Modelling and prediction of default + deployment via AWS Sagemaker

Description

The task is to predict the probability of default for the provided dataset where the target values are missing.
Use Python
Deploy model via AWS Sagemaker
Data

Parallel plot of hyper params optimization with optuna: parallel-plot-hyper-params-optuna.html
Deepchecks report (download to view): deepchecks_report.html

Name		Name	Last commit message	Last commit date
Latest commit History 65 Commits
artifacts-selected		artifacts-selected
sagemaker_catboost		sagemaker_catboost
sagemaker_xgboost		sagemaker_xgboost
test		test
.gitignore		.gitignore
README.md		README.md
conda.yml		conda.yml
config.py		config.py
create-venv.sh		create-venv.sh
cv.py		cv.py
etl.py		etl.py
metrics.py		metrics.py
predict.py		predict.py
requirements.txt		requirements.txt
run_pipeline.py		run_pipeline.py
select_feats.py		select_feats.py
solution_report.py		solution_report.py
solution_report_gen_html.sh		solution_report_gen_html.sh
train.py		train.py
try-deepchecks.py		try-deepchecks.py
tune_hyper_params_optuna.py		tune_hyper_params_optuna.py
tune_hyper_params_rand.py		tune_hyper_params_rand.py
utils.py		utils.py