### Loading the function
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.3 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── 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
### Uploading the file
df = read_csv("C:/Users/miam/Desktop/X Fall Semester/Data Wrangling/Modules/Week 10/Assignment 3/acs_2015_county_data_revised.csv")
## Rows: 3142 Columns: 35
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): state, county
## dbl (33): census_id, total_pop, men, women, hispanic, white, black, native, ...
##
## 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.
nrow(df)
## [1] 3142
ncol(df)
## [1] 35
### Data Types Conversion. Here I converting the State and County columns from character to categorical for analysis purpose.
glimpse(df)
## Rows: 3,142
## Columns: 35
## $ census_id <dbl> 1001, 1003, 1005, 1007, 1009, 1011, 1013, 1015, 1017, 1…
## $ state <chr> "Alabama", "Alabama", "Alabama", "Alabama", "Alabama", …
## $ county <chr> "Autauga", "Baldwin", "Barbour", "Bibb", "Blount", "Bul…
## $ total_pop <dbl> 55221, 195121, 26932, 22604, 57710, 10678, 20354, 11664…
## $ men <dbl> 26745, 95314, 14497, 12073, 28512, 5660, 9502, 56274, 1…
## $ women <dbl> 28476, 99807, 12435, 10531, 29198, 5018, 10852, 60374, …
## $ hispanic <dbl> 2.6, 4.5, 4.6, 2.2, 8.6, 4.4, 1.2, 3.5, 0.4, 1.5, 7.6, …
## $ white <dbl> 75.8, 83.1, 46.2, 74.5, 87.9, 22.2, 53.3, 73.0, 57.3, 9…
## $ black <dbl> 18.5, 9.5, 46.7, 21.4, 1.5, 70.7, 43.8, 20.3, 40.3, 4.8…
## $ native <dbl> 0.4, 0.6, 0.2, 0.4, 0.3, 1.2, 0.1, 0.2, 0.2, 0.6, 0.4, …
## $ asian <dbl> 1.0, 0.7, 0.4, 0.1, 0.1, 0.2, 0.4, 0.9, 0.8, 0.3, 0.3, …
## $ pacific <dbl> 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, …
## $ citizen <dbl> 40725, 147695, 20714, 17495, 42345, 8057, 15581, 88612,…
## $ income <dbl> 51281, 50254, 32964, 38678, 45813, 31938, 32229, 41703,…
## $ income_per_cap <dbl> 24974, 27317, 16824, 18431, 20532, 17580, 18390, 21374,…
## $ poverty <dbl> 12.9, 13.4, 26.7, 16.8, 16.7, 24.6, 25.4, 20.5, 21.6, 1…
## $ child_poverty <dbl> 18.6, 19.2, 45.3, 27.9, 27.2, 38.4, 39.2, 31.6, 37.2, 3…
## $ professional <dbl> 33.2, 33.1, 26.8, 21.5, 28.5, 18.8, 27.5, 27.3, 23.3, 2…
## $ service <dbl> 17.0, 17.7, 16.1, 17.9, 14.1, 15.0, 16.6, 17.7, 14.5, 1…
## $ office <dbl> 24.2, 27.1, 23.1, 17.8, 23.9, 19.7, 21.9, 24.2, 26.3, 1…
## $ construction <dbl> 8.6, 10.8, 10.8, 19.0, 13.5, 20.1, 10.3, 10.5, 11.5, 13…
## $ production <dbl> 17.1, 11.2, 23.1, 23.7, 19.9, 26.4, 23.7, 20.4, 24.4, 2…
## $ drive <dbl> 87.5, 84.7, 83.8, 83.2, 84.9, 74.9, 84.5, 85.3, 85.1, 8…
## $ carpool <dbl> 8.8, 8.8, 10.9, 13.5, 11.2, 14.9, 12.4, 9.4, 11.9, 12.1…
## $ transit <dbl> 0.1, 0.1, 0.4, 0.5, 0.4, 0.7, 0.0, 0.2, 0.2, 0.2, 0.2, …
## $ walk <dbl> 0.5, 1.0, 1.8, 0.6, 0.9, 5.0, 0.8, 1.2, 0.3, 0.6, 1.1, …
## $ other_transp <dbl> 1.3, 1.4, 1.5, 1.5, 0.4, 1.7, 0.6, 1.2, 0.4, 0.7, 1.4, …
## $ work_at_home <dbl> 1.8, 3.9, 1.6, 0.7, 2.3, 2.8, 1.7, 2.7, 2.1, 2.5, 1.9, …
## $ mean_commute <dbl> 26.5, 26.4, 24.1, 28.8, 34.9, 27.5, 24.6, 24.1, 25.1, 2…
## $ employed <dbl> 23986, 85953, 8597, 8294, 22189, 3865, 7813, 47401, 136…
## $ private_work <dbl> 73.6, 81.5, 71.8, 76.8, 82.0, 79.5, 77.4, 74.1, 85.1, 7…
## $ public_work <dbl> 20.9, 12.3, 20.8, 16.1, 13.5, 15.1, 16.2, 20.8, 12.1, 1…
## $ self_employed <dbl> 5.5, 5.8, 7.3, 6.7, 4.2, 5.4, 6.2, 5.0, 2.8, 7.9, 4.1, …
## $ family_work <dbl> 0.0, 0.4, 0.1, 0.4, 0.4, 0.0, 0.2, 0.1, 0.0, 0.5, 0.5, …
## $ unemployment <dbl> 7.6, 7.5, 17.6, 8.3, 7.7, 18.0, 10.9, 12.3, 8.9, 7.9, 9…
df = df %>% mutate(state = as.factor(state), county = as.factor(county))
glimpse(df)
## Rows: 3,142
## Columns: 35
## $ census_id <dbl> 1001, 1003, 1005, 1007, 1009, 1011, 1013, 1015, 1017, 1…
## $ state <fct> Alabama, Alabama, Alabama, Alabama, Alabama, Alabama, A…
## $ county <fct> Autauga, Baldwin, Barbour, Bibb, Blount, Bullock, Butle…
## $ total_pop <dbl> 55221, 195121, 26932, 22604, 57710, 10678, 20354, 11664…
## $ men <dbl> 26745, 95314, 14497, 12073, 28512, 5660, 9502, 56274, 1…
## $ women <dbl> 28476, 99807, 12435, 10531, 29198, 5018, 10852, 60374, …
## $ hispanic <dbl> 2.6, 4.5, 4.6, 2.2, 8.6, 4.4, 1.2, 3.5, 0.4, 1.5, 7.6, …
## $ white <dbl> 75.8, 83.1, 46.2, 74.5, 87.9, 22.2, 53.3, 73.0, 57.3, 9…
## $ black <dbl> 18.5, 9.5, 46.7, 21.4, 1.5, 70.7, 43.8, 20.3, 40.3, 4.8…
## $ native <dbl> 0.4, 0.6, 0.2, 0.4, 0.3, 1.2, 0.1, 0.2, 0.2, 0.6, 0.4, …
## $ asian <dbl> 1.0, 0.7, 0.4, 0.1, 0.1, 0.2, 0.4, 0.9, 0.8, 0.3, 0.3, …
## $ pacific <dbl> 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, …
## $ citizen <dbl> 40725, 147695, 20714, 17495, 42345, 8057, 15581, 88612,…
## $ income <dbl> 51281, 50254, 32964, 38678, 45813, 31938, 32229, 41703,…
## $ income_per_cap <dbl> 24974, 27317, 16824, 18431, 20532, 17580, 18390, 21374,…
## $ poverty <dbl> 12.9, 13.4, 26.7, 16.8, 16.7, 24.6, 25.4, 20.5, 21.6, 1…
## $ child_poverty <dbl> 18.6, 19.2, 45.3, 27.9, 27.2, 38.4, 39.2, 31.6, 37.2, 3…
## $ professional <dbl> 33.2, 33.1, 26.8, 21.5, 28.5, 18.8, 27.5, 27.3, 23.3, 2…
## $ service <dbl> 17.0, 17.7, 16.1, 17.9, 14.1, 15.0, 16.6, 17.7, 14.5, 1…
## $ office <dbl> 24.2, 27.1, 23.1, 17.8, 23.9, 19.7, 21.9, 24.2, 26.3, 1…
## $ construction <dbl> 8.6, 10.8, 10.8, 19.0, 13.5, 20.1, 10.3, 10.5, 11.5, 13…
## $ production <dbl> 17.1, 11.2, 23.1, 23.7, 19.9, 