Spaces:
Runtime error
Runtime error
File size: 3,609 Bytes
e669abf f387393 1abbe27 e669abf 0e20e10 1b8c45e e669abf f057421 998e5ed e669abf 9cc7c4e e669abf 9cc7c4e 2888c51 9cc7c4e 7f48a24 68fbe9e 0e1a661 68fbe9e a6d17eb 55ecc4c 7f48a24 e669abf 579be1d e669abf 518ac36 4a73816 3a53d21 7f48a24 c35e70a a6d17eb 518ac36 a6d17eb 518ac36 e669abf 42c5082 e669abf a6d17eb e669abf cde5ee9 e669abf 42c5082 e669abf cde5ee9 c78f4ac e669abf cde5ee9 a6d17eb 55ecc4c e669abf 42c5082 9cc7c4e a6d17eb f1c8fb6 e669abf 3553235 aa5b3ba 998e5ed a6d17eb f1c8fb6 e669abf |
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 |
import streamlit as st
import gradio as gr
import shap
import numpy as np
import scipy as sp
import torch
import tensorflow as tf
import transformers
from transformers import pipeline
from transformers import RobertaTokenizer, RobertaModel
from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer
import matplotlib.pyplot as plt
import sys
import csv
csv.field_size_limit(sys.maxsize)
device = "cuda:0" if torch.cuda.is_available() else "cpu"
tokenizer = AutoTokenizer.from_pretrained("paragon-analytics/ADRv1")
model = AutoModelForSequenceClassification.from_pretrained("paragon-analytics/ADRv1").to(device)
# build a pipeline object to do predictions
pred = transformers.pipeline("text-classification", model=model,
tokenizer=tokenizer, return_all_scores=True)
explainer = shap.Explainer(pred)
##
classifier = transformers.pipeline("text-classification", model = "cross-encoder/qnli-electra-base")
def med_score(x):
label = x['label']
score_1 = x['score']
return round(score_1,3)
# def sym_score(x):
# label2sym= x['label']
# score_1sym = x['score']
# return round(score_1sym,3)
##
def adr_predict(x):
encoded_input = tokenizer(x, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = tf.nn.softmax(scores)
shap_values = explainer([str(x).lower()])
local_plot = shap.plots.text(shap_values[0], display=False)
med = med_score(classifier(x+str(", There is a medication."))[0])
# sym = sym_score(classifier(x+str(", There is a symptom."))[0])
return {"Severe Reaction": float(scores.numpy()[1]), "Non-severe Reaction": float(scores.numpy()[0])}, local_plot, {"Contains Medication": float(med), "No Medications": float(1-med)}
# , {"Contains Symptoms": float(sym), "No Symptoms": float(1-sym)}
def main(prob1):
text = str(prob1).lower()
obj = adr_predict(text)
return obj[0],obj[1],obj[2]
# ,obj[3]
title = "Welcome to **ADR Detector** 🪐"
description1 = """This app takes text (up to a few sentences) and predicts to what extent the text describes severe (or non-severe) adverse reaction to medicaitons. Please do NOT use for medical diagnosis."""
with gr.Blocks(title=title) as demo:
gr.Markdown(f"## {title}")
gr.Markdown(description1)
gr.Markdown("""---""")
prob1 = gr.Textbox(label="Enter Your Text Here:",lines=2, placeholder="Type it here ...")
submit_btn = gr.Button("Analyze")
with gr.Row():
with gr.Column(visible=True) as output_col:
label = gr.Label(label = "Predicted Label")
local_plot = gr.HTML(label = 'Shap:')
with gr.Column(visible=True) as output_col:
med = gr.Label(label = "Contains Medication")
# sym = gr.Label(label = "Contains Symptoms")
submit_btn.click(
main,
[prob1],
[label
,local_plot, med
# , sym
], api_name="adr"
)
with gr.Row():
gr.Markdown("### Click on any of the examples below to see how it works:")
gr.Examples([["I had severe headache after taking Aspirin."],["I had minor stomachache after taking Acetaminophen."]], [prob1], [label,local_plot, med
# , sym
], main, cache_examples=True)
demo.launch()
|