message

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 from datasets import load_dataset
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 
 dataset_dict = load_dataset('HUPD/hupd',
     name='sample',
@@ -11,5 +12,48 @@ dataset_dict = load_dataset('HUPD/hupd',
     val_filing_end_date='2016-01-31',
 )
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+st.title("Patentability Score")
+
+abstracts={}
+claims={}
+
+
+dataset = dataset_dict["train"].shuffle(seed=42).select(range(20))
+
+for i in range(0, 20):
+
+    abstracts[dataset['patent_number'][i]] = dataset['abstract'][i]
+    claims[dataset['patent_number'][i]] = dataset['claims'][i]
+
+
+#def get_score(abstract):
+
+   # model = AutoModelForSequenceClassification.from_pretrained("arianasutanto/finetuned-distilbert")
+   # tokenizer = AutoTokenizer.from_pretrained("arianasutanto/finetuned-distilbert", pad_to_max_length=True)
+    #inputs = tokenizer(abstract, max_length=512, padding='max_length', truncation=True, return_tensors='pt')
+
+    #outputs = model(inputs['input_ids'], attention_mask=inputs['attention_mask'])
+    #scores = torch.softmax(outputs.logits, dim=1)[0]
+
+    #probs = F.softmax(scores, dim=0)
+   # accept_prob = probs[0].item()
+
+    #print(accept_prob)
+
+    #return #accept_prob
+
+
+
+
+patent_num = st.selectbox("Choose a patent number", options=abstracts.keys())
+if st.button("Submit"):
+   abstract = st.text_area(label="Abstract",value=abstracts[patent_num])
+   claim = st.text_area(label="Claims",value=claims[patent_num])
+   #get_score(abstract)
+
+
+#abstract = abstracts[patent_num]
+#st.write(abstract)
+#claim = claims[patent_num]
+#st.write(claim)
+