Spaces:
Runtime error
Runtime error
import spacy_streamlit | |
from spacy.symbols import * | |
import streamlit as st | |
import html | |
import spacy | |
import subprocess | |
import sys | |
subprocess.run([f"{sys.executable}", "python -m spacy download en_core_web_sm"]) | |
from htbuilder import H, HtmlElement, styles | |
from htbuilder.units import unit | |
# Only works in 3.7+: from htbuilder import div, span | |
div = H.div | |
span = H.span | |
# Only works in 3.7+: from htbuilder.units import px, rem, em | |
px = unit.px | |
rem = unit.rem | |
em = unit.em | |
# Colors from the Streamlit palette. | |
# These are red-70, orange-70, ..., violet-70, gray-70. | |
PALETTE = [ | |
"#ff4b4b", | |
"#ffa421", | |
"#ffe312", | |
"#21c354", | |
"#00d4b1", | |
"#00c0f2", | |
"#1c83e1", | |
"#803df5", | |
"#808495", | |
] | |
OPACITIES = [ | |
"33", "66", | |
] | |
DEFAULT_TEXT = """AI has reached superhuman levels in various areas such as playing complex strategic and video games, calculating protein folding, and visual recognition. Are we close to superhuman levels in conversational AI as well?""" | |
spacy_model = "en_core_web_sm" | |
replacement_dict= { | |
"superhuman levels" : "high accuracy", | |
"conversational AI" : "language generation" | |
} | |
def annotation(body, label="", background=None, color=None, **style): | |
""" | |
from https://github.com/tvst/st-annotated-text/blob/master/annotated_text/util.py | |
""" | |
color_style = {} | |
if color: | |
color_style['color'] = color | |
if not background: | |
label_sum = sum(ord(c) for c in label) | |
background_color = PALETTE[label_sum % len(PALETTE)] | |
background_opacity = OPACITIES[label_sum % len(OPACITIES)] | |
background = background_color + background_opacity | |
return ( | |
span( | |
style=styles( | |
background=background, | |
border_radius=rem(0.33), | |
padding=(rem(0.125), rem(0.5)), | |
overflow="hidden", | |
**color_style, | |
**style, | |
))( | |
html.escape(body), | |
span( | |
style=styles( | |
padding_left=rem(0.5), | |
text_transform="uppercase", | |
))( | |
span( | |
style=styles( | |
font_size=em(0.67), | |
opacity=0.5, | |
))( | |
html.escape(label), | |
), | |
), | |
) | |
) | |
def get_annotated_html(*args): | |
out = div() | |
for arg in args: | |
if isinstance(arg, str): | |
out(html.escape(arg)) | |
elif isinstance(arg, HtmlElement): | |
out(arg) | |
elif isinstance(arg, tuple): | |
out(annotation(*arg)) | |
elif isinstance(arg,list): | |
for el in arg: | |
if isinstance(el, str): | |
out(html.escape(el)) | |
elif isinstance(el, HtmlElement): | |
out(el) | |
elif isinstance(el, tuple): | |
out(annotation(*el)) | |
else: | |
raise Exception("Oh noes!") | |
return str(out) | |
st.title("AI Hype Checker") | |
text = st.text_area("Paste your over-hyped text here:", DEFAULT_TEXT, height=100) | |
doc = spacy_streamlit.process_text(spacy_model, text) | |
for chunk in doc.noun_chunks: | |
if chunk.text in replacement_dict.keys(): | |
text= text.replace(chunk.text, replacement_dict[chunk.text]) | |
else: | |
continue | |
text = st.text_area("Fixed it! See below:", text, height=100) | |
st.markdown("## Here are the terms that we flagged:") | |
chunks= [chunk.text for chunk in doc.noun_chunks] | |
flagged_chunks=[] | |
for i in range(len(chunks)): | |
if chunks[i] in replacement_dict.keys(): | |
flagged_chunks.append((chunks[i], replacement_dict[chunks[i]])) | |
flagged_chunks = list(set(flagged_chunks)) | |
for f in flagged_chunks: | |
st.markdown( | |
get_annotated_html(f), | |
unsafe_allow_html=True, | |
) | |
#st.text(f"Analyzed using spaCy model {spacy_model}") | |