adding parquets

app.py

@@ -224,15 +224,6 @@ if __name__ == "__main__":
  ["distilbert-base-uncased-finetuned-sst-2-english",
  "albert-base-v2-yelp-polarity"],
  )
-
- loss_quantile = st.sidebar.slider(
- "Loss Quantile", min_value=0.5, max_value=1.0,step=0.01,value=0.95
- )
-
- run_kmeans = st.sidebar.radio("Cluster error slice?", ('True', 'False'), index=0)
-
- num_clusters = st.sidebar.slider("# clusters", min_value=1, max_value=20, step=1, value=3)
-
  ### LOAD DATA AND SESSION VARIABLES ###
  data_df = pd.read_parquet('./assets/data/'+dataset+ '_'+ model+'.parquet')
  if model == 'albert-base-v2-yelp-polarity':
@@ -243,13 +234,28 @@ if __name__ == "__main__":
  st.session_state["user_data"] = data_df
  if "selected_slice" not in st.session_state:
  st.session_state["selected_slice"] = None
-
+ 
+ loss_quantile = st.sidebar.slider(
+ "Loss Quantile", min_value=0.5, max_value=1.0,step=0.01,value=0.95
+ )
  data_df['loss'] = data_df['loss'].astype(float)
  losses = data_df['loss']
  high_loss = losses.quantile(loss_quantile)
  data_df['slice'] = 'high-loss'
  data_df['slice'] = data_df['slice'].where(data_df['loss'] > high_loss, 'low-loss')
 
+ with rcol:
+ with st.spinner(text='loading...'):
+ st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)
+ commontokens = frequent_tokens(data_df, 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)
+
+ run_kmeans = st.sidebar.radio("Cluster error slice?", ('True', 'False'), index=0)
+
+ num_clusters = st.sidebar.slider("# clusters", min_value=1, max_value=20, step=1, value=3)
+
  if run_kmeans == 'True':
  merged = kmeans(data_df,num_clusters=num_clusters)
  with lcol:
@@ -264,12 +270,5 @@ if __name__ == "__main__":
  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.")
  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)
- 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)