Update app.py

app.py

@@ -40,6 +40,7 @@ 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.write("Number of submissions at ICLR 2023:", len(raw_notes))
 
 df_raw = pd.json_normalize(raw_notes)
@@ -49,42 +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)