Add dropdown options

app.py

@@ -1,10 +1,32 @@
 import streamlit as st
+<<<<<<< HEAD
+from datasets import load_dataset, Features, Value, Sequence
+=======
 from datasets import load_dataset
+>>>>>>> 81414ba96ac55f927033c62ee5c2db6c6a22349c
 from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
 
 decision_to_str = {'REJECTED': 0, 'ACCEPTED': 1, 'PENDING': 2, 'CONT-REJECTED': 3, 'CONT-ACCEPTED': 4, 'CONT-PENDING': 5}
 
 dataset_dict = load_dataset('HUPD/hupd',
+<<<<<<< HEAD
+    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['validation']
+
+model_abstract = DistilBertForSequenceClassification.from_pretrained('theresatvan/hupd-distilbert-abstract')
+tokenizer_abstract = DistilBertTokenizer.from_pretrained('theresatvan/hupd-distilbert-abstract')
+
+model_claims = DistilBertForSequenceClassification.from_pretrained('theresatvan/hupd-distilbert-claims')
+tokenizer_claims = DistilBertTokenizer.from_pretrained('theresatvan/hupd-distilbert-claims')
+=======
     name='all',
     data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather", 
     icpr_label=None,
@@ -22,6 +44,7 @@ tokenizer_abstract = DistilBertTokenizer('theresatvan/hupd-distilbert-abstract')
 
 model_claims = DistilBertForSequenceClassification('theresatvan/hupd-distilbert-claims')
 tokenizer_claims = DistilBertTokenizer('theresatvan/hupd-distilbert-claims')
+>>>>>>> 81414ba96ac55f927033c62ee5c2db6c6a22349c
 
 
 def predict(model_abstract, model_claims, tokenizer_abstract, tokenizer_claims, input):
@@ -52,13 +75,21 @@ if __name__ == '__main__':
     st.title = "Can I Patent This?"
     
     form = st.form('patent-prediction-form')
+<<<<<<< HEAD
+    dropdown = [example['application_number'] for example in dataset]
+=======
     dropdown = []
+>>>>>>> 81414ba96ac55f927033c62ee5c2db6c6a22349c
     
     input_application = form.selectbox('Select a patent\'s application number', patents_dropdown)
     submit = form.form_submit_button("Submit")
     
     if submit:
+<<<<<<< HEAD
+        input = dataset.filter(lambda e: e['patent_number'] == input_application)
+=======
         input = dataset.filter(lambda e: e['application_number'] == input_application)
+>>>>>>> 81414ba96ac55f927033c62ee5c2db6c6a22349c
         
         label, prob = predict(model_abstract, model_claims, tokenizer_abstract, tokenizer_claims, input)