added offline files

app.py

@@ -202,6 +202,25 @@ def topic_distribution(weights, smoothing=0.01):
  # for category in categories_sorted:
  # return(topic_frequencies[category], topic_frequencies_spotlight[category], topic_ratios[category], category)
 
+def populate_session(dataset,model):
+ data_df = pd.read_parquet('./assets/data/'+dataset+ '_'+ model+'.parquet')
+ if model == 'albert-base-v2-yelp-polarity':
+ tokenizer = AutoTokenizer.from_pretrained('textattack/'+model)
+ else:
+ tokenizer = AutoTokenizer.from_pretrained(model)
+ if "user_data" not in st.session_state:
+ 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') 
 
 if __name__ == "__main__":
  ### STREAMLIT APP CONGFIG ###
@@ -224,26 +243,10 @@ if __name__ == "__main__":
  ["distilbert-base-uncased-finetuned-sst-2-english",
  "albert-base-v2-yelp-polarity"],
  )
- ### LOAD DATA AND SESSION VARIABLES ###
- data_df = pd.read_parquet('./assets/data/'+dataset+ '_'+ model+'.parquet')
- if model == 'albert-base-v2-yelp-polarity':
- tokenizer = AutoTokenizer.from_pretrained('textattack/'+model)
- else:
- tokenizer = AutoTokenizer.from_pretrained(model)
- if "user_data" not in st.session_state:
- 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')
 
+ ### LOAD DATA AND SESSION VARIABLES ###
+ ##uncomment the next next line to run dynamically and not from file
+ #populate_session(dataset, model)
  with rcol:
  with st.spinner(text='loading...'):
  st.markdown('<h3>Word Distribution in Error Slice</h3>', unsafe_allow_html=True)