Spaces:
Runtime error
Runtime error
File size: 3,681 Bytes
0e46a6f 83e19cd 0e46a6f 83e19cd 7a4b44a d5ab659 0e46a6f 83e19cd 0e46a6f 83e19cd 0e46a6f 83e19cd 0e46a6f 83e19cd 824c411 83e19cd 54d8a35 83e19cd |
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
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
from datasets import load_dataset
# Milestone-3
if "viability" not in st.session_state:
st.session_state.viability = ""
if "score" not in st.session_state:
st.session_state.score = ""
def get_patent_score(pipeline, abstract, claims):
abstract_score = pipeline(abstract)
claims_score = pipeline(claims)
abstract_label = abstract_score[0]["label"]
claims_label = claims_score[0]["label"]
st.session_state.score = "{:.2f}".format(
((abstract_score[0]["score"] + claims_score[0]["score"]) / 2) * 100
)
if abstract_label == claims_label:
st.session_state.viability = abstract_label
else:
if abstract_score[0]["score"] > claims_score[0]["label"]:
st.session_state.viability = abstract_label
else:
st.session_state.viability = claims_label
checkpoint_file = "./checkpoint-3024"
model = AutoModelForSequenceClassification.from_pretrained(checkpoint_file)
tokenizer = AutoTokenizer.from_pretrained(checkpoint_file)
pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
dataset_dict = load_dataset('HUPD/hupd',
name='sample',
data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather",
icpr_label=None,
train_filing_start_date='2016-01-01',
train_filing_end_date='2016-01-21',
val_filing_start_date='2016-01-22',
val_filing_end_date='2016-01-31',
)
dataset = dataset_dict["train"]
abstract_dict = {}
claims_dict = {}
for i in range(10):
abstract_dict[dataset["title"][i]] = dataset["abstract"][i]
claims_dict[dataset["title"][i]] = dataset["claims"][i]
st.title("Patent Vibility Score Checker")
chosen_patent = st.selectbox(
"Chose a patent to run the checker on", options=abstract_dict.keys())
abstract = st.text_area(
label="Abstract",
value=abstract_dict[chosen_patent]
)
claims = st.text_area(
label="Claims",
value=claims_dict[chosen_patent]
)
st.button("Check Viability", on_click=get_patent_score,
options=(pipeline, abstract, claims))
st.markdown(body="Outcome: {}, Score: {}%".format(
st.session_state.viability, st.session_state.score))
# Milestone-2
# if "sentiment" not in st.session_state:
# st.session_state.sentiment = ""
# if "score" not in st.session_state:
# st.session_state.score = ""
# def run_model(text_in, model_in):
# classifier = pipeline(task="sentiment-analysis",
# model=model_in)
# analysis = classifier(text_in)
# st.session_state.sentiment = analysis[0]["label"]
# st.session_state.score = "{:.2f}".format(analysis[0]["score"] * 100)
# models_available = {"Roberta Large English": "siebert/sentiment-roberta-large-english",
# "Generic": "Seethal/sentiment_analysis_generic_dataset",
# "Twitter Roberta": "cardiffnlp/twitter-roberta-base-sentiment"}
# st.title("Sentiment Analysis Web Application")
# text_input = st.text_area(
# label="Enter the text to analyze", value="I Love Pizza")
# model_picked = st.selectbox(
# "Choose a model to run on", options=models_available.keys())
# st.button("Submit", on_click=run_model, args=(
# text_input, models_available[model_picked]))
# st.markdown(body="Sentiment: {}, Confidence Score: {} %".format(
# st.session_state.sentiment, st.session_state.score))
|