# Numerical data: Programming exercises

Take some time to complete the following exercises to practice what you've
learned in
[First steps with numerical data](https://developers.google.com/machine-learning/crash-course/numerical-data/first-steps).

- **Get statistics on a dataset** , which shows you how to find columns containing blatant outliers: [<button>Open math statistics exercise</button>](https://colab.research.google.com/github/google/eng-edu/blob/main/ml/cc/exercises/numerical_data_stats.ipynb?utm_source=mlcc&utm_campaign=colab-external&utm_medium=referral&utm_content=numerical_data_stats)
- **Find the bad part of the dataset** , which guides you through visual and mathematical ways to find hidden *bad* values in a dataset: [<button>Open "bad part" dataset exercise</button>](https://colab.research.google.com/github/google/eng-edu/blob/main/ml/cc/exercises/numerical_data_bad_values.ipynb?utm_source=mlcc&utm_campaign=colab-external&utm_medium=referral&utm_content=numerical_data_bad_values)

Programming exercises run directly in your browser (no setup
required!) using the [Colaboratory](https://colab.research.google.com)
platform. Colaboratory is supported on most major browsers, and is most
thoroughly tested on desktop versions of Chrome and Firefox.
[Help Center](https://support.google.com/machinelearningeducation)