Spaces:
Runtime error
Runtime error
File size: 4,125 Bytes
06b4325 1d4fc05 06b4325 1d4fc05 06b4325 1d4fc05 06b4325 |
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 |
# external libraries
import streamlit as st
from transformers import pipeline
import pandas as pd
# internal libraries
from config import config
import pipeline
def main():
st.set_page_config(
layout="centered", # Can be "centered" or "wide". In the future also "dashboard", etc.
initial_sidebar_state="auto", # Can be "auto", "expanded", "collapsed"
page_title=config.main_title, # String or None. Strings get appended with "• Streamlit".
page_icon=config.logo_path, # String, anything supported by st.image, or None.
)
if "output" not in st.session_state:
st.session_state['data'] = pd.read_csv(config.sample_texts_path)
st.session_state['sample_text'] = None
generate_text()
st.session_state["output"] = False
st.session_state["output_text"] = ""
st.session_state['inputs'] = {}
col1, col2, col3 = st.columns(3)
col1.write(' ')
col2.image(config.logo_path)
col3.write(' ')
st.markdown(f"<h1 style='text-align: center;'>{config.main_title}</h1>", unsafe_allow_html=True)
st.markdown(f"<h3 style='text-align: center;'>{config.lecture_title}</h3>", unsafe_allow_html=True)
# topic modelling radio bar
input_topic_modelling = st.radio(
config.topic_modelling_title,
config.topic_modelling_answers,
horizontal=True)
st.session_state['inputs']['input_topic_modelling'] = input_topic_modelling
# input text area
input_text = st.text_area(config.input_text, st.session_state['sample_text'], height=300)
st.session_state['inputs']['input_text'] = input_text
# generate sample text button
st.button(config.button_text, on_click=generate_text)
# choosing segmenter radio bar
input_segmenter = st.radio(
config.segmenter_title,
config.segmenter_answers,
horizontal=True)
st.session_state['inputs']['input_segmenter'] = input_segmenter
# choosing summarizer algorithm radio bar
input_summarizer = st.radio(
config.summarizer_title,
config.summarizer_answers,
horizontal=True)
st.session_state['inputs']['input_summarizer'] = input_summarizer
# generating summary button
col1, col2, col3 = st.columns(3)
col1.header(' ')
col2.button(config.generate_text, on_click=generate_summary)
col3.header(' ')
if st.session_state["output"]:
TOPICS = [key for key, value in st.session_state["output_text"].items() if key != '#']
if config.filter_threshold_summaries:
TOPICS = [key for key in TOPICS if st.session_state["output_text"][key]['summary'] != config.threshold_error]
st.write(config.output_title)
options = {}
for topic in TOPICS:
option = st.checkbox(topic)
options[topic] = option
if len(options) == 0:
st.warning(config.warning_len_input_text, icon="⚠️")
for topic, option in options.items():
if option == True:
st.text_area(topic,
st.session_state["output_text"][topic]['summary'],
disabled=True)
def generate_text():
df = st.session_state['data']
df = df[~df['data'].isnull()]
df = df[df['data'].str.len().gt(100)]
st.session_state['sample_text'] = df.sample(1)['data'].values[0]
def generate_summary():
st.session_state["output"] = True
MODELS = {
'summarizer':st.session_state['inputs']['input_summarizer'],
'topic_modelling':st.session_state['inputs']['input_topic_modelling'],
'segmentizer':st.session_state['inputs']['input_segmenter']
}
with st.spinner('Generating the output of Topic Modeling for Summarization...'):
OUTPUT = pipeline.run(st.session_state['inputs']['input_text'], MODELS)
st.session_state["output_text"] = OUTPUT
st.success('Done!')
if __name__ == "__main__":
main() |