Create temp1.py

mylab/temp1.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from datasets import load_dataset
+import pandas as pd
+
+# Model selection: Use a fine-tuned model for patent classification
+model_name = "juliaannjose/finetuned_model"
+
+@st.cache_resource
+def load_model(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
+    return tokenizer, model
+
+tokenizer, model = load_model(model_name)
+
+# Load dataset with training and validation data for more comprehensive analysis
+with st.spinner("Loading patent dataset..."):
+    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="2016-01-31",
+        val_filing_start_date="2017-01-22",
+        val_filing_end_date="2017-01-31",
+    )
+    df_train = pd.DataFrame(dataset_dict["train"])
+    df_val = pd.DataFrame(dataset_dict["validation"])
+    df = pd.concat([df_train, df_val], ignore_index=True)
+
+# Clean and structure the DataFrame
+df = df[["patent_number", "decision", "abstract", "claims", "filing_date"]]
+PAN = df["patent_number"].drop_duplicates()
+
+# Streamlit UI
+st.title("Harvard USPTO Patentability Predictor")
+
+with st.form("patent-form"):
+    make_choice = st.selectbox("Select the Patent Application Number:", PAN)
+    submitted = st.form_submit_button(label="Submit")
+
+    if submitted:
+        abstract = df["abstract"].loc[df["patent_number"] == make_choice].values[0]
+        claims = df["claims"].loc[df["patent_number"] == make_choice].values[0]
+        decision = df["decision"].loc[df["patent_number"] == make_choice].values[0]
+
+        st.subheader(":blue[Patent Abstract]")
+        st.info(abstract)
+        st.subheader(":blue[Patent Claims]")
+        st.info(claims)
+
+        # Combine abstract and claims for a comprehensive prediction
+        input_text = abstract + " " + claims
+        inputs = tokenizer(input_text, truncation=True, padding=True, return_tensors="pt")
+
+        with torch.no_grad():
+            outputs = model(**inputs)
+            probabilities = torch.nn.functional.softmax(outputs.logits, dim=1)
+
+        id2label = {0: "REJECTED", 1: "ACCEPTED"}
+        predicted_class_id = probabilities.argmax().item()
+        pred_label = id2label[predicted_class_id]
+
+        st.subheader(":green[Prediction Result]")
+        if pred_label == "ACCEPTED":
+            st.success(f"The patent is likely to be **ACCEPTED** with a score of {probabilities[0][1].item():.2f}.")
+        else:
+            st.error(f"The patent is likely to be **REJECTED** with a score of {probabilities[0][0].item():.2f}.")
+
+        st.write(f"**Decision Summary:** {decision}")