Finish report

[carrascomj]

Christmas is coming and the deadline is looming! Please tell others if you are working on one of the tasks and edit this issue as you please.

Urgent and doable right now

• Introduction (in Overleaf).
• Methods.
• Draft of Abstract.
• Pre-processing exploitation.
• Pre-processing explain: add information in the input pd.DataFrame about the
  functions of each gene so we can find explanations later.
• Post-processing gathering (put all the functions together).
• Table of results/performance/confusion matrix (try stuff and annotate
  results).

Urgent but blocked

• Results.
• Discussion.
• Conclusion (I am keen on separating all the sections, but these three
  may be combined if needed).
• Finish Abstract.
• Analysis of difficult cases.

Not urgent but doable

• Convnet: Try one hot encoding instead of index input (4 input channels)
• Convnet: analysis of activations.
• CBOW: tSNE/PCA.
• Proper handling of UNK characters (N, S, etc.), just remove them and break
  the window at this point.

Proposed in feedback

• Add more conv layers with different kernel size.
• Explore CBOW k.
• There were more things but I don't remember them, just edit this section if you feel like doing so.

[carrascomj]

Added some classifiers to the gene ranges in the input dataframe (10138d0). Those classifiers are name and product_accession of their corresponding "CDS" region, whose id should allow us to cluster and analyze "difficult cases".

This feature makes the preprocessing workflow slower. To get to the same performance, we would need to change the logic in src/pre-processing/get_labeled_ranges to work with pd.DataFrame instead of numpy arrays.

EDIT: improved a bit with memoization based on sequentiality of overlapping windows.

[carrascomj]

Overlapping windows is now the default for the window_pipeline.

[carrascomj]

All the post-processing was updated as used in the notebooks (commit b5969bc). As an extra, the functions for the calculation of the confussion matrix and the CLI were updated in /src/evaluation and /bin, respectively.