genomic_distribution_cor.py 文件源码

def scatterCorr(arrayA, arrayB, threshold, outPath):
    """

        Interpretation of strength of correlation

        very weak: < 0,15 
        weak: 0,15-0,25  
        moderate: 0,25-0,40 
        strong: 0,40-0,75
        very strong: >0,75

    """
    corr = stats.spearmanr(arrayA, arrayB)
    coefficient = float(format(corr[0], '.3f'))
    pvalue = float(corr[1])
    print "pvalue: ", pvalue

    ## Make scatterplot if rho >= threshold or <= -theshold
    if (coefficient >= threshold) or (coefficient <= -threshold):

        # Make scatterplot
        fig = plt.figure(figsize=(6,6))
        ax1 = fig.add_subplot(1, 1, 1)
        #plot = sns.jointplot(x=arrayA, y=arrayB, kind="hex", xlim=(0,40), gridsize=50, dropna=True, cmap="Blues", stat_func=spearmanr)
        plot = sns.jointplot(x=arrayA, y=arrayB, kind="kde", space=0, xlim=(0,30), gridsize=50, dropna=True, cmap="Blues", stat_func=spearmanr)
        plt.xlabel('# L1', fontsize=12)
        plt.ylabel('Replication time', fontsize=12)

#        sns.plt.subplots_adjust(left=0.2, right=0.8, top=0.8, bottom=0.2)  # shrink fig so cbar is visible
#        cax = plot.fig.add_axes([.85, .25, .05, .4])  # x, y, width, height
#        sns.plt.colorbar(cax=cax)

        #sns.jointplot(x=arrayA, y=arrayB, kind="kde", space=0, color="b", xlim=(0,30))



        ## Save figure
        fileName = outPath + '_' + str(coefficient) + '_correlation.pdf' 

        plt.savefig(fileName)

    return coefficient, pvalue


#### MAIN ####

## Import modules ##