Making the outputs a bit more organized, adding some more stats to them

build_tag_stats_model.py

@@ -1,6 +1,6 @@
 from dataclasses import dataclass, field
 from operator import itemgetter
-from typing import List
+from typing import Any, Dict, List
 
 from stats_model import StatsModel
 
@@ -11,13 +11,26 @@ class BuildTagStatsModel(StatsModel):
     operation: str = 'build_tag_stats'
 
     # Posts ranked from most popular to least popular by notes.
-    ranked_post_urls: List[str] = field(init=False)
+    ranked_posts: List[Dict[str, Any]] = field(init=False)
 
     def __post_init__(self):
         super().__post_init__()
-        self.ranked_post_urls = self.determine_ranked_post_urls()
+        self.ranked_posts = self.determine_ranked_posts()
 
-    def determine_ranked_post_urls(self) -> List[str]:
-        post_list = sorted(list(self.original_post_map.values()),
-                           key=itemgetter('note_count'), reverse=True)
-        return [post['post_url'] for post in post_list]
+    def determine_ranked_posts(self) -> List[Dict[str, Any]]:
+        post_list: List[Dict[str, Any]] = []
+        for post_key in self.original_post_map:
+            post = self.original_post_map[post_key]
+            post_list.append({
+                'id_string': post['id_string'],
+                'post_url': post['post_url'],
+                'tags': post['tags'],
+                'note_count': post['note_count']
+            })
+
+        sorted_list = sorted(post_list, key=itemgetter('note_count'),
+                             reverse=True)
+        for i, post in enumerate(sorted_list):
+            post['rank'] = i + 1
+
+        return sorted_list

build_total_stats_model.py

@@ -1,6 +1,5 @@
 from dataclasses import dataclass, field
-from operator import itemgetter
-from typing import Any, Dict, List
+from typing import Dict, List
 
 from stats_model import StatsModel
 
@@ -17,4 +16,4 @@ class BuildTotalStatsModel(StatsModel):
     top_post_urls_by_month_and_year: Dict[str, List[str]] = field(init=False)
 
     def __post_init__(self):
-        super().__post_init__()
+        super().__post_init__()

stats_model.py

@@ -59,22 +59,32 @@ class StatsModel:
         return total
 
     def calculate_total_original_post_notes_by_month_and_year(self) -> Dict[str, int]:
-        date_map: Dict[str, int] = {}
+        date_map: Dict[str, Any] = {}
+        date_map = defaultdict(lambda: {'note_count': 0,
+                                        'post_count': 0},
+                               date_map)
         for post_key in self.original_post_map:
             post = self.original_post_map[post_key]
             # Format is like 2025-12-28 20:00:34 GMT
             post_date: datetime = datetime.strptime(
                 post['date'], '%Y-%m-%d %H:%M:%S %Z')
             post_date_key = f"{post_date.year}-{post_date.month:02}"
-            if post_date_key in date_map:
-                date_map[post_date_key] += post['note_count']
-            else:
-                date_map[post_date_key] = post['note_count']
+            sts = date_map[post_date_key]
+            sts['year_month'] = post_date_key
+            sts['post_count'] += 1
+            sts['note_count'] += post['note_count']
+
+        for date in date_map:
+            sts = date_map[date]
+            post_count = sts['post_count']
+            note_count = sts['note_count']
+            sts['notes_to_posts_ratio'] = note_count / post_count
+
         return date_map
 
     def determine_most_popular_tags(self) -> List[Dict[str, Any]]:
         tag_dict: Dict[str, Any] = {}
-        tag_dict = defaultdict(lambda : {'note_count': 0,
+        tag_dict = defaultdict(lambda: {'note_count': 0,
                                         'post_count': 0},
                                tag_dict)
         for post_key in self.original_post_map:

tumblr_stats.py

@@ -182,7 +182,7 @@ def main() -> None:
 
     # Write the chosen model as JSON output.
     with open('./tumblr_stats.json', 'w') as f:
-        json.dump(asdict(stats_model), f, indent=1)
+        json.dump(asdict(stats_model), f, indent=1, default=str)
 
     # If there were original posts, create a CSV for them.
     if post_map: