evegarcianz commited on
Commit
fb448bd
1 Parent(s): ab872f2

upload 3 files

Browse files
Files changed (3) hide show
  1. app.py +19 -0
  2. df_merged.csv +0 -0
  3. requirements.txt +3 -0
app.py ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import topicwizard
3
+ from sklearn.decomposition import NMF
4
+ from topicwizard.pipeline import make_topic_pipeline
5
+ from sklearn.feature_extraction.text import CountVectorizer
6
+
7
+ df = pd.read_csv('df_merged.csv')
8
+ abstracts=df['description'].tolist()
9
+ vectorizer = CountVectorizer(min_df=5, max_df=0.8, stop_words="english")
10
+ model = NMF(n_components=10)
11
+ topic_pipeline = make_topic_pipeline(vectorizer, model)
12
+ topic_pipeline.fit(abstracts)
13
+ topicwizard.visualize(abstracts, pipeline=topic_pipeline)
14
+
15
+ app = topicwizard.get_dash_app(vectorizer, model, corpus=abstracts)
16
+
17
+ # main.py
18
+ if __name__ == "__main__":
19
+ app.run_server(debug=False, port=8050)
df_merged.csv ADDED
The diff for this file is too large to render. See raw diff
 
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ pandas
2
+ scikit-learn
3
+ topic-wizard