Spaces:
Runtime error
Runtime error
File size: 3,899 Bytes
dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab a432184 dabf7ab 66700ad dabf7ab |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
import streamlit as st
import transformers
import pickle
import seaborn as sns
from pandas import DataFrame
from transformers import AutoTokenizer, AutoModelForSequenceClassification
st.markdown("# Hello, friend!")
st.markdown(" This magic application going to help you with understanding of science paper topic! Cool? Yeah! ")
try:
model_name_global = "allenai/scibert_scivocab_uncased"
tokenizer_ = AutoTokenizer.from_pretrained(model_name_global)
with open('./models/scibert/decode_dict.pkl', 'rb') as f:
decode_dict = pickle.load(f)
except ValueError:
st.error("Load tokenizer or decode answer dict goes wrong! Pls contact author alekseystepin13@gmail.com")
with st.form(key="my_form"):
st.markdown("### 🎈 Do you want a little magic? ")
st.markdown(" Write your article title and abstract to textboxes bellow and I'll gues topic of your paper! ")
ce, c2, c3 = st.columns([0.07, 7, 0.07])
with c2:
doc_title = st.text_area(
"Paste your abstract title below (1 to 50 words)",
height=210,
)
doc_abstract = st.text_area(
"Paste your abstract text below (1 to 500 words)",
height=410,
)
MAX_WORDS_TITLE, MAX_WORDS_ABSTRACT = 50, 500
import re
len_title = len(re.findall(r"\w+", doc_title))
len_abstract = len(re.findall(r"\w+", doc_abstract))
if len_title > MAX_WORDS_TITLE:
st.warning(
"⚠️ Your title contains "
+ str(len_title)
+ " words."
+ " Only the first 50 words will be reviewed. Stay tuned as increased allowance is coming! 😊"
)
doc_title = doc_title[:MAX_WORDS_TITLE]
if len_abstract > MAX_WORDS_ABSTRACT:
st.warning(
"⚠️ Your abstract contains "
+ str(len_abstract)
+ " words."
+ " Only the first 500 words will be reviewed. Stay tuned as increased allowance is coming! 😊"
)
doc_abstract = doc_abstract[:MAX_WORDS_ABSTRACT]
submit_button = st.form_submit_button(label="✨ Let's play, try it!")
if not submit_button:
st.stop()
if len_title < 1:
st.error("Article without any words in title? Pls give me correct title!")
st.stop()
if len_abstract < 1:
st.error("Article without any words in abstract? Pls give me correct abstract!")
st.stop()
# allow_output_mutation=True
@st.cache(suppress_st_warning=True)
def load_model():
st.write("Loading big model")
return AutoModelForSequenceClassification.from_pretrained("models/scibert/")
def make_predict(tokens, decode_dict):
model_ = load_model()
outs = model_(tokens.input_ids)
probs = outs["logits"].softmax(dim=-1).tolist()[0]
topic_probs = {}
for i, p in enumerate(probs):
if p > 0.1:
topic_probs[decode_dict[i]] = p
return topic_probs
model_local = "models/scibert/"
title = doc_title
abstract = doc_abstract
try:
tokens = tokenizer_(title + abstract, return_tensors="pt")
except ValueError:
st.error("Word parsing into tokens went wrong! Is input valid? If yes, pls contact author alekseystepin13@gmail.com")
predicts = make_predict(tokens, decode_dict)
st.markdown("## 🎈 Yor article probably about: ")
st.header("")
df = (
DataFrame(predicts.items(), columns=["Topic", "Prob"])
.sort_values(by="Prob", ascending=False)
.reset_index(drop=True)
)
df.index += 1
# Add styling
cmGreen = sns.light_palette("green", as_cmap=True)
cmRed = sns.light_palette("red", as_cmap=True)
df = df.style.background_gradient(
cmap=cmGreen,
subset=[
"Prob",
],
)
c1, c2, c3 = st.columns([1, 3, 1])
format_dictionary = {
"Prob": "{:.1%}",
}
df = df.format(format_dictionary)
with c2:
st.table(df)
|