Step by step installation

Assumptions

• Python3.5 on Ubuntu 16.04 machine

🖥️ Installation

🐍 environment

Install requirements in your Python3.5 environment, (preferably create new environment: virtualenv home-credit -p python3.5)

pip3 install -r requirements.txt

🗒️ Code

Clone repository

git clone https://github.com/minerva-ml/open-solution-home-credit.git

Update data directories in the neptune.yaml configuration file, specifically:

project: ORGANIZATION/home-credit   # ORGANIZATION is your user-name.

...

# Data
  train_filepath:                 YOUR/PATH/TO/application_train.csv
  test_filepath:                  YOUR/PATH/TO/application_test.csv
  bureau_balance_filepath:        YOUR/PATH/TO/bureau_balance.csv
  bureau_filepath:                YOUR/PATH/TO/bureau.csv
  credit_card_balance_filepath:   YOUR/PATH/TO/credit_card_balance.csv
  installments_payments_filepath: YOUR/PATH/TO/installments_payments.csv
  POS_CASH_balance_filepath:      YOUR/PATH/TO/POS_CASH_balance.csv
  previous_application_filepath:  YOUR/PATH/TO/previous_application.csv
  sample_submission_filepath:     YOUR/PATH/TO/sample_submission.csv
  experiment_directory:           YOUR/PATH/WORKDIR

🔱 Neptune setup

1. Register to the neptune.ml (if you wish to use it)
2. Go to the neptune.ml, log in and create project Home-Credit-Default-Risk (button at the top left side of the screen).

🔬 Run experiment

Run experiment based on LightGBM:

🔱

neptune login
neptune run --config configs/neptune.yaml main.py train_evaluate_predict_cv --pipeline_name lightGBM

🐍

python main.py -- train_evaluate_predict_cv --pipeline_name lightGBM

Collect submit from experiment_directory specified in the neptune.yaml

Happy training 😃