NPO-Accounting/conservancy_beancount Changeset - 86f4232df19e

Changeset - 86f4232df19e

Parent rev.

Child rev.

[Not reviewed]

0 1 0

Ben Sturmfels (bsturmfels) - 16 months ago 2023-02-11 07:30:22
ben@sturm.com.au

reconciler: Move other score thresholds to constants

1 file changed with 14 insertions and 10 deletions:

conservancy_beancount/reconcile/statement_reconciler.py

0 comments (0 inline, 0 general)

conservancy_beancount/reconcile/statement_reconciler.py

➞

Show inline comments

@@ ... / @@ -152,8 +152,10 @@ JUNK_WORDS = [ @@
+]
 JUNK_WORDS_RES = [re.compile(word, re.IGNORECASE) for word in JUNK_WORDS]
 ZERO_RE = re.compile('^0+')
 FULL_MATCH_THRESHOLD = 0.8
 PARTIAL_MATCH_THRESHOLD = 0.4
 PAYEE_FULL_MATCH_THRESHOLD = 0.8
 PAYEE_PARTIAL_MATCH_THRESHOLD = 0.4
 OVERALL_EXCELLENT_MATCH_THRESHOLD = 0.8  # Clear winner
 OVERALL_ACCEPTABLE_MATCH_THRESHOLD = 0.5  # Acceptable if only one match found
 def remove_duplicate_words(text: str) -> str:
@@ ... @@
     else:
         check_score = 0.0
         payee_score = payee_match(r1['payee'], r2['payee'])
-        if payee_score > FULL_MATCH_THRESHOLD:
+        if payee_score > PAYEE_FULL_MATCH_THRESHOLD:
             payee_message = ''
-        elif payee_score > PARTIAL_MATCH_THRESHOLD:
+        elif payee_score > PAYEE_PARTIAL_MATCH_THRESHOLD:
             payee_message = 'partial payee match'
         else:
             payee_message = 'payee mismatch'
@@ ... / @@ -435,16 +437,16 @@ def match_statement_and_books( @@
         matches_found = 0
         for i, r2 in enumerate(books_trans):
             score, note = records_match(r1, r2)
-            if score >= 0.5 and score >= best_match_score:
+            if score >= OVERALL_ACCEPTABLE_MATCH_THRESHOLD and score >= best_match_score:
                 matches_found += 1
                 best_match_score = score
                 best_match_index = i
                 best_match_note = note
         if (
-            best_match_score > 0.5
+            best_match_score > OVERALL_ACCEPTABLE_MATCH_THRESHOLD
             and matches_found == 1
             and 'check-id mismatch' not in best_match_note
-            or best_match_score > 0.8
+            or best_match_score > OVERALL_EXCELLENT_MATCH_THRESHOLD
         ):
             matches.append(([r1], [books_trans[best_match_index]], best_match_note))
             # Don't try to make a second match against this books entry.
@@ ... / @@ -484,16 +486,16 @@ def subset_match( @@
         r2['amount'] = total
         for i, r1 in enumerate(statement_trans):
             score, note = records_match(r1, r2)
-            if score >= 0.5 and score >= best_match_score:
+            if score >= OVERALL_ACCEPTABLE_MATCH_THRESHOLD and score >= best_match_score:
                 matches_found += 1
                 best_match_score = score
                 best_match_index = i
                 best_match_note = note
         if (
-            best_match_score > 0.5
+            best_match_score > OVERALL_ACCEPTABLE_MATCH_THRESHOLD
             and matches_found == 1
             and 'check-id mismatch' not in best_match_note
-            or best_match_score > 0.8
+            or best_match_score > OVERALL_EXCELLENT_MATCH_THRESHOLD
         ):
             matches.append(
                 ([statement_trans[best_match_index]], group_items, best_match_note)
@@ ... / @@ -795,6 +797,8 @@ def main( @@
         statement_trans = read_csv(f)
     # Dates are taken from the beginning/end of the statement.
     # TODO: FR statements include the last day of previous statement and the
     # last day of this statement in the first/last rows.
     begin_date = statement_trans[0]['date']
     end_date = statement_trans[-1]['date']

0 comments (0 inline, 0 general)