patent classifier code

app.py

@@ -0,0 +1,41 @@
+import streamlit as st
+from transformers import pipeline
+from datasets import load_dataset, Dataset, DatasetDict
+
+# load the dataset and
+# use the patent number, abstract and claim columns for UI
+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",
+)
+
+# widget for selecting our finetuned langugae model
+language_model_path = "juliaannjose/finetuned_model"
+
+# pass the model to transformers pipeline - model selection component.
+classifier_model = pipeline(model=language_model_path)
+
+# drop down menu with patent numbers
+_patent_id = st.selectbox(
+    "Select the Patent Number",
+    dataset_dict["train"]["patent_number"],
+)
+
+# get abstract and claim corresponding to this patent id
+_abstract = dataset_dict["train"][["patent_number"] == _patent_id]["abstract"]
+_claim = dataset_dict["train"][["patent_number"] == _patent_id]["claim"]
+
+# display abstract and claim
+st.write(_abstract)
+st.write(_claim)
+
+# when submit button clicked, run the model and get result
+if st.button("Submit"):
+    results = classifier_model([_abstract + _claim])
+    st.write(results)