stats.py 文件源码

def amedian (inarray,numbins=1000):
    """
    Calculates the COMPUTED median value of an array of numbers, given the
    number of bins to use for the histogram (more bins approaches finding the
    precise median value of the array; default number of bins = 1000).  From
    G.W. Heiman's Basic Stats, or CRC Probability & Statistics.
    NOTE:  THIS ROUTINE ALWAYS uses the entire passed array (flattens it first).

    Usage:   amedian(inarray,numbins=1000)
    Returns: median calculated over ALL values in inarray
    """
    inarray = N.ravel(inarray)
    (hist, smallest, binsize, extras) = ahistogram(inarray,numbins,[min(inarray),max(inarray)])
    cumhist = N.cumsum(hist)            # make cumulative histogram
    otherbins = N.greater_equal(cumhist,len(inarray)/2.0)
    otherbins = list(otherbins)         # list of 0/1s, 1s start at median bin
    cfbin = otherbins.index(1)                # get 1st(!) index holding 50%ile score
    LRL = smallest + binsize*cfbin        # get lower read limit of that bin
    cfbelow = N.add.reduce(hist[0:cfbin])        # cum. freq. below bin
    freq = hist[cfbin]                        # frequency IN the 50%ile bin
    median = LRL + ((len(inarray)/2.0-cfbelow)/float(freq))*binsize # MEDIAN
    return median