Log message:
math/py-scikit-learn: Update to 0.19.1

Notable new features since 0.18.2:
- `neighbors.LocalOutlierFactor` for anomaly detection
- `preprocessing.QuantileTransformer` for robust feature transformation
- `multioutput.ClassifierChain` meta-estimator to simply account
  for dependencies between classes in multilabel problem
- multiplicative update in `decomposition.NMF`
- multinomial `linear_model.LogisticRegression` with L1 loss

Log message:
math/py-scikit-learn: Update to 0.18.2

Changes:
- Fixes for compatibility with NumPy 1.13.0
- Minor compatibility changes in the examples

Log message:
Import py-scikit-learn-0.18.1 from pkgsrc as math/py-scikit-learn

Packaged by Filip Hajny and updated by Kamel Derouiche and me.

scikit-learn is a Python module integrating classic machine learning
algorithms in the tightly-knit scientific Python world (numpy, scipy,
matplotlib). It aims to provide simple and efficient solutions to
learning problems, accessible to everybody and reusable in various
contexts: machine-learning as a versatile tool for science and
engineering.