FeatureEncoding.py 文件源码

def __ApplyOHE(cls, data, d_feat):
        """"""
        n = len(data)
        result = np.zeros((n, len(d_feat)), dtype='int8')
        ##
        d_stat = {}
        for i in range(n):
            for col in cls.CategoryCols:
                v = data.ix[i, col]
                if(col not in d_stat):
                    d_stat[col] = {}
                if(pd.isnull(v)):
                    result[i, d_feat['%s:missing' % col]] = 1
                    if('missing' in d_stat[col]):
                        d_stat[col]['missing'] += 1
                    else:
                        d_stat[col]['missing'] = 1
                elif('%s:%s' % (col, v) in d_feat):
                    result[i, d_feat['%s:%s' % (col, v)]] = 1
                    if('hit' in d_stat[col]):
                        d_stat[col]['hit'] += 1
                    else:
                        d_stat[col]['hit'] = 1
                else:
                    result[i, d_feat['%s:less' % col]] = 1
                    if('less' in d_stat[col]):
                        d_stat[col]['less'] += 1
                    else:
                        d_stat[col]['less'] = 1

        ## check
        for col in d_stat:
            if(np.sum(list(d_stat[col].values())) != n):
                print('Encoding for column %s error, %d : %d. ' % (col, np.sum(list(d_stat[col].values())),n))

        return result