kde.py 文件源码

def kde(data, N=None, MIN=None, MAX=None):

    # Parameters to set up the mesh on which to calculate
    N = 2**14 if N is None else int(2**sci.ceil(sci.log2(N)))
    if MIN is None or MAX is None:
        minimum = min(data)
        maximum = max(data)
        Range = maximum - minimum
        MIN = minimum - Range/10 if MIN is None else MIN
        MAX = maximum + Range/10 if MAX is None else MAX

    # Range of the data
    R = MAX-MIN

    # Histogram the data to get a crude first approximation of the density
    M = len(data)
    DataHist, bins = sci.histogram(data, bins=N, range=(MIN,MAX))
    DataHist = DataHist/M
    DCTData = scipy.fftpack.dct(DataHist, norm=None)

    I = [iN*iN for iN in xrange(1, N)]
    SqDCTData = (DCTData[1:]/2)**2

    # The fixed point calculation finds the bandwidth = t_star
    guess = 0.1
    try:
        t_star = scipy.optimize.brentq(fixed_point, 0, guess, 
                                       args=(M, I, SqDCTData))
    except ValueError:
        print 'Oops!'
        return None

    # Smooth the DCTransformed data using t_star
    SmDCTData = DCTData*sci.exp(-sci.arange(N)**2*sci.pi**2*t_star/2)
    # Inverse DCT to get density
    density = scipy.fftpack.idct(SmDCTData, norm=None)*N/R
    mesh = [(bins[i]+bins[i+1])/2 for i in xrange(N)]
    bandwidth = sci.sqrt(t_star)*R

    density = density/sci.trapz(density, mesh)
    return bandwidth, mesh, density