Performance-Metric without sklearn

This Repository contains scratch implementations of the famous metrics used to evaluate machine learning models.

This Repository is done as hard coding exercise. We usually use sklearn.metrics to evaluate all the models. It is equally important to know the logics behind them and how they perform under different situations. There are many metrics in the module. The ones implemented here are classification metric :

1. Confusion matrix
2. Accuracy
3. Precision
4. F1 Score
5. AUC

Regression metric:
1. Mean squared error
2. Coefficient of determination(R2)
3. Mean absolute percentage error(MAPE)