Spaces:
Runtime error
Runtime error
File size: 6,442 Bytes
34b12ff |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
import networkx as nx
from streamlit.components.v1 import html
import streamlit as st
import helpers
st.set_page_config(layout='wide',
page_title='S-Tri-P: Semantic Similarity of Scientific Papers!',
page_icon='💡'
)
def main():
st.title('S-Tri-P (S3P): Semantic Similarity of Scientific Papers!')
st.header('📂 Load Data')
uploaded_file = st.file_uploader("Choose a CSV file",
help='Upload a CSV file with the following columns: Title, Abstract')
##########
# Load data
##########
if uploaded_file is not None:
df = helpers.load_data(uploaded_file)
else:
df = helpers.load_data('data.csv')
data = df.copy()
st.write(f'Number of papers: {len(data)}')
st.write('First 5 rows of loaded data:')
st.write(data[['Title', 'Abstract']].head())
if data is not None:
##########
# Topic modeling
##########
st.header('🔥 Topic Modeling')
cols = st.columns(3)
with cols[0]:
min_topic_size = st.slider('Minimum topic size', key='min_topic_size', min_value=2,
max_value=int(len(data)/3), step=1, value=3,
help='The minimum size of the topic. Increasing this value will lead to a lower number of clusters/topics.')
with cols[1]:
n_gram_range = st.slider('N-gram range', key='n_gram_range', min_value=1,
max_value=4, step=1, value=(1, 3),
help='N-gram range for the topic model')
with cols[2]:
st.text('')
st.text('')
st.button('Reset Defaults', on_click=helpers.reset_default_topic_sliders, key='reset_topic_sliders',
kwargs={'min_topic_size': 3, 'n_gram_range': (1, 3)})
with st.spinner('Topic Modeling'):
data, topic_model, topics = helpers.topic_modeling(
data, min_topic_size=min_topic_size, n_gram_range=n_gram_range)
mapping = {
'Topic Keywords': topic_model.visualize_barchart,
'Topic Similarities': topic_model.visualize_heatmap,
'Topic Hierarchies': topic_model.visualize_hierarchy,
'Intertopic Distance': topic_model.visualize_topics
}
cols = st.columns(3)
with cols[0]:
topic_model_vis_option = st.selectbox(
'Select Topic Modeling Visualization', mapping.keys())
try:
fig = mapping[topic_model_vis_option]()
fig.update_layout(title='')
st.plotly_chart(fig, use_container_width=True)
except:
st.warning(
'No visualization available. Try a lower Minimum topic size!')
##########
# S-TRI-P Network
##########
st.header('🚀 S-TRI-P Network')
with st.spinner('Embedding generation'):
data = helpers.embeddings(data)
with st.spinner('Cosine Similarity Calculation'):
cosine_sim_matrix = helpers.cosine_sim(data)
min_value, value = helpers.calc_optimal_threshold(
cosine_sim_matrix,
# 25% is a good value for the number of papers
max_connections=helpers.calc_max_connections(len(data), 0.25)
)
cols = st.columns(3)
with cols[0]:
threshold = st.slider('Cosine Similarity Threshold', key='threshold', min_value=min_value,
max_value=1.0, step=0.01, value=value,
help='The minimum cosine similarity between papers to draw a connection. Increasing this value will lead to a lesser connections.')
neighbors, num_connections = helpers.calc_neighbors(
cosine_sim_matrix, threshold)
st.write(f'Number of connections: {num_connections}')
with cols[1]:
st.text('')
st.text('')
st.button('Reset Defaults', on_click=helpers.reset_default_threshold_slider, key='reset_threshold',
kwargs={'threshold': value})
with st.spinner('Network Generation'):
nx_net, pyvis_net = helpers.network_plot(
data, topics, neighbors)
# Save and read graph as HTML file (on Streamlit Sharing)
try:
path = '/tmp'
pyvis_net.save_graph(f'{path}/pyvis_graph.html')
HtmlFile = open(f'{path}/pyvis_graph.html',
'r', encoding='utf-8')
# Save and read graph as HTML file (locally)
except:
path = '/html_files'
pyvis_net.save_graph(f'{path}/pyvis_graph.html')
HtmlFile = open(f'{path}/pyvis_graph.html',
'r', encoding='utf-8')
# Load HTML file in HTML component for display on Streamlit page
html(HtmlFile.read(), height=800)
##########
# Centrality
##########
st.header('🏅 Most Important Papers')
centrality_mapping = {
'Closeness Centrality': nx.closeness_centrality,
'Degree Centrality': nx.degree_centrality,
'Eigenvector Centrality': nx.eigenvector_centrality,
'Betweenness Centrality': nx.betweenness_centrality,
}
cols = st.columns(3)
with cols[0]:
centrality_option = st.selectbox(
'Select Centrality Measure', centrality_mapping.keys())
# Calculate centrality
centrality = centrality_mapping[centrality_option](nx_net)
with st.spinner('Network Centrality Calculation'):
fig = helpers.network_centrality(
data, centrality, centrality_option)
st.plotly_chart(fig, use_container_width=True)
st.markdown(
"""
💡🔥🚀 S-TRI-P v1.0 🚀🔥💡
👨🔬 Author: Marie Stephen Leo
👔 Linkedin: [Marie Stephen Leo](https://www.linkedin.com/in/marie-stephen-leo/)
📝 Medium: [@stephen-leo](https://stephen-leo.medium.com/)
💻 Github: [stephenleo](https://github.com/stephenleo)
"""
)
if __name__ == '__main__':
main()
|