230 ASSIGNMENT - 2

Author

FH-010:- Mahrab Kabir

Questions: 1

library(haven)
Warning: package 'haven' was built under R version 4.4.2
bdhs2014 <- read_dta("C:/Users/mkabi/Downloads/Compressed/bdhs2014.dta/bdhs2014.dta")
View(bdhs2014)
library(dplyr)
Warning: package 'dplyr' was built under R version 4.4.2

Attaching package: 'dplyr'
The following objects are masked from 'package:stats':

    filter, lag
The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union
library(tidyverse)
Warning: package 'tidyverse' was built under R version 4.4.2
Warning: package 'ggplot2' was built under R version 4.4.2
Warning: package 'tibble' was built under R version 4.4.2
Warning: package 'tidyr' was built under R version 4.4.2
Warning: package 'readr' was built under R version 4.4.2
Warning: package 'purrr' was built under R version 4.4.2
Warning: package 'forcats' was built under R version 4.4.2
Warning: package 'lubridate' was built under R version 4.4.2
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.0     ✔ readr     2.1.5
✔ ggplot2   3.5.1     ✔ stringr   1.5.1
✔ lubridate 1.9.4     ✔ tibble    3.2.1
✔ purrr     1.0.2     ✔ tidyr     1.3.1
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(labelled)
Warning: package 'labelled' was built under R version 4.4.2

1

print(sprintf("the bdhs2014 data have %s observations and variables",dim_desc(bdhs2014)))
[1] "the bdhs2014 data have [7,886 x 76] observations and variables"

2

bdhs2014 |>
  rename(religion = v130)
# A tibble: 7,886 × 76
   caseid   hidx v000   v001  v002  v003  v004  v008  v011  v012 v013    v015   
   <chr>   <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl+l> <dbl+l>
 1 "     …     1 BD6     306    29     2   306  1377  1066    25 3 [25-… 1 [com…
 2 "     …     1 BD6     568    87     7   568  1377  1161    18 1 [15-… 1 [com…
 3 "     …     1 BD6     298    37     4   298  1376  1076    25 3 [25-… 1 [com…
 4 "     …     1 BD6     289    95     2   289  1378  1100    23 2 [20-… 1 [com…
 5 "     …     1 BD6     337    25     2   337  1379   968    34 4 [30-… 1 [com…
 6 "     …     1 BD6     500    95     4   500  1376  1126    20 2 [20-… 1 [com…
 7 "     …     1 BD6      25   121     2    25  1375  1122    21 2 [20-… 1 [com…
 8 "     …     1 BD6     327    18     2   327  1375  1006    30 4 [30-… 1 [com…
 9 "     …     1 BD6     473    90     2   473  1376  1110    22 2 [20-… 1 [com…
10 "     …     1 BD6     473    69     2   473  1376  1068    25 3 [25-… 1 [com…
# ℹ 7,876 more rows
# ℹ 64 more variables: v020 <dbl+lbl>, v024 <dbl+lbl>, v025 <dbl+lbl>,
#   v102 <dbl+lbl>, v106 <dbl+lbl>, v107 <dbl+lbl>, v113 <dbl+lbl>,
#   v116 <dbl+lbl>, v119 <dbl+lbl>, v120 <dbl+lbl>, v121 <dbl+lbl>,
#   v122 <dbl+lbl>, v123 <dbl+lbl>, v124 <dbl+lbl>, v125 <dbl+lbl>,
#   v127 <dbl+lbl>, v128 <dbl+lbl>, v129 <dbl+lbl>, religion <dbl+lbl>,
#   v133 <dbl+lbl>, v135 <dbl+lbl>, v136 <dbl>, v137 <dbl>, v138 <dbl>, …

