Spaces:
Sleeping
Sleeping
File size: 1,995 Bytes
606291c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
import streamlit as st
import streamlit.components.v1 as components
import pandas as pd
@st.experimental_memo
def read_xsum_samples():
df = pd.read_csv('./data/small_x_sum.csv')
df = df[['ID', 'Content', 'Summary']]
all_index = list(df.index)
all_text = list(df.Content)
text_dict = dict(zip(all_index, all_text))
return text_dict
@st.experimental_memo
def read_squad_samples():
df = pd.read_csv('./data/squad_sample.tsv', sep='\t')
df = df[['id', 'context', 'question']]
all_index = list(df.index)
all_text = list(df.context)
text_dict = dict(zip(all_index, all_text))
return text_dict
@st.experimental_memo
def read_conll_samples():
df = pd.read_pickle('./data/conll_df.pkl')
df = df[['doc-text', 'ner-tag']]
all_index = list(df.index)
all_text = list(df['doc-text'])
text_dict = dict(zip(all_index, all_text))
return text_dict
def get_default_texts(chosen_datasets):
if "bbc-xsum-summarization" in chosen_datasets:
the_dict = read_xsum_samples()
elif "conll-ner" in chosen_datasets:
the_dict = read_conll_samples()
else:
the_dict = read_squad_samples()
return the_dict
def display_output(all_outputs):
all_tabs = [tab[0] for tab in all_outputs]
tabs = st.tabs(all_tabs)
for tab_index in range(len(all_tabs)):
if all_outputs[tab_index][0] == 'Predicted Answer':
with tabs[tab_index]:
st.text_area('Best Answer found:', value=all_outputs[tab_index][1], disabled=True)
elif all_outputs[tab_index][0] == 'Predicted Entities':
with tabs[tab_index]:
# st.markdown(all_outputs[tab_index][1], unsafe_allow_html=True)
components.html(all_outputs[tab_index][1], scrolling=True)
else:
with tabs[tab_index]:
st.text_area('Best Prediction found', value=all_outputs[tab_index][1], disabled=True)
if __name__ == '__main__':
read_conll_samples()
|