2

我正在使用 SVM 对我的文本进行分类，其中我实际上并没有得到结果，而是得到了数值概率。

数据框（1:20 训练集，21:50 测试集）

更新：

     ou <- structure(list(text = structure(c(1L, 6L, 1L, 1L, 8L, 13L, 24L, 
5L, 11L, 12L, 33L, 36L, 20L, 25L, 4L, 19L, 9L, 29L, 22L, 3L, 
8L, 8L, 8L, 2L, 8L, 27L, 30L, 3L, 14L, 35L, 3L, 34L, 23L, 31L, 
22L, 6L, 6L, 7L, 17L, 3L, 8L, 32L, 18L, 15L, 21L, 26L, 3L, 16L, 
10L, 28L), .Label = c("access, access, access, access", "character(0)", 
"report", "report, access", "report, access, access", "report, access, access, access", 
"report, access, access, access, access, access, access", "report, access, access, access, access, access, access, access", 
"report, access, access, access, access, access, access, report", 
"report, access, access, access, access, access, report", "report, access, access, access, report", 
"report, access, access, access, report, access", "report, access, access, report, access, access, access, access, access, access", 
"report, data", "report, data, data", "report, data, data, data", 
"report, data, data, data, data", "report, data, data, data, data, data", 
"report, data, data, data, report, report, data, access,access", 
"report, data, data, report", "report, data, report", "report, report", 
"report, report, access, access, access", "report, report, access, access, report, report, report, report, report, report, data, data, report, access, report, report", 
"report, report, access, report, report, report, report, report, data, data, report, access, report, report", 
"report, report, access, report, report, report, report, report, report, data, data, report, access, report, report", 
"report, report, data", "report, report, data, report", "report, report, report, data, report, report, data, data, report, data, data", 
"report, report, report, report", "report, report, report, report, data, report, report, data, report, data, report", 
"report, report, report, report, report, data, report, data, data", 
"report, report, report, report, report, report, report", "report, report, report, report, report, report, report, access, access, access", 
"report, report, report, report, report, report, report, report, data, data, report, access, report, report", 
"report, report, report, report, report, report, report, report, report, report, data, report, report, report, report, report, report, report,report"
), class = "factor"), value = structure(c(2L, 2L, 2L, 2L, 2L, 
2L, 3L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 2L, 3L, 2L, 3L, 3L, 3L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("", 
"Access", "Report/Data"), class = "factor")), .Names = c("text", 
"value"), class = "data.frame", row.names = c(NA, -50L))

使用的代码：

        library(RTextTools)

        doc_matrix <- create_matrix(ou$text, language="english", removeNumbers=TRUE, stemWords=TRUE, removeSparseTerms=.998)

        #container <- create_container(doc_matrix, ou$text, trainSize=1:20, testSize=21:50, virgin=FALSE)
        container <- create_container(doc_matrix, as.numeric(factor(ou$text)), trainSize=1:20, testSize=21:50, virgin=FALSE)

        #Training models
        SVM <- train_model(container,"SVM")
        MAXENT <- train_model(container,"MAXENT")
        BAGGING <- train_model(container,"BAGGING")
        TREE <- train_model(container,"TREE")

        #Classify data using trained models
        SVM_CLASSIFY <- classify_model(container, SVM)
        MAXENT_CLASSIFY <- classify_model(container, MAXENT)
        BAGGING_CLASSIFY <- classify_model(container, BAGGING)

        #Analytics

        analytics <- create_analytics(container,SVM_CLASSIFY)

        models <- train_models(container, algorithms=c("MAXENT","SVM"))
        results <- classify_models(container, models)
        analytics <- create_analytics(container, results)
        summary(analytics)
        SVM <- cross_validate(container, 5, "SVM")
        write.csv(analytics@document_summary, "DocumentSummary.csv")

预期结果：

          text                                                          value
     21 report, access, access, access, access, access, access, access       Access
     22 report, access, access, access, access, access, access, access       Access
     23 report, access, access, access, access, access, access, access       Access
     24 character(0)                                                          NA
     25 report, access, access, access, access, access, access, access       Access
     26 report, report, data                                             Report/Data
     27 report, report, report, report                                   Report/Data
     28 report                                                          Report/Data
     29 report, data                                                    Report/Data
     30 report, report, report, report, report, report, report, report,
         data, data, report, access, report, report                      Report/Data

概率为的结果：

>   MAXENTROPY_LABEL    MAXENTROPY_PROB SVM_LABEL   SVM_PROB    MANUAL_CODE CONSENSUS_CODE  CONSENSUS_AGREE CONSENSUS_INCORRECT PROBABILITY_CODE    PROBABILITY_INCORRECT
> 1 8   0.999999066 22  0.070090645 8   8   1   0   8   0
> 2 8   0.999999066 22  0.070090645 8   8   1   0   8   0
> 3 8   0.999999066 22  0.070090645 8   8   1   0   8   0
> 4 1   0.055555556 12  0.071384112 2   12  1   1   12  1
> 5 8   0.999999066 22  0.070090645 8   8   1   0   8   0
> 6 25  1   12  0.074126949 27  25  1   1   25  1
> 7 33  0.627904676 13  0.068572857 30  33  1   1   33  1
> 8 33  0.406792176 12  0.074592181 3   33  1   1   33  1
> 9 20  1   12  0.074507793 14  20  1   1   20  1

编辑 1：如何实现标签名称而不是 SVM 标签编号。

4

1 回答 1

0

我通常做的是

ou <- cbind(ou$text, results)

并打印标签：

ou$value <- "NONE"
ou$value[results$SVM_LABEL=="1"]  <- "Access"
ou$value[results$SVM_LABEL=="-1"] <- "Report/Data"
ou

（假设您在训练模型时使用了 1 和 -1）

我知道这有点原始，但它很清晰并且工作正常

于 2016-05-27T20:21:19.637 回答