class sklearn.kernel_approximation.Nystroem(kernel='rbf', gamma=None, coef0=1, degree=3, kernel_params=None, n_components=100, random_state=None) [source] Approximate a kernel map using a subset of the training data. Constructs an approximate feature map for an arbitrary kernel using a subset of the data as basis. Read more in the User Guide. Parameters: kernel : string or callable, default=?rbf? Kernel map to be approximated. A callable should accept two arguments and the keyword argumen

class sklearn.kernel_approximation.AdditiveChi2Sampler(sample_steps=2, sample_interval=None) [source] Approximate feature map for additive chi2 kernel. Uses sampling the fourier transform of the kernel characteristic at regular intervals. Since the kernel that is to be approximated is additive, the components of the input vectors can be treated separately. Each entry in the original space is transformed into 2*sample_steps+1 features, where sample_steps is a parameter of the method. Typical

This example shows that Kernel PCA is able to find a projection of the data that makes data linearly separable. print(__doc__) # Authors: Mathieu Blondel # Andreas Mueller # License: BSD 3 clause import numpy as np import matplotlib.pyplot as plt from sklearn.decomposition import PCA, KernelPCA from sklearn.datasets import make_circles np.random.seed(0) X, y = make_circles(n_samples=400, factor=.3, noise=.05) kpca = KernelPCA(kernel="rbf", fit_inverse_transform=True, gamma=1

This example shows how kernel density estimation (KDE), a powerful non-parametric density estimation technique, can be used to learn a generative model for a dataset. With this generative model in place, new samples can be drawn. These new samples reflect the underlying model of the data. Out: best bandwidth: 3.79269019073 import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import load_digits from sklearn.neighbors import KernelDensity from sklearn.decomposition imp

The plots display firstly what a K-means algorithm would yield using three clusters. It is then shown what the effect of a bad initialization is on the classification process: By setting n_init to only 1 (default is 10), the amount of times that the algorithm will be run with different centroid seeds is reduced. The next plot displays what using eight clusters would deliver and finally the ground truth. print(__doc__) # Code source: Ga Varoquaux # Modified for documentation by Jaqu

This shows an example of a neighbors-based query (in particular a kernel density estimate) on geospatial data, using a Ball Tree built upon the Haversine distance metric ? i.e. distances over points in latitude/longitude. The dataset is provided by Phillips et. al. (2006). If available, the example uses basemap to plot the coast lines and national boundaries of South America. This example does not perform any learning over the data (see Species distribution modeling for an example of classific

The multi-task lasso allows to fit multiple regression problems jointly enforcing the selected features to be the same across tasks. This example simulates sequential measurements, each task is a time instant, and the relevant features vary in amplitude over time while being the same. The multi-task lasso imposes that features that are selected at one time point are select for all time point. This makes feature selection by the Lasso more stable. print(__doc__) # Author: Alexandre Gramfort &l

class sklearn.isotonic.IsotonicRegression(y_min=None, y_max=None, increasing=True, out_of_bounds='nan') [source] Isotonic regression model. The isotonic regression optimization problem is defined by: min sum w_i (y[i] - y_[i]) ** 2 subject to y_[i] <= y_[j] whenever X[i] <= X[j] and min(y_) = y_min, max(y_) = y_max where: y[i] are inputs (real numbers) y_[i] are fitted X specifies the order. If X is non-decreasing then y_ is non-decreasing. w[i] are optional strictly positive w

An illustration of the isotonic regression on generated data. The isotonic regression finds a non-decreasing approximation of a function while minimizing the mean squared error on the training data. The benefit of such a model is that it does not assume any form for the target function such as linearity. For comparison a linear regression is also presented. print(__doc__) # Author: Nelle Varoquaux <nelle.varoquaux@gmail.com> # Alexandre Gramfort <alexandre.gramfort@inria.fr&g

An example using IsolationForest for anomaly detection. The IsolationForest ?isolates? observations by randomly selecting a feature and then randomly selecting a split value between the maximum and minimum values of the selected feature. Since recursive partitioning can be represented by a tree structure, the number of splittings required to isolate a sample is equivalent to the path length from the root node to the terminating node. This path length, averaged over a forest of such random tree