Method lean_str_sst

data_processor.py:58–65

Tokenization/string cleaning for the SST yelp_dataset Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py

(self, string)

        return " ".join(new_doc).lower()

    def lean_str_sst(self, string):
        """
            Tokenization/string cleaning for the SST yelp_dataset
            Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
            """
        string = re.sub(self.other_char, " ", string)
        string = re.sub(r"\s{2,}", " ", string)
        return string.strip().lower()

    def remove_stopword(self, string):
        if self.stop_words is None: