from io import StringIO import gradio as gr import pandas as pd import spacy nlp = spacy.load('en_core_web_sm') HTML_RED = '{t}' HTML_GRN = '{t}' HTML_BLU = '{t}' HTML_PLN = '{t}' 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() 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(( '', "" "", "", "", "", "", '\n'.join( '\n' + '\n'.join(''.format(cell) for cell in row) + '\n' for row in table_content ), '
idGoldModel AModel B
{}
' )) 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"): viz = gr.HTML(label='Upload a csv file to start.') run.click(colorize, data, viz) demo.launch() if __name__ == '__main__': main()