Data Analysis: Creating the sample data

Data set

Full verbs and their parts-of-speech across registers and subcorpora in the Brown family

• Query: [pos="VV.*"]
  
• Download: Download query as plain-text tabulation
  
• Attributes: lemma of verb, pos of verb, text_reg (register) text_sc (subcorpus: BROWN, FROWN, BLOB, FLOB, LOB)
  
• Output options: simple tabulate output

The results should look like this: sample data set

Add meta data information to the data set. We will use metadata listed in two files

• brown_family_register_meta.txt and
• brown_family_meta.txt.

d <- read.table("data/distr_vfull_lemma-pos-reg-sc_brownfam.txt",header=F,sep="\t",row.names = NULL,quote="")
colnames(d) <- c("verb","pos","register","corpus")
d.meta <- read.table("data/brown_family_meta.txt",sep="\t",header=T,row.names = NULL,quote="")
d.reg.meta <- read.table("data/brown_family_register_meta.txt",sep="\t",header=T,row.names = NULL,quote="")
d <- merge(d,d.meta)
d <- merge(d,d.reg.meta)

write.table(d,file = "data/distr_vfull_lemma-pos-reg-sc_brownfam-meta.txt",quote=FALSE,sep="\t",row.names = FALSE,col.names = T)

Data set with subcorpus sizes

• Query: []
• Download: Download query as plain-text tabulation
• Attributes: text_reg, text_sc
• Output option: sort and group output

The result should look like this: sample data set with subcorpus frequencies (register and corpora)

We will add the meta data to the subcorpus size file as well.

d <- read.table("data/brown_family_csizes.txt",header=F,sep="\t",row.names = NULL,quote="")
colnames(d) <- c("N","register","corpus")
d.meta <- read.table("data/brown_family_meta.txt",sep="\t",header=T,row.names = NULL,quote="")
d.reg.meta <- read.table("data/brown_family_register_meta.txt",sep="\t",header=T,row.names = NULL,quote="")
d <- merge(d,d.meta)
d <- merge(d,d.reg.meta)
write.table(d,file = "data/brown_family_csizes-meta.txt",quote=FALSE,sep="\t",row.names = FALSE,col.names = T)