Spaces:
Runtime error
Runtime error
File size: 3,668 Bytes
1ca0686 d042411 1ca0686 d042411 3112e6e 1ca0686 d042411 1ca0686 d042411 1ca0686 d042411 3112e6e d042411 |
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 |
import streamlit as st
import pandas as pd
from transformers import pipeline
from pprint import pprint
from datasets import load_dataset
from torch.utils.data import DataLoader
st.title("CS634 - milestone2 - Tedi Pano")
@st.cache_resource
def load_data():
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',
)
st.write('Loading is done!')
return dataset_dict
@st.cache_resource
def training_computation(_dataset_dict):
df = pd.DataFrame(_dataset_dict['train'])
vf = pd.DataFrame(_dataset_dict['validation'])
accepted_rejected = ['ACCEPTED', 'REJECTED']
df = df[df['decision'].isin(accepted_rejected)]
df['patentability_score'] = df['decision'].map({'ACCEPTED': 1, 'REJECTED': 0})
vf = vf[vf['decision'].isin(accepted_rejected)]
vf['patentability_score'] = vf['decision'].map({'ACCEPTED': 1, 'REJECTED': 0})
st.write("Processed the data")
from sklearn.model_selection import train_test_split
dftrain, dftest = train_test_split(df, test_size = 0.90, random_state = 0)
from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
X_dtrain = dftrain['abstract'].tolist()
y_dtrain = dftrain['patentability_score'].tolist()
X_vtrain = vf['abstract'].tolist()
y_vtrain = vf['patentability_score'].tolist()
X_dtest = dftest['abstract'].tolist()
y_dtest = dftest['patentability_score'].tolist()
train_encodings = tokenizer(X_dtrain, truncation=True, padding=True)
val_encodings = tokenizer(X_vtrain, truncation=True, padding=True)
test_encodings = tokenizer(X_dtest, truncation=True, padding=True)
st.write("tokenizing completed!")
import tensorflow as tf
train_dataset = tf.data.Dataset.from_tensor_slices((
dict(train_encodings),
y_dtrain
))
val_dataset = tf.data.Dataset.from_tensor_slices((
dict(val_encodings),
y_vtrain
))
test_dataset = tf.data.Dataset.from_tensor_slices((
dict(test_encodings),
y_dtest
))
st.write("back to dataset!")
from transformers import TFDistilBertForSequenceClassification, TFTrainer, TFTrainingArguments
training_args = TFTrainingArguments(
output_dir='./results',
num_train_epochs=2,
per_device_train_batch_size=16,
per_device_eval_batch_size=16,
warmup_steps=500,
eval_steps=500,
weight_decay=0.01
)
with training_args.strategy.scope():
model = TFDistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")
trainer = TFTrainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=val_dataset
)
trainer.train()
st.write("training completed")
return trainer
dataset_dict = load_data()
trainer = training_computation(dataset_dict)
patents = pd.DataFrame(dataset_dict['train'])
patent_selection = st.selectbox("Select Patent",patents['patent_number'])
patent = patents.loc[patents['patent_number'] == patent_selection]
st.write(patent['abstract'])
st.write(patent['claims'])
|