added offline files

app.py

@@ -140,16 +140,15 @@ def frequent_tokens(data, tokenizer, loss_quantile=0.95, top_k=200, smoothing=0.
 
 
 @st.cache(ttl=600)
-def get_data(spotlight, emb):
- preds = spotlight.outputs.numpy()
- losses = spotlight.losses.numpy()
+def get_data(inference, emb):
+ preds = inference.outputs.numpy()
+ losses = inference.losses.numpy()
  embeddings = pd.DataFrame(emb, columns=['x', 'y'])
  num_examples = len(losses)
  # dataset_labels = [dataset[i]['label'] for i in range(num_examples)]
  return pd.concat([pd.DataFrame(np.transpose(np.vstack([dataset[:num_examples]['content'], 
  dataset[:num_examples]['label'], preds, losses])), columns=['content', 'label', 'pred', 'loss']), embeddings], axis=1)
 
-@st.cache(ttl=600)
 def clustering(data,num_clusters):
  X = np.array(data['embedding'].tolist())
  kclusterer = KMeansClusterer(
@@ -158,11 +157,8 @@ def clustering(data,num_clusters):
  assigned_clusters = kclusterer.cluster(X, assign_clusters=True)
  data['cluster'] = pd.Series(assigned_clusters, index=data.index).astype('int')
  data['centroid'] = data['cluster'].apply(lambda x: kclusterer.means()[x])
- 
-
  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)
@@ -171,7 +167,6 @@ def kmeans(df, num_clusters=3):
  merged['cluster'] = merged['cluster'].fillna(num_clusters).astype('int')
  return merged
 
-@st.cache(ttl=600)
 def distance_from_centroid(row):
  return sdist.norm(row['embedding'] - row['centroid'].tolist())
 
@@ -249,7 +244,7 @@ if __name__ == "__main__":
  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)