R Notebook

# Just copy the data in the file and paste it here. Then, run this code chunk to create the vectors

presid_name= c("Obama","Bush","Bush","Clinton","Clinton","Bush Father","Reagan","Reagan","Carter","Nixon","Nixon","Johnson","Kennedy","Eisenhower","Eisenhower","Truman")

winner = c(185, 182, 182, 188, 188, 188, 185, 185, 177, 182, 182, 193, 183, 179, 179, 175)

opponent = c(175, 193, 185, 187, 188, 173, 180, 177, 183, 185, 180, 180, 182, 178, 178, 173)

year= seq (from= 2008, to= 1948, by=-4)

isWinnerTaller= winner > opponent

isWinnerTaller

##  [1]  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE FALSE FALSE  TRUE  TRUE
## [13]  TRUE  TRUE  TRUE  TRUE

sum(isWinnerTaller)

## [1] 11

df_presidents= data.frame(presid_name, year, winner, opponent, isWinnerTaller)
df_presidents

head(df_presidents)

str(df_presidents)

## 'data.frame':    16 obs. of  5 variables:
##  $ presid_name   : chr  "Obama" "Bush" "Bush" "Clinton" ...
##  $ year          : num  2008 2004 2000 1996 1992 ...
##  $ winner        : num  185 182 182 188 188 188 185 185 177 182 ...
##  $ opponent      : num  175 193 185 187 188 173 180 177 183 185 ...
##  $ isWinnerTaller: logi  TRUE FALSE FALSE TRUE FALSE TRUE ...

colnames(df_presidents)

## [1] "presid_name"    "year"           "winner"         "opponent"      
## [5] "isWinnerTaller"

ncol(df_presidents)

## [1] 5

nrow(df_presidents)

## [1] 16

df_presidents$difference = winner - opponent
df_presidents

df_presidents[,-6]

df_presidents

df_presidents[ , colnames(df_presidents) != 'difference' ]

df_presidents= df_presidents[ , colnames(df_presidents) != 'difference' ]

df_presidents

df_presidents[ , 2]

##  [1] 2008 2004 2000 1996 1992 1988 1984 1980 1976 1972 1968 1964 1960 1956 1952
## [16] 1948

df_presidents[1,]

df_presidents[ , ncol(df_presidents)]

##  [1]  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE FALSE FALSE  TRUE  TRUE
## [13]  TRUE  TRUE  TRUE  TRUE

df_presidents [c(1,2,3), c(3,4)]

subset (df_presidents, df_presidents$isWinnerTaller==TRUE)

subset (df_presidents$presid_name, df_presidents$isWinnerTaller==TRUE)

##  [1] "Obama"       "Clinton"     "Bush Father" "Reagan"      "Reagan"     
##  [6] "Nixon"       "Johnson"     "Kennedy"     "Eisenhower"  "Eisenhower" 
## [11] "Truman"

party= c("Dem", "Rep", "Rep", "Dem", "Dem", "Rep", "Rep", "Rep", "Dem","Rep","Rep","Dem","Dem","Rep","Rep","Dem")

df_presidents$presid_party= party
df_presidents

tapply (df_presidents$winner, df_presidents$presid_party, mean)

##      Dem      Rep 
## 184.1429 182.6667

tapply (df_presidents$winner, df_presidents$presid_party, max)

## Dem Rep 
## 193 188

apply (df_presidents [, c("winner", "opponent")] ,2, mean)

##   winner opponent 
## 183.3125 181.0625

colMeans (df_presidents [, c("winner", "opponent")])

##   winner opponent 
## 183.3125 181.0625

apply (df_presidents [, c("winner", "opponent")] , 2, sd)

##   winner opponent 
## 4.629165 5.579352

sd(df_presidents [, "winner"])

## [1] 4.629165

sd(df_presidents [, "opponent"])

## [1] 5.579352