Add Streamlit app for patentability score prediction

app.py

@@ -0,0 +1,49 @@
+# app.py
+
+import streamlit as st
+import pandas as pd
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_path = "rb757/new_app"
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+
+# Load the dataset
+dataset_url = "https://huggingface.co/datasets/HUPD/hupd/resolve/main/hupd_metadata_2022-02-22.feather"
+df = pd.read_feather(dataset_url)
+
+# Title and description
+st.title("Milestone Patent 🐨")
+st.write("Select a patent application to evaluate its patentability.")
+
+# Dropdown for application filing numbers
+application_numbers = df['application_number'].unique()
+selected_application = st.selectbox("Select Application Filing Number", application_numbers)
+
+# Retrieve abstract and claims
+if selected_application:
+    patent_info = df[df['application_number'] == selected_application].iloc[0]
+    abstract = patent_info['abstract']
+    claims = patent_info['claims']
+
+    # Display the abstract and claims
+    st.text_area("Abstract", abstract, height=150)
+    st.text_area("Claims", claims, height=150)
+
+    # Submit button
+    if st.button("Get Patentability Score"):
+        # Prepare the input text
+        input_text = f"{abstract} {claims}"
+        inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True)
+
+        # Get the model prediction
+        with torch.no_grad():
+            logits = model(**inputs).logits
+            predictions = torch.argmax(logits, dim=-1)
+
+        # Display the patentability score
+        decision_labels = ['REJECTED', 'ACCEPTED', 'PENDING', 'CONT-REJECTED', 'CONT-ACCEPTED', 'CONT-PENDING']
+        score = decision_labels[predictions.item()]
+        st.write(f"Patentability Score: **{score}**")