Getting Data In and Out of R

R Programming for Data Science

# install.packages('tinytex')
# tinytex::install_tinytex()  # install TinyTeX

\[\int{\dfrac{5x^2}{3x+2}}dx\]

Reference

R Programming for Data Science by Roger D. Peng, May 31, 2022

Textbook

1 Reading and Writing Data

1.1 Functions for reading data in R

• read.table, read.csv, for reading tabular data

• readLines, for reading lines of a text file

• source, for reading in R code files (inverse of dump)

• dget, for reading in R code files (inverse of dput)

• load, for reading in saved workspaces

• unserialize, for reading single R objects in binary form

team_standing <- read.csv("team_standings.csv")
str(team_standing)

'data.frame':   32 obs. of  2 variables:
 $ Standing: int  1 2 3 4 5 6 7 8 9 10 ...
 $ Team    : chr  "Spain" "Netherlands" "Germany" "Uruguay" ...

team_standing

head(team_standing, 10)

tail(team_standing,5)

little_mermaid <- read.table("little_mermaid.txt",
                             col.names = "The_Little_Mermaid")
little_mermaid

1.2 Functions for writing data in R

• write.table, for writing tabular data to text files (i.e. CSV) or connections

• writeLines, for writing character data line-by-line to a file or connection

• dump, for dumping a textual representation of multiple R objects

• dput, for outputting a textual representation of an R object

• save, for saving an arbitrary number of R objects in binary format (possibly compressed) to a file.

• serialize, for converting an R object into a binary format for outputting to a connection (or file).

str(iris)

'data.frame':   150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

iris

write.csv(x = iris,
          file = "iris.csv",
          row.names = FALSE)

str(swiss)

'data.frame':   47 obs. of  6 variables:
 $ Fertility       : num  80.2 83.1 92.5 85.8 76.9 76.1 83.8 92.4 82.4 82.9 ...
 $ Agriculture     : num  17 45.1 39.7 36.5 43.5 35.3 70.2 67.8 53.3 45.2 ...
 $ Examination     : int  15 6 5 12 17 9 16 14 12 16 ...
 $ Education       : int  12 9 5 7 15 7 7 8 7 13 ...
 $ Catholic        : num  9.96 84.84 93.4 33.77 5.16 ...
 $ Infant.Mortality: num  22.2 22.2 20.2 20.3 20.6 26.6 23.6 24.9 21 24.4 ...

write.table(x = swiss,
            file = "swiss.txt",
            sep = ";",
            row.names = FALSE)

swiss_v2 <- read.table(file = "swiss.txt",
                       header = TRUE,
                       sep = ";")
swiss_v2

1.3 Reading in Larger Datasets

initial <- read.table("president2022_05131447.csv",
                      sep = ",",
                      nrows = 100,
                      header = TRUE)

head(initial)

str(initial)

