library(readr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionoptions(repos = c(CRAN = “https://cran.rstudio.com”))
if (!requireNamespace(“DT”, quietly = TRUE)) { install.packages(“DT”, dependencies = TRUE) }
mydata <- read_delim("C:\\Users\\abhir\\OneDrive\\Documents\\luddy\\H510-Stats,R\\adult.csv", delim = ",")## Rows: 32561 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): Work-Class, Education, Marital Status, Occupation, Relationship, Ra...
## dbl (6): Age, Fnl_Wgt, Education_Level, Capital_Gain, Capital_Loss, hrs_week
##
## 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.spec(mydata)## cols(
## Age = col_double(),
## `Work-Class` = col_character(),
## Fnl_Wgt = col_double(),
## Education = col_character(),
## Education_Level = col_double(),
## `Marital Status` = col_character(),
## Occupation = col_character(),
## Relationship = col_character(),
## Race = col_character(),
## Sex = col_character(),
## Capital_Gain = col_double(),
## Capital_Loss = col_double(),
## hrs_week = col_double(),
## Country = col_character(),
## Annual_pay = col_character()
## )mydata## # A tibble: 32,561 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 39 " State-gov" 77516 " Bachelo… 13 " Never-married"
## 2 50 " Self-emp-not-inc" 83311 " Bachelo… 13 " Married-civ-s…
## 3 38 " Private" 215646 " HS-grad" 9 " Divorced"
## 4 53 " Private" 234721 " 11th" 7 " Married-civ-s…
## 5 28 " Private" 338409 " Bachelo… 13 " Married-civ-s…
## 6 37 " Private" 284582 " Masters" 14 " Married-civ-s…
## 7 49 " Private" 160187 " 9th" 5 " Married-spous…
## 8 52 " Self-emp-not-inc" 209642 " HS-grad" 9 " Married-civ-s…
## 9 31 " Private" 45781 " Masters" 14 " Never-married"
## 10 42 " Private" 159449 " Bachelo… 13 " Married-civ-s…
## # ℹ 32,551 more rows
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>library(dplyr)
df <- mydata
num_samples <- 5
sample_size <- round(0.5 * nrow(df))
sample_list <- list()
for (i in 1:num_samples) {
sample_data <- df %>% sample_n(sample_size, replace = FALSE)
sample_list[[i]] <- sample_data
}
for (i in 1:num_samples) {
cat("Sample", i, ":\n")
print(head(sample_list[[i]]))
cat("\n")
}## Sample 1 :
## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 62 " Local-gov" 115763 " Masters" 14 " Married-civ-s…
## 2 39 " Self-emp-inc" 216473 " Bachelors" 13 " Married-civ-s…
## 3 49 " Private" 334787 " HS-grad" 9 " Married-civ-s…
## 4 27 " Private" 167336 " Some-college" 10 " Never-married"
## 5 58 " Private" 175127 " 12th" 8 " Married-civ-s…
## 6 55 " State-gov" 136819 " HS-grad" 9 " Married-civ-s…
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>
##
## Sample 2 :
## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 19 " Private" 170720 " HS-grad" 9 " Never-married"
## 2 46 " Private" 328669 " Assoc-vo… 11 " Married-civ-s…
## 3 35 " Private" 105138 " Bachelor… 13 " Married-civ-s…
## 4 38 " Self-emp-inc" 125324 " Some-col… 10 " Married-civ-s…
## 5 23 " Private" 278107 " HS-grad" 9 " Married-civ-s…
## 6 55 " Self-emp-not-inc" 98361 " HS-grad" 9 " Never-married"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>
##
## Sample 3 :
## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 41 " Private" 274363 " Some-college" 10 " Married-civ-s…
## 2 56 " Private" 200316 " Some-college" 10 " Married-civ-s…
## 3 49 " Private" 218676 " Some-college" 10 " Married-civ-s…
## 4 29 " Self-emp-inc" 31778 " HS-grad" 9 " Separated"
## 5 26 " Private" 199143 " HS-grad" 9 " Married-civ-s…
## 6 19 " Without-pay" 344858 " HS-grad" 9 " Never-married"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>
##
## Sample 4 :
## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 38 " Private" 79619 " Bachelor… 13 " Married-civ-s…
## 2 47 " Private" 102771 " HS-grad" 9 " Married-civ-s…
## 3 67 " Self-emp-not-inc" 217892 " Doctorat… 16 " Married-civ-s…
## 4 75 " Private" 311184 " Bachelor… 13 " Married-civ-s…
## 5 29 " Private" 161444 " HS-grad" 9 " Married-civ-s…
## 6 44 " Self-emp-not-inc" 274562 " HS-grad" 9 " Never-married"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>
##
## Sample 5 :
## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 18 " Private" 133654 " HS-grad" 9 " Never-married"
## 2 32 " Private" 283400 " HS-grad" 9 " Never-married"
## 3 24 " Private" 190709 " Some-college" 10 " Married-civ-sp…
## 4 42 " Local-gov" 180318 " 10th" 6 " Never-married"
## 5 35 " Federal-gov" 20469 " Some-college" 10 " Divorced"
## 6 45 " Private" 27332 " HS-grad" 9 " Divorced"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>library(dplyr)
num_subsamples <- 5
subsample_size <- floor(0.5 * nrow(mydata))
subsamples_list <- list()
set.seed(123)
for (i in 1:num_subsamples) {
# Sample rows with replacement
subsample_indices <- sample(1:nrow(mydata), size = subsample_size, replace = TRUE)
