Function fda

ot/dr.py:82–138

r"""Fisher Discriminant Analysis Parameters ---------- X : ndarray, shape (n, d) Training samples. y : ndarray, shape (n,) Labels for training samples. p : int, optional Size of dimensionality reduction. reg : float, optional Regularization te

(X, y, p=2, reg=1e-16)

def fda(X, y, p=2, reg=1e-16):
    r"""Fisher Discriminant Analysis

    Parameters
    ----------
    X : ndarray, shape (n, d)
        Training samples.
    y : ndarray, shape (n,)
        Labels for training samples.
    p : int, optional
        Size of dimensionality reduction.
    reg : float, optional
        Regularization term >0 (ridge regularization)

    Returns
    -------
    P : ndarray, shape (d, p)
        Optimal transportation matrix for the given parameters
    proj : callable
        projection function including mean centering
    """

    mx = np.mean(X)
    X -= mx.reshape((1, -1))

    # data split between classes
    d = X.shape[1]
    xc = split_classes(X, y)
    nc = len(xc)

    p = min(nc - 1, p)

    Cw = 0
    for x in xc:
        Cw += np.cov(x, rowvar=False)
    Cw /= nc

    mxc = np.zeros((d, nc))

    for i in range(nc):
        mxc[:, i] = np.mean(xc[i])

    mx0 = np.mean(mxc, 1)
    Cb = 0
    for i in range(nc):
        Cb += (mxc[:, i] - mx0).reshape((-1, 1)) * (mxc[:, i] - mx0).reshape((1, -1))

    w, V = linalg.eig(Cb, Cw + reg * np.eye(d))

    idx = np.argsort(w.real)

    Popt = V[:, idx[-p:]]

    def proj(X):
        return (X - mx.reshape((1, -1))).dot(Popt)

    return Popt, proj