Animal nutrition journal report: Mar 2018
by Youngjun Na
A report is published for a personal interesting of the recent animal nutrition. The papers about “animal nutrition” which published at some SCI(E) journals were selected and analyzed. HTML scraping, data visualization, English-Korean translation, and report generation are automate process except sorting of the papers. Codes are available at https://github.com/YoungjunNa/journal_scraping
1. List of journals
journal_list <- readxl::read_excel("journal_result_2018_3.xlsx")
table <- table(journal_list$journal) %>% data.frame()
colnames(table) <- c("Journal","Articles")
kable(table)| Journal | Articles |
|---|---|
| AJAS | 8 |
| animal | 6 |
| animal feed science and technology | 17 |
| journal of animal science | 10 |
| journal of dairy science | 11 |
| livestock science | 6 |
| poultry science | 10 |
ggplot(table, aes(x=Journal, y=Articles, fill=Journal)) + geom_col() + theme(axis.text.x=element_text(angle=45, hjust=1)) + scale_fill_brewer(palette="Set3")
2. List of papers
2.1. Review
results <- readxl::read_excel("journal_result_2018_3.xlsx")
results <- results[,c(7,9,8,5,4,1,2,3,6)]
filter(results, type=="review")2.2. Monogastric
filter(results, type=="original article" & class=="monogastric")2.3. Ruminant
filter(results, type=="original article" & class=="ruminant")3. Wordcloud analysis
3.1. Monogastric
wc <- readxl::read_excel("journal_result_2018_3.xlsx")
#wc <- filter(wc, class == "ruminant")
wc <- filter(wc, class == "monogastric")
#wc <- filter(wc, str_detect(wc$subject,"supplement")==TRUE)
#WORDCLOUD
wc <- Corpus(VectorSource(wc$subject))
wc_data<-tm_map(wc,stripWhitespace)
wc_data<-tm_map(wc_data, removeWords, c("and"))
wc_data<-tm_map(wc_data, tolower)
wc_data<-tm_map(wc_data,removeNumbers)
wc_data<-tm_map(wc_data, removePunctuation)
wc_data<-tm_map(wc_data, removeWords, stopwords("english"))
wc_data<-tm_map(wc_data, removeWords, c("affect","effect","effects","and","the","our","that","for","are","also","more","has","must","have","should","this","with"))
tdm_wc<-TermDocumentMatrix(wc_data) #Creates a TDM
TDM1<-as.matrix(tdm_wc) #Convert this into a matrix format
v = sort(rowSums(TDM1), decreasing = TRUE) #Gives you the frequencies for every word
wordcloud(wc_data, max.words = Inf, min.freq = 1, random.order = FALSE, rot.per = 0.1, colors = brewer.pal(8, "Dark2")) 
## Term-Document
dtm <- TermDocumentMatrix(wc_data)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
d3.2. Ruminant
wc <- readxl::read_excel("journal_result_2018_3.xlsx")
wc <- filter(wc, class == "ruminant")
#wc <- filter(wc, class == "monogastric")
#wc <- filter(wc, str_detect(wc$subject,"supplement")==TRUE)
#WORDCLOUD
wc <- Corpus(VectorSource(wc$subject))
wc_data<-tm_map(wc,stripWhitespace)
wc_data<-tm_map(wc_data, removeWords, c("and"))
wc_data<-tm_map(wc_data, tolower)
wc_data<-tm_map(wc_data,removeNumbers)
wc_data<-tm_map(wc_data, removePunctuation)
wc_data<-tm_map(wc_data, removeWords, stopwords("english"))
wc_data<-tm_map(wc_data, removeWords, c("cattle","affect","effect","effects","and","the","our","that","for","are","also","more","has","must","have","should","this","with"))
tdm_wc<-TermDocumentMatrix(wc_data) #Creates a TDM
TDM1<-as.matrix(tdm_wc) #Convert this into a matrix format
v = sort(rowSums(TDM1), decreasing = TRUE) #Gives you the frequencies for every word
wordcloud(wc_data, max.words = Inf, min.freq = 1, random.order = FALSE, rot.per = 0.1, colors = brewer.pal(8, "Dark2")) 
## Term-Document
dtm <- TermDocumentMatrix(wc_data)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
d3.3. Overall
wc <- readxl::read_excel("journal_result_2018_3.xlsx")
#wc <- filter(wc, class == "ruminant")
#wc <- filter(wc, class == "monogastric")
#wc <- filter(wc, str_detect(wc$subject,"supplement")==TRUE)
#WORDCLOUD
wc <- Corpus(VectorSource(wc$subject))
wc_data<-tm_map(wc,stripWhitespace)
wc_data<-tm_map(wc_data, removeWords, c("and"))
wc_data<-tm_map(wc_data, tolower)
wc_data<-tm_map(wc_data,removeNumbers)
wc_data<-tm_map(wc_data, removePunctuation)
wc_data<-tm_map(wc_data, removeWords, stopwords("english"))
wc_data<-tm_map(wc_data, removeWords, c("affect","effect","effects","and","the","our","that","for","are","also","more","has","must","have","should","this","with"))
tdm_wc<-TermDocumentMatrix(wc_data) #Creates a TDM
TDM1<-as.matrix(tdm_wc) #Convert this into a matrix format
v = sort(rowSums(TDM1), decreasing = TRUE) #Gives you the frequencies for every word
wordcloud(wc_data, max.words = Inf, min.freq = 1, random.order = FALSE, rot.per = 0.1, colors = brewer.pal(8, "Dark2")) 
## Term-Document
dtm <- TermDocumentMatrix(wc_data)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
dSubscribe via RSS