pipeline/scripts/diagnose_compare_gaps.py

@@ -255,3 +255,48 @@ if __name__ == "__main__":
 # available to this pipeline. Task 6's meltano.yml change (Step 2) and the
 # filebrowser upload should NOT proceed for 202122; there is nothing to
 # upload.
+
+# TASK 7 VALUE SAMPLE 2026-07-12: live value_counts() over the 7 report-card
+# columns (plus the related safeguarding-effective flag) in the same MI CSV
+# resolved by discover_csv_url() as at run time (31 May 2026 inspections
+# file). Blank cells read as the literal string 'NULL' (matches
+# keep_default_na=False in tap.py). Observed non-blank values, verbatim:
+#
+#   'Safeguarding standards':                 'Met' (1319), 'Not met' (10)
+#   'Inclusion':                               'Expected standard' (710),
+#       'Strong standard' (447), 'Needs attention' (130), 'Exceptional' (23),
+#       'Urgent improvement' (19)
+#   'Curriculum and teaching':                 'Expected standard' (797),
+#       'Needs attention' (287), 'Strong standard' (206),
+#       'Urgent improvement' (28), 'Exceptional' (11)
+#   'Achievement':                             'Expected standard' (701),
+#       'Needs attention' (364), 'Strong standard' (207),
+#       'Urgent improvement' (39), 'Exceptional' (18)
+#   'Attendance and behaviour':                'Expected standard' (699),
+#       'Strong standard' (405), 'Needs attention' (188),
+#       'Urgent improvement' (21), 'Exceptional' (16)
+#   'Personal development and wellbeing':      'Expected standard' (728),
+#       'Strong standard' (504), 'Needs attention' (66), 'Exceptional' (23),
+#       'Urgent improvement' (8)
+#   'Leadership and governance':               'Expected standard' (813),
+#       'Strong standard' (292), 'Needs attention' (172),
+#       'Urgent improvement' (34), 'Exceptional' (18)
+#   'Latest OEIF  safeguarding is effective?' (note double space, not used by
+#   Task 7 -- kept for completeness): 'Yes' (12970), 'No' (96)
+#
+# So the 6 graded report-card columns share exactly one 5-value vocabulary:
+# {'Exceptional', 'Strong standard', 'Expected standard', 'Needs attention',
+# 'Urgent improvement'} -- no 'Attention needed' variant was observed
+# anywhere, so parse_report_card_grade.sql does NOT need that speculative
+# branch from the task brief. 'Safeguarding standards' is a separate
+# two-value vocabulary {'Met', 'Not met'}.
+#
+# Collision check: 'Achievement' matches by EXACT list-membership
+# (`candidate in df_columns`, a Python list containment check against the
+# full column-name list, not a substring/regex match) against only
+# ['Achievement', 'Achievement - date of grade'] -- the date-paired column
+# has a different exact string and is never selected. Same check for
+# 'Safeguarding standards' found only itself, its own date-of-grade column,
+# and the unrelated 'Latest OEIF  safeguarding is effective?' column (not
+# mapped to any rc_* field). No legacy OEIF column is accidentally consumed
+# by an rc_ mapping.