Python stats.ttest_ind方法代码示例

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def getDiffGeneTTest(self):
                cut=5e-2
                AE=[item.E for item in self.fromNode.cells]
                BE=[item.E for item in self.toNode.cells]
                G=range(len(AE[0]))
                #pdb.set_trace()
                TT=[]
                for i in G:
                        X=[item[i] for item in AE]
                        Y=[item[i] for item in BE]
                        pxy=ttest_ind(X,Y)[-1]
                        TT.append([pxy,i])
                TT.sort()
                TT=[item for item in TT if item[0]<cut]
                DG=[[self.GL[item[1]],item[0]] for item in TT if self.GL[item[1]]]
                return DG

        #------------------------------------------------------------------- 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_knn(datasets_dimred, genes, labels, idx, distr, xlabels):
    knns = [ 5, 10, 50, 100 ]
    len_distr = len(distr)
    for knn in knns:
        integrated = assemble(datasets_dimred[:], knn=knn, sigma=150)
        X = np.concatenate(integrated)
        distr.append(sil(X[idx, :], labels[idx]))
        for d in distr[:len_distr]:
            print(ttest_ind(np.ravel(X[idx, :]), np.ravel(d)))
        xlabels.append(str(knn))
    print('')
    
    plt.figure()
    plt.boxplot(distr, showmeans=True, whis='range')
    plt.xticks(range(1, len(xlabels) + 1), xlabels)
    plt.ylabel('Silhouette Coefficient')
    plt.ylim((-1, 1))
    plt.savefig('param_sensitivity_{}.svg'.format('knn')) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_sigma(datasets_dimred, genes, labels, idx, distr, xlabels):
    sigmas = [ 10, 50, 100, 200 ]
    len_distr = len(distr)
    for sigma in sigmas:
        integrated = assemble(datasets_dimred[:], sigma=sigma)
        X = np.concatenate(integrated)
        distr.append(sil(X[idx, :], labels[idx]))
        for d in distr[:len_distr]:
            print(ttest_ind(np.ravel(X[idx, :]), np.ravel(d)))
        xlabels.append(str(sigma))
    print('')
    
    plt.figure()
    plt.boxplot(distr, showmeans=True, whis='range')
    plt.xticks(range(1, len(xlabels) + 1), xlabels)
    plt.ylabel('Silhouette Coefficient')
    plt.ylim((-1, 1))
    plt.savefig('param_sensitivity_{}.svg'.format('sigma')) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_alpha(datasets_dimred, genes, labels, idx, distr, xlabels):
    alphas = [ 0, 0.05, 0.20, 0.50 ]
    len_distr = len(distr)
    for alpha in alphas:
        integrated = assemble(datasets_dimred[:], alpha=alpha, sigma=150)
        X = np.concatenate(integrated)
        distr.append(sil(X[idx, :], labels[idx]))
        for d in distr[:len_distr]:
            print(ttest_ind(np.ravel(X[idx, :]), np.ravel(d)))
        xlabels.append(str(alpha))
    print('')
    
    plt.figure()
    plt.boxplot(distr, showmeans=True, whis='range')
    plt.xticks(range(1, len(xlabels) + 1), xlabels)
    plt.ylabel('Silhouette Coefficient')
    plt.ylim((-1, 1))
    plt.savefig('param_sensitivity_{}.svg'.format('alpha')) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_approx(datasets_dimred, genes, labels, idx, distr, xlabels):
    integrated = assemble(datasets_dimred[:], approx=False, sigma=150)
    X = np.concatenate(integrated)
    distr.append(sil(X[idx, :], labels[idx]))
    len_distr = len(distr)
    for d in distr[:len_distr]:
        print(ttest_ind(np.ravel(X[idx, :]), np.ravel(d)))
    xlabels.append('Exact NN')
    print('')
    
    plt.figure()
    plt.boxplot(distr, showmeans=True, whis='range')
    plt.xticks(range(1, len(xlabels) + 1), xlabels)
    plt.ylabel('Silhouette Coefficient')
    plt.ylim((-1, 1))
    plt.savefig('param_sensitivity_{}.svg'.format('approx')) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_perplexity(datasets_dimred, genes, labels, idx,
                    distr, xlabels):
    X = np.concatenate(datasets_dimred)

