awacke1 commited on
Commit
06e9888
·
1 Parent(s): 09d04b2

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +14 -9
app.py CHANGED
@@ -9,15 +9,15 @@ from hdbscan import HDBSCAN
9
  from sklearn.feature_extraction.text import CountVectorizer
10
 
11
  st.set_page_config(page_title="HF-BERTopic")
12
- st.title("HF-BERTopic A front end for BERTopic")
13
- st.caption("By Allen Roush")
14
- st.caption("github: https://github.com/Hellisotherpeople")
15
- st.caption("Linkedin: https://www.linkedin.com/in/allen-roush-27721011b/")
16
- st.image("https://raw.githubusercontent.com/MaartenGr/BERTopic/master/images/logo.png", width = 380)
17
- st.caption("By Maarten Grootendorst")
18
- st.caption("github: https://github.com/MaartenGr/BERTopic")
19
- st.caption("Linkedin: https://www.linkedin.com/in/mgrootendorst/")
20
- st.image("https://maartengr.github.io/BERTopic/img/algorithm.png")
21
 
22
 
23
  form = st.sidebar.form("Main Settings")
@@ -28,10 +28,15 @@ form.header("Main Settings")
28
 
29
  dataset_name = form.text_area("Enter the name of the huggingface dataset to do analysis of:", value = "Hellisotherpeople/DebateSum")
30
  dataset_name_2 = form.text_area("Enter the name of the config for the dataset if it has one", value = "")
 
31
  split_name = form.text_area("Enter the name of the split of the dataset that you want to use", value = "train")
 
32
  number_of_records = form.number_input("Enter the number of documents that you want to analyze from the dataset", value = 200)
 
33
  column_name = form.text_area("Enter the name of the column that we are doing analysis on (the X value)", value = "Full-Document")
 
34
  labels = form.checkbox("Does this dataset have labels that you want to use?", value = True)
 
35
  if labels == True:
36
  labels_column_name = form.text_area("Enter the name of the column that we are using for labels doing analysis on (the Y value)", value = "OriginalDebateFileName")
37
 
 
9
  from sklearn.feature_extraction.text import CountVectorizer
10
 
11
  st.set_page_config(page_title="HF-BERTopic")
12
+ #st.title("HF-BERTopic A front end for BERTopic")
13
+ #st.caption("By Allen Roush")
14
+ #st.caption("github: https://github.com/Hellisotherpeople")
15
+ #st.caption("Linkedin: https://www.linkedin.com/in/allen-roush-27721011b/")
16
+ #st.image("https://raw.githubusercontent.com/MaartenGr/BERTopic/master/images/logo.png", width = 380)
17
+ #st.caption("By Maarten Grootendorst")
18
+ #st.caption("github: https://github.com/MaartenGr/BERTopic")
19
+ #st.caption("Linkedin: https://www.linkedin.com/in/mgrootendorst/")
20
+ #st.image("https://maartengr.github.io/BERTopic/img/algorithm.png")
21
 
22
 
23
  form = st.sidebar.form("Main Settings")
 
28
 
29
  dataset_name = form.text_area("Enter the name of the huggingface dataset to do analysis of:", value = "Hellisotherpeople/DebateSum")
30
  dataset_name_2 = form.text_area("Enter the name of the config for the dataset if it has one", value = "")
31
+
32
  split_name = form.text_area("Enter the name of the split of the dataset that you want to use", value = "train")
33
+
34
  number_of_records = form.number_input("Enter the number of documents that you want to analyze from the dataset", value = 200)
35
+
36
  column_name = form.text_area("Enter the name of the column that we are doing analysis on (the X value)", value = "Full-Document")
37
+
38
  labels = form.checkbox("Does this dataset have labels that you want to use?", value = True)
39
+
40
  if labels == True:
41
  labels_column_name = form.text_area("Enter the name of the column that we are using for labels doing analysis on (the Y value)", value = "OriginalDebateFileName")
42