dsutils.py 文件源码

def plot_correlation(X, Y, title, corr=None):
    if corr == None:
        corr, _ = stats.pearsonr(X, Y)
    # extract 90-th percentile
    thresh = np.percentile(Y, 99)
    X90 = X[X > thresh]
    Y90 = Y[X > thresh]
    sample = np.random.choice(X90.shape[0], size=100, replace=False)
    Xsample = X90[sample]
    Ysample = Y90[sample]
    plt.scatter(Xsample, Ysample, color="red")
    plt.xlim([np.min(Xsample), np.max(Xsample)])
    plt.ylim([np.min(Ysample), np.max(Ysample)])
    plt.title("{:s} (corr: {:.3f})".format(title, corr))
    plt.xlabel("X")
    plt.ylabel("Y")