add back gcc data and top5 by cost

count_asst_prof_ucwages.py

@@ -0,0 +1,67 @@
+"""
+count_asst_prof_ucwages.py
+============================
+Cross-check against the GCC-based analysis: count non-medical Assistant
+Professors UC-wide in 2024 using the UC-wages JSON data (uc_wages_data/),
+the same source uc_salary_pipeline.py normally uses. This can't give
+salary+benefits (no benefits field in this source) but it's a useful
+sanity check on headcount, since it's a different upstream source than GCC.
+
+Reuses classifier.py's classify_title/is_medical_center, plus the
+assistant-rank filter from analyze_asst_prof_comp.py.
+"""
+
+import json
+import glob
+import re
+
+from classifier import classify_title, is_medical_center
+from analyze_asst_prof_comp import is_assistant_rank, is_recognised_non_assistant_senate
+from uc_wages_downloader import LOCATIONS
+
+FOLDER_TO_CAMPUS = {folder: campus for campus, folder in LOCATIONS.items()}
+
+YEAR = 2024
+
+
+def main():
+    counts = {}
+    unrecognised_senate_titles = set()
+    total = 0
+
+    for path in sorted(glob.glob(f"uc_wages_data/*/wages_{YEAR}.json")):
+        folder = path.split("/")[1]
+        campus = FOLDER_TO_CAMPUS[folder]
+        with open(path) as f:
+            data = json.load(f)
+
+        n = 0
+        for rec in data["records"]:
+            title = rec["title"]
+            if classify_title(title) != "SENATE_FACULTY":
+                continue
+            if is_medical_center(title, campus):
+                continue
+            if not is_assistant_rank(title):
+                if not is_recognised_non_assistant_senate(title):
+                    unrecognised_senate_titles.add(title)
+                continue
+            n += 1
+
+        counts[campus] = n
+        total += n
+
+    if unrecognised_senate_titles:
+        print("NOTE: Senate-faculty titles not matched by any rank pattern:")
+        for t in sorted(unrecognised_senate_titles):
+            print(f"  - {t}")
+        print()
+
+    print(f"{'Campus':<10}{'N':>6}")
+    for campus in sorted(counts):
+        print(f"{campus:<10}{counts[campus]:>6}")
+    print(f"\nTotal non-medical Assistant Professors, UC system-wide, {YEAR}: {total}")
+
+
+if __name__ == "__main__":
+    main()