Spaces:
Sleeping
Sleeping
from io import StringIO | |
import itertools | |
import gradio as gr | |
import pandas as pd | |
import spacy | |
nlp = spacy.load('en_core_web_sm') | |
HTML_RED = '<span style="background-color: rgba(255, 0, 0, 0.2)">{t}</span>' | |
HTML_GRN = '<span style="background-color: rgba(0, 255, 0, 0.3)">{t}</span>' | |
HTML_YLW = '<span style="background-color: rgba(255, 255, 0, 0.3)">{t}</span>' | |
HTML_BLU = '<span style="background-color: rgba(0, 0, 255, 0.2)">{t}</span>' | |
HTML_PLN = '<span>{t}</span>' | |
TABLE_CSS = ''' | |
th, td { | |
padding: 4px; | |
} | |
table, th, td { | |
border: 1px solid black; | |
border-collapse: collapse; | |
} | |
''' | |
def colorize(file_obj): | |
with open(file_obj.name, 'r') as f: | |
raw = f.read() | |
raw = raw[raw.find('example_id'):] | |
data = pd.read_csv(StringIO(raw)) | |
table_content = [] | |
for row in data.iterrows(): | |
id_ = row[1]['example_id'] | |
gold, genA, genB = nlp.pipe(( | |
row[1]['target summary'], | |
row[1]['model summary A'], | |
row[1]['model summary B'] | |
)) | |
tokens_gold = {token.lemma_.lower(): 0 for token in gold} | |
for token in itertools.chain(genA, genB): | |
if token.lemma_.lower() in tokens_gold: | |
tokens_gold[token.lemma_.lower()] += 1 | |
gold_text = ''.join([ | |
( | |
HTML_PLN.format(t=token.text) | |
if token.pos_ not in {'NOUN', 'PROPN', 'VERB'} | |
else ( | |
( | |
HTML_BLU if tokens_gold[token.lemma_.lower()] > 0 | |
else HTML_YLW | |
).format(t=token.text) | |
) | |
) + token.whitespace_ | |
for token in gold | |
]) | |
table_content.append( | |
[id_, gold_text] + | |
[ | |
''.join( | |
( | |
HTML_PLN.format(t=token.text) | |
if token.pos_ not in {'NOUN', 'PROPN', 'VERB'} | |
else ( | |
HTML_GRN.format(t=token.text) | |
if token.lemma_.lower() in tokens_gold | |
else HTML_RED.format(t=token.text) | |
) | |
) + token.whitespace_ | |
for token in gen | |
) | |
for gen in (genA, genB) | |
] | |
) | |
# return an HTML table using data in table_content | |
return '\n'.join(( | |
'<table>', | |
"<tr>" | |
"<td><b>id</b></td>", | |
"<td><b>Gold</b></td>", | |
"<td><b>Model A</b></td>", | |
"<td><b>Model B</b></td>", | |
"</tr>", | |
'\n'.join( | |
'<tr>\n' + | |
'\n'.join('<td>{}</td>'.format(cell) for cell in row) + | |
'\n</tr>' | |
for row in table_content | |
), | |
'</table>' | |
)) | |
def main(): | |
with gr.Blocks(css=TABLE_CSS) as demo: | |
gr.Markdown( | |
"After uploading, click Run and switch to the Visualization tab." | |
) | |
with gr.Tabs(): | |
with gr.TabItem("Upload"): | |
data = gr.File( | |
label='upload csv with Annotations', type='file' | |
) | |
run = gr.Button(label='Run') | |
with gr.TabItem("Visualization"): | |
gr.HTML( | |
''.join( | |
( | |
"<b>Explanation of colors:</b>", | |
"<br><ul>", | |
"<li><b>", | |
HTML_RED.format(t='Red'), | |
"</b>: word is in generated, but not in gold.</li>", | |
"<li><b>", | |
HTML_GRN.format(t='Green'), | |
"</b>: word is in generated summary and gold.</li>", | |
"<li><b>", | |
HTML_YLW.format(t='Yellow'), | |
"</b>: word is in gold, but not in generated.</li>", | |
"<li><b>", | |
HTML_BLU.format(t='Blue'), | |
"</b>: word is in gold and in generated.</li>", | |
"</ul>", | |
"<br>", | |
"<b>Important</b>: Only nouns, verbs and proper ", | |
"nouns are colored.</b>" | |
) | |
) | |
) | |
viz = gr.HTML(label='Upload a csv file to start.') | |
run.click(colorize, data, viz) | |
demo.launch() | |
if __name__ == '__main__': | |
main() | |