Data Frames

Data Input

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)

Data Manipulation

First, add a boolean column stating if the winner is taller or not:

isWinnerTaller= winner > opponent

Count how many times the winner has been taller than the opponent:

sum(isWinnerTaller)

## [1] 11

Create a data frame including all the created columns:

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

Return only the first 6 rows of the data frame:

head(df_presidents)

Return the structure of the data frame:

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 ...

Return all the column names of the data frame:

colnames(df_presidents)

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

Return the number of columns of the data frame:

ncol(df_presidents)

## [1] 5

Return the number of rows of the data frame:

nrow(df_presidents)

## [1] 16

Create a new column “difference” that calculates the height difference between the winner and the opponent:

df_presidents$difference = winner - opponent

Return a new data frame that deletes column no. 6 which is the newly generated “difference column

df_presidents [ , -6]

In order to save this change, update df_presidents to this new data frame:

df_presidents = df_presidents [, -6]

Return the new changed data frame:

df_presidents

Add the difference column again:

df_presidents$difference = winner - opponent

Finally, delete the column again. This time using the column name specifically:

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

Print the final data frame (not including the difference column since it got deleted):

df_presidents

Indexing a Data Frame

Return the second column of the data frame

df_presidents[ , 2]

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

# alternative 2: df_presidents [, 'year']

# alternative 3: df_presidents$year

Return the last column:

df_presidents[ , ncol(df_presidents)]

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

# alternative: df_presidents[ , 5]

Return a subset of the data including the first 3 rows and rows 3 and 4:

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

# alternative: df_presidents [1:3 , c(3,4)]

Some useful functions to work with data frames

Use the subset() function to get the rows from the data frame where the Winner > Opponent

subset (df_presidents, df_presidents$isWinnerTaller==TRUE)

# or, more succinct: subset (df_presidents, isWinnerTaller)

Get the winners’ names only for cases when Winner > Opponent

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

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

Add a new column “party”:

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

Put the column party in the data frame, calling it “presid_party”:

df_presidents$presid_party= party
df_presidents

Return the mean of the winners` height, separated by party:

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

##      Dem      Rep 
## 184.1429 182.6667

Return the max of the winners` height, separated by party:

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

## Dem Rep 
## 193 188

Return the mean heights, separated by winner and opponent:

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

##   winner opponent 
## 183.3125 181.0625

# alternative: colMeans (df_presidents [, c("winner", "opponent")])

Return the standard deviation of the heights, separated by winner and opponent:

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

##   winner opponent 
## 4.629165 5.579352

Print the standard deviation of “winner” individually:

sd(df_presidents [, "winner"])

## [1] 4.629165

Print the standard deviation of “opponent” individually:

sd(df_presidents [, "opponent"])

## [1] 5.579352