We what to extract the most meaningful / significant words from a text using a Python script, and to calculate the Lix value of the text. (see: [url removed, login to view]).
The text is in a pure text that format that is currently saved in a table in a MySQL Db. There is about 350 text pieces in the Db. The text is in Danish, but could in the future be in any language, and the solution should be open for any language.
The job is to create a scrip in Python that reads the texts pieces in the current DB, and then saves the most significant 4 words from each text piece and the Lix value of the text into a new database, using the existing databases page id as a reference.
There must be a management function in the script that allow us to rerun the script on an ongoing basis to ensure updated values, as the content of the source db changes.
24 freelancere byder i gennemsnit €160 på dette job
Hello, I have been work with natural language for over 18 months. I have experience from machine learning projects in finance, news and sports. I have worked with sql numerous times. Regards, Steven