# 23rd private (1437th public, 4 submissions total) - regular expressions

1) I look for any word from this list ['Survey', 'Data', 'Study', 'Database', 'Statistics'] in text.
2) Then I look 5 words backward and forward for words starting from upper case letter.
3) From all sequences I choose only sequences with more than 2 words
4) Then I add found labels from train dataset.
Link:
[https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0](https://www.kaggle.com/ilyenkov/coleridgeinitiative-show-us-the-data-v0)