AzureML:"火车火柴盒推荐者"没有工作,也没有说明错误

时间:2016-05-22 14:18:46

标签: azure machine-learning cortana-intelligence azure-machine-learning-studio

我尝试使用该模块创建自己的实验,但未能使其工作。 这是我得到的例外:

  

错误0018:用户项评级三元组的训练数据集包含无效数据。   [Critical] {" InputParameters":{" DataTable":[{" Rows":14," Columns":3,&#34 ; estimatedSize":12668928," ColumnTypes" {" System.String":1," System.Int32":1,"系统。双":1}," IsComplete":真,"统计" {" 0":[10,0]," 1&# 34;:[5422.0,5999.0,873.0,6616.0,1758.0582820478173,7.0,0.0]" 2":1.0,1.0,1.0,1.0,0.0,1.0,0.0]}},{&#34 ;行":2338,"列":3," estimatedSize":1404928," ColumnTypes" {" System.String" :1," System.Int32":1," System.Double":1}," IsComplete":真,"统计&#34 ;: {" 0":[2338,0]" 1":[7.5367835757057318,3.0,0.0,704.0,17.738259318519511,64.0,0.0]" 2&#34 ;: [3.3737234816082085,1.5,0.0,352.0,8.3956874404883841,122.0,0.0]}},{"行":2532,"列":22," estimatedSize&#34 ;: 4648960," ColumnTypes" {" System.Int32":10," System.String":5," System.Double":6 " System.B oolean":1}," IsComplete":真,"统计" {" 0":[4575.7263033175359,5326.5,539.0,6871.0,1987.9561375024909,2532.0 ,0.0]," 1":[4575.7263033175359,5326.5,539.0,6871.0,1987.9561375024909,2532.0,0.0]" 2":[613.0,613.0,613.0,613.0,0.0,1.0 ,0.0]," 3":[0,2532]," 4":[0,2532]," 5":[4575.7263033175359,5326.5,539.0, 6871.0,1987.9561375024909,2532.0,0.0]" 6":[23.647231437598673,19.99,1.99,149.99,17.237723488320938,90.0,0.0]" 7":[0.043827014218009476,0.0,0.0, 45.99,1.3460680431173562,3.0,0.0]" 8":0.0,0.0,0.0,0.0,0.0,1.0,0.0]" 9":[0.0,0.0,0.0, 0.0,0.0,1.0,0.0]" 10":0.0,0.0,0.0,0.0,0.0,1.0,0.0]" 11":[0.0,0.0,0.0, 0.0,0.0,1.0,0.0]" 12":0.0,0.0,0.0,0.0,0.0,1.0,0.0]" 13":[0.0,0.0,0.0, 0.0,0.0,1.0,0.0]" 14":0.0,0.0,0.0,0.0,0.0,1.0,0.0]" 15":[0.0,0.0,0.0, 0.0,0.0,1.0,0.0]" 16":0.0,0.0,0.0,0.0,0.0,1.0,0.0]" 17":[0.0,0.0,0.0, 0.0,0.0,1.0,0.0]" 18&#34 ;: [2524,0]" 19":[242,18]," 20":[1,0]," 21":[2524,0] }}],"通用" {" traitCount":10," iterationCount":5," batchCount&#34:4}},& #34; OutputParameters":[]," ModuleType":" Microsoft.Analytics.Modules.MatchboxRecommender.Dll""的ModuleVersion":" Version = 6.0.0.0"," AdditionalModuleInfo":" Microsoft.Analytics.Modules.MatchboxRecommender.Dll,Version = 6.0.0.0,Culture = neutral,PublicKeyToken = 69c3241e6f0468ca; Microsoft.Analytics .Modules.MatchboxRecommender.Dll.MatchboxRecommender; Train"," Errors":" Microsoft.Analytics.Exceptions.ErrorMapping + ModuleException:错误0018:用户项评级三元组的训练数据集包含d:\ _ Bld \ 8833 \ 7669 \ Sources \ Product \ Source \ Modules \ MatchboxRecommender.Dll \中的Microsoft.Analytics.Modules.MatchboxRecommender.Dll.Utilities.UpdateRatingMetadata(DataTable数据集,字符串数据集名称)中的数据无效。\ r \ n Utilities.cs:第179行\ r \ n在Microsoft.Analytics.Modules.MatchboxRecommender.Dll.MatchboxRecommender.TrainImpl(DataTable userItemRatingTriples,DataTable userFeatures,DataTable itemFeatures,Int32 traitCount,Int32 iterationCount,Int32 batchCount)中的d:\ _ Bld \ 8833 \ 7669 \ Sources \ Product \ Source \ Modules \ MatchboxRecommender.Dll \ MatchboxRecommender.cs:第62行"," Wa rnings":[],"持续时间":" 00:00:00.6722068"}   模块在运行时00:00:01.1250071之后完成,退出代码为-2   模块因负退出代码-2

而失败

我已经检查输入数据我设置为输入用户位置评级表,记录(不用担心它只有14条记录),这里是:

the input data

以下是该实验的屏幕截图: the experiment

由于错误信息不是很有用,我不知道从哪里开始,所以,如果有人有想法,我会很高兴听到它。

更新: 我的一位朋友建议添加"编辑元数据"模块改变"评级"功能进入" int"或者"浮动"类型,以及另外两个(placeID和userID)成为字符串功能。这也没有帮助。

1 个答案:

答案 0 :(得分:2)

火柴盒推荐者要求评级为数字或分类。此外,在培训时,您的评分不可能都是一样的。

您需要使用元数据编辑器https://msdn.microsoft.com/en-us/library/azure/dn905986.aspx将评分转换为数字功能,并且您需要确保使用一系列评分。

然后这应该有效!