XY

没有任何借口!!!
  博客园  :: 首页  :: 新随笔  :: 联系 :: 订阅 订阅  :: 管理

找出n个数中重复最多的10个数

Posted on 2017-09-29 21:54  路缘  阅读(112)  评论(0编辑  收藏  举报

题目很清晰,直接上python代码

 

 1 import pandas as pd
 2 import copy
 3 
 4 class BenchMark:
 5     def __init__(self):
 6         self.MIN = 10000
 7         self.data = 0
 8     def Reset(self):
 9         self.MIN = 10000
10         self.data = 0
11 
12 dictCounts = {}
13 dictTop10_D2C = {}
14 BENCH_MARK = BenchMark()
15 LAST_BENCH_MARK = BenchMark()
16 run_count1 = 0
17 run_count2 = 0
18 
19 def FindTop10(data):
20     global BENCH_MARK, LAST_BENCH_MARK,run_count1,run_count2
21     if(data in dictCounts):
22         dictCounts[data] += 1
23     else:
24         dictCounts[data] = 1
25 
26     temp = dictCounts[data]
27     
28     #just record run times
29     run_count1 += 1
30     
31     if LAST_BENCH_MARK.MIN != 10000 and temp< LAST_BENCH_MARK.MIN:
32         return
33 
34     dictTop10_D2C[data] = temp
35 
36     if len(dictTop10_D2C)>10:
37         BENCH_MARK.Reset()
38         for item in dictTop10_D2C:
39             
40             #just record run times
41             run_count2+=1
42             
43             if dictTop10_D2C[item] < BENCH_MARK.MIN:
44                 BENCH_MARK.MIN = dictTop10_D2C[item]
45                 BENCH_MARK.data = item
46         LAST_BENCH_MARK = copy.deepcopy(BENCH_MARK)
47         dictTop10_D2C.pop(BENCH_MARK.data)
48 
49 def PrintData2Count(aDict):
50     for key in aDict:
51         print('%.1f:%d' % (key, aDict[key]))
52 
53 if __name__ == '__main__':
54     df = pd.read_csv('D:/data/ctp_data/rb/201709/rb1801_20170905.csv')
55     for data in df['LastPx']:
56         FindTop10(data)
57 
58     PrintData2Count(dictCounts)
59     print("==============dictCounts length:", len(dictCounts))
60     PrintData2Count(dictTop10_D2C)
61 
62     print("run_count1:%d,run_count2:%d" %(run_count1,run_count2))

 

 

运行结果如下:

。。。。。。

4121.0:206
4123.0:278
4124.0:180
4122.0:244
4125.0:118
4126.0:34
4127.0:4
4081.0:1366
4080.0:1073
4077.0:1072
4078.0:1091
4079.0:800
4076.0:874
4075.0:886
4074.0:1108
4071.0:719
4073.0:1281
4072.0:1049
4070.0:567
4069.0:442
4068.0:290
4067.0:199
4066.0:204
4065.0:109
4064.0:60
4063.0:80
4062.0:57
4061.0:70
4060.0:70
4059.0:32
4057.0:6
4058.0:22
4129.0:6
4137.0:2
4135.0:2
4133.0:2
==============dictCounts length: 75
4109.0:2080
4108.0:2047
4095.0:3009
4096.0:2785
4094.0:2265
4099.0:2573
4098.0:2702
4097.0:2491
4100.0:2147
4107.0:1809
run_count1:70684,run_count2:19679