Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -4,9 +4,10 @@ import shap
|
|
4 |
import numpy as np
|
5 |
import scipy as sp
|
6 |
import torch
|
7 |
-
|
8 |
import transformers
|
9 |
from transformers import pipeline
|
|
|
10 |
from transformers import AutoModelForSequenceClassification
|
11 |
from transformers import TFAutoModelForSequenceClassification
|
12 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
@@ -19,8 +20,8 @@ csv.field_size_limit(sys.maxsize)
|
|
19 |
|
20 |
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
21 |
|
22 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
23 |
-
model = AutoModelForSequenceClassification.from_pretrained("
|
24 |
|
25 |
# build a pipeline object to do predictions
|
26 |
pred = transformers.pipeline("text-classification", model=model,
|
@@ -41,11 +42,17 @@ explainer = shap.Explainer(pred)
|
|
41 |
# score_1sym = x['score']
|
42 |
# return round(score_1sym,3)
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
def adr_predict(x):
|
45 |
encoded_input = tokenizer(x, return_tensors='pt')
|
46 |
output = model(**encoded_input)
|
47 |
-
scores = output[0][0].detach()
|
48 |
-
scores =
|
49 |
|
50 |
shap_values = explainer([str(x).lower()])
|
51 |
# # Find the index of the class you want as the default reference (e.g., 'label_1')
|
@@ -83,10 +90,9 @@ def adr_predict(x):
|
|
83 |
prev_end = end
|
84 |
|
85 |
htext += x[prev_end:]
|
86 |
-
|
87 |
-
return {"Severe Reaction": float(scores.numpy()[1]), "Non-severe Reaction": float(scores.numpy()[0])}, local_plot,htext
|
88 |
-
# ,{"Contains Medication": float(med), "No Medications": float(1-med)} , {"Contains Symptoms": float(sym), "No Symptoms": float(1-sym)}
|
89 |
|
|
|
|
|
90 |
|
91 |
def main(prob1):
|
92 |
text = str(prob1).lower()
|
|
|
4 |
import numpy as np
|
5 |
import scipy as sp
|
6 |
import torch
|
7 |
+
import tensorflow as tf
|
8 |
import transformers
|
9 |
from transformers import pipeline
|
10 |
+
from transformers import RobertaTokenizer, RobertaModel
|
11 |
from transformers import AutoModelForSequenceClassification
|
12 |
from transformers import TFAutoModelForSequenceClassification
|
13 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
|
|
20 |
|
21 |
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
22 |
|
23 |
+
tokenizer = AutoTokenizer.from_pretrained("paragon-analytics/ADRv1")
|
24 |
+
model = AutoModelForSequenceClassification.from_pretrained("paragon-analytics/ADRv1").to(device)
|
25 |
|
26 |
# build a pipeline object to do predictions
|
27 |
pred = transformers.pipeline("text-classification", model=model,
|
|
|
42 |
# score_1sym = x['score']
|
43 |
# return round(score_1sym,3)
|
44 |
|
45 |
+
ner_tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
|
46 |
+
ner_model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
|
47 |
+
|
48 |
+
ner_pipe = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
|
49 |
+
#
|
50 |
+
|
51 |
def adr_predict(x):
|
52 |
encoded_input = tokenizer(x, return_tensors='pt')
|
53 |
output = model(**encoded_input)
|
54 |
+
scores = output[0][0].detach().numpy()
|
55 |
+
scores = tf.nn.softmax(scores)
|
56 |
|
57 |
shap_values = explainer([str(x).lower()])
|
58 |
# # Find the index of the class you want as the default reference (e.g., 'label_1')
|
|
|
90 |
prev_end = end
|
91 |
|
92 |
htext += x[prev_end:]
|
|
|
|
|
|
|
93 |
|
94 |
+
return {"Severe Reaction": float(scores.numpy()[1]), "Non-severe Reaction": float(scores.numpy()[0])}, local_plot,htext
|
95 |
+
# ,{"Contains Medication": float(med), "No Medications": float(1-med)} , {"Contains Symptoms": float(sym), "No Symptoms": float(1-sym)}
|
96 |
|
97 |
def main(prob1):
|
98 |
text = str(prob1).lower()
|