features_text_2.py 文件源码

def build(self):
        train, _, test, _ = data.get()
        cset = []
        ntrain = len(train)
        df = pd.concat([train, test], axis=0)
        to_drop = df.columns
        for sc in ['height', 'weight', 'ap_hi', 'ap_lo']:
            tc = df[sc].apply(str)
            maxc = tc.apply(len).max()
            for n in range(maxc):
                df['ft_l_'+sc+'_'+str(n)] = tc.apply(lambda s:ord(s[n])  if n < len(s) else -1)
                df['ft_r_'+sc+'_'+str(n)] = tc.apply(lambda s:ord(s[-n]) if n < len(s) else -1)
                cset.append('ft_l_'+sc+'_'+str(n))
                cset.append('ft_r_'+sc+'_'+str(n))

        df = pd.get_dummies(df, columns=cset).drop(to_drop, axis=1)
        self.train_= df[:ntrain]
        self.test_ = df[ntrain:]
        return self.train_, self.test_, None