Jupyter Notebook exploring the 2017 survey dataset - https://www.kaggle.com/kaggle/kaggle-survey-2017
Placeholder for few questions:
- keeping errs and having execute all
- column dependancy (asking how useful was a given tool after asking if the tool was used)
- since ther is no demand for prediction - just exploration - how to end that?
- If I have shown the main problems with the data, do I need to process the entire set?
- Как да излъжа Markdown да задраска код снипет (via ~~)?
- rewrite the encoder to use CountVectorizer()