HypeCheck / app.py
sasha's picture
sasha HF staff
nevermind
1a60d47
raw
history blame
3.8 kB
import spacy_streamlit
from spacy.symbols import *
import streamlit as st
import html
import spacy
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}")