26.4, 23.7, 20.4, 24.4, 2…
## $ drive <dbl> 87.5, 84.7, 83.8, 83.2, 84.9, 74.9, 84.5, 85.3, 85.1, 8…
## $ carpool <dbl> 8.8, 8.8, 10.9, 13.5, 11.2, 14.9, 12.4, 9.4, 11.9, 12.1…
## $ transit <dbl> 0.1, 0.1, 0.4, 0.5, 0.4, 0.7, 0.0, 0.2, 0.2, 0.2, 0.2, …
## $ walk <dbl> 0.5, 1.0, 1.8, 0.6, 0.9, 5.0, 0.8, 1.2, 0.3, 0.6, 1.1, …
## $ other_transp <dbl> 1.3, 1.4, 1.5, 1.5, 0.4, 1.7, 0.6, 1.2, 0.4, 0.7, 1.4, …
## $ work_at_home <dbl> 1.8, 3.9, 1.6, 0.7, 2.3, 2.8, 1.7, 2.7, 2.1, 2.5, 1.9, …
## $ mean_commute <dbl> 26.5, 26.4, 24.1, 28.8, 34.9, 27.5, 24.6, 24.1, 25.1, 2…
## $ employed <dbl> 23986, 85953, 8597, 8294, 22189, 3865, 7813, 47401, 136…
## $ private_work <dbl> 73.6, 81.5, 71.8, 76.8, 82.0, 79.5, 77.4, 74.1, 85.1, 7…
## $ public_work <dbl> 20.9, 12.3, 20.8, 16.1, 13.5, 15.1, 16.2, 20.8, 12.1, 1…
## $ self_employed <dbl> 5.5, 5.8, 7.3, 6.7, 4.2, 5.4, 6.2, 5.0, 2.8, 7.9, 4.1, …
## $ family_work <dbl> 0.0, 0.4, 0.1, 0.4, 0.4, 0.0, 0.2, 0.1, 0.0, 0.5, 0.5, …
## $ unemployment <dbl> 7.6, 7.5, 17.6, 8.3, 7.7, 18.0, 10.9, 12.3, 8.9, 7.9, 9…
### Missing values
sum(is.na(df))
## [1] 2
colSums(is.na(df))
## census_id state county total_pop men
## 0 0 0 0 0
## women hispanic white black native
## 0 0 0 0 0
## asian pacific citizen income income_per_cap
## 0 0 0 1 0
## poverty child_poverty professional service office
## 0 1 0 0 0
## construction production drive carpool transit
## 0 0 0 0 0
## walk other_transp work_at_home mean_commute employed
## 0 0 0 0 0
## private_work public_work self_employed family_work unemployment
## 0 0 0 0 0
### Hera are two missing values- one in income and the other one in child_poverty. So I will impute these two values with mean value of their particular columns.
df = df %>% mutate(income = replace_na(income, mean(income, na.rm = TRUE)))
df = df %>% mutate(child_poverty = replace_na(child_poverty, mean(child_poverty, na.rm = TRUE)))
colSums(is.na(df))
## census_id state county total_pop men
## 0 0 0 0 0
## women hispanic white black native
## 0 0 0 0 0
## asian pacific citizen income income_per_cap
## 0 0 0 0 0
## poverty child_poverty professional service office
## 0 0 0 0 0
## construction production drive carpool transit
## 0 0 0 0 0
## walk other_transp work_at_home mean_commute employed
## 0 0 0 0 0
## private_work public_work self_employed family_work unemployment
## 0 0 0 0 0
### Examining the unusual values. Here are some unusual values in some columns like total_pop, transit, walk. But these are realistic. For analysis purpose, we can create variables based on different criteria. The county_size variable was created based on population size from total_pop.
