Alex Galarce
53b38ea15c
Refactor/split investment and client * refactor: clean up tests * Renamed tests/qcqa to tests/qa_qc for consistency * comment out faulty test - see docstring note at top * split to client/investment * add __init__.py to investment and client to avoid mypy confusion * fix imports * update imports for consistency across investment module * move back to one config * try changing import to relative * add init.py to src * try relative import * try one more sys.path.append * fix path for client main * fix imports in file_processing * make prompts common * move keywords out to `src` * move smart_chunking_funcs to `src` * fix mypy error * start moving to explicit imports * remove old keywords and fix imports for keywords and prompts * change all imports to full paths * fix unit tests * add readme for new way of running things * isort after all that import work * remove unused sys.path.append from some tests Approved-by: Katon Minhas
116 lines
4.5 KiB
Python
116 lines
4.5 KiB
Python
# Methodology
|
|
# regex = make 'keyword' arg a pattern (NPI, TIN, Dates, etc)
|
|
# hierarchical and/or = Run and condition first, if nothing, then run or
|
|
# hierarchy = run each keyword independently in order of listing - case sensitive
|
|
# and = run each keyword if all are present, case insensitive
|
|
# or = run each keyword if any are present, case insensitive
|
|
|
|
|
|
# Example: {'blue_group' : {'fields' : ['TermClause', ContractAuto', ...], 'methodology' : 'or', 'keywords' : ['renew', 'term']}
|
|
# "irs_group / "Gray Group":"
|
|
# 'Tax ID,TIN,IRS,Provider Name,National Provider Identifier,NPI,Other NPIs,To Provider At:,To Provider at:'
|
|
|
|
from src import config
|
|
|
|
GROUPED_KEYWORD_MAPPINGS = {
|
|
"term_group": {
|
|
"fields": [
|
|
"TERM_CLAUSE",
|
|
"CONTRACT_AUTO_RENEWAL_IND",
|
|
"CONTRACT_TERMINATION_DT",
|
|
"TERMINATION_UPON_NOTICE",
|
|
"TERMINATION_UPON_CAUSE",
|
|
],
|
|
"methodology": "or",
|
|
"keywords": ["TERM AND TERMINATION", "Term and Termination", "Term and termination", "term and termination", "Term"
|
|
, "Renew", "renew", "Auto renew", "auto renew", "automatically renew", "evergreen", "Evergreen"
|
|
, "upon notice", "Notice", "NOTICE", "with notice", "without cause", "With Cause", "with cause"
|
|
, "Termination", "Terminate"],
|
|
"case_sensitive": True,
|
|
},
|
|
"AGREEMENT_NAME": {
|
|
"fields": [
|
|
"CONTRACT_TITLE"
|
|
],
|
|
"methodology": "hierarchy",
|
|
"keywords": ["AGREEMENT", "AMENDMENT", "ADDENDUM", "PROVIDER", "CONTRACT", "MEMORANDUM", "LETTER", "REQUEST", "EFFECTIVE"],
|
|
"case_sensitive": False,
|
|
},
|
|
"notice_provider_group": {
|
|
"fields": ["NOTICE_PROVIDER_NAME", "NOTICE_PROVIDER_ADDRESS"],
|
|
"methodology": "or",
|
|
"keywords": ["Attn", "Inc.", "Suite", "Ste", "P.O Box", "To Provider at:"],
|
|
"case_sensitive": False,
|
|
},
|
|
"LATE_PAID_CLAIMS_LANGUAGE": {
|
|
"fields": ["LATE_PAID_CLAIMS_LANGUAGE"],
|
|
"methodology": "hierarchy",
|
|
"keywords": [
|
|
"late paid",
|
|
"late payment",
|
|
"interest",
|
|
"late fee",
|
|
"interest shall be paid",
|
|
"interest payment",
|
|
],
|
|
"case_sensitive": False,
|
|
},
|
|
"NON_RENEWAL_LANGUAGE": {
|
|
"fields": ["NON_RENEWAL_LANGUAGE"],
|
|
"methodology": "or",
|
|
"keywords": ["not to renew", "non-renewal", "non renewal", "nonrenewal"],
|
|
"case_sensitive": False,
|
|
},
|
|
"HCBS_SERVICES": {
|
|
"fields": ["HCBS_SERVICES"],
|
|
"methodology": "hierarchy",
|
|
"keywords": ["%", "Plan shall pay", "hcbs"],
|
|
"case_sensitive": False,
|
|
},
|
|
"POLICIES_AND_PROCEDURES": {
|
|
"fields": ["POLICIES_AND_PROCEDURES"],
|
|
"methodology": "or",
|
|
"keywords": ["2.4", "policies", "procedures"],
|
|
"case_sensitive": False,
|
|
},
|
|
"REGULATORY_REQUIREMENTS": {
|
|
"fields": ["REGULATORY_REQUIREMENTS"],
|
|
"methodology": "or",
|
|
"keywords": ["8.3", "6.4", "regulatory requirements", "regulatory"],
|
|
"case_sensitive": False,
|
|
},
|
|
"RECOVERY_RIGHTS": {
|
|
"fields": ["RECOVERY_RIGHTS"],
|
|
"methodology": "or",
|
|
"keywords": ["3.5", "recovery rights"],
|
|
"case_sensitive": False,
|
|
},
|
|
"RELATIONSHIP_OF_PARTIES_LANGUAGE": {
|
|
"fields": ["RELATIONSHIP_OF_PARTIES_LANGUAGE"],
|
|
"methodology": "or",
|
|
"keywords": ["8.1", "relationship of parties"],
|
|
"case_sensitive": False,
|
|
},
|
|
"EXCLUSIVITY_REQUIREMENT_LANGUAGE": {
|
|
"fields": ["EXCLUSIVITY_REQUIREMENT_LANGUAGE"],
|
|
"methodology": "or",
|
|
"keywords": ["27", "exclusiv"],
|
|
"case_sensitive": False,
|
|
},
|
|
"CONTRACT_EFFECTIVE_DT": {
|
|
"fields": ["CONTRACT_EFFECTIVE_DT"],
|
|
"methodology": "include_exclude",
|
|
"included_keywords" : ["Effective Date", "entered into", "shall be effective", "will become effective", "dated this", "made and entered into", "made this", "dated and effective"] \
|
|
if any([cand in config.BATCH_ID.lower() for cand in ["cnc-4","cnc-4a","cnc-4b"]]) \
|
|
else ["Effective Date", "entered into", "shall be effective", "will become effective"],
|
|
"excluded_keywords" : ["Permit","Registration","Department of Public Health"],
|
|
"case_sensitive": False,
|
|
},
|
|
"TERMINATION_UPON_NOTICE": {
|
|
"fields": ["TERMINATION_UPON_NOTICE"],
|
|
"methodology": "or",
|
|
"keywords": ["notice", "upon notice", "termination"],
|
|
"case_sensitive": False,
|
|
}
|
|
}
|