added instr

app.py

@@ -1,5 +1,5 @@
- ### LIBRARIES ###
-# # Data
+## LIBRARIES ###
+## Data
 import numpy as np
 import pandas as pd
 import torch
@@ -62,16 +62,8 @@ def down_samp(embedding):
 
 
 def data_comparison(df):
- # set up a dropdown select bindinf
- # input_dropdown = alt.binding_select(options=['Negative Sentiment','Positive Sentiment'])
- #data_kmeans['distance_from_centroid'] = data_kmeans.apply(distance_from_centroid, axis=1)
-
  selection = alt.selection_multi(fields=['cluster','label'])
- color = alt.condition(alt.datum.slice == 'high-loss', alt.Color('cluster:N', scale = alt.Scale(domain=df.cluster.tolist())), alt.value("lightgray"))
- # color = alt.condition(selection, 
- # alt.Color('cluster:Q', legend=None),
- # # scale = alt.Scale(domain = pop_domain,range=color_range)),
- # alt.value('lightgray'))
+ color = alt.condition(alt.datum.slice == 'high-loss', alt.Color('cluster:N', scale = alt.Scale(domain=df.cluster.unique().tolist())), alt.value("lightgray"))
  opacity = alt.condition(selection, alt.value(0.7), alt.value(0.25))
 
  # basic chart
@@ -97,7 +89,7 @@ def data_comparison(df):
  selection
  )
  
- layered = legend | scatter
+ layered = scatter | legend
 
  layered = layered.configure_axis(
  grid=False
@@ -112,14 +104,12 @@ def quant_panel(embedding_df):
  """ Quantitative Panel Layout"""
 
  all_metrics = {}
- # st.warning("**Data Comparison**")
-
- # with st.expander("how to read this chart:"):
- # st.markdown("* each **point** is a single sentence")
- # st.markdown("* the **position** of each dot is determined mathematically based upon an analysis of the words in a sentence. The **closer** two points on the visualization the **more similar** the sentences are. The **further apart ** two points on the visualization the **more different** the sentences are")
- # st.markdown(
- # " * the **shape** of each point reflects whether it a positive (diamond) or negative sentiment (circle)")
- # st.markdown("* the **color** of each point is the ")
+ st.warning("**Error slice visualization**")
+
+ with st.expander("How to read this chart:"):
+ st.markdown("* Each **point** is an input example.")
+ st.markdown("* Gray points have low-loss and the colored have high-loss. High-loss instances are clustered using **kmeans** and each color represents a cluster.")
+ 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)))
 
 def frequent_tokens(data, tokenizer, loss_quantile=0.95, top_k=200, smoothing=0.005):
@@ -246,7 +236,7 @@ if __name__ == "__main__":
  )
 
  loss_quantile = st.sidebar.slider(
- "Loss Quantile", min_value=0.0, max_value=1.0,step=0.1,value=0.95
+ "Loss Quantile", min_value=0.0, max_value=1.0,step=0.01,value=0.95
  )
 
  run_kmeans = st.sidebar.radio("Cluster error slice?", ('True', 'False'), index=0)
@@ -280,15 +270,16 @@ if __name__ == "__main__":
  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)
- # st_aggrid.AgGrid(dataframe)
- # table_html = dataframe.to_html(columns=['content', 'label', 'pred', 'loss'], max_rows=100)
- # table_html = table_html.replace("<th>", '<th align="left">') # left-align the headers
- # st.write(table_html)
+ with st.expander("How to read the table:"):
+ st.markdown("* The table displays model error slices on the test set, 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:
  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)

error_analysis/utils/style_hacks.py

@@ -1,5 +1,5 @@
 """
- streamlit style hacks
+ placeholder for all streamlit style hacks
 """
 import streamlit as st
 
@@ -10,12 +10,13 @@ def init_style():
  <style>
  /* Side Bar */
  [data-testid="stSidebar"][aria-expanded="true"] > div:first-child {
- width: 225px;
- margin-left: -500px;
+ width: 300px;
  }
  [data-testid="stSidebar"][aria-expanded="false"] > div:first-child {
- width: 225px;
- margin-left: -500px;
+ width: 300px;
+ }
+ [data-testid="stSidebar"]{
+ flex-basis: unset;
  }
  .css-1outpf7 {
  background-color:rgb(254 244 219);
@@ -23,11 +24,7 @@ def init_style():
  padding:10px 10px 10px 10px;
  }
 
- /* Main Panel*/ 
- [data-testid="stVerticalBlock"]{
- margin-left: -200px;
- padding:10px 10px 10px -200px;
- } 
+ /* Main Panel*/ 
  .css-18e3th9 {
  padding:10px 10px 10px -200px;
  }