just trying out a gist

Density estimation with Gaussian Kernel with the scikit-learn API (draft)

from scipy import stats

class GaussianKernelDensityEstimation(object):
    """docstring for GaussianKernelDensityEstimation"""
    def __init__(self):
        self.gkde = None

    def fit(self, X):
        """docstring for fit"""
        self.gkde = stats.gaussian_kde(X.T)
        return self

    def predict(self, X):
        return self.gkde.evaluate(X.T)

if __name__ == '__main__':
    #I'm just adding some comments to see how gist work
    import numpy as np

    # Create some dummy data
    X = np.random.randn(400,2)
    X[200:,:] += 3.5

    # Regular grid to evaluate kde upon
    n_grid_points = 128
    xmin, ymin = X.min(axis=0)
    xmax, ymax = X.max(axis=0)
    xx = np.linspace(xmin - 0.5, xmax + 0.5, n_grid_points)
    yy = np.linspace(ymin - 0.5, ymax + 0.5, n_grid_points)

    xg, yg = np.meshgrid(xx, yy)
    grid_coords = np.c_[xg.ravel(), yg.ravel()]

    # Compute density estimation
    kde = GaussianKernelDensityEstimation()
    kde.fit(X) # Fit
    zz = kde.predict(grid_coords) # Evaluate density on grid points

    zz = zz.reshape(*xg.shape)

    import matplotlib.pylab as pl
    pl.close('all')
    pl.set_cmap(pl.cm.Paired)
    pl.figure()
    pl.contourf(xx, yy, zz, label='density')
    pl.scatter(X[:,0], X[:,1], color='k', label='samples')
    pl.axis('tight')
    pl.legend()
    pl.title('Kernel Density Estimation')
    pl.show()