Update app.py & requirements

app.py

@@ -1,29 +1,68 @@
 import streamlit as st
-from transformers import pipeline
-from huggingface_hub import HfApi, ModelFilter
+from datasets import load_dataset
+from transformers import DistilBertForSequenceClassification, DistilBertTokenizer
 
-# Set up Hugging Face Hub API client
-api = HfApi()
+decision_to_str = {'REJECTED': 0, 'ACCEPTED': 1, 'PENDING': 2, 'CONT-REJECTED': 3, 'CONT-ACCEPTED': 4, 'CONT-PENDING': 5}
 
-# Display title
-st.title("Text Sentiment Analyzer")
+dataset_dict = load_dataset('HUPD/hupd',
+    name='all',
+    data_files="https://huggingface.co/datasets/HUPD/hupd/blob/main/hupd_metadata_2022-02-22.feather", 
+    icpr_label=None,
+    force_extract=True,
+    train_filing_start_date='2016-01-01',
+    train_filing_end_date='2016-01-01',
+    val_filing_start_date='2017-01-01',
+    val_filing_end_date='2017-05-31',
+)
 
-# Retrieve all text classification models
-models = api.list_models(filter=ModelFilter(task="text-classification"))[:10]
-model_ids = [model.modelId for model in models]
+dataset = dataset_dict['validation'].filter(lambda e: e['decision'] in ['REJECTED', 'ACCEPTED'])
 
-# Create submission form
-form = st.form("sentiment-form")
-select_model = form.selectbox("Select a pretrained model", model_ids)
-input = form.text_area('Enter your text here.')
-submit = form.form_submit_button("Submit")
+model_abstract = DistilBertForSequenceClassification('theresatvan/hupd-distilbert-abstract')
+tokenizer_abstract = DistilBertTokenizer('theresatvan/hupd-distilbert-abstract')
 
-if submit:
-    # Create pipeline to user's selected pre-trained model
-    classifier = pipeline(task="sentiment-analysis", model=select_model)
+model_claims = DistilBertForSequenceClassification('theresatvan/hupd-distilbert-claims')
+tokenizer_claims = DistilBertTokenizer('theresatvan/hupd-distilbert-claims')
+
+
+def predict(model_abstract, model_claims, tokenizer_abstract, tokenizer_claims, input):
+    device = 'cuda' if torch.cuda.is_available() else 'cpu'
+    
+    model_abstract.to(device)
+    model_claims.to(device)
+    
+    model_abstract.eval()
+    model_claims.eval()
+    
+    abstract, claims = input['abstract'], input['claims']
+    
+    input_abstract = tokenizer_abstract(abstract, return_tensors='pt')
+    input_claims = tokenizer_claims(claims, return_tensors='pt')
+    
+    with torch.no_grad():
+        outputs_abstract = model_abstract(**input_abstract)
+        outputs_claims = model_claims(**input_claims)
+        
+    combined_prob = (outputs_abstract.logits.softmax(dim=1) + outputs_claims.logits.softmax(dim=1)) / 2
+    label = torch.argmax(combined_prob, dim=1)
+    
+    return label, combined_prob
+    
+    
+if __name__ == '__main__':
+    st.title = "Can I Patent This?"
+    
+    form = st.form('patent-prediction-form')
+    dropdown = []
     
-    # Extract prediction from the results
-    pred = classifier(input)
+    input_application = form.selectbox('Select a patent\'s application number', patents_dropdown)
+    submit = form.form_submit_button("Submit")
     
-    # Display prediction
-    st.write(pred)
+    if submit:
+        input = dataset.filter(lambda e: e['application_number'] == input_application)
+        
+        label, prob = predict(model_abstract, model_claims, tokenizer_abstract, tokenizer_claims, input)
+        
+        st.write(label)
+        st.write(predict)
+        st.write(input['decision'])
+    

requirements.txt

@@ -1,3 +1,4 @@
 streamlit
 transformers
-torch
+torch
+datasets