3

bdhs_age_20_plus <-
  bdhs2014 |>
    filter(v012 >25)

bdhs_age_20_plus
# A tibble: 3,547 × 76
   caseid   hidx v000   v001  v002  v003  v004  v008  v011  v012 v013    v015   
   <chr>   <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl+l> <dbl+l>
 1 "     …     1 BD6     337    25     2   337  1379   968    34 4 [30-… 1 [com…
 2 "     …     1 BD6     327    18     2   327  1375  1006    30 4 [30-… 1 [com…
 3 "     …     1 BD6      80    35     2    80  1377   982    32 4 [30-… 1 [com…
 4 "     …     1 BD6     213   106     2   213  1375   940    36 5 [35-… 1 [com…
 5 "     …     1 BD6      52    50     2    52  1375  1010    30 4 [30-… 1 [com…
 6 "     …     1 BD6     455   115     2   455  1377  1030    28 3 [25-… 1 [com…
 7 "     …     1 BD6     549    77     2   549  1375  1054    26 3 [25-… 1 [com…
 8 "     …     1 BD6      85    85     2    85  1376   952    35 5 [35-… 1 [com…
 9 "     …     1 BD6     210    19     2   210  1378   881    41 6 [40-… 1 [com…
10 "     …     1 BD6     512    40     7   512  1375  1051    27 3 [25-… 1 [com…
# ℹ 3,537 more rows
# ℹ 64 more variables: v020 <dbl+lbl>, v024 <dbl+lbl>, v025 <dbl+lbl>,
#   v102 <dbl+lbl>, v106 <dbl+lbl>, v107 <dbl+lbl>, v113 <dbl+lbl>,
#   v116 <dbl+lbl>, v119 <dbl+lbl>, v120 <dbl+lbl>, v121 <dbl+lbl>,
#   v122 <dbl+lbl>, v123 <dbl+lbl>, v124 <dbl+lbl>, v125 <dbl+lbl>,
#   v127 <dbl+lbl>, v128 <dbl+lbl>, v129 <dbl+lbl>, v130 <dbl+lbl>,
#   v133 <dbl+lbl>, v135 <dbl+lbl>, v136 <dbl>, v137 <dbl>, v138 <dbl>, …

4

  bdhs2014 |>
  mutate(age_gap = v730 - v012)|>
  select(caseid, v730, v012, age_gap)
# A tibble: 7,886 × 4
   caseid            v730       v012 age_gap
   <chr>             <dbl+lbl> <dbl>   <dbl>
 1 "      306 29  2" 32           25       7
 2 "      568 87  7" 25           18       7
 3 "      298 37  4" 35           25      10
 4 "      289 95  2" 40           23      17
 5 "      337 25  2" 48           34      14
 6 "      500 95  4" 26           20       6
 7 "       25121  2" 27           21       6
 8 "      327 18  2" 34           30       4
 9 "      473 90  2" 26           22       4
10 "      473 69  2" 35           25      10
# ℹ 7,876 more rows

5

bdhs2014 |>
  mutate(
    ecb = if_else(v212 < 18, 1,0)
    ) |>
  select(caseid, v212, ecb)
# A tibble: 7,886 × 3
   caseid             v212   ecb
   <chr>             <dbl> <dbl>
 1 "      306 29  2"    23     0
 2 "      568 87  7"    16     1
 3 "      298 37  4"    19     0
 4 "      289 95  2"    19     0
 5 "      337 25  2"    19     0
 6 "      500 95  4"    19     0
 7 "       25121  2"    15     1
 8 "      327 18  2"    21     0
 9 "      473 90  2"    16     1
10 "      473 69  2"    17     1
# ℹ 7,876 more rows

6

bdhs2014 |>
  mutate( 
    age_category = case_when(
      v012 >= 15 & v012 < 17 ~ "[15-17)",
      v012 >= 18 & v012 < 19 ~ "[18-19)",
      v012 >= 20 & v012 < 29 ~ "[20-29)",
      v012 >= 30 & v012 < 39 ~ "[30-39)",
      v012 >= 40 & v012 < 50 ~ "[40-50)"
    )
  ) |> 
  select(caseid, v012, age_category)
# A tibble: 7,886 × 3
   caseid             v012 age_category
   <chr>             <dbl> <chr>       
 1 "      306 29  2"    25 [20-29)     
 2 "      568 87  7"    18 [18-19)     
 3 "      298 37  4"    25 [20-29)     
 4 "      289 95  2"    23 [20-29)     
 5 "      337 25  2"    34 [30-39)     
 6 "      500 95  4"    20 [20-29)     
 7 "       25121  2"    21 [20-29)     
 8 "      327 18  2"    30 [30-39)     
 9 "      473 90  2"    22 [20-29)     
10 "      473 69  2"    25 [20-29)     
# ℹ 7,876 more rows

