Update quick_ref.txt

quick_ref.txt

@@ -0,0 +1,95 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from datasets import load_dataset
+import pandas as pd
+
+
+# finetuned model
+language_model_path = "juliaannjose/finetuned_model"
+
+# load the dataset to
+# use the patent number, abstract and claim columns for UI
+with st.spinner("Loading..."):
+    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",
+    )
+    df_train = pd.DataFrame(dataset_dict["train"])
+    df_val = pd.DataFrame(dataset_dict["validation"])
+    df = pd.concat([df_train, df_val], ignore_index=True)
+
+
+# drop down menu with patent numbers
+_patent_id = st.selectbox(
+    "Select the Patent Number",
+    options=df["patent_number"],
+)
+
+
+# display abstract and claim
+def get_abs_claim(_pid):
+    # get abstract and claim corresponding to this patent id
+    _abs = df.loc[df["patent_number"] == _pid]["abstract"]
+    _cl = df.loc[df["patent_number"] == _pid]["claims"]
+    return _abs.values[0], _cl.values[0]
+
+
+_abstract, _claim = get_abs_claim(_patent_id)
+st.title("Abstract:")  # display abstract
+st.write(_abstract)
+st.title("Claim:")  # display claims
+st.write(_claim)
+
+
+# model and tokenizer initialization
+@st.cache_resource
+def load_model(language_model_path):
+    tokenizer = AutoTokenizer.from_pretrained(language_model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(language_model_path)
+    return tokenizer, model
+
+
+tokenizer, model = load_model(language_model_path)
+# input to our model
+input_text = _abstract + _claim
+# get tokens
+inputs = tokenizer(
+    input_text,
+    truncation=True,
+    padding=True,
+    return_tensors="pt",
+)
+
+# get predictions
+id2label = {0: "REJECTED", 1: "ACCEPTED"}
+# when submit button clicked, run the model and get result
+if st.button("Submit"):
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probability = torch.nn.functional.softmax(outputs.logits, dim=1)
+
+    predicted_class_id = probability.argmax().item()
+    pred_label = id2label[predicted_class_id]
+    st.title("Predicted Patentability")
+    if probability[0][0] > probability[0][1]:
+        st.write("Rejection Score:")
+        st.write(probability[0][0].item())
+    else:
+        st.write("Acceptance Score:")
+        st.write(probability[0][1].item())
+    st.write("Result:", pred_label)
+
+
+
+
+
+-----------------------------------------------------------
+
+