- The hardware you used: CPU specs, number of CPU cores, memory, GPU specs, number of GPUs.
Online kaggle environment: 4 CPU cores, 16 Gigabytes of RAM, No GPU.
- OS/platform you used, including version number.
Latest kaggle docker: https://github.com/Kaggle/docker-python
- Any necessary 3rd-party software, including version numbers, and installation steps. This can be provided as a Dockerfile instead of as a section in the readme.
No
-
How to prepare data
Run prepare_data.py
-
How to train your model
Run train.py
-
How to make predictions on a new test set.
Run predict.py
-
Important side effects of your code. For example, if your data processing code overwrites the original data.
On data cleaning code overwrites some outliers.
- Key assumptions made by your code. For example, if the outputs folder must be empty when starting a training run.
No