Hello Human,
Jeremy Howard (of Fast.ai) has recently published a lot of Kaggle Kernels walking through the entire process of gathering the data, cleaning it, implementing a learning algorithm, and submitting an entry (for a Kaggle Competition).
If you're trying to do practical end to end machine learning, these are definitely worth studying. These kernels are linked to this Kaggle Competition - https://www.kaggle.com/c/rsna-intracranial-hemorrhage-detection.
Kaggle Kernels / Notebooks:
https://www.kaggle.com/jhoward/from-prototyping-to-submission-fastai
https://www.kaggle.com/jhoward/cleaning-the-data-for-rapid-prototyping-fastai
https://www.kaggle.com/jhoward/some-dicom-gotchas-to-be-aware-of-fastai
https://www.kaggle.com/jhoward/don-t-see-like-a-radiologist-fastai
Regards,
Abdul Majed