2017.04.10：python数据可视化01

def is_outlier(points, threshold=3.5):
    """
    Returns a boolean array with True if points are outliers and False 
    otherwise.
    
    Data points with a modified z-score greater than this 
    # value will be classified as outliers.
    """
    # transform into vector
    if len(points.shape) == 1:
        points = points[:,None]

    # compute median value
    # axis=0表述列; axis=1,表述行
    median = np.median(points, axis=0)
    
    # compute diff sums along the axis
    diff = np.sum((points - median)**2, axis=-1)
    diff = np.sqrt(diff)
    # compute MAD
    med_abs_deviation = np.median(diff)
    
    # compute modified Z-score
    # http://www.itl.nist.gov/div898/handbook/eda/section4/eda43.htm#Iglewicz
    modified_z_score = 0.6745 * diff / med_abs_deviation

    # return a mask for each outlier
    return modified_z_score > threshold