7

bdhs2014 |>
  arrange(v002)
# A tibble: 7,886 × 76
   caseid   hidx v000   v001  v002  v003  v004  v008  v011  v012 v013    v015   
   <chr>   <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl+l> <dbl+l>
 1 "     …     2 BD6     370     1     2   370  1377  1117    21 2 [20-… 1 [com…
 2 "     …     1 BD6      36     1     3    36  1376  1115    21 2 [20-… 1 [com…
 3 "     …     1 BD6      59     1     2    59  1377  1073    25 3 [25-… 1 [com…
 4 "     …     1 BD6       9     1     3     9  1376  1135    20 2 [20-… 1 [com…
 5 "     …     1 BD6     160     1     2   160  1377   931    37 5 [35-… 1 [com…
 6 "     …     1 BD6     397     1     2   397  1378   999    31 4 [30-… 1 [com…
 7 "     …     1 BD6     370     1     2   370  1377  1117    21 2 [20-… 1 [com…
 8 "     …     1 BD6     510     1     6   510  1378   999    31 4 [30-… 1 [com…
 9 "     …     1 BD6      89     1     2    89  1375   956    34 4 [30-… 1 [com…
10 "     …     1 BD6      87     1    11    87  1375  1142    19 1 [15-… 1 [com…
# ℹ 7,876 more rows
# ℹ 64 more variables: v020 <dbl+lbl>, v024 <dbl+lbl>, v025 <dbl+lbl>,
#   v102 <dbl+lbl>, v106 <dbl+lbl>, v107 <dbl+lbl>, v113 <dbl+lbl>,
#   v116 <dbl+lbl>, v119 <dbl+lbl>, v120 <dbl+lbl>, v121 <dbl+lbl>,
#   v122 <dbl+lbl>, v123 <dbl+lbl>, v124 <dbl+lbl>, v125 <dbl+lbl>,
#   v127 <dbl+lbl>, v128 <dbl+lbl>, v129 <dbl+lbl>, v130 <dbl+lbl>,
#   v133 <dbl+lbl>, v135 <dbl+lbl>, v136 <dbl>, v137 <dbl>, v138 <dbl>, …

8

bdhs2014 |>
  select(v012) |>
  summarise(
    mean_age = mean(v012),
    median_age = median(v012),
    mode_age = mode(v012),
    min_age = min(v012),
    max_age = max(v012),
    sd_age = sd(v012),
    iqr_age = IQR(v012)
    ) 
# A tibble: 1 × 7
  mean_age median_age mode_age min_age max_age sd_age iqr_age
     <dbl>      <dbl> <chr>      <dbl>   <dbl>  <dbl>   <dbl>
1     25.5         25 numeric       15      49   5.87       8

9

bdhs2014 |>
  mutate(
    ecb = if_else(v212 < 18, 1,0)
    )|>
  count(ecb)
# A tibble: 2 × 2
    ecb     n
  <dbl> <int>
1     0  4310
2     1  3576
bdhs2014 |>
  mutate( 
    age_category = case_when(
      v012 >= 15 & v012 < 17 ~ "[15-17)",
      v012 >= 18 & v012 < 19 ~ "[18-19)",
      v012 >= 20 & v012 < 29 ~ "[20-29)",
      v012 >= 30 & v012 < 39 ~ "[30-39)",
      v012 >= 40 & v012 < 50 ~ "[40-50)"
    )
  ) |>
  count(age_category)
# A tibble: 6 × 2
  age_category     n
  <chr>        <int>
1 [15-17)        163
2 [18-19)        329
3 [20-29)       4517
4 [30-39)       1650
5 [40-50)        152
6 <NA>          1075
bdhs2014 |>
  rename(religion = v130)|>
  count(religion)
# A tibble: 5 × 2
  religion              n
  <dbl+lbl>         <int>
1  1 [islam]         7249
2  2 [hinduism]       576
3  3 [buddhism]        47
4  4 [christianity]    13
5 96 [other]            1
bdhs2014 |>
  rename(welath_index = v190) |>
  count(welath_index)
# A tibble: 5 × 2
  welath_index     n
  <dbl+lbl>    <int>
1 1 [poorest]   1737
2 2 [poorer]    1503
3 3 [middle]    1516
4 4 [richer]    1602
5 5 [richest]   1528

