|
|
|
import streamlit as st |
|
import streamlit.components.v1 as components |
|
|
|
import pandas as pd |
|
import numpy as np |
|
import re |
|
from sklearn.metrics.pairwise import cosine_similarity |
|
import string |
|
import nltk |
|
from nltk.corpus import stopwords |
|
from nltk.stem import WordNetLemmatizer |
|
nltk.download("stopwords") |
|
nltk.download('wordnet') |
|
from sentence_transformers import SentenceTransformer |
|
import plotly.express as px |
|
import pandas as pd |
|
from sklearn.decomposition import PCA |
|
|
|
st.set_page_config(page_title="Mental disorder by description", page_icon="π€") |
|
|
|
def convert_string_to_numpy_array(s): |
|
'''Function to convert a string to a NumPy array''' |
|
numbers_list = re.findall(r'-?\d+\.\d+', s) |
|
return np.array(numbers_list, dtype=np.float64) |
|
|
|
|
|
@st.cache_resource |
|
def get_models(): |
|
st.write('Loading the model...') |
|
name = "stsb-bert-large" |
|
model = SentenceTransformer(name) |
|
st.write("The app is loaded and ready to use!") |
|
lemmatizer = WordNetLemmatizer() |
|
return model, lemmatizer |
|
|
|
model, lemmatizer = get_models() |
|
stop_words = set(stopwords.words('english')) |
|
|
|
|
|
@st.cache_data |
|
def load_data(): |
|
df_icd = pd.read_csv('icd_embedded.csv') |
|
df_icd['numpy_array'] = df_icd['Embeddings'].apply(convert_string_to_numpy_array) |
|
icd_embeddings = np.array(df_icd["numpy_array"].tolist()) |
|
return df_icd, icd_embeddings |
|
|
|
df_icd, icd_embeddings = load_data() |
|
|
|
|
|
@st.cache_data |
|
def create_disease_list(): |
|
disease_names = [] |
|
for name in df_icd["Disease"]: |
|
disease_names.append(name) |
|
return disease_names |
|
|
|
disease_names = create_disease_list() |
|
|
|
if 'descriptions' not in st.session_state: |
|
st.session_state.descriptions = [] |
|
|
|
def similarity_top(descr_emb, disorder_embs): |
|
|
|
descr_emb = descr_emb.reshape(1, -1) |
|
|
|
similarity_scores = cosine_similarity(disorder_embs, descr_emb) |
|
|
|
scores_names = [] |
|
for score, name in zip(similarity_scores, disease_names): |
|
data = {"disease_name": name, "similarity_score": score} |
|
scores_names.append(data) |
|
|
|
scores_names = sorted(scores_names, key=lambda x: x['similarity_score'], reverse=True) |
|
|
|
results = [] |
|
|
|
for item in scores_names: |
|
disease_name = item['disease_name'] |
|
similarity_score = item['similarity_score'][0] |
|
results.append((disease_name, similarity_score)) |
|
|
|
return results[:5] |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
st.title("Detect the disorder") |
|
st.markdown( |
|
"This mini-app predicts a mental disorder based on your description." |
|
) |
|
|
|
input = st.text_input(label="Your description)", placeholder="Insert a description of a character") |
|
if input: |
|
input_embed = model.encode(input) |
|
sim_score = similarity_top(input_embed, icd_embeddings) |
|
st.write(sim_score) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
text_spinner_placeholder = st.empty() |
|
|