From 68bdf2a41fec733de7e5ca232d6731cd20eac083 Mon Sep 17 00:00:00 2001
From: Andrea Vos <andrea@avris.it>
Date: Sun, 25 Feb 2024 13:31:24 +0000
Subject: [PATCH] (pl)(census) update python script for 2024 questions

---
 census/analyse.py | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/census/analyse.py b/census/analyse.py
index 0f21ce929..480a4726d 100644
--- a/census/analyse.py
+++ b/census/analyse.py
@@ -183,7 +183,14 @@ def analyse(group: str, df: pd.DataFrame, echo: bool = False, diffs: List[str] =
         'namesAggr': extractQuestion(df, 16, includeAnswers=False, includeAggregates=True),
         'english': extractQuestion(df, 17, includeAggregates=True),
         'labelsGender': extractQuestion(df, 18, includeAggregates=True, removeUnderscores=False),
-        'labelsSexuality': extractQuestion(df, 19, includeAggregates=True, removeUnderscores=False),
+        'labelsSexuality': extractQuestion(df, 20, includeAggregates=True, removeUnderscores=False),
+        'labelsRomantic': extractQuestion(df, 21, includeAggregates=True, removeUnderscores=False),
+        'transitionSocial': extractQuestionSingle(df, 23),
+        'transitionName': extractQuestionSingle(df, 24),
+        'transitionMarker': extractQuestionSingle(df, 25),
+        'transitionPhysical': extractQuestionSingle(df, 26),
+        'transitionHormonal': extractQuestionSingle(df, 27),
+        'transitionMedical': extractQuestionSingle(df, 28),
     }
 
     stats_json = {
@@ -194,7 +201,10 @@ def analyse(group: str, df: pd.DataFrame, echo: bool = False, diffs: List[str] =
 
     stats_json['diff'] = {}
     for prev_year in (diffs or []):
-        with open(outputDir.parent / prev_year / group / 'stats.json', 'r') as f:
+        file_path = outputDir.parent / prev_year / group / 'stats.json'
+        if not file_path.exists():
+            continue
+        with open(file_path, 'r') as f:
             prev_stats = json.load(f)
             stats_json['diff'][prev_year] = {}
             for k, v in stats_json.items():
@@ -246,7 +256,7 @@ if __name__ == '__main__':
     df.loc[:, 'age'] = year - df['3_']
     df.loc[df['age'] > 100, 'age'] = None
 
-    diffs = ['spis-2022']
+    diffs = ['spis-2022', 'spis-2023']
 
     print(df)
 
@@ -257,6 +267,8 @@ if __name__ == '__main__':
         'agab_f': analyse('agab_f', df[df['1_'] == 'żeńską'], args.echo, diffs),
         'agab_m': analyse('agab_m', df[df['1_'] == 'męską'], args.echo, diffs),
         # 'agab_x': analyse('agab_x', df[df['1_'] == 'inną (w jurysdykcjach, gdzie to możliwe)'], args.echo, diffs),
+        'younger': analyse('younger', df[df['age'] < 25], args.echo, diffs),
+        'older': analyse('older', df[df['age'] >= 25], args.echo, diffs),
     }
 
     comparisons = {
@@ -270,6 +282,11 @@ if __name__ == '__main__':
             'agab_f': 'AFAB',
             'agab_m': 'AMAB',
         },
+        'by_age': {
+            'general': 'Ogół',
+            'younger': 'Młodsze',
+            'older': 'Starsze',
+        },
     }
 
     graphs = {
@@ -290,6 +307,13 @@ if __name__ == '__main__':
         'english': 'Zaimki w języku angielskim',
         'labelsGender': 'Etykietki opisujące płeć',
         'labelsSexuality': 'Etykietki opisujące orientację seksualną',
+        'labelsRomantic': 'Etykietki opisujące orientację romantyczną',
+        'transitionSocial': 'Tranzycja społeczna',
+        'transitionName': 'Tranzycja prawna – imię',
+        'transitionMarker': 'Tranzycja prawna – znacznik płci',
+        'transitionPhysical': 'Tranzycja medyczna – bindery, packery, itp.',
+        'transitionHormonal': 'Tranzycja medyczna – hormony',
+        'transitionMedical': 'Tranzycja medyczna – zmiany chirurgiczne',
     }
 
     for group, group_stats in stats.items():