Merged in bugfix/fix-nltk-to-new-path (pull request #367)

Bugfix/fix nltk to new path

* point NLTK to right path finally

* take out unreferenced function


Approved-by: Katon Minhas

fieldExtraction/src/investment/smart_chunking_funcs.py

@@ -19,7 +19,7 @@ import json
 import nltk
 import os
 # Append path of NLTK data directory (fieldExtraction/nltk_data)
-nltk.data.path.append(os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data"))
+nltk.data.path.append(os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), "nltk_data"))
 
 from nltk.tokenize import word_tokenize
 from itertools import combinations
@@ -117,33 +117,6 @@ def group_fields(field_set: FieldSet, threshold=3):
     return groups
 
 
-def get_full_context_fields(
-    ac_answers_dict: dict[str, str], no_keyword_matches: list
-) -> list:
-
-    smartly_chunked = []
-
-    for field_groups in keywords.GROUPED_KEYWORD_MAPPINGS.keys():
-        for fields in keywords.GROUPED_KEYWORD_MAPPINGS[field_groups]["fields"]:
-            smartly_chunked.append(fields)
-
-    # Instantiate full context fields from those that weren't smart chunked
-    full_context_fields = [
-        field for field in prompts.AC_DICT if field not in smartly_chunked
-    ]
-
-    # Add fields with no keyword matches to full context list
-    if len(no_keyword_matches) > 0:
-        full_context_fields.extend(no_keyword_matches)
-
-    # Filter out fields that already have answers
-    # e.g., some have already been filled out by regex chunking
-    full_context_fields = [
-        field for field in full_context_fields if field not in ac_answers_dict.keys()
-    ]
-    return full_context_fields
-
-
 
 
 def chunk_hierarchical(