Using the GraphLasso estimator to learn a covariance and sparse precision from a small number of samples. To estimate a probabilistic model (e.g

Learning the parameters of a prediction function and testing it on the same data is a methodological mistake: a model that would just repeat

class sklearn.cluster.MeanShift(bandwidth=None, seeds=None, bin_seeding=False, min_bin_freq=1, cluster_all=True, n_jobs=1)

The PCA does an unsupervised dimensionality reduction, while the logistic regression does the prediction. We use a GridSearchCV to

class sklearn.feature_selection.SelectKBest(score_func=, k=10)

Hyper-parameters are parameters that are not directly learnt within estimators. In scikit-learn they are passed as arguments to the constructor of

sklearn.datasets.fetch_lfw_people(data_home=None, funneled=True, resize=0.5, min_faces_per_person=0, color=False, slice_=(slice(70

This example uses a large dataset of faces to learn a set of 20 x 20 images patches that constitute faces. From the programming standpoint

sklearn.ensemble.partial_dependence.plot_partial_dependence(gbrt, X, features, feature_names=None, label=None

sklearn.metrics.calinski_harabaz_score(X, labels)