summary(df)
## census_id state county total_pop
## Min. : 1001 Texas : 254 Washington: 31 Min. : 85
## 1st Qu.:18178 Georgia : 159 Jefferson : 26 1st Qu.: 11028
## Median :29176 Virginia: 133 Franklin : 25 Median : 25768
## Mean :30384 Kentucky: 120 Jackson : 24 Mean : 100737
## 3rd Qu.:45081 Missouri: 115 Lincoln : 24 3rd Qu.: 67552
## Max. :56045 Kansas : 105 Madison : 20 Max. :10038388
## (Other) :2256 (Other) :2992
## men women hispanic white
## Min. : 42 Min. : 43 Min. : 0.000 Min. : 0.90
## 1st Qu.: 5546 1st Qu.: 5466 1st Qu.: 1.900 1st Qu.:65.60
## Median : 12826 Median : 12907 Median : 3.700 Median :84.60
## Mean : 49565 Mean : 51172 Mean : 8.826 Mean :77.28
## 3rd Qu.: 33319 3rd Qu.: 34122 3rd Qu.: 9.000 3rd Qu.:93.30
## Max. :4945351 Max. :5093037 Max. :98.700 Max. :99.80
##
## black native asian pacific
## Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.00000
## 1st Qu.: 0.600 1st Qu.: 0.100 1st Qu.: 0.200 1st Qu.: 0.00000
## Median : 2.100 Median : 0.300 Median : 0.500 Median : 0.00000
## Mean : 8.879 Mean : 1.766 Mean : 1.258 Mean : 0.08475
## 3rd Qu.:10.175 3rd Qu.: 0.600 3rd Qu.: 1.200 3rd Qu.: 0.00000
## Max. :85.900 Max. :92.100 Max. :41.600 Max. :35.30000
##
## citizen income income_per_cap poverty
## Min. : 80 Min. : 19328 Min. : 8292 Min. : 1.4
## 1st Qu.: 8254 1st Qu.: 38826 1st Qu.:20471 1st Qu.:12.0
## Median : 19434 Median : 45113 Median :23577 Median :16.0
## Mean : 70804 Mean : 46830 Mean :24338 Mean :16.7
## 3rd Qu.: 50728 3rd Qu.: 52249 3rd Qu.:27138 3rd Qu.:20.3
## Max. :6046749 Max. :123453 Max. :65600 Max. :53.3
##
## child_poverty professional service office
## Min. : 0.00 Min. :13.50 Min. : 5.00 Min. : 4.10
## 1st Qu.:16.10 1st Qu.:26.70 1st Qu.:15.90 1st Qu.:20.20
## Median :22.50 Median :30.00 Median :18.00 Median :22.40
## Mean :23.29 Mean :31.04 Mean :18.26 Mean :22.13
## 3rd Qu.:29.48 3rd Qu.:34.40 3rd Qu.:20.20 3rd Qu.:24.30
## Max. :72.30 Max. :74.00 Max. :36.60 Max. :35.40
##
## construction production drive carpool
## Min. : 1.70 Min. : 0.00 Min. : 5.20 Min. : 0.00
## 1st Qu.: 9.80 1st Qu.:11.53 1st Qu.:76.60 1st Qu.: 8.50
## Median :12.20 Median :15.40 Median :80.60 Median : 9.90
## Mean :12.74 Mean :15.82 Mean :79.08 Mean :10.33
## 3rd Qu.:15.00 3rd Qu.:19.40 3rd Qu.:83.60 3rd Qu.:11.88
## Max. :40.30 Max. :55.60 Max. :94.60 Max. :29.90
##
## transit walk other_transp work_at_home
## Min. : 0.0000 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.1000 1st Qu.: 1.400 1st Qu.: 0.900 1st Qu.: 2.800
## Median : 0.4000 Median : 2.400 Median : 1.300 Median : 4.000
## Mean : 0.9675 Mean : 3.307 Mean : 1.614 Mean : 4.697
## 3rd Qu.: 0.8000 3rd Qu.: 4.000 3rd Qu.: 1.900 3rd Qu.: 5.700
## Max. :61.7000 Max. :71.200 Max. :39.100 Max. :37.200
##
## mean_commute employed private_work public_work
## Min. : 4.90 Min. : 62 Min. :25.00 Min. : 5.80
## 1st Qu.:19.30 1st Qu.: 4524 1st Qu.:70.90 1st Qu.:13.10
## Median :22.90 Median : 10644 Median :75.80 Median :16.10
## Mean :23.15 