import streamlit as st import spacy from spacy_streamlit import visualize_ner from support_functions import HealthseaPipe import operator # Header with open("style.css") as f: st.markdown("", unsafe_allow_html=True) # Intro 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/thomashacker/healthsea). Visit our [blog post](https://explosion.ai/) or more about the Healthsea project. """ ) st.write( """This app visualizes the individual processing steps of the pipeline in which you can write custom reviews to get insights into the functionality of all the different components. You can visit the [Healthsea Demo app](https://huggingface.co/spaces/edichief/healthsea-demo) for exploring the Healthsea processing on productive data. """ ) st.markdown("""---""") # Setup 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 it also caused rashes.", "I'm diagnosed with gastritis. This product helped!", "This has made my insomnia even worse.", "It didn't help my joint pain.", ] # Functions def kpi(n, text): html = f"""

{n}

{text}
""" return html def central_text(text): html = f"""

{text}

""" return html def format_clause(text, meta, pred): html = f"""
{text}
{meta}
""" return html def format_effect(text, pred): html = f"""
{text}
""" return html # Load model load_state = st.info("Loading...") try: load_state.info("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.info ("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.success ("Loading complete!") # Pipeline 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.info("""The NER identifies two labels: 'Condition' and 'Benefit'. 'Condition' entities are generally diseases, symptoms, or general health problems (e.g. joint pain), while 'Benefit' entities 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.info("""The text is segmented into clauses and classified by a Text Classification model. We additionally blind found entities to improve generalization and to inform the model about our current target entity. The Text Classification predicts four exclusive classes that represent the health effect: 'Positive', 'Negative', 'Neutral', 'Anamnesis'.""") st.info("""The 'Anamnesis' class is defined as the current state of health of a reviewer (e.g. 'I am diagnosed with joint pain'). It is used to link health aspects to health effects that are mentioned later in a review.""") 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.info("""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)