loading

app.py

@@ -80,7 +80,7 @@ def data_comparison(df):
  ).interactive()
 
  legend = alt.Chart(df).mark_point().encode(
- y=alt.Y('cluster:N', axis=alt.Axis(orient='right'), title=""),
+ y=alt.Y('cluster:N', axis=alt.Axis(orient='left'), title=""),
  x=alt.X("label"),
  shape=alt.Shape('label', scale=alt.Scale(
  range=['circle', 'diamond']), legend=None),
@@ -89,7 +89,7 @@ def data_comparison(df):
  selection
  )
  
- layered = scatter | legend
+ layered = legend | scatter
 
  layered = layered.configure_axis(
  grid=False
@@ -99,7 +99,7 @@ def data_comparison(df):
 
  return layered
 
-
+@st.cache(ttl=600)
 def quant_panel(embedding_df):
  """ Quantitative Panel Layout"""
 
@@ -112,6 +112,7 @@ def quant_panel(embedding_df):
  st.markdown("* The **shape** of each point reflects the label category -- positive (diamond) or negative sentiment (circle).")
  st.altair_chart(data_comparison(down_samp(embedding_df)))
 
+@st.cache(ttl=600)
 def frequent_tokens(data, tokenizer, loss_quantile=0.95, top_k=200, smoothing=0.005):
  unique_tokens = []
  tokens = []
@@ -171,6 +172,7 @@ def clustering(data,num_clusters):
 
  return data, assigned_clusters
 
+@st.cache(ttl=600)
 def kmeans(df, num_clusters=3):
  data_hl = df.loc[df['slice'] == 'high-loss']
  data_kmeans,clusters = clustering(data_hl,num_clusters)
@@ -276,10 +278,11 @@ if __name__ == "__main__":
  st.write(dataframe,width=900, height=300)
  
  with rcol:
- st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
- commontokens = frequent_tokens(merged, tokenizer, loss_quantile=loss_quantile)
- with st.expander("How to read the table:"):
- st.markdown("* The table displays the most frequent tokens in error slices, relative to their frequencies in the val set.")
- st.write(commontokens)
-
- quant_panel(merged)
+ with st.spinner(text='loading...'):
+ st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
+ commontokens = frequent_tokens(merged, tokenizer, loss_quantile=loss_quantile)
+ with st.expander("How to read the table:"):
+ st.markdown("* The table displays the most frequent tokens in error slices, relative to their frequencies in the val set.")
+ st.write(commontokens)
+ with st.spinner(text='visualizing...'):
+ quant_panel(merged)