    perplexities = [ 10, 100, 500, 2000 ]
    len_distr = len(distr)
    for perplexity in perplexities:
        embedding = fit_tsne(X, perplexity=perplexity)
        distr.append(sil(embedding[idx, :], labels[idx]))
        for d in distr[:len_distr]:
            print(ttest_ind(np.ravel(X[idx, :]), np.ravel(d)))
        xlabels.append(str(perplexity))
    print('')
    
    plt.figure()
    plt.boxplot(distr, showmeans=True, whis='range')
    plt.xticks(range(1, len(xlabels) + 1), xlabels)
    plt.ylabel('Silhouette Coefficient')
    plt.ylim((-1, 1))
    plt.savefig('param_sensitivity_{}.svg'.format('perplexity')) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def stat_tests(ref_cors, exp_cors, alternative):
  _, mwp = mannwhitneyu(ref_cors, exp_cors, alternative=alternative)
  tt, tp = ttest_ind(ref_cors, exp_cors)

  if alternative == 'less':
    if tt > 0:
      tp = 1 - (1-tp)/2
    else:
      tp /= 2
  elif alternative == 'greater':
    if tt <= 0:
      tp /= 2
    else:
      tp = 1 - (1-tp)/2

  return mwp, tp

################################################################################
# __main__
################################################################################ 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def tTestVoxelization(group1, group2, signed = False, removeNaN = True, pcutoff = None):
    """t-Test on differences between the individual voxels in group1 and group2, group is a array of voxelizations"""
    
    g1 = self.readDataGroup(group1);  
    g2 = self.readDataGroup(group2);  
    
    tvals, pvals = stats.ttest_ind(g1, g2, axis = 0, equal_var = True);

    #remove nans
    if removeNaN: 
        pi = numpy.isnan(pvals);
        pvals[pi] = 1.0;
        tvals[pi] = 0;

    pvals = self.cutoffPValues(pvals, pcutoff = pcutoff);

    #return
    if signed:
        return pvals, numpy.sign(tvals);
    else:
        return pvals; 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def tTestPointsInRegions(pointCounts1, pointCounts2, labeledImage = lbl.DefaultLabeledImageFile, signed = False, removeNaN = True, pcutoff = None, equal_var = False):
    """t-Test on differences in counts of points in labeled regions"""
    
    #ids, p1 = countPointsGroupInRegions(pointGroup1, labeledImage = labeledImage, withIds = True);
    #p2 = countPointsGroupInRegions(pointGroup2,  labeledImage = labeledImage, withIds = False);   
    
    tvals, pvals = stats.ttest_ind(pointCounts1, pointCounts2, axis = 1, equal_var = equal_var);
    
    #remove nans
    if removeNaN: 
        pi = numpy.isnan(pvals);
        pvals[pi] = 1.0;
        tvals[pi] = 0;

    pvals = self.cutoffPValues(pvals, pcutoff = pcutoff);
    
    #pvals.shape = (1,) + pvals.shape;
    #ids.shape = (1,) + ids.shape;
    #pvals = numpy.concatenate((ids.T, pvals.T), axis = 1);
    
    if signed:
        return pvals, numpy.sign(tvals);
    else:
        return pvals; 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_weightstats_1(self):
        x1, x2 = self.x1, self.x2
        w1, w2 = self.w1, self.w2
        w1_ = 2. * np.ones(len(x1))
        w2_ = 2. * np.ones(len(x2))

        d1 = DescrStatsW(x1)
#        print ttest_ind(x1, x2)
#        print ttest_ind(x1, x2, usevar='unequal')
#        #print ttest_ind(x1, x2, usevar='unequal')
#        print stats.ttest_ind(x1, x2)
#        print ttest_ind(x1, x2, usevar='unequal', alternative='larger')
#        print ttest_ind(x1, x2, usevar='unequal', alternative='smaller')
#        print ttest_ind(x1, x2, usevar='unequal', weights=(w1_, w2_))
#        print stats.ttest_ind(np.r_[x1, x1], np.r_[x2,x2])
        assert_almost_equal(ttest_ind(x1, x2, weights=(w1_, w2_))[:2],
                            stats.ttest_ind(np.r_[x1, x1], np.r_[x2, x2])) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def compare_different_objectivefunctions(like1,like2):
    """
    Performs the Welch’s t-test (aka unequal variances t-test)

