File size: 3,906 Bytes
d9d1579 |
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 |
# Import from 3rd party libraries
import streamlit as st
import streamlit.components.v1 as components
# import streamlit_analytics
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="🤖")
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)
#load the model
@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'))
#load the dataframe with disorder embeddings
@st.cache_data # 👈 Add the caching decorator
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()
#create a list of disease names
@st.cache_data # 👈 Add the caching decorator
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):
# reshaping the character_embedding to match the shape of mental_disorder_embeddings
descr_emb = descr_emb.reshape(1, -1)
# calculating the cosine similarity
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]
# with text_spinner_placeholder:
# with st.spinner("Please wait while your Tweet is being generated..."):
# mood_prompt = f"{mood} " if mood else ""
# if style:
# twitter = twe.Tweets(account=style)
# tweets = twitter.fetch_tweets()
# tweets_prompt = "\n\n".join(tweets)
# prompt = (
# f"Write a {mood_prompt}Tweet about {topic} in less than 120 characters "
# f"and in the style of the following Tweets:\n\n{tweets_prompt}\n\n"
# Configure Streamlit page and state
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)
# mood = st.text_input(
# label="Mood (e.g. inspirational, funny, serious) (optional)",
# placeholder="inspirational",
# )
# style = st.text_input(
# label="Twitter account handle to style-copy recent Tweets (optional, limited by Twitter's API)",
# placeholder="elonmusk",
# )
text_spinner_placeholder = st.empty()
|