Mean : 46387 Mean :74.44 Mean :17.35
## 3rd Qu.:26.60 3rd Qu.: 29254 3rd Qu.:79.80 3rd Qu.:20.10
## Max. :44.00 Max. :4635465 Max. :88.30 Max. :66.20
##
## self_employed family_work unemployment
## Min. : 0.000 Min. :0.0000 Min. : 0.000
## 1st Qu.: 5.400 1st Qu.:0.1000 1st Qu.: 5.500
## Median : 6.900 Median :0.2000 Median : 7.500
## Mean : 7.921 Mean :0.2915 Mean : 7.815
## 3rd Qu.: 9.400 3rd Qu.:0.3000 3rd Qu.: 9.700
## Max. :36.600 Max. :9.8000 Max. :29.400
##
df = df %>%
mutate(county_size = case_when(
total_pop < 10000 ~ "Rural Area",
total_pop < 200000 ~ "Sub-urban Area",
total_pop > 200000 ~ "Metropolitan Area"
))
glimpse(df)
## Rows: 3,142
## Columns: 36
## $ census_id <dbl> 1001, 1003, 1005, 1007, 1009, 1011, 1013, 1015, 1017, 1…
## $ state <fct> Alabama, Alabama, Alabama, Alabama, Alabama, Alabama, A…
## $ county <fct> Autauga, Baldwin, Barbour, Bibb, Blount, Bullock, Butle…
## $ total_pop <dbl> 55221, 195121, 26932, 22604, 57710, 10678, 20354, 11664…
## $ men <dbl> 26745, 95314, 14497, 12073, 28512, 5660, 9502, 56274, 1…
## $ women <dbl> 28476, 99807, 12435, 10531, 29198, 5018, 10852, 60374, …
## $ hispanic <dbl> 2.6, 4.5, 4.6, 2.2, 8.6, 4.4, 1.2, 3.5, 0.4, 1.5, 7.6, …
## $ white <dbl> 75.8, 83.1, 46.2, 74.5, 87.9, 22.2, 53.3, 73.0, 57.3, 9…
## $ black <dbl> 18.5, 9.5, 46.7, 21.4, 1.5, 70.7, 43.8, 20.3, 40.3, 4.8…
## $ native <dbl> 0.4, 0.6, 0.2, 0.4, 0.3, 1.2, 0.1, 0.2, 0.2, 0.6, 0.4, …
## $ asian <dbl> 1.0, 0.7, 0.4, 0.1, 0.1, 0.2, 0.4, 0.9, 0.8, 0.3, 0.3, …
## $ pacific <dbl> 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, …
## $ citizen <dbl> 40725, 147695, 20714, 17495, 42345, 8057, 15581, 88612,…
## $ income <dbl> 51281, 50254, 32964, 38678, 45813, 31938, 32229, 41703,…
## $ income_per_cap <dbl> 24974, 27317, 16824, 18431, 20532, 17580, 18390, 21374,…
## $ poverty <dbl> 12.9, 13.4, 26.7, 16.8, 16.7, 24.6, 25.4, 20.5, 21.6, 1…
## $ child_poverty <dbl> 18.6, 19.2, 45.3, 27.9, 27.2, 38.4, 39.2, 31.6, 37.2, 3…
## $ professional <dbl> 33.2, 33.1, 26.8, 21.5, 28.5, 18.8, 27.5, 27.3, 23.3, 2…
## $ service <dbl> 17.0, 17.7, 16.1, 17.9, 14.1, 15.0, 16.6, 17.7, 14.5, 1…
## $ office <dbl> 24.2, 27.1, 23.1, 17.8, 23.9, 19.7, 21.9, 24.2, 26.3, 1…
## $ construction <dbl> 8.6, 10.8, 10.8, 19.0, 13.5, 20.1, 10.3, 10.5, 11.5, 13…
## $ production <dbl> 17.1, 11.2, 23.1, 23.7, 19.9, 26.4, 23.7, 20.4, 24.4, 2…
## $ drive <dbl> 87.5, 84.7, 83.8, 83.2, 84.9, 74.9, 84.5, 85.3, 85.1, 8…
## $ carpool <dbl> 8.8, 8.8, 10.9, 13.5, 11.2, 14.9, 12.4, 9.4, 11.9, 12.1…
## $ transit <dbl> 0.1, 0.1, 0.4, 0.5, 0.4, 0.7, 0.0, 0.2, 0.2, 0.2, 0.2, …
## $ walk <dbl> 0.5, 1.0, 1.8, 0.6, 0.9, 5.0, 0.8, 1.2, 0.3, 0.6, 1.1, …
## $ other_transp <dbl> 1.3, 1.4, 1.5, 1.5, 0.4, 1.7, 0.6, 1.2, 0.4, 0.7, 1.4, …
## $ work_at_home <dbl> 1.8, 3.9, 1.6, 0.7, 2.3, 2.8, 1.7, 2.7, 2.1, 2.5, 1.9, …
## $ mean_commute <dbl> 26.5, 26.4, 24.1, 28.8, 34.9, 27.5, 24.6, 24.1, 25.1, 2…
## $ employed <dbl> 23986, 85953, 8597, 8294, 22189, 3865, 7813, 