utils.py 文件源码

def mean_target_rate(name,out,idcol,ycol):
    if os.path.exists(out):
        return pickle.load(open(out,'rb'))
    yc,cc = defaultdict(float),defaultdict(float)
    for c,row in enumerate(csv.DictReader(open(name))):
        y = float(row[ycol])
        for i in row:
            if i in [idcol,ycol]:
                continue
            v = "%s-%s"%(i,row[i])
            yc[v] += y
            cc[v] += 1.0

        if c>0 and c%100000 == 0:
            print("rows %d len_cc %d"%(c,len(cc)))
    for i in yc:
        yc[i] = yc[i]/cc[i]
    pickle.dump(yc,open(out,'wb'))
    return yc