    :like1: objectivefunction values
    :type: list

    :like2: Other objectivefunction values
    :type: list

    :return: p Value
    :rtype: list
    """
    from scipy import stats
    out = stats.ttest_ind(like1, like2, equal_var=False)
    print(out)
    if out[1]>0.05:
        print('like1 is NOT signifikant different to like2: p>0.05')
    else:
        print('like1 is signifikant different to like2: p<0.05' )
    return out 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def t_test(covariates, groups):
    """ 
    Two sample t test for the distribution of treatment and control covariates
    
    Parameters
    ----------
    covariates : DataFrame 
        Dataframe with one covariate per column.
        If matches are with replacement, then duplicates should be 
        included as additional rows.
    groups : array-like
        treatment assignments, must be 2 groups
    
    Returns
    -------
    A list of p-values, one for each column in covariates
    """
    colnames = list(covariates.columns)
    J = len(colnames)
    pvalues = np.zeros(J)
    for j in range(J):
        var = covariates[colnames[j]]
        res = ttest_ind(var[groups == 1], var[groups == 0])
        pvalues[j] = res.pvalue
    return pvalues 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def test_ttest_ind_nan_2nd_arg():
    # regression test for gh-6134: nans in the second arg were not handled
    x = [np.nan, 2.0, 3.0, 4.0]
    y = [1.0, 2.0, 1.0, 2.0]

    r1 = stats.ttest_ind(x, y, nan_policy='omit')
    r2 = stats.ttest_ind(y, x, nan_policy='omit')
    assert_allclose(r2.statistic, -r1.statistic, atol=1e-15)
    assert_allclose(r2.pvalue, r1.pvalue, atol=1e-15)

    # NB: arguments are not paired when NaNs are dropped
    r3 = stats.ttest_ind(y, x[1:])
    assert_allclose(r2, r3, atol=1e-15)

    # .. and this is consistent with R. R code:
    # x = c(NA, 2.0, 3.0, 4.0)
    # y = c(1.0, 2.0, 1.0, 2.0)
    # t.test(x, y, var.equal=TRUE)
    assert_allclose(r2, (-2.5354627641855498, 0.052181400457057901), atol=1e-15) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def ttest(df, fields, indep, dep):
    # Ensure single field
    dep_field_name = dep[0]
    indep_field_name = indep[0]
    unique_indep_values = get_unique(df[indep_field_name])

    subsets = {}
    for v in unique_indep_values:
        subsets[v] = np.array(df[df[indep_field_name] == v][dep_field_name])

    result = {}
    for (x, y) in combinations(unique_indep_values, 2):
        (statistic, pvalue) = ttest_ind(subsets[x], subsets[y])
        result[str([x, y])] = {
            'statistic': statistic,
            'pvalue': pvalue
        }

    return result



##################
#Functions to determine which tests could be run
################## 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import ttest_ind [as 别名]
def tellDifference(nodeCells,nodePCells,geneIndex,fcut=0.6):
	if len(nodePCells)==0:
		return [0,1,0]
	X=[item.E[geneIndex] for item in nodeCells]
	Y=[item.E[geneIndex] for item in nodePCells]
	fc=sum(X)/len(X)-sum(Y)/len(Y)
	pv=ttest_ind(X,Y)[1]
	
	pcut=0.05
	if pv<pcut and fc>fcut:
		return [1,pv,fc]
	if pv<pcut and fc<-1*fcut:
		return [-1,pv,fc]	
	return [0,pv,fc]
#-----------------------------------------------------------------------------
# filter X