|
import streamlit as st |
|
from pathlib import Path |
|
import json |
|
from support_functions import HealthseaSearch |
|
|
|
|
|
with open("style.css") as f: |
|
st.markdown("<style>" + f.read() + "</style>", unsafe_allow_html=True) |
|
|
|
|
|
st.title("Welcome to Healthsea 🪐") |
|
|
|
intro, jellyfish = st.columns(2) |
|
jellyfish.markdown("\n") |
|
|
|
intro.subheader("Create easier access to health✨") |
|
|
|
jellyfish.image("data/img/Jellymation.gif") |
|
intro.markdown( |
|
"""Healthsea is an end-to-end spaCy v3 pipeline for analyzing user reviews to supplementary products and extracting their potential effects on health.""" |
|
) |
|
intro.markdown( |
|
"""The code for Healthsea is provided in this [github repository](https://github.com/explosion/healthsea). Visit our [blog post](https://explosion.ai/blog/healthsea) or more about the Healthsea project. |
|
""" |
|
) |
|
|
|
st.write( |
|
"""This app visualizes the results of Healthsea on a dataset of up to 1 million reviews to 10.000 products. You can use the app to search for any health aspect, whether it's a disease (e.g. joint pain) or a positive state of health (e.g. energy), the app returns a list of products and substances. |
|
You can visit the [Healthsea Pipeline app](https://huggingface.co/spaces/spacy/healthsea-pipeline) for exploring the pipeline itself. |
|
""" |
|
) |
|
|
|
st.warning("""Healthsea is an experimental project and the results should not be used as a foundation for solving health problems. Nor do we want to give the impression that supplements are the answer to anyone's health issues.""") |
|
|
|
|
|
health_aspect_path = Path("data/health_aspects.json") |
|
product_path = Path("data/products.json") |
|
condition_path = Path("data/condition_vectors.json") |
|
benefit_path = Path("data/benefit_vectors.json") |
|
|
|
|
|
@st.cache(allow_output_mutation=True) |
|
def load_data( |
|
_health_aspect_path: Path, |
|
_product_path: Path, |
|
_condition_path: Path, |
|
_benefit_path: Path, |
|
): |
|
with open(_health_aspect_path) as reader: |
|
health_aspects = json.load(reader) |
|
with open(_product_path) as reader: |
|
products = json.load(reader) |
|
with open(_condition_path) as reader: |
|
conditions = json.load(reader) |
|
with open(_benefit_path) as reader: |
|
benefits = json.load(reader) |
|
return health_aspects, products, conditions, benefits |
|
|
|
|
|
|
|
def kpi(n, text): |
|
html = f""" |
|
<div class='kpi'> |
|
<h1 class='kpi_header'>{n}</h1> |
|
<span>{text}</span> |
|
</div> |
|
""" |
|
return html |
|
|
|
|
|
def central_text(text): |
|
html = f"""<h2 class='central_text'>{text}</h2>""" |
|
return html |
|
|
|
|
|
health_aspects, products, conditions, benefits = load_data( |
|
health_aspect_path, product_path, condition_path, benefit_path |
|
) |
|
search_engine = HealthseaSearch(health_aspects, products, conditions, benefits) |
|
|
|
|
|
st.markdown("""---""") |
|
|
|
st.markdown(central_text("🎀 Dataset"), unsafe_allow_html=True) |
|
|
|
kpi_products, kpi_reviews, kpi_condition, kpi_benefit = st.columns(4) |
|
|
|
def round_to_k(value): |
|
return str(round(value/1000,1))+"k" |
|
|
|
kpi_products.markdown(kpi(round_to_k(len(products)), "Products"), unsafe_allow_html=True) |
|
kpi_reviews.markdown(kpi(round_to_k(int(933240)), "Reviews"), unsafe_allow_html=True) |
|
kpi_condition.markdown(kpi(round_to_k(len(conditions)), "Conditions"), unsafe_allow_html=True) |
|
kpi_benefit.markdown(kpi(round_to_k(len(benefits)), "Benefits"), unsafe_allow_html=True) |
|
|
|
st.markdown("""---""") |
|
|
|
|
|
show_conditions, show_benefits = st.columns(2) |
|
|
|
with show_conditions.expander("Top mentioned Conditions"): |
|
st.write(search_engine.get_all_conditions_df()) |
|
|
|
with show_benefits.expander("Top mentioned Benefits"): |
|
st.write(search_engine.get_all_benefits_df()) |
|
|
|
st.markdown("""---""") |
|
|
|
|
|
search = st.text_input(label="Search for an health aspect", value="joint pain") |
|
n = st.slider("Show top n results", min_value=10, max_value=1000, value=25) |
|
|
|
st.markdown("""---""") |
|
st.markdown(central_text("🧃 Products"), unsafe_allow_html=True) |
|
|
|
st.info("""The product score is based on the results of Healthsea. Variables used for the score are: health effect prediction, product rating, helpful count and whether the review is considered a 'fake review'. """) |
|
|
|
|
|
st.write(search_engine.get_products_df(search, n)) |
|
|
|
|
|
aspect_alias = search_engine.get_aspect(search)["alias"] |
|
|
|
kpi_product_mentions, kpi_alias = st.columns(2) |
|
|
|
kpi_product_mentions.markdown(kpi(len(search_engine.get_aspect(search)["products"]), "Products"), unsafe_allow_html=True) |
|
|
|
|
|
kpi_alias.markdown( |
|
kpi(len(aspect_alias), "Similar health aspects"), |
|
unsafe_allow_html=True, |
|
) |
|
|
|
depth = st.slider("Depth", min_value=0, max_value=5, value=2) |
|
|
|
recursive_alias, recursive_edges = search_engine.get_recursive_alias(search,0,{},[],depth) |
|
|
|
vectors = [] |
|
main_aspect = search_engine.get_aspect_meta(search) |
|
vectors.append((main_aspect["name"], main_aspect["vector"])) |
|
for aspect in aspect_alias: |
|
current_aspect = search_engine.get_aspect_meta(aspect) |
|
vectors.append((current_aspect["name"], current_aspect["vector"])) |
|
st.markdown("\n") |
|
st.info("""Health aspects with a high similarity (>=90%) are clustered together.""") |
|
|
|
search_engine.pyvis2(recursive_alias,recursive_edges) |
|
|
|
st.markdown("""---""") |
|
|
|
|
|
st.markdown(central_text("🍯 Substances"), unsafe_allow_html=True) |
|
st.info("""Substance scores are based on product scores""") |
|
|
|
|
|
st.write(search_engine.get_substances_df(search, n)) |
|
kpi_substances, empty = st.columns(2) |
|
kpi_substances.markdown( |
|
kpi(len(search_engine.get_aspect(search)["substance"]), "Substances"), |
|
unsafe_allow_html=True, |
|
) |
|
|