'data.frame':   100 obs. of  23 variables:
 $ PRECINCT_CODE      : int  1010017 1010017 1010017 1010017 1010017 1010017 1010017 1010017 1010017 1010017 ...
 $ CONTEST_CODE       : int  199000 199000 199000 199000 199000 199000 199000 199000 199000 199000 ...
 $ CANDIDATE_CODE     : num  9.9e+09 9.9e+09 9.9e+09 9.9e+09 9.9e+09 ...
 $ PARTY_CODE         : int  35 180 36 3 38 22 182 16 1 180 ...
 $ VOTES_AMOUNT       : int  1 0 0 7 5 17 616 0 3 31 ...
 $ TOTALIZATION_ORDER : int  4 1 2 3 5 6 7 8 9 10 ...
 $ NUMBER_VOTERS      : int  697 697 697 697 697 697 697 697 697 697 ...
 $ UNDERVOTE          : int  2 2 2 2 2 2 2 2 2 2 ...
 $ OVERVOTE           : int  15 15 15 15 15 15 15 15 15 15 ...
 $ RECEPTION_DATE     : chr  "05/09/2022 - 08:07:08 PM" "05/09/2022 - 08:07:08 PM" "05/09/2022 - 08:07:08 PM" "05/09/2022 - 08:07:08 PM" ...
 $ CONTEST_NAME       : chr  "PRESIDENT PHILIPPINES" "PRESIDENT PHILIPPINES" "PRESIDENT PHILIPPINES" "PRESIDENT PHILIPPINES" ...
 $ CANDIDATE_NAME     : chr  "GONZALES, NORBERTO (PDSP)" "ABELLA, ERNIE (IND)" "DE GUZMAN, LEODY (PLM)" "DOMAGOSO, ISKO MORENO (AKSYON)" ...
 $ PARTIES_NAME       : chr  "PARTIDO DEMOKRATIKO SOSYALISTA NG PILIPINAS" "INDEPENDENT" "PARTIDO LAKAS NG MASA" "AKSYON DEMOKRATIKO" ...
 $ PARTIES_ALIAS      : chr  "PDSP" "IND" "PLM" "AKSYON" ...
 $ REGION             : chr  "CAR" "CAR" "CAR" "CAR" ...
 $ PROVINCE           : chr  "ABRA" "ABRA" "ABRA" "ABRA" ...
 $ MUNICIPALITY       : chr  "BANGUED" "BANGUED" "BANGUED" "BANGUED" ...
 $ BARANGAY           : chr  "AGTANGAO" "AGTANGAO" "AGTANGAO" "AGTANGAO" ...
 $ CLUSTER            : int  17 17 17 17 17 17 17 17 17 17 ...
 $ CLUSTERTOTAL       : int  783 783 783 783 783 783 783 783 783 783 ...
 $ CLUSTERED_PRECINCTS: chr  "0045A, 0045B, 0050A, 0050B" "0045A, 0045B, 0050A, 0050B" "0045A, 0045B, 0050A, 0050B" "0045A, 0045B, 0050A, 0050B" ...
 $ POLLINGCENTER      : chr  "AGTANGAO ELEMENTARY SCHOOL, AGTANGAO, BANGUED, ABRA" "AGTANGAO ELEMENTARY SCHOOL, AGTANGAO, BANGUED, ABRA" "AGTANGAO ELEMENTARY SCHOOL, AGTANGAO, BANGUED, ABRA" "AGTANGAO ELEMENTARY SCHOOL, AGTANGAO, BANGUED, ABRA" ...
 $ DISTRICT           : chr  "ABRA - LONE DISTRICT" "ABRA - LONE DISTRICT" "ABRA - LONE DISTRICT" "ABRA - LONE DISTRICT" ...

classes <- sapply(initial, class)
classes

      PRECINCT_CODE        CONTEST_CODE      CANDIDATE_CODE          PARTY_CODE        VOTES_AMOUNT 
          "integer"           "integer"           "numeric"           "integer"           "integer" 
 TOTALIZATION_ORDER       NUMBER_VOTERS           UNDERVOTE            OVERVOTE      RECEPTION_DATE 
          "integer"           "integer"           "integer"           "integer"         "character" 
       CONTEST_NAME      CANDIDATE_NAME        PARTIES_NAME       PARTIES_ALIAS              REGION 
        "character"         "character"         "character"         "character"         "character" 
           PROVINCE        MUNICIPALITY            BARANGAY             CLUSTER        CLUSTERTOTAL 
        "character"         "character"         "character"           "integer"           "integer" 
CLUSTERED_PRECINCTS       POLLINGCENTER            DISTRICT 
        "character"         "character"         "character" 

library(tictoc)

tic()
pres2022 <- read.csv("president2022_05131447.csv")
toc()

25.92 sec elapsed

dim(pres2022)

[1] 1060080      23

names(pres2022)

 [1] "PRECINCT_CODE"       "CONTEST_CODE"        "CANDIDATE_CODE"      "PARTY_CODE"         
 [5] "VOTES_AMOUNT"        "TOTALIZATION_ORDER"  "NUMBER_VOTERS"       "UNDERVOTE"          
 [9] "OVERVOTE"            "RECEPTION_DATE"      "CONTEST_NAME"        "CANDIDATE_NAME"     
[13] "PARTIES_NAME"        "PARTIES_ALIAS"       "REGION"              "PROVINCE"           
[17] "MUNICIPALITY"        "BARANGAY"            "CLUSTER"             "CLUSTERTOTAL"       
[21] "CLUSTERED_PRECINCTS" "POLLINGCENTER"       "DISTRICT"           

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ──────────────────────────────────────────────────────────── tidyverse 1.3.2 ──✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
✔ tibble  3.1.8      ✔ dplyr   1.0.10
✔ tidyr   1.2.1      ✔ stringr 1.4.1 
✔ readr   2.1.2      ✔ forcats 0.5.2 ── Conflicts ─────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

pres2022 %>%
  filter(PROVINCE == "NEGROS ORIENTAL") %>%
  group_by(CANDIDATE_NAME) %>%
  summarise(VOTES_AMOUNT = sum(VOTES_AMOUNT)) %>%
  ungroup() %>%
  arrange(desc(VOTES_AMOUNT))

1.4 Calculating Memory Requirements

paste(1060080 * 23 * 8, "bytes")

[1] "195054720 bytes"

paste(195054720 / 2^{20}, "MB")

[1] "186.018676757812 MB"