jm3.qmd

library(readr)
train <- read_csv("train.csv")

Rows: 891 Columns: 12
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (5): Name, Sex, Ticket, Cabin, Embarked
dbl (7): PassengerId, Survived, Pclass, Age, SibSp, Parch, Fare

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(train)

# A tibble: 6 × 12
  PassengerId Survived Pclass Name    Sex     Age SibSp Parch Ticket  Fare Cabin
        <dbl>    <dbl>  <dbl> <chr>   <chr> <dbl> <dbl> <dbl> <chr>  <dbl> <chr>
1           1        0      3 Braund… male     22     1     0 A/5 2…  7.25 <NA> 
2           2        1      1 Cuming… fema…    38     1     0 PC 17… 71.3  C85  
3           3        1      3 Heikki… fema…    26     0     0 STON/…  7.92 <NA> 
4           4        1      1 Futrel… fema…    35     1     0 113803 53.1  C123 
5           5        0      3 Allen,… male     35     0     0 373450  8.05 <NA> 
6           6        0      3 Moran,… male     NA     0     0 330877  8.46 <NA> 
# ℹ 1 more variable: Embarked <chr>

?head
tail(train)

# A tibble: 6 × 12
  PassengerId Survived Pclass Name    Sex     Age SibSp Parch Ticket  Fare Cabin
        <dbl>    <dbl>  <dbl> <chr>   <chr> <dbl> <dbl> <dbl> <chr>  <dbl> <chr>
1         886        0      3 "Rice,… fema…    39     0     5 382652 29.1  <NA> 
2         887        0      2 "Montv… male     27     0     0 211536 13    <NA> 
3         888        1      1 "Graha… fema…    19     0     0 112053 30    B42  
4         889        0      3 "Johns… fema…    NA     1     2 W./C.… 23.4  <NA> 
5         890        1      1 "Behr,… male     26     0     0 111369 30    C148 
6         891        0      3 "Doole… male     32     0     0 370376  7.75 <NA> 
# ℹ 1 more variable: Embarked <chr>

train[ 500:515, ]

# A tibble: 16 × 12
   PassengerId Survived Pclass Name  Sex     Age SibSp Parch Ticket   Fare Cabin
         <dbl>    <dbl>  <dbl> <chr> <chr> <dbl> <dbl> <dbl> <chr>   <dbl> <chr>
 1         500        0      3 "Sve… male     24     0     0 350035   7.80 <NA> 
 2         501        0      3 "Cal… male     17     0     0 315086   8.66 <NA> 
 3         502        0      3 "Can… fema…    21     0     0 364846   7.75 <NA> 
 4         503        0      3 "O'S… fema…    NA     0     0 330909   7.63 <NA> 
 5         504        0      3 "Lai… fema…    37     0     0 4135     9.59 <NA> 
 6         505        1      1 "Mai… fema…    16     0     0 110152  86.5  B79  
 7         506        0      1 "Pen… male     18     1     0 PC 17… 109.   C65  
 8         507        1      2 "Qui… fema…    33     0     2 26360   26    <NA> 
 9         508        1      1 "Bra… male     NA     0     0 111427  26.6  <NA> 
10         509        0      3 "Ols… male     28     0     0 C 4001  22.5  <NA> 
11         510        1      3 "Lan… male     26     0     0 1601    56.5  <NA> 
12         511        1      3 "Dal… male     29     0     0 382651   7.75 <NA> 
13         512        0      3 "Web… male     NA     0     0 SOTON…   8.05 <NA> 
14         513        1      1 "McG… male     36     0     0 PC 17…  26.3  E25  
15         514        1      1 "Rot… fema…    54     1     0 PC 17…  59.4  <NA> 
16         515        0      3 "Col… male     24     0     0 349209   7.50 <NA> 
# ℹ 1 more variable: Embarked <chr>

train[ 490:495, 1:2]

# A tibble: 6 × 2
  PassengerId Survived
        <dbl>    <dbl>
1         490        1
2         491        0
3         492        0
4         493        0
5         494        0
6         495        0

train[ 490:495, c(1,5)]

# A tibble: 6 × 2
  PassengerId Sex  
        <dbl> <chr>
1         490 male 
2         491 male 
3         492 male 
4         493 male 
5         494 male 
6         495 male 

str(train)

spc_tbl_ [891 × 12] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ PassengerId: num [1:891] 1 2 3 4 5 6 7 8 9 10 ...
 $ Survived   : num [1:891] 0 1 1 1 0 0 0 0 1 1 ...
 $ Pclass     : num [1:891] 3 1 3 1 3 3 1 3 3 2 ...
 $ Name       : chr [1:891] "Braund, Mr. Owen Harris" "Cumings, Mrs. John Bradley (Florence Briggs Thayer)" "Heikkinen, Miss. Laina" "Futrelle, Mrs. Jacques Heath (Lily May Peel)" ...
 $ Sex        : chr [1:891] "male" "female" "female" "female" ...
 $ Age        : num [1:891] 22 38 26 35 35 NA 54 2 27 14 ...
 $ SibSp      : num [1:891] 1 1 0 1 0 0 0 3 0 1 ...
 $ Parch      : num [1:891] 0 0 0 0 0 0 0 1 2 0 ...
 $ Ticket     : chr [1:891] "A/5 21171" "PC 17599" "STON/O2. 3101282" "113803" ...
 $ Fare       : num [1:891] 7.25 71.28 7.92 53.1 8.05 ...
 $ Cabin      : chr [1:891] NA "C85" NA "C123" ...
 $ Embarked   : chr [1:891] "S" "C" "S" "S" ...
 - attr(*, "spec")=
  .. cols(
  ..   PassengerId = col_double(),
  ..   Survived = col_double(),
  ..   Pclass = col_double(),
  ..   Name = col_character(),
  ..   Sex = col_character(),
  ..   Age = col_double(),
  ..   SibSp = col_double(),
  ..   Parch = col_double(),
  ..   Ticket = col_character(),
  ..   Fare = col_double(),
  ..   Cabin = col_character(),
  ..   Embarked = col_character()
  .. )
 - attr(*, "problems")=<externalptr> 

install.packages("visdat")

Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
(as 'lib' is unspecified)

library(visdat)
vis_dat(train)