47401, 136…
## $ private_work <dbl> 73.6, 81.5, 71.8, 76.8, 82.0, 79.5, 77.4, 74.1, 85.1, 7…
## $ public_work <dbl> 20.9, 12.3, 20.8, 16.1, 13.5, 15.1, 16.2, 20.8, 12.1, 1…
## $ self_employed <dbl> 5.5, 5.8, 7.3, 6.7, 4.2, 5.4, 6.2, 5.0, 2.8, 7.9, 4.1, …
## $ family_work <dbl> 0.0, 0.4, 0.1, 0.4, 0.4, 0.0, 0.2, 0.1, 0.0, 0.5, 0.5, …
## $ unemployment <dbl> 7.6, 7.5, 17.6, 8.3, 7.7, 18.0, 10.9, 12.3, 8.9, 7.9, 9…
## $ county_size <chr> "Sub-urban Area", "Sub-urban Area", "Sub-urban Area", "…
### Data Manipulation and Insights
#### 5. How many counties have more women than men?-In 1985 counties,number of women are greater than men.
df |>
filter(women > men) |>
nrow()
## [1] 1985
#### 6. How many counties have an unemployment rate lower than 10%?-2420
df |>
filter(unemployment < 10) |>
nrow()
## [1] 2420
#### 7. The top 10 counties with the highest mean commute
df |>
select( census_id, state, county, mean_commute) |>
arrange(desc(mean_commute)) |>
dplyr::top_n(10)
## Selecting by mean_commute
## # A tibble: 10 × 4
## census_id state county mean_commute
## <dbl> <fct> <fct> <dbl>
## 1 42103 Pennsylvania Pike 44
## 2 36005 New York Bronx 43
## 3 24017 Maryland Charles 42.8
## 4 51187 Virginia Warren 42.7
## 5 36081 New York Queens 42.6
## 6 36085 New York Richmond 42.6
## 7 51193 Virginia Westmoreland 42.5
## 8 8093 Colorado Park 42.4
## 9 36047 New York Kings 41.7
## 10 54015 West Virginia Clay 41.4
#### 8. The top 10 counties with the lowest percentages of women
df |>
mutate(women_prct = (women/total_pop)*100) |>
dplyr::top_n(10, wt = -women_prct) |>
select(census_id, state, county, women_prct) |>
arrange(women_prct)
## # A tibble: 10 × 4
## census_id state county women_prct
## <dbl> <fct> <fct> <dbl>
## 1 42053 Pennsylvania Forest 26.8
## 2 8011 Colorado Bent 31.4
## 3 51183 Virginia Sussex 31.5
## 4 13309 Georgia Wheeler 32.1
## 5 6035 California Lassen 33.2
## 6 48095 Texas Concho 33.3
## 7 13053 Georgia Chattahoochee 33.4
## 8 2013 Alaska Aleutians East Borough 33.5
## 9 22125 Louisiana West Feliciana 33.6
## 10 32027 Nevada Pershing 33.7
#### 9. The sum of all races in percentage
##### a. The top 10 counties with the lowest sum of these race percentage
df = df |>
mutate(race_sum = hispanic + white + black + native + asian + pacific)
df |>
dplyr::top_n(10, wt = -race_sum) |>
select(census_id, state, county,race_sum) |>
arrange(race_sum)
## # A tibble: 10 × 4
## census_id state county race_sum
## <dbl> <fct> <fct> <dbl>
## 1 15001 Hawaii Hawaii 76.4
## 2 15009 Hawaii Maui 79.2
## 3 40097 Oklahoma Mayes 79.7
## 4 15003 Hawaii Honolulu 81.5
## 5 40123 Oklahoma Pontotoc 82.8
## 6 47061 Tennessee Grundy 83
## 7 2282 Alaska Yakutat City and Borough 83.4
## 8 40069 Oklahoma Johnston 84
## 9 15007 Hawaii Kauai 84.1
## 10 40003 Oklahoma Alfalfa 85.1
#### b. The lowest sum of these race percentage
df |>
group_by(state) |>
summarise(average_race_sum = mean(race_sum, is.na = TRUE)) |>
arrange(average_race_sum) |>
head(1)
