library(languageR)
#Exercise 1:
spanishMeta
## Author YearOfBirth TextName PubDate Nwords FullName
## 1 C 1916 X14458gll 1983 2972 Cela
## 2 C 1916 X14459gll 1951 3040 Cela
## 3 C 1916 X14460gll 1956 3066 Cela
## 4 C 1916 X14461gll 1948 3044 Cela
## 5 C 1916 X14462gll 1942 3053 Cela
## 6 M 1943 X14463gll 1986 3013 Mendoza
## 7 M 1943 X14464gll 1992 3049 Mendoza
## 8 M 1943 X14465gll 1989 3042 Mendoza
## 9 M 1943 X14466gll 1982 3039 Mendoza
## 10 M 1943 X14467gll 2002 3045 Mendoza
## 11 V 1936 X14472gll 1965 3037 VargasLLosa
## 12 V 1936 X14473gll 1963 3067 VargasLLosa
## 13 V 1936 X14474gll 1977 3020 VargasLLosa
## 14 V 1936 X14475gll 1987 3016 VargasLLosa
## 15 V 1936 X14476gll 1981 3054 VargasLLosa
colnames(spanishMeta)
## [1] "Author" "YearOfBirth" "TextName" "PubDate" "Nwords"
## [6] "FullName"
nrow(spanishMeta)
## [1] 15
#Exercise 2:
xtabs(~spanishMeta$FullName, data = spanishMeta)
## spanishMeta$FullName
## Cela Mendoza VargasLLosa
## 5 5 5
with(spanishMeta, tapply(PubDate, list(FullName), mean))
## Cela Mendoza VargasLLosa
## 1956.0 1990.2 1974.6
#Exercise 3:
spanishMeta[order(spanishMeta$YearOfBirth, spanishMeta$Nwords), ]
## Author YearOfBirth TextName PubDate Nwords FullName
## 1 C 1916 X14458gll 1983 2972 Cela
## 2 C 1916 X14459gll 1951 3040 Cela
## 4 C 1916 X14461gll 1948 3044 Cela
## 5 C 1916 X14462gll 1942 3053 Cela
## 3 C 1916 X14460gll 1956 3066 Cela
## 14 V 1936 X14475gll 1987 3016 VargasLLosa
## 13 V 1936 X14474gll 1977 3020 VargasLLosa
## 11 V 1936 X14472gll 1965 3037 VargasLLosa
## 15 V 1936 X14476gll 1981 3054 VargasLLosa
## 12 V 1936 X14473gll 1963 3067 VargasLLosa
## 6 M 1943 X14463gll 1986 3013 Mendoza
## 9 M 1943 X14466gll 1982 3039 Mendoza
## 8 M 1943 X14465gll 1989 3042 Mendoza
## 10 M 1943 X14467gll 2002 3045 Mendoza
## 7 M 1943 X14464gll 1992 3049 Mendoza
#Exercise 4:
spanishMeta$PubDate -> PubDate.v
PubDate.v = sort(PubDate.v)
help(sort)
sort(PubDate.v, decreasing = T) -> PubDate.v
#The question here says "sort the row names of meta"
#the rownames are just integers so I'm sorting the colnames #instead:
sort(colnames(spanishMeta))
## [1] "Author" "FullName" "Nwords" "PubDate" "TextName"
## [6] "YearOfBirth"
#Exercise 5:
spanishMeta[spanishMeta$PubDate < 1980, ]
## Author YearOfBirth TextName PubDate Nwords FullName
## 2 C 1916 X14459gll 1951 3040 Cela
## 3 C 1916 X14460gll 1956 3066 Cela
## 4 C 1916 X14461gll 1948 3044 Cela
## 5 C 1916 X14462gll 1942 3053 Cela
## 11 V 1936 X14472gll 1965 3037 VargasLLosa
## 12 V 1936 X14473gll 1963 3067 VargasLLosa
## 13 V 1936 X14474gll 1977 3020 VargasLLosa
#Exercise 6:
mean(spanishMeta$PubDate)
## [1] 1973.6
sum(spanishMeta$PubDate) / length(spanishMeta$PubDate)
## [1] 1973.6
#Exercise 7:
composer = data.frame(Author = c("Cela", "Mendoza", "VargasLLosa"), Favorite = c("Stravinsky", "Bach", "Villa-Lobos"))
newSpanishMeta = merge(spanishMeta, composer, by.x = "FullName", by.y = "Author")
summary(cars)
## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00