Update app.py

app.py

@@ -39,8 +39,8 @@ def get_conference_notes(venue, blind_submission=False):
 
 raw_notes = get_conference_notes(venue, blind_submission=True)
 
-st.set_page_config(page_title="ICLR2023 Papers Visualization", page_icon="🐞", layout="centered")
 
+st.title("ICLR2023 Papers Visualization")
 st.write("Number of submissions at ICLR 2023:", len(raw_notes))
 
 df_raw = pd.json_normalize(raw_notes)
@@ -50,42 +50,42 @@ accepted_venues = ['ICLR 2023 poster', 'ICLR 2023 notable top 5%', 'ICLR 2023 no
 df = df_raw[df_raw["content.venue"].isin(accepted_venues)]
 st.write("Number of submissions accepted at ICLR 2023:", len(df))
 
-# df_filtered = df[['id', 'content.title', 'content.keywords', 'content.abstract']]
-# df = df_filtered
-# if "CO_API_KEY" not in os.environ:
-#     raise KeyError("CO_API_KEY not found in st.secrets or os.environ. Please set it in "
-#                    ".streamlit/secrets.toml or as an environment variable.")
+df_filtered = df[['id', 'content.title', 'content.keywords', 'content.abstract']]
+df = df_filtered
+if "CO_API_KEY" not in os.environ:
+    raise KeyError("CO_API_KEY not found in st.secrets or os.environ. Please set it in "
+                   ".streamlit/secrets.toml or as an environment variable.")
 
-# co = cohere.Client(os.environ["CO_API_KEY"])
+co = cohere.Client(os.environ["CO_API_KEY"])
 
-# def get_visualizations():
-#     list_of_titles = list(df["content.title"].values)
-#     embeds = co.embed(texts=list_of_titles,                  				
-#   					model="small").embeddings
+def get_visualizations():
+    list_of_titles = list(df["content.title"].values)
+    embeds = co.embed(texts=list_of_titles,                  				
+  					model="small").embeddings
     
-#     embeds_npy = np.array(embeds)
+    embeds_npy = np.array(embeds)
     
-#     # Load and initialize BERTopic to use KMeans clustering with 8 clusters only.
-#     cluster_model = KMeans(n_clusters=8)
-#     topic_model = BERTopic(hdbscan_model=cluster_model)
+    # Load and initialize BERTopic to use KMeans clustering with 8 clusters only.
+    cluster_model = KMeans(n_clusters=8)
+    topic_model = BERTopic(hdbscan_model=cluster_model)
     
-#     # df is a dataframe. df['title'] is the column of text we're modeling
-#     df['topic'], probabilities = topic_model.fit_transform(df['content.title'], embeds_npy)
+    # df is a dataframe. df['title'] is the column of text we're modeling
+    df['topic'], probabilities = topic_model.fit_transform(df['content.title'], embeds_npy)
     
-#     app = Topically(os.environ["CO_API_KEY"])
+    app = Topically(os.environ["CO_API_KEY"])
     
-#     df['topic_name'], topic_names = app.name_topics((df['content.title'], df['topic']), num_generations=5)
+    df['topic_name'], topic_names = app.name_topics((df['content.title'], df['topic']), num_generations=5)
     
-#     #st.write("Topics extracted are:", topic_names)
+    #st.write("Topics extracted are:", topic_names)
     
-#     topic_model.set_topic_labels(topic_names)
-#     fig1 = topic_model.visualize_documents(df['content.title'].values, 
-#                                     embeddings=embeds_npy,
-#                                     topics = list(range(8)),
-#                                     custom_labels=True)
-#     topic_model.set_topic_labels(topic_names)
-#     fig2 = topic_model.visualize_barchart(custom_labels=True)
-#     st.plotly_chart(fig1)
-#     st.plotly_chart(fig2)
+    topic_model.set_topic_labels(topic_names)
+    fig1 = topic_model.visualize_documents(df['content.title'].values, 
+                                    embeddings=embeds_npy,
+                                    topics = list(range(8)),
+                                    custom_labels=True)
+    topic_model.set_topic_labels(topic_names)
+    fig2 = topic_model.visualize_barchart(custom_labels=True)
+    st.plotly_chart(fig1)
+    st.plotly_chart(fig2)
 
-# st.button("Run Visualization", on_click=get_visualizations)
+st.button("Run Visualization", on_click=get_visualizations)