LIS661 Notebook

library(readr)
Dataset <- read_csv("C:/Users/coblem/Documents/Home/Matt/Graduate School/LIS-661/Dataset/Dataset.csv")

## Parsed with column specification:
## cols(
##   .default = col_double(),
##   HRHHID = col_character(),
##   Skip2 = col_character(),
##   GESTFIPS = col_character(),
##   Skip3 = col_character(),
##   Skip7 = col_character(),
##   Skip8 = col_character(),
##   Column29 = col_character()
## )

## See spec(...) for full column specifications.

Now assign this to a data frame

df_Dataset <- data.frame(Dataset)

Lets take a look a the unique value:

sapply(df_Dataset, function(x) length(unique(x)))

##   HRHHID  HRMONTH  HRYEAR4    Skip1 HUSPNISH    Skip2 GESTFIPS    Skip3 
##    62224        1        1      109        2    63203       51     8776 
##   PRTAGE    Skip4 PEMARITL    Skip5    PESEX PEAFEVER    Skip6  PEEDUCA 
##       83        2        7       15        3        3        3       17 
## PTDTRACE    Skip7 PENATVTY PEMNTVTY PEFNTVTY PRCITSHP    Skip8     PES1 
##       27     2130      161      161      160        6   152096        6 
##     PES2    Skip9     PES4     PES5 Column29 
##        6       13       15        6      406

So the csv headers imported and were assigned to the columns as field names. There are 9 columns I just don’t care about at the moment, so they are identified as Skip1, Skip2, …

What is the mean age (PRTAGE)?

mean(df_Dataset$PRTAGE)

## [1] 33.8675

Let’s look at a histogram of the age (PRTAGE)

hist(Dataset$PRTAGE)

I’m pretty sure that the PRTAGE is a numeric, but I just want to check:

str(df_Dataset)

## 'data.frame':    152096 obs. of  29 variables:
##  $ HRHHID  : chr  "710004140617571" "710004140617571" "710004140617571" "000110157414767" ...
##  $ HRMONTH : num  11 11 11 11 11 11 11 11 11 11 ...
##  $ HRYEAR4 : num  2016 2016 2016 2016 2016 ...
##  $ Skip1   : num  1201 1201 1201 1201 1201 ...
##  $ HUSPNISH: num  0 0 0 0 0 0 0 0 0 0 ...
##  $ Skip2   : chr  "1 1 1-1 115-1-1-1  18258606 1 3 3 6 2 0 204011 1  2-1-1-1-1 36" "1 1 1-1 115-1-1-1  18258606 1 3 3 6 2 0 204011 1  2-1-1-1-1 36" "1 1 1-1 115-1-1-1  18258606 1 3 3 6 2 0 204011 1  2-1-1-1-1 36" "1 1 1-1 115-1-1-1  17848407 1 4 1 6 2 0 204011 1  2-1-1-1-1 36" ...
##  $ GESTFIPS: chr  "01" "01" "01" "01" ...
##  $ Skip3   : chr  "338600002103000        1-1" "338600002103000        4 1" "338600002103000        5 2" "338600002103000        1-1" ...
##  $ PRTAGE  : num  63 31 5 45 52 19 14 45 48 17 ...
##  $ Skip4   : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ PEMARITL: num  3 4 -1 1 1 6 -1 1 1 6 ...
##  $ Skip5   : num  -1 -1 -1 2 1 -1 -1 2 1 -1 ...
##  $ PESEX   : num  1 1 1 2 1 2 2 2 1 1 ...
##  $ PEAFEVER: num  1 1 -1 2 2 2 -1 2 2 2 ...
##  $ Skip6   : num  2 2 -1 2 2 2 -1 2 2 2 ...
##  $ PEEDUCA : num  44 39 -1 43 44 39 -1 44 39 36 ...
##  $ PTDTRACE: num  1 1 1 1 1 1 1 1 1 1 ...
##  $ Skip7   : chr  "-1 9   1   1 1 1 2 4 2" "-1 9   2   2 1 3 2 5 2" "-1 9   3   2 3 3 2-1 1" "-1 9   1   1 1 1 2 1 2" ...
##  $ PENATVTY: num  57 57 57 57 57 57 57 57 57 57 ...
##  $ PEMNTVTY: num  57 57 57 57 57 57 57 57 57 57 ...
##  $ PEFNTVTY: num  57 57 57 57 57 57 57 57 57 57 ...
##  $ PRCITSHP: num  1 1 1 1 1 1 1 1 1 1 ...
##  $ Skip8   : chr  "0 0 1 5 3-1-1 2-1-1-1 1-1 2-1-1-1-1-1-1-1-1-1-1-1 -1-1-1-1-1-1-1-1-1-1-1 -1-1     -1-1-1-1-1-1-1-1-1-1-1-1-1 -1"| __truncated__ "0 0 2 1 1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1 2-140-1-1 40-1-1-1-1 2-1 2-140-1 40-1      2 5 5-1 2 3 5 2-1-1-1-1-1 -1"| __truncated__ "0 0-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1-1 -1-1-1-1-1-1-1-1-1-1-1 -1-1     -1-1-1-1-1-1-1-1-1-1-1-1-1 -1"| __truncated__ "0 0 1 7 2-1-1 2-1 2-1-1-1-1-1-1 2 2-1-1-1-1-1-1-1 -1-1-1-1-1-1-1-1-1-1-1 -1-1     -1-1-1-1-1-1-1-1-1-1-1-1-1 -1"| __truncated__ ...
##  $ PES1    : num  1 1 -1 1 1 2 -1 1 1 -1 ...
##  $ PES2    : num  -1 -1 -1 -1 -1 2 -1 -1 -1 -1 ...
##  $ Skip9   : num  -1 -1 -1 -1 -1 -3 -1 -1 -1 -1 ...
##  $ PES4    : num  -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 ...
##  $ PES5    : num  1 1 -1 1 1 -1 -1 1 1 -1 ...
##  $ Column29: chr  "1 6 4 1" "1 1 4 2" "-1-1-1-1" "1 3 2 1" ...

Yep, that’s numeric. Now what’s the mean age?

mean(df_Dataset$PRTAGE)

## [1] 33.8675

And the media age?

median(df_Dataset$PRTAGE)

## [1] 33

Need to create a function to calculate Mode…

Mode = function(x){ 
    ta = table(x)
    tam = max(ta)
    if (all(ta == tam))
         mod = NA
    else
         if(is.numeric(x))
    mod = as.numeric(names(ta)[ta == tam])
    else
         mod = names(ta)[ta == tam]
    return(mod)
}

Mode(df_Dataset$PRTAGE)

## [1] -1

And yes, -1 is a legal value indicating that they choose not to say. I’ll have to figure out how to filter those out.

LIS661 Notebook

Comments

Leave a Reply Cancel reply