Spaces:
Runtime error
Runtime error
File size: 5,360 Bytes
69abbc0 7921022 69abbc0 7921022 69abbc0 99e6b78 69abbc0 99e6b78 03bdce4 99e6b78 b57c5aa 99e6b78 69abbc0 03bdce4 69abbc0 03bdce4 69abbc0 03bdce4 69abbc0 03bdce4 69abbc0 03bdce4 69abbc0 |
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 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
import streamlit as st
import spacy
from spacy_streamlit import visualize_ner
from support_functions import HealthseaPipe
import operator
def visualize_pipeline():
healthsea_pipe = HealthseaPipe()
color_code = {
"POSITIVE": ("#3C9E58", "#1B7735"),
"NEGATIVE": ("#FF166A", "#C0094B"),
"NEUTRAL": ("#7E7E7E", "#4E4747"),
"ANAMNESIS": ("#E49A55", "#AD6B2D"),
}
example_reviews = [
"This is great for joint pain.",
"Product helped my joint pain but also causes rashes.",
"I'm diagnosed with gastritis. This product helped!",
"This has made my insomnia even worse.",
"I don't think this has helped my energy levels.",
]
# Functions
def kpi(n, text):
html = f"""
<div class='kpi'>
<h1>{n}</h1>
<span>{text}</span>
</div>
"""
return html
def central_text(text):
html = f"""<h2 class='central_text'>{text}</h2>"""
return html
def format_clause(text, meta, pred):
html = f"""
<div>
<div class="clause" style="background-color:{color_code[pred][0]} ; box-shadow: 0px 5px {color_code[pred][1]}; border-color:{color_code[pred][1]};">
<div class="clause_text">{text}</div>
</div>
<div class="clause_meta">
<div>{meta}</div>
</div>
</div>"""
return html
def format_effect(text, pred):
html = f"""
<div>
<div class="clause" style="background-color:{color_code[pred][0]} ; box-shadow: 0px 5px {color_code[pred][1]}; border-color:{color_code[pred][1]};">
<div class="clause_text">{text}</div>
</div>
</div>"""
return html
load_state = st.markdown ("#### Loading...")
# Load model
try:
load_state.markdown ("#### Loading model...")
if "model" not in st.session_state:
nlp = spacy.load("en_healthsea")
st.session_state["model"] = nlp
# Download model
except LookupError:
import nltk
import benepar
load_state.markdown ("#### Downloading model...")
benepar.download('benepar_en3')
if "model" not in st.session_state:
nlp = spacy.load("en_healthsea")
st.session_state["model"] = nlp
load_state.markdown ("#### Loading done!")
# Pipeline
st.markdown("""This app visualizes the processing steps of the Healthsea pipeline. You can test it by writing an example review.""")
st.markdown("""---""")
st.markdown(central_text("⚙️ Pipeline"), unsafe_allow_html=True)
check = st.checkbox("Use predefined examples")
if not check:
text = st.text_input(label="Write a review", value="This is great for joint pain!")
else:
text = st.selectbox("Predefined example reviews", example_reviews)
nlp = st.session_state["model"]
doc = nlp(text)
# NER
visualize_ner(
doc,
labels=nlp.get_pipe("ner").labels,
show_table=False,
title="✨ Named Entity Recognition",
colors={"CONDITION": "#FF4B76", "BENEFIT": "#629B68"},
)
st.markdown("""The first processing step is to identify Conditions or Benefits with Named Entity Recognition. Conditions are diseases, symptoms and general health problems (e.g. joint pain), while Benefits are positive desired health aspects (e.g. energy)""")
st.markdown("""---""")
# Segmentation, Blinding, Classification
st.markdown("## 🔮 Segmentation, Blinding, Classification")
clauses = healthsea_pipe.get_clauses(doc)
for doc_clause, clause in zip(clauses, doc._.clauses):
classification = max(clause["cats"].items(), key=operator.itemgetter(1))[0]
percentage = round(float(clause["cats"][classification]) * 100, 2)
meta = f"{clause['ent_name']} ({classification} {percentage}%)"
st.markdown(
format_clause(doc_clause.text, meta, classification), unsafe_allow_html=True
)
st.markdown("\n")
st.markdown("""The review is segmented into sub-clauses and then classified by a Text Classification model. We additionally blind the found entities to improve generalization and also to inform the model about our current target entity of which we want to get the prediction of.
The Text Classification predicts four exclusive classes: 'Positive', 'Negative', 'Neutral', 'Anamnesis', they represent the health effect.""")
st.markdown("""---""")
# Aggregation
st.markdown("## 🔗 Aggregation")
for effect in doc._.health_effects:
st.markdown(
format_effect(
f"{doc._.health_effects[effect]['effect']} effect on {effect}",
doc._.health_effects[effect]["effect"],
),
unsafe_allow_html=True,
)
st.markdown("\n")
st.markdown("""Multiple classification are aggregated into one final classification.""")
st.markdown("""---""")
# Indepth
st.markdown("## 🔧 Pipeline attributes")
clauses_col, effect_col = st.columns(2)
clauses_col.markdown("### doc._.clauses")
for clause in doc._.clauses:
clauses_col.json(clause)
effect_col.markdown("### doc._.health_effects")
effect_col.json(doc._.health_effects)
|