Mateusz1017/company_reports_final

该数据集包含多个特征，如公司标识（cik）、年份（year）、公司名称（company_name）、行业代码（sic_code）、输入ID（input_ids）、股票代码（ticker）、回报率（returns）、月度回报率矩阵（logged_monthly_returns_matrix）等。数据集分为训练集，包含26,000个样本，总大小为2,181,583,406字节，下载大小为710,638,649字节。

The dataset includes multiple features such as cik, year, section_1, company_name, sic_code, input_ids, ticker, returns, logged_monthly_returns_matrix, __index_level_0__, and input_ids_length. These features cover company identifiers, year, company name, industry code, input IDs, stock tickers, return rates, monthly return rate matrices, etc. The dataset is divided into a training set containing 26,000 samples, with a total size of 2,181,583,406 bytes and a download size of 710,638,649 bytes.