【发布时间】：2020-03-31 12:53:19
【问题描述】：
对于这种分类方法，rtexttools 或其他软件包是否有替代品，因为这些软件包已被删除，还有 maxent 和 glmnet，它们依赖于 rtexttools，反之亦然；这是我试图应用和分类的脚本
library(maxent)
library(openxlsx)
library(RTextTools)
library(readxl)
library("tm")
library("SnowballC")
library("wordcloud")
library("RColorBrewer")
library("tidyverse")
library(purrrlyr)
library(text2vec)
library(caret)
library(glmnet)
library(ggrepel)
library(arm)
cas = read_excel("C:/Users/Desktop/Modelo JUN19/Copia de Data Final Entrenamiento - ML DS CAS - 21-06-2019 - REV01.xlsx")
datos=data.frame(clase=cas$servicio,text=cas$a_subject)
trainIndex <- createDataPartition(datos$clase, p = 0.8,
list = FALSE,times = 1)
data_train=datos[trainIndex,]
data_test=datos[-trainIndex,]
matrix_train <- create_matrix(data_train$text,language="spanish",stemWords=FALSE)
matrix_test <- create_matrix_test(data_test$text,language="spanish",stemWords=FALSE,
originalMatrix=matrix_train )
container_train <- create_container(matrix_train,data_train$clase,
trainSize=1:length(data_train$clase),virgin=FALSE)
container_test <- create_container(matrix_test,labels=rep(0,length(data_test$clase)),
trainSize=1:length(data_test$clase),
virgin=FALSE)
##################### SVM
#lineal
t_svm_lineal <- Sys.time()
model_SVM_lineal <- train_model(container_train, "SVM", kernel="linear")
print(difftime(Sys.time(), t_svm_lineal, units = 'mins'))
#Clasificación según el modelo
clas_svm_lineal_train <- classify_model(container_train, model_SVM_lineal )
clas_svm_lineal_test <- classify_model(container_test, model_SVM_lineal )
# tasa acertado
aceptacion_svm_lineal_train=summary(as.character(data_train$clase)==as.character(clas_svm_lineal_train$SVM_LABEL))
aceptacion_svm_lineal_test=summary(as.character(data_test$clase)==as.character(clas_svm_lineal_test$SVM_LABEL))
#Resumen de las categorias
summary(clas_svm_lineal_train$SVM_LABEL)
table(clas_svm_lineal_train$SVM_LABEL,data_train$clase)
table(clas_svm_lineal_test$SVM_LABEL,data_test$clase)
【问题讨论】：
标签： r machine-learning nlp