def _get_unaligned_corpora(self, ss, main_target_date, vocab_id_dict):
def get_ss_index(word_seq, ss):
ss = ss.lower()
ss_index = len(word_seq) - 1 # init
if ss in word_seq:
ss_index = word_seq.index(ss)
else:
if '$' in word_seq:
dollar_index = word_seq.index('$')
if dollar_index is not len(word_seq) - 1 and ss in word_seq[dollar_index + 1]:
ss_index = dollar_index + 1
else:
for index in range(dollar_index + 1, len(word_seq)):
if ss in word_seq[index]:
ss_index = index
break
return ss_index
"""
This function is from def _get_unaligned_corpora in DataPipe.py file
I am not sure what we are doing if stock symbol ss is not in the word_Seq?
"""
""" This function is from def _get_unaligned_corpora in DataPipe.py file I am not sure what we are doing if stock symbol ss is not in the word_Seq?