## # A tibble: 1 × 2
## state average_race_sum
## <fct> <dbl>
## 1 Hawaii 84
#### c. Counties with a sum greater than 100%
#### Here, the ouput shows 100 but actual value is greater than 100. Like 100.0001.
df |>
filter((race_sum) > 100) |>
select(census_id, county, state, race_sum)
## # A tibble: 11 × 4
## census_id county state race_sum
## <dbl> <fct> <fct> <dbl>
## 1 28021 Claiborne Mississippi 100
## 2 31073 Gosper Nebraska 100.
## 3 31091 Hooker Nebraska 100.
## 4 31125 Nance Nebraska 100.
## 5 48017 Bailey Texas 100.
## 6 48131 Duval Texas 100
## 7 48137 Edwards Texas 100.
## 8 48261 Kenedy Texas 100
## 9 48263 Kent Texas 100
## 10 48377 Presidio Texas 100
## 11 49001 Beaver Utah 100
#### d. States have a sum that equals exactly to 100%
df |>
group_by(state) |>
summarise(average_race_sum = mean(race_sum, na.rm = TRUE)) |>
filter(average_race_sum == 100) |>
nrow()
## [1] 0
#### 10.
#### a. Carpool_rnak variable
df <- df |>
mutate(carpool_rank = min_rank(carpool))
#### b. The 10 highest ranked counties for carpooling
df |>
dplyr::top_n(10, wt = carpool_rank) |>
select(census_id, state, county, carpool, carpool_rank) |>
arrange(desc(carpool_rank))
## # A tibble: 10 × 5
## census_id state county carpool carpool_rank
## <dbl> <fct> <fct> <dbl> <int>
## 1 13061 Georgia Clay 29.9 3142
## 2 18087 Indiana LaGrange 27 3141
## 3 13165 Georgia Jenkins 25.3 3140
## 4 5133 Arkansas Sevier 24.4 3139
## 5 20175 Kansas Seward 23.4 3138
## 6 48079 Texas Cochran 22.8 3137
## 7 48247 Texas Jim Hogg 22.6 3136
## 8 48393 Texas Roberts 22.4 3135
## 9 39075 Ohio Holmes 21.8 3134
## 10 21197 Kentucky Powell 21.6 3133
#### c. The 10 lowest ranked counties for carpooling
df |>
dplyr::top_n(10, wt = -carpool_rank) |>
select(census_id, state, county, carpool, carpool_rank) |>
arrange((carpool_rank))
## # A tibble: 11 × 5
## census_id state county carpool carpool_rank
## <dbl> <fct> <fct> <dbl> <int>
## 1 48261 Texas Kenedy 0 1
## 2 48269 Texas King 0 1
## 3 48235 Texas Irion 0.9 3
## 4 31183 Nebraska Wheeler 1.3 4
## 5 36061 New York New York 1.9 5
## 6 13309 Georgia Wheeler 2.3 6
## 7 38029 North Dakota Emmons 2.3 6
## 8 30019 Montana Daniels 2.6 8
## 9 31057 Nebraska Dundy 2.6 8
## 10 46069 South Dakota Hyde 2.8 10
## 11 51720 Virginia Norton city 2.8 10
#### d. On average, the best state is ranked for carpooling
df |>
group_by(state) |>
summarise(mean_rank = mean(carpool_rank, na.rm = TRUE)) |>
arrange(desc(mean_rank)) |>
head(1)
## # A tibble: 1 × 2
## state mean_rank
## <fct> <dbl>
## 1 Arizona 2138.
#### e. The top 5 states for carpooling
df |>
group_by(state) |>
summarise(mean_rank = mean(carpool_rank, na.rm = TRUE)) |>
arrange(desc(mean_rank)) |>
head(5)
## # A tibble: 5 × 2
## state mean_rank
## <fct> <dbl>
## 1 Arizona 2138.
## 2 Utah 2097.
## 3 Arkansas 2059.
## 4 Hawaii 2047.
## 5 Alaska 2034.