interactive legend

app.py

@@ -80,8 +80,8 @@ def data_comparison(df):
  ).interactive()
 
  legend = alt.Chart(df).mark_point(size=100, filled=True).encode(
- x=alt.X("label"),
- y=alt.Y('cluster:N', axis=alt.Axis(orient='right'), title=""),
+ x=alt.X("label:N"),
+ y=alt.Y('cluster:N', axis=alt.Axis(orient='right'), sort='descending', title=''),
  shape=alt.Shape('label:N', scale=alt.Scale(
  range=['circle', 'diamond']), legend=None),
  color=color,
@@ -247,6 +247,22 @@ if __name__ == "__main__":
  data_df['slice'] = 'high-loss'
  data_df['slice'] = data_df['slice'].where(data_df['loss'] > high_loss, 'low-loss') 
 
+ with lcol:
+ st.markdown('<h3>Error Slices</h3>',unsafe_allow_html=True)
+ with st.expander("How to read the table:"):
+ st.markdown("* *Error slice* refers to the subset of evaluation dataset the model performs poorly on.")
+ st.markdown("* The table displays model error slices on the evaluation dataset, sorted by loss.")
+ st.markdown("* Each row is an input example that includes the label, model pred, loss, and error cluster.")
+ with st.spinner(text='loading error slice...'):
+ dataframe=read_file_to_df('./assets/data/'+dataset+ '_'+ model+'_error-slices.parquet')
+ #uncomment the next next line to run dynamically and not from file
+ # dataframe = merged[['content', 'label', 'pred', 'loss', 'cluster']].sort_values(
+ # by=['loss'], ascending=False)
+ # table_html = dataframe.to_html(
+ # columns=['content', 'label', 'pred', 'loss', 'cluster'], max_rows=50)
+ # table_html = table_html.replace("<th>", '<th align="left">') # left-align the headers
+ st.write(dataframe,width=900, height=300)
+
  with rcol:
  with st.spinner(text='loading...'):
  st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
@@ -264,20 +280,6 @@ if __name__ == "__main__":
  if run_kmeans == 'True':
  with st.spinner(text='running kmeans...'):
  merged = kmeans(data_df,num_clusters=num_clusters)
- with lcol:
- st.markdown('<h3>Error Slices</h3>',unsafe_allow_html=True)
- with st.expander("How to read the table:"):
- st.markdown("* *Error slice* refers to the subset of evaluation dataset the model performs poorly on.")
- st.markdown("* The table displays model error slices on the evaluation dataset, sorted by loss.")
- st.markdown("* Each row is an input example that includes the label, model pred, loss, and error cluster.")
- with st.spinner(text='loading error slice...'):
- dataframe=read_file_to_df('./assets/data/'+dataset+ '_'+ model+'_error-slices.parquet')
- #uncomment the next next line to run dynamically and not from file
- # dataframe = merged[['content', 'label', 'pred', 'loss', 'cluster']].sort_values(
- # by=['loss'], ascending=False)
- # table_html = dataframe.to_html(
- # columns=['content', 'label', 'pred', 'loss', 'cluster'], max_rows=50)
- # table_html = table_html.replace("<th>", '<th align="left">') # left-align the headers
- st.write(dataframe,width=900, height=300)
+
  with st.spinner(text='loading visualization...'):
  quant_panel(merged)