Add classification and regression metrics

[msluszniak]

I want to add all the existing metrics which are present in Sci-kit Learn.

Classification Metrics

• [x] Accuracy
• [x] AUC
• [x] Average Precision (AP)
• [x] Balanced Accuracy
• [x] Brier Score Loss
• [x] Cohen Kappa Score
• [x] Confusion Matrix
• [x] Discounted Cumulative Gain (DCG)
• [ ] Detection Error Tradeoff Curve (DET curve)
• [x] F1 Score
• [x] F-beta Score
• [x] Hamming Loss
• [x] Log Loss
• [x] Matthews correlation coefficient (MCC)
• [x] Normalized Discounted Cumulative Gain (Normalized DCG)
• [x] Precision Recall Curve
• [x] Precision Recall Fscore Support
• [x] Precision
• [x] Recall
• [x] ROC-AUC
• [x] ROC Curve
• [x] Top-k Accuracy Score
• [x] Zero-one Classification Loss

Regression Metrics

• [x] Explained Variance Score
• [x] Maximum Residual Error
• [x] Mean Absolute Error (MAE)
• [x] Mean Squared Error (MSE)
• [x] Mean Squared Log Error
• [x] Mean Absolute Percentage Error (MAPE)
• [x] $R^2$ Score
• [x] Mean Poisson deviance
• [x] Mean Gamma deviance
• [x] Mean Tweedie deviance
• [x] $D^2$ - Fraction of Tweedie Deviance Explained
• [x] Mean Pinball Loss
• [ ] $D^2$ - Fraction of Pinball Loss Explained
• [ ] $D^2$ - Fraction of Absolute Error Explained

We can do the same for distances after (look #149).