2025-09-10:仓库迁移

1.数据结构与算法/15.根据字段分组.py

@@ -0,0 +1,39 @@
+# 假如我们有一个记录需要进行分组
+
+rows = [
+    {"address": "5412 N CLARK", "date": "07/01/2012"},
+    {"address": "5148 N CLARK", "date": "07/04/2012"},
+    {"address": "5800 E 58TH", "date": "07/02/2012"},
+    {"address": "2122 N CLARK", "date": "07/03/2012"},
+    {"address": "5645 N RAVENSWOOD", "date": "07/02/2012"},
+    {"address": "1060 W ADDISON", "date": "07/02/2012"},
+    {"address": "4801 N BROADWAY", "date": "07/01/2012"},
+    {"address": "1039 W GRANVILLE", "date": "07/04/2012"},
+]
+
+# 如果我们想按日期进行分组，那itertools里的groupby会很好用
+from operator import itemgetter
+from itertools import groupby
+
+# 因为groupby只能检查连续的项，所以我们先对列表进行排序
+rows.sort(key=itemgetter("date"))
+print(rows)
+
+# 然后我们进行分组操作：
+for date, items in groupby(rows, itemgetter("date")):
+    print(date)
+    for i in items:
+        print(' ', i)
+# groupby每次返回的是一个值（分组名称）和一个子迭代器（组内数据）
+
+
+# 当然如果是单纯的分组，一键多值字典是个好东西
+from collections import defaultdict
+data = defaultdict(list)
+for item in rows:
+    data[item["date"]].append(item)
+    
+print(data)
+
+# 在不考虑内存开销的情况下，这东西比先排序再groupby快
+