preprocess_data.py 文件源码

def fixnans(Xin, method='spline'):
    def fixrow(rowin, methodloc='spline'):
        rowout = np.array(rowin)

        unknown = isnan(rowin)
        known = [not xx for xx in unknown]

        tknown = np.nonzero(known)[0]
        tunknown = np.nonzero(unknown)[0]

        xknown = np.take(rowin, tknown)

        if methodloc == 'spline':
            if len(xknown) > 3:
                sf = spinter.UnivariateSpline(tknown, xknown)
            else:
                sf = spinter.UnivariateSpline(tknown, xknown, k=len(xknown)-1)
            rowout[tunknown] = sf(tunknown)
        else:
            raise ValueError('Provided interpolation method is not supported')

        return rowout

    Xinloc = deepcopy(Xin)
    N = np.size(Xinloc, 0)
    M = np.size(Xinloc, 1)
    Xout = np.zeros([N, M])

    with warnings.catch_warnings():
        warnings.simplefilter('ignore')
        for i in range(N):
            sumnans = sum(isnan(Xinloc[i]))
            notnans = [x for x in Xinloc[i] if not isnan(x)]
            if sumnans < M - 1:
                if math.isnan(Xinloc[i, 0]):
                    Xinloc[i, 0] = notnans[0]
                if math.isnan(Xinloc[i, -1]):
                    Xinloc[i, -1] = notnans[-1]
                Xout[i] = fixrow(Xinloc[i], method)
            elif sumnans == M - 1:
                Xout[i] = [notnans[0] for x in range(M)]
    return Xout