blade
/
dc-ml-emea-ar
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Consider multiple share short names cases.

This commit is contained in:
Blade He 2024-10-02 17:25:25 -05:00
parent edb90c718e
commit f0dd7f9e89
2 changed files with 53 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
main.py
View File

@ -574,9 +574,9 @@ def test_data_extraction_metrics():
def test_mapping_raw_name():
doc_id = "483617247"
raw_name = "CPR Invest Global Disruptive Opportunities Class I sw EUR - Acc"
raw_share_name = "Class I sw EUR - Acc"
doc_id = "394778487"
raw_name = "Invesco Global Real Assets Fund FCP-RAIF Invesco Global Property Plus Fund Z Gross QD USD"
raw_share_name = "Z Gross QD USD"
output_folder = r"/data/emea_ar/output/mapping_data/docs/by_text/"
data_mapping = DataMapping(
doc_id,
@ -589,7 +589,7 @@ def test_mapping_raw_name():
mapping_info = data_mapping.matching_with_database(
raw_name=raw_name,
raw_share_name=raw_share_name,
parent_id=None,
parent_id="FS0000H1C9",
matching_type="share",
process_cache=process_cache
)
@ -705,7 +705,7 @@ if __name__ == "__main__":
]
# special_doc_id_list = check_mapping_doc_id_list
special_doc_id_list = check_db_mapping_doc_id_list
# special_doc_id_list = ["483617247"]
# special_doc_id_list = ["380945052", "382366116", "387202452", "394778487", "469138353"]
output_mapping_child_folder = r"/data/emea_ar/output/mapping_data/docs/"
output_mapping_total_folder = r"/data/emea_ar/output/mapping_data/total/"
re_run_extract_data = False

56
utils/biz_utils.py
View File

@ -172,7 +172,7 @@ def get_most_similar_name(text: str,
if process_cache is not None and isinstance(process_cache, dict):
if process_cache.get(text, None) is not None:
cache = process_cache.get(text)
text_share_short_name = cache.get("share_short_name")
text_share_short_name_list = cache.get("share_short_name")
text_feature = cache.get("share_feature")
text_currency = cache.get("share_currency")
else:
@ -212,6 +212,8 @@ def get_most_similar_name(text: str,
print(e)
print_exc()
similarity = 0
if similarity == 1:
return full_name, similarity
copy_name_2 = replace_abbrevation(copy_name)
if copy_name != copy_name_2:
similarity_2 = get_jacard_similarity(text,
@ -229,6 +231,7 @@ def get_most_similar_name(text: str,
copy_name_currency = cache.get("share_currency")
else:
copy_name_short_name_list = get_share_short_name_from_text(copy_share_name)
if copy_name_short_name_list is not None:
copy_name_short_name_list.sort()
copy_name_feature = get_share_feature_from_text(copy_share_name)
copy_name_currency = get_currency_from_text(copy_share_name)
@ -255,7 +258,12 @@ def get_most_similar_name(text: str,
if matching_type == "share":
if text_share_short_name_list is not None and len(text_share_short_name_list) > 0 and \
copy_name_short_name_list is not None and len(copy_name_short_name_list) > 0:
if text_share_short_name_list != copy_name_short_name_list:
raw_short_not_in_compare = False
for short in text_share_short_name_list:
if short not in copy_name_short_name_list:
raw_short_not_in_compare = True
break
if raw_short_not_in_compare:
continue
max_similarity = similarity
max_similarity_full_name = full_name
@ -285,19 +293,26 @@ def get_most_similar_name(text: str,
def get_share_part_list(text_list: list):
share_part_list = []
for text in text_list:
text_split = text.split("Fund")
text_split = text.split("Funds")
if len(text_split) == 1:
text_split = text.split("funds")
text_split = text.split("Fund")
if len(text_split) == 1:
text_split = text.split("Portfolio")
if len(text_split) == 1:
text_split = text.split("Bond")
if len(text_split) == 1:
text_split = text.split("Bonds")
if len(text_split) == 1:
text_split = text.split("Bond")
if len(text_split) > 1:
share_part_list.append(text_split[-1].strip())
share_part_text = text_split[-1].strip()
else:
share_part_list.append(text)
share_part_text = text.strip()
share_part_text = ' '.join([split for split in share_part_text.split()
if remove_special_characters(split).lower()
not in ['fund', "funds", 'portfolio',
'bond', 'bonds',
'class', 'classes',
'share', 'shares']])
share_part_list.append(share_part_text)
return share_part_list
@ -316,9 +331,20 @@ def get_share_short_name_from_text(text: str):
break
if split.lower() not in temp_share_features and \
split.upper() not in total_currency_list:
if len(split) <= 3 and split.upper() == split:
if len(split) <= 3:
share_short_name_list.append(split.upper())
count += 1
if len(share_short_name_list) > 1:
remove_number = []
for short_name in share_short_name_list[::-1]:
if short_name.isdigit():
remove_number.append(short_name)
else:
break
for remove in remove_number:
if remove in share_short_name_list:
share_short_name_list.remove(remove)
return share_short_name_list
def get_share_feature_from_text(text: str):
@ -481,6 +507,7 @@ def remove_common_word(text_list: list):
# the result is ['Global', 'Growth']
common_word_list = []
new_text_splits_list = [text.split() for text in new_text_list]
with_common_word = False
for i in range(len(new_text_splits_list)):
for j in range(i+1, len(new_text_splits_list)):
if common_word_list is None or len(common_word_list) == 0:
@ -489,6 +516,12 @@ def remove_common_word(text_list: list):
else:
common_word_list = list(
set(common_word_list).intersection(set(new_text_splits_list[j])))
if len(common_word_list) > 0:
with_common_word = True
if with_common_word and len(common_word_list) == 0:
break
if with_common_word and len(common_word_list) == 0:
break
remove_list = []
# if exists the share name and currency name, remove from the list
@ -631,7 +664,8 @@ def get_beginning_common_words(text_list: list):
def replace_abbrevation(text: str):
if text is None or len(text.strip()) == 0:
return text
text = text.strip()
text = text.replace('(', ' ').replace(')', ' ').replace('-', ' ')
text = re.sub(r'\s+', ' ', text).strip()
if 'swiss franc' in text.lower():
text = re.sub(r'swiss\s+franc', 'CHF', text, flags=re.IGNORECASE)
elif 'us dollar' in text.lower():
@ -710,6 +744,8 @@ def replace_abbrevation(text: str):
new_text_splits.append('US')
elif split.lower() in ['nc', 'nc.']:
new_text_splits.append('no trail')
elif split.lower() in ['non']:
new_text_splits.append('Not')
else:
new_text_splits.append(split)