medical Licensing Exam Explorer with Speech Synthesis, Plotly and Seaborn 📊")
# Dropdown for file selection
file_option = st.selectbox("Select file:", ["small_file.jsonl", "large_file.jsonl"])
st.write(f"You selected: {file_option}")
# Load the data
small_data = load_jsonl("usmle_16.2MB.jsonl")
large_data = load_jsonl("usmle_2.08MB.jsonl")
# Show filtered data grid
if file_option == "small_file.jsonl":
data = small_data
else:
data = large_data
# Text input for search keyword
search_keyword = st.text_input("Enter a keyword to filter data (e.g., Heart, Lung, Pain, Memory):")
# Button to trigger search
if st.button("Search"):
filtered_data = filter_by_keyword(data, search_keyword)
st.write(f"Filtered Dataset by '{search_keyword}'")
selected_data = st.dataframe(filtered_data)
def generate_html_with_textarea(text_to_speak):
return f'''
<!DOCTYPE html>
<html>
<head>
<title>Read It Aloud</title>
<script type="text/javascript">
function readAloud() {{
const text = document.getElementById("textArea").value;
const speech = new SpeechSynthesisUtterance(text);
window.speechSynthesis.speak(speech);
}}
</script>
</head>
<body>
<h1>🔊 Read It Aloud</h1>
<textarea id="textArea" rows="10" cols="80">
{text_to_speak}
</textarea>
<br>
<button onclick="readAloud()">🔊 Read Aloud</button>
</body>
</html>
'''
# Define your text passage
text_passage = "A 60-year-old man is brought to the emergency department by police officers because he was acting strangely in public. The patient was found talking nonsensically to characters on cereal boxes in the store. Past medical history is significant for multiple hospitalizations for alcohol-related injuries and seizures. The patient’s vital signs are within normal limits. Physical examination shows a disheveled male who is oriented to person, but not time or place. Neurologic examination shows nystagmus and severe gait ataxia. A T1/T2 MRI is performed and demonstrates evidence of damage to the mammillary bodies. The patient is given the appropriate treatment for recovering most of his cognitive functions. However, significant short-term memory deficits persist. The patient remembers events from his past such as the school and college he attended, his current job, and the names of family members quite well. Which of the following is the most likely diagnosis in this patient?"
# Generate HTML code
documentHTML5 = generate_html_with_textarea(text_passage)
# 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(question_text, "", idx)
html_blocks.append(documentHTML5)
all_html = ''.join(html_blocks)
components.html(all_html, width=1280, height=1024)
else:
st.warning("No rows to read.")
# Insert the HTML into Streamlit
# Button to read all filtered rows
if st.button("Read Aloud Text"):
components.html(documentHTML5, width=1280, height=1024)
# Plotly and Seaborn charts for EDA
if st.button("Generate Charts"):
st.subheader("Plotly Charts 📈")
# 1. Scatter Plot
fig = px.scatter(data, x=data.columns[0], y=data.columns[1])
st.plotly_chart(fig)
# 2. Line Plot
fig = px.line(data, x=data.columns[0], y=data.columns[1])
st.plotly_chart(fig)
# 3. Bar Plot
fig = px.bar(data, x=data.columns[0], y=data.columns[1])
st.plotly_chart(fig)
# 4. Histogram
fig = px.histogram(data, x=data.columns[0])
st.plotly_chart(fig)
# 5. Box Plot
fig = px.box(data, x=data.columns[0], y=data.columns[1])
st.plotly_chart(fig)
st.subheader("Seaborn Charts 📊")
# 6. Violin Plot
fig, ax = plt.subplots()
sns.violinplot(x=data.columns[0], y=data.columns[1], data=data)
st.pyplot(fig)
# 7. Swarm Plot
fig, ax = plt.subplots()
sns.swarmplot(x=data.columns[0], y=data.columns[1], data=data)
st.pyplot(fig)
# 8. Pair Plot
fig = sns.pairplot(data)
st.pyplot(fig)
# 9. Heatmap
fig, ax = plt.subplots()
sns.heatmap(data.corr(), annot=True)
st.pyplot(fig)
# 10. Regplot (Regression Plot)
fig, ax = plt.subplots()
sns.regplot(x=data.columns[0], y=data.columns[1], data=data)
st.pyplot(fig) |