Question

对于我的硕士论文，我正在分析一所大学的课程。我有3个变量（作为列）的1134门课程（作为行）。由于我很少有R的经验，所以我正在努力为其编写代码。这是更多信息，并且在其中，我将数据库的样本附加为图像。

第1列是课程名称第2列是课程说明第三列是学习成果

我想清除数据并删除停用词，标点符号和其他不相关的字符。我使用以下代码执行此操作：

rm(list=ls());
library(readxl);
library(MASS);
library(nnet);
library(NLP);
library(tm);
database <- read_excel("/Volumes/GoogleDrive/My Drive/TU e Innovation Management /Thesis/testdatabasematrix.xlsx");

#name columns
colnames(database)[1] <- "Name";
colnames(database)[2] <- "Description";
colnames(database)[3] <- "LearningOutcomes";

#replace punctuation
database2 <- gsub(pattern = "\\W", replace = " ", database)
#replace digits
database2 <- gsub(pattern="\\d", " ", database2)
#everything to lower
database2 <- tolower(database2)

#until here everything fine
database2 <- removeWords(database2, stopwords());

#When I try to save the database in a data frame, the output is merely 3 observations of 1 variable instead of 1141 obs. of 3 variables
database2 <- data.frame(database2)

希望您能帮助我:)。如果您需要更多信息，请这样说，我当然会提供。

最好，克里斯蒂安（Christiaan）

Answer 1

似乎removeWords需要一个字符向量作为第一个参数。所以也许

for (x in colnames(database2)) database2[,x] <- removeWords(database2[,x], stopwords())

起到了作用。

Answer 2

您还可以考虑使用tidytext和dplyr软件包，这非常好：

# some data similar to yours
database <- data.frame(Name = c('Aalto Fellows II', 'Aalto introduction to Services'),
                       Description = c('This course is a lot of words I do not know.','Service economy, whatever it does mean.'),
                       LearningOutcomes = c('Aalto Fellows, which are the smartest, learn.','Knowing what does Service economy means.'), stringsAsFactors = FALSE)

# cool packages
library(tidytext)
library(dplyr)

# here the text transformations for titles
title <- tibble(line = 1:nrow(database), text = database$Name) %>%        # as tibble
         unnest_tokens(word, text)%>%                                     # remove punctuations, lowercase, put words in column
         anti_join(stop_words, by = c("word" = "word")) %>%               # remove stopwords
         group_by(line) %>% summarise(title = paste(word,collapse =' '))  # now all in a row!

# here the text transformations for descriptions
description <- tibble(line = 1:nrow(database), text = database$Description) %>%
               unnest_tokens(word, text) %>%  
               anti_join(stop_words, by = c("word" = "word"))  %>%
               group_by(line) %>% summarise(title = paste(word,collapse =' '))

# here the text transformations for learning outcomes
learningoutcomes <- tibble(line = 1:nrow(database), text = database$LearningOutcomes) %>% 
                    unnest_tokens(word, text) %>%
                    anti_join(stop_words, by = c("word" = "word"))  %>%
                    group_by(line) %>% summarise(title = paste(word,collapse =' '))

# now the full dataset
database2 <- title %>% left_join(description, by = 'line') %>% left_join(learningoutcomes, by = 'line')
colnames(database2) <- c("line","Name","Description","LearningOutcomes")
database2

# A tibble: 2 x 4
   line Name                        Description     LearningOutcomes             
  <int> <chr>                       <chr>           <chr>                        
1     1 aalto fellows ii            lot words       aalto fellows smartest learn 
2     2 aalto introduction services service economy knowing service economy means

您可以使用data.frame()将其转换为data.frame。

Answer 3

由于您尚未提供示例数据集，因此我创建了一个示例数据集。此解决方案还使用了tidytext和dplyr软件包，但与上面的稍有不同。在这种情况下，您可以直接使用数据框并在继续操作时维护数据框。

# Create dataframe    
database <- data.frame("Name" = c("Hello how, are , you.", "I am fine thank you!"),
                           "Description" = c("installation of package ‘tibble’",
                                             "package ‘readxl’ successfully unpacked "),
                           "LearningOutcome" = c("Volumes/GoogleDrive/My Drive",
                                                 "TU e Innovation Management")


# Take off stop words
data(stop_words)

database_stopwords <- database %>%
  filter(!Name %in% stop_words$word) %>%
  filter(!Description %in% stop_words$word) %>%
  filter(!LearningOutcome %in% stop_words$word)

# Convert to lower
database_lower <- database_stopwords %>% mutate(
  Name = tolower(Name),
  Description = tolower(Description),
  LearningOutcome = tolower(LearningOutcome)
)

# Take off punctuation and others
database_lower$Name = gsub("\\W|\\d|http\\w?", " ", database_lower$Name, perl = T)
database_lower$Description = gsub("\\W|\\d|http\\w?", " ", database_lower$Description, perl = T)
database_lower$LearningOutcome = gsub("\\W|\\d|http\\w?", " ", database_lower$LearningOutcome, perl = T)

从R中的Excel文件清除文本（删除停用词，标点符号等）

3 个答案: