Buckeyes2019 commited on
Commit
2e6f5d4
1 Parent(s): 672ef3c

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -8
app.py CHANGED
@@ -1,15 +1,14 @@
1
  import streamlit as st
2
- import torch
3
  from transformers import pipeline
4
  import spacy
5
  from spacy import displacy
6
  import plotly.express as px
7
  import numpy as np
8
 
9
- st.set_page_config(page_title="NIU NLP Prototype")
10
 
11
  st.title("Natural Language Processing Prototype")
12
- st.write("_This web application is intended for educational use, please do not upload any classified, proprietary, or sensitive information._")
13
  st.subheader("__Which natural language processing task would you like to try?__")
14
  st.write("- __Sentiment Analysis:__ Identifying whether a piece of text has a positive or negative sentiment.")
15
  st.write("- __Named Entity Recognition:__ Identifying all geopolitical entities, organizations, people, locations, or dates in a body of text.")
@@ -67,7 +66,6 @@ with st.spinner(text="Please wait for the models to load. This should take appro
67
  if option == 'Text Classification':
68
  cat1 = st.text_input('Enter each possible category name (separated by a comma). Maximum 5 categories.')
69
  text = st.text_area('Enter Text Below:', height=200)
70
- #uploaded_file = st.file_uploader("Choose a file", type=['txt'])
71
  submit = st.button('Generate')
72
  if submit:
73
  st.subheader("Classification Results:")
@@ -82,18 +80,16 @@ if option == 'Text Summarization':
82
  max_lengthy = st.slider('Maximum summary length (words)', min_value=30, max_value=150, value=60, step=10)
83
  num_beamer = st.slider('Speed vs quality of summary (1 is fastest)', min_value=1, max_value=8, value=4, step=1)
84
  text = st.text_area('Enter Text Below (maximum 800 words):', height=300)
85
- #uploaded_file = st.file_uploader("Choose a file", type=['txt'])
86
  submit = st.button('Generate')
87
  if submit:
88
  st.subheader("Summary:")
89
  with st.spinner(text="This may take a moment..."):
90
  summWords = sum2(text, max_length=max_lengthy, min_length=15, num_beams=num_beamer, do_sample=True, early_stopping=True, repetition_penalty=1.5, length_penalty=1.5)
91
- text2 =summWords[0]["summary_text"] #re.sub(r'\s([?.!"](?:\s|$))', r'\1', )
92
  st.write(text2)
93
 
94
  if option == 'Sentiment Analysis':
95
  text = st.text_area('Enter Text Below:', height=200)
96
- #uploaded_file = st.file_uploader("Choose a file", type=['txt'])
97
  submit = st.button('Generate')
98
  if submit:
99
  st.subheader("Sentiment:")
@@ -104,7 +100,6 @@ if option == 'Sentiment Analysis':
104
 
105
  if option == 'Named Entity Recognition':
106
  text = st.text_area('Enter Text Below:', height=300)
107
- #uploaded_file = st.file_uploader("Choose a file", type=['txt'])
108
  submit = st.button('Generate')
109
  if submit:
110
  entities = []
 
1
  import streamlit as st
 
2
  from transformers import pipeline
3
  import spacy
4
  from spacy import displacy
5
  import plotly.express as px
6
  import numpy as np
7
 
8
+ st.set_page_config(page_title="NLP Prototype")
9
 
10
  st.title("Natural Language Processing Prototype")
11
+ st.write("_This web application is intended for educational use, please do not upload any sensitive information._")
12
  st.subheader("__Which natural language processing task would you like to try?__")
13
  st.write("- __Sentiment Analysis:__ Identifying whether a piece of text has a positive or negative sentiment.")
14
  st.write("- __Named Entity Recognition:__ Identifying all geopolitical entities, organizations, people, locations, or dates in a body of text.")
 
66
  if option == 'Text Classification':
67
  cat1 = st.text_input('Enter each possible category name (separated by a comma). Maximum 5 categories.')
68
  text = st.text_area('Enter Text Below:', height=200)
 
69
  submit = st.button('Generate')
70
  if submit:
71
  st.subheader("Classification Results:")
 
80
  max_lengthy = st.slider('Maximum summary length (words)', min_value=30, max_value=150, value=60, step=10)
81
  num_beamer = st.slider('Speed vs quality of summary (1 is fastest)', min_value=1, max_value=8, value=4, step=1)
82
  text = st.text_area('Enter Text Below (maximum 800 words):', height=300)
 
83
  submit = st.button('Generate')
84
  if submit:
85
  st.subheader("Summary:")
86
  with st.spinner(text="This may take a moment..."):
87
  summWords = sum2(text, max_length=max_lengthy, min_length=15, num_beams=num_beamer, do_sample=True, early_stopping=True, repetition_penalty=1.5, length_penalty=1.5)
88
+ text2 =summWords[0]["summary_text"]
89
  st.write(text2)
90
 
91
  if option == 'Sentiment Analysis':
92
  text = st.text_area('Enter Text Below:', height=200)
 
93
  submit = st.button('Generate')
94
  if submit:
95
  st.subheader("Sentiment:")
 
100
 
101
  if option == 'Named Entity Recognition':
102
  text = st.text_area('Enter Text Below:', height=300)
 
103
  submit = st.button('Generate')
104
  if submit:
105
  entities = []