Duplicate from UVA-MSBA/Mod4Team3

Co-authored-by: Chris Clark <chrisclark1016@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Mod4Team3
+emoji: 🐨
+colorFrom: indigo
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.28.0
+app_file: app.py
+pinned: false
+duplicated_from: UVA-MSBA/Mod4Team3
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,143 @@
+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, AutoModelForTokenClassification
+
+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("chrisclark1016/ADR_best")  
+model = AutoModelForSequenceClassification.from_pretrained("chrisclark1016/ADR_best").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)
+
+ner_tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
+ner_model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
+
+ner_pipe = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
+
+
+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()])
+    # # Find the index of the class you want as the default reference (e.g., 'label_1')
+    # label_1_index = np.where(np.array(explainer.output_names) == 'label_1')[0][0]
+
+    # # Plot the SHAP values for a specific instance in your dataset (e.g., instance 0)
+    # shap.plots.text(shap_values[label_1_index][0])
+
+
+    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])
+
+    res = ner_pipe(x)
+    
+    entity_colors = {
+    'Severity': 'red',
+    'Sign_symptom': 'green',
+    'Medication': 'lightblue',
+    'Age': 'pink',
+    'Sex':'yellow',
+    'Diagnostic_procedure':'gray',
+    'Biological_structure':'silver'}
+
+    htext = ""
+    prev_end = 0
+
+    for entity in res:
+        start = entity['start']
+        end = entity['end']
+        word = entity['word'].replace("##", "")
+        color = entity_colors[entity['entity_group']]
+        
+        htext += f"{x[prev_end:start]}<mark style='background-color:{color};'>{word}</mark>"
+        prev_end = end
+
+    htext += x[prev_end:]
+   
+    return {"Severe Reaction": float(scores.numpy()[1]), "Non-severe Reaction": float(scores.numpy()[0])}, local_plot,htext
+    # ,{"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]
+
+title = "🦾 DAVA 🦾"
+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 medications. 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")
+            
+
+        with gr.Column(visible=True) as output_col:
+            local_plot = gr.HTML(label = 'Shap:')
+            htext = gr.HTML(label="NER")
+            # med = gr.Label(label = "Contains Medication")
+            # sym = gr.Label(label = "Contains Symptoms")
+            
+    submit_btn.click(
+        main,
+        [prob1],
+        [label
+         ,local_plot, htext
+         # , med, sym
+        ], api_name="adr"
+    )
+    
+    with gr.Row():
+        gr.Markdown("### Click on any of the examples below to see how it works:")
+        gr.Examples([["A 35 year-old male had severe headache after taking Aspirin. The lab results were normal."],
+                     ["A 35 year-old female had minor pain in upper abdomen after taking Acetaminophen."]], 
+                    [prob1], [label,local_plot, htext
+         # , med, sym
+                             ], main, cache_examples=True)
+    
+demo.launch()

requirements.txt

@@ -0,0 +1,12 @@
+transformers==4.20.1
+gradio==3.1.3
+tensorflow==2.11.0
+tensorflow_hub
+Pillow
+matplotlib
+spacy_streamlit
+streamlit
+torch==1.12.1
+shap==0.41.0
+numpy
+scipy