A tool to retrieve filings from the SEC based on a specified identifier (tikcer, cik), form (10k, 20f, etc.), year, amendment, etc.
I also provide basic functionality for word frequency analysis from a given dictionary, including options for removing stop words and stemming.
The implementation has been optimized with multithreading to enhance retrieval speed.
It can skip existing files.
The code is encrypted for personal use; please reach out for collaboration or academic inquiries.
- Retrieve Filings: Access and download filings based on a specified conditions.
- Word Frequency Analysis: Analyze the frequency of terms from a provided dictionary within the filings.
- Stop Words Removal: Filter out common stop words to focus on significant terms.
- Stemming: Reduce words to their root form for accurate frequency counts.
- Multithreading: Optimize retrieval speed using concurrent processing.
The code is intended for personal use only and has been encrypted. If you have academic needs or wish to discuss further, feel free to reach out for collaboration and exchange of ideas.
Last Updated: November 18, 2024