RidgeRegression.py 文件源码

def train(self):
        """"""
        start = time.time()

        print('size before truncated outliers is %d ' % len(self.TrainData))
        TrainData = self.TrainData[(self.TrainData['logerror'] > self._low) & (self.TrainData['logerror'] < self._up)]
        print('size after truncated outliers is %d ' % len(TrainData))

        X = TrainData.drop(self._l_drop_cols, axis=1)
        Y = TrainData['logerror']
        self._l_train_columns = X.columns
        X = X.values.astype(np.float32, copy=False)

        rr = Ridge(alpha= self._alpha,
                   max_iter = self._iter,
                   solver= 'svd')

        self._model = rr.fit(X, Y)
        end = time.time()

        print('time consumed %d ' % ((end - start)))

        self._f_eval_train_model = '{0}/{1}_{2}.pkl'.format(self.OutputDir, self.__class__.__name__,
                                                            datetime.now().strftime('%Y%m%d-%H:%M:%S'))
        with open(self._f_eval_train_model, 'wb') as o_file:
            pickle.dump(self._model, o_file, -1)
        o_file.close()

        self.TrainData = pd.concat([self.TrainData, self.ValidData[self.TrainData.columns]],
                                   ignore_index=True)  ## ignore_index will reset the index or index will be overlaped

        return