Initial Code setup

[NISH1001]

This iteration consists of a few modules and scripts, notably:

• data standardization process (preprocessing)
• clustering and feature selection (clustering/feature_selection)
• data merging of gene + phenotype CSV (preprocessing)
• scripts/ directory consists of usages of available modules (bps_numerical)

TODO

• notebooks
• model training and feature importance computation
• standardize pipeline for seamless processing

cc: @xhagrg

[NISH1001]

@xhagrg can I merge now?

[xhagrg]

Fix the lint errors and we are golden.

[NISH1001]

Fix the lint errors and we are golden.

The lining error is a bit weird as I am manually adding bps_numerical library to the external scripts at scripts/. So, before importing anything else, I have to do sys.path.append(...) (for time being, until we create a setup.py based installation)

For instance, the following code could remove the lining error "Module level import not at top of file (E402)", but the script will throw an error as we can't import the bps_numerical module beforehand:

import os
import sys
import time

import click
from bps_numerical.preprocessing import merge_gene_phenotype, standardize_gene_data
from loguru import logger

sys.path.append("./")
sys.path.append("../code/")
sys.path.append("./code/")

To resolve this, we could create setup.py (which I am thinking in the next release). Or perhaps PYTHONPATH works?

Edit:

PYTHONPATH worked