Python scipy.stats 模块，wilcoxon() 实例源码

def significance(metric):
    if not args.significance:
        return {}

    desc, rank = sorted(results.items(), key=lambda item: item[1][metric], reverse=True), 1

    ranks = {}

    for (path1, results1), (path2, results2) in pairwise(desc):
        x, y = list(results1['scores'][metric]), list(results2['scores'][metric])

        ranks[path1] = rank

        rank += int(wilcoxon(x, y).pvalue < args.alpha)

        ranks[path2] = rank

    return ranks

def significance(metric):
    if not args.significance:
        return {}

    desc, rank = sorted(results.items(), key=lambda item: item[1][metric], reverse=True), 1

    ranks = {}

    for (path1, results1), (path2, results2) in pairwise(desc):
        x, y = list(results1['scores'][metric]), list(results2['scores'][metric])

        ranks[path1] = rank

        rank += int(wilcoxon(x, y).pvalue < args.alpha)

        ranks[path2] = rank

    return ranks

def score_event(nx, ny, ncommon, barcode_frequencies, resamples=100):
    """
    perform a resampling test, based on the number of fragments in each region
    and the barcode frequency distribution (the latter because some barcodes
    have more DNA in them than others)
    """

    samples = []
    for _ in range(resamples):
        s1 = numpy.random.choice(len(barcode_frequencies), nx, replace=False, p=barcode_frequencies)
        s2 = numpy.random.choice(len(barcode_frequencies), ny, replace=False, p=barcode_frequencies)
        common = len(set(s1).intersection(set(s2)))
        samples.append(common)

    # make a one-sided one-sample Wilcoxon test
    statistic, pvalue = stats.wilcoxon(numpy.array(samples)-ncommon)
    if numpy.mean(samples) > ncommon:
        pvalue = 1 - pvalue/2.0
    else:
        pvalue = pvalue/2.0

    # result = r["wilcox.test"](samples, mu=ncommon, alternative="less")
    # pvalue2 = result.rx2("p.value")[0]

    # print "::::::", nx, ny, ncommon, (numpy.array(samples)>ncommon).sum(), pvalue, pvalue2
    return pvalue

def _evalstat(x, bsl, meth, n_perm, metric, maxstat, tail):
    """Statistical evaluation of features

    [x] = [xn] = (nFce, npts, nTrials)
    [bsl] = (nFce, nTrials)
    """
    # Get shape of xF :
    nf, npts, nt = x.shape
    pvalues = np.ones((nf, npts))

    # Permutations :
    if meth == 'permutation':
        perm = perm_swaparray(a, b, n_perm=200, axis=-1, rndstate=0)
        from brainpipe.xPOO.stats import permutation
        # Pre-define permutations :
        pObj = permutation(n_perm)
        perm = np.zeros((n_perm, nf, npts))
        # For each permutation :
        for p in range(n_perm):
            # Get 1D iterations :
            ite = product(range(nf), range(npts))
            permT = np.random.permutation(2*nt)
            for f, pts in ite:
                bs, xs = bsl[f, :], x[f, pts, :]
                # Reshape data :
                subX = np.vstack((bsl[f, :], x[f, pts, :])).reshape(2*nt,)
                # Shuffle data :
                subX = subX[permT].reshape(nt, 2)
                # Normalize data :
                subX = normalize(subX[:, 0], subX[:, 1], norm=norm)
                # Get mean of data :
                perm[p, f, pts] = np.mean(subX)
        # Get final pvalues :
        pvalues = pObj.perm2p(np.mean(xn, 2), perm, tail=tail,
                              maxstat=maxstat)

    # Wilcoxon test :
    elif meth == 'wilcoxon':
        from scipy.stats import wilcoxon
        # Get iterations :
        ite = product(range(nf), range(npts))
        # Compute wilcoxon :
        for k, i in ite:
            _, pvalues[k, i] = wilcoxon(x[k, i, :], bsl[k, :])

    # Kruskal-Wallis :
    elif meth == 'kruskal':
        from scipy.stats import kruskal
        # Get iterations :
        ite = product(range(nf), range(npts))
        # Compute Kruskal-Wallis :
        for k, i in ite:
            _, pvalues[k, i] = kruskal(x[k, i, :], bsl[k, :])

    return pvalues