src/patent_train.py

from datasets import load_dataset
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Import data for specifically January 2016
dataset_dict = load_dataset(
    'HUPD/hupd',
    name='Jan2016 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',
)

print(dataset_dict)

"""
data_fields = {
    "application_number": "...",
    "publication_number": "...",
    "title": "...",
    "decision": "...",
    "date_produced": "...",
    "date_published": "...",
    "main_cpc_label": "...",
    "cpc_labels": ["...", "...", "..."],
    "main_ipcr_label": "...",
    "ipcr_labels": ["...", "...", "..."],
    "patent_number": "...",
    "filing_date": "...",
    "patent_issue_date": "...",
    "abandon_date": "...",
    "uspc_class": "...",
    "uspc_subclass": "...",
    "examiner_id": "...",
    "examiner_name_last": "...",
    "examiner_name_first": "...",
    "examiner_name_middle": "...",
    "inventor_list": [
        {
            "inventor_name_last": "...",
            "inventor_name_first": "...",
            "inventor_city": "...",
            "inventor_state": "...",
            "inventor_country": "..."
        }
    ],
    "abstract": "...",
    "claims": "...",
    "background": "...",
    "summary": "...",
    "full_description": "..."
}
"""