10

bdhs2014 |>
  count(v106, v025)
# A tibble: 8 × 3
  v106             v025          n
  <dbl+lbl>        <dbl+lbl> <int>
1 0 [no education] 1 [urban]   309
2 0 [no education] 2 [rural]   924
3 1 [primary]      1 [urban]   592
4 1 [primary]      2 [rural]  1614
5 2 [secondary]    1 [urban]  1138
6 2 [secondary]    2 [rural]  2483
7 3 [higher]       1 [urban]   449
8 3 [higher]       2 [rural]   377

Question 2

library(dplyr)
data(starwars)
glimpse(starwars)
Rows: 87
Columns: 14
$ name       <chr> "Luke Skywalker", "C-3PO", "R2-D2", "Darth Vader", "Leia Or…
$ height     <int> 172, 167, 96, 202, 150, 178, 165, 97, 183, 182, 188, 180, 2…
$ mass       <dbl> 77.0, 75.0, 32.0, 136.0, 49.0, 120.0, 75.0, 32.0, 84.0, 77.…
$ hair_color <chr> "blond", NA, NA, "none", "brown", "brown, grey", "brown", N…
$ skin_color <chr> "fair", "gold", "white, blue", "white", "light", "light", "…
$ eye_color  <chr> "blue", "yellow", "red", "yellow", "brown", "blue", "blue",…
$ birth_year <dbl> 19.0, 112.0, 33.0, 41.9, 19.0, 52.0, 47.0, NA, 24.0, 57.0, …
$ sex        <chr> "male", "none", "none", "male", "female", "male", "female",…
$ gender     <chr> "masculine", "masculine", "masculine", "masculine", "femini…
$ homeworld  <chr> "Tatooine", "Tatooine", "Naboo", "Tatooine", "Alderaan", "T…
$ species    <chr> "Human", "Droid", "Droid", "Human", "Human", "Human", "Huma…
$ films      <list> <"A New Hope", "The Empire Strikes Back", "Return of the J…
$ vehicles   <list> <"Snowspeeder", "Imperial Speeder Bike">, <>, <>, <>, "Imp…
$ starships  <list> <"X-wing", "Imperial shuttle">, <>, <>, "TIE Advanced x1",…

####1

starwars |>
  count(name) |>
  summarise(total_humans = sum(n))
# A tibble: 1 × 1
  total_humans
         <int>
1           87

2

starwars |>
  count(gender)
# A tibble: 3 × 2
  gender        n
  <chr>     <int>
1 feminine     17
2 masculine    66
3 <NA>          4

3

starwars |>
  summarise("Most individuals" = max(homeworld, na.rm=T)) 
# A tibble: 1 × 1
  `Most individuals`
  <chr>             
1 Zolan

4

starwars |>
  filter(eye_color == "orange") |>
  summarise("Mean height of all individuals with orange eyes" = mean(height))
# A tibble: 1 × 1
  `Mean height of all individuals with orange eyes`
                                              <dbl>
1                                              180.

5

starwars |>
  filter(species == "Droid") |>
  summarise(
    "Median height for all droids" = median(height, na.rm=T),
    "Mean height for all droids" = mean(height, na.rm=T),
    "standard deviation of height for all droids" = sd(height, na.rm=T)
    )
# A tibble: 1 × 3
  `Median height for all droids` Mean height for all dr…¹ standard deviation o…²
                           <int>                    <dbl>                  <dbl>
1                             97                     131.                   49.1
# ℹ abbreviated names: ¹​`Mean height for all droids`,
#   ²​`standard deviation of height for all droids`