# Create a subsample data frame with the desired name format
subsample_name <- paste0("subsample_", i)
assign(subsample_name, mydata[subsample_indices, ])
subsamples_list[[subsample_name]] <- mydata[subsample_indices, ]
}
print(head(subsample_1))## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 33 " ?" 102130 " Some-college" 10 " Never-married"
## 2 26 " Private" 130931 " HS-grad" 9 " Never-married"
## 3 40 " Private" 233130 " 7th-8th" 4 " Married-civ-s…
## 4 36 " Self-emp-inc" 107218 " Some-college" 10 " Divorced"
## 5 43 " State-gov" 28451 " Bachelors" 13 " Married-civ-s…
## 6 23 " Private" 161708 " Bachelors" 13 " Never-married"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>print(head(subsample_2))## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 72 " Federal-gov" 39110 " 11th" 7 " Divorced"
## 2 27 " Private" 384308 " Some-col… 10 " Never-married"
## 3 46 " State-gov" 295791 " Assoc-vo… 11 " Divorced"
## 4 19 " Self-emp-not-inc" 30800 " 10th" 6 " Married-spous…
## 5 67 " Private" 134906 " HS-grad" 9 " Widowed"
## 6 26 " Private" 136226 " HS-grad" 9 " Never-married"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>print(head(subsample_3))## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 43 " Private" 152159 " Bachelors" 13 " Married-civ-s…
## 2 46 " Private" 269284 " Assoc-acdm" 12 " Widowed"
## 3 51 " Self-emp-inc" 192973 " Bachelors" 13 " Married-civ-s…
## 4 57 " Federal-gov" 278763 " HS-grad" 9 " Divorced"
## 5 19 " Private" 387215 " Some-college" 10 " Never-married"
## 6 84 " ?" 368925 " 5th-6th" 3 " Widowed"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>print(head(subsample_4))## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 29 " Private" 95423 " HS-grad" 9 " Married-AF-sp…
## 2 31 " State-gov" 29152 " 12th" 8 " Married-civ-s…
## 3 48 " Private" 101684 " HS-grad" 9 " Married-civ-s…
## 4 27 " Private" 116531 " Bachelor… 13 " Never-married"
## 5 39 " Self-emp-inc" 218184 " 9th" 5 " Married-civ-s…
## 6 35 " Self-emp-not-inc" 233533 " Bachelor… 13 " Separated"
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>print(head(subsample_5))## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 42 " Self-emp-not-inc" 79036 " Bachelor… 13 " Married-civ-s…
## 2 29 " Private" 79387 " Bachelor… 13 " Never-married"
## 3 34 " Federal-gov" 284703 " Some-col… 10 " Married-civ-s…
## 4 54 " Private" 182854 " HS-grad" 9 " Married-civ-s…
## 5 23 " Private" 170070 " 12th" 8 " Never-married"
## 6 44 " Private" 116632 " Masters" 14 " Married-civ-s…
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>#Mean Age of Each SUbSample
calculate_average_age<- function(subsample_df) {
mean(subsample_df$`Age`, na.rm = TRUE)
}
average_age <- numeric(num_subsamples)
# Calculate the average age for each subsample and print the results
for (i in 1:num_subsamples) {
subsample_name <- paste0("subsample_", i)
average_age <- calculate_average_age(get(subsample_name))
cat("Average age for", subsample_name, ":", average_age, "\n")
}## Average age for subsample_1 : 38.44963
## Average age for subsample_2 : 38.55872
## Average age for subsample_3 : 38.55049
## Average age for subsample_4 : 38.70639
## Average age for subsample_5 : 38.54681#Mean Education of Each SubSample
calculate_average_Education<- function(subsample_df) {
mean(subsample_df$`Education_Level`, na.rm = TRUE)
}
average_Education <- numeric(num_subsamples)
# Calculate the average Education lEvel for each subsample and print the results
for (i in 1:num_subsamples) {
subsample_name <- paste0("subsample_", i)
average_Education <- calculate_average_Education(get(subsample_name))
cat("Average Education Level for", subsample_name, ":", average_Education, "\n")
}## Average Education Level for subsample_1 : 10.10934
## Average Education Level for subsample_2 : 10.10184
## Average Education Level for subsample_3 : 10.06517
## Average Education Level for subsample_4 : 10.09189
## Average Education Level for subsample_5 : 10.0567#Average Work Hours of Each Subsample
calculate_average_workhrs <- function(subsample_df) {
mean(subsample_df$`hrs_week`, na.rm = TRUE)
}
average_workhrs <- numeric(num_subsamples)
# average work hours for each subsample and print the results
for (i in 1:num_subsamples) {
subsample_name <- paste("subsample_", i, sep = "")
subsample <- get(subsample_name) # Retrieve the subsample dataframe
average_workhrs[i] <- calculate_average_workhrs(subsample)
cat("Average Work hours for", subsample_name, ":", average_workhrs[i], "\n")
}## Average Work hours for subsample_1 : 40.46824
## Average Work hours for subsample_2 : 40.44969
## Average Work hours for subsample_3 : 40.33471
## Average Work hours for subsample_4 : 40.54828
## Average Work hours for subsample_5 : 40.33778```
#There is no much difference in the Averages of 3 different observations