As seen below, there are 35 columns and 3,142 rows in the dataset.
library(tidyverse)
data <- read_csv("acs_2015_county_data_revised.csv")
ncol(data)## [1] 35nrow(data)## [1] 3142No, as you can see, all the variables are numeric except for state and county which are characters.
glimpse(data)## Rows: 3,142
## Columns: 35
## $ census_id <dbl> 1001, 1003, 1005, 1007, 1009, 1011, 1013, 1015, 1017...
## $ state <chr> "Alabama", "Alabama", "Alabama", "Alabama", "Alabama...
## $ county <chr> "Autauga", "Baldwin", "Barbour", "Bibb", "Blount", "...
## $ total_pop <dbl> 55221, 195121, 26932, 22604, 57710, 10678, 20354, 11...
## $ men <dbl> 26745, 95314, 14497, 12073, 28512, 5660, 9502, 56274...
## $ women <dbl> 28476, 99807, 12435, 10531, 29198, 5018, 10852, 6037...
## $ hispanic <dbl> 2.6, 4.5, 4.6, 2.2, 8.6, 4.4, 1.2, 3.5, 0.4, 1.5, 7....
## $ white <dbl> 75.8, 83.1, 46.2, 74.5, 87.9, 22.2, 53.3, 73.0, 57.3...
## $ black <dbl> 18.5, 9.5, 46.7, 21.4, 1.5, 70.7, 43.8, 20.3, 40.3, ...
## $ native <dbl> 0.4, 0.6, 0.2, 0.4, 0.3, 1.2, 0.1, 0.2, 0.2, 0.6, 0....
## $ asian <dbl> 1.0, 0.7, 0.4, 0.1, 0.1, 0.2, 0.4, 0.9, 0.8, 0.3, 0....
## $ pacific <dbl> 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, 886...
## $ income <dbl> 51281, 50254, 32964, 38678, 45813, 31938, 32229, 417...
## $ income_per_cap <dbl> 24974, 27317, 16824, 18431, 20532, 17580, 18390, 213...
## $ poverty <dbl> 12.9, 13.4, 26.7, 16.8, 16.7, 24.6, 25.4, 20.5, 21.6...
## $ child_poverty <dbl> 18.6, 19.2, 45.3, 27.9, 27.2, 38.4, 39.2, 31.6, 37.2...
## $ professional <dbl> 33.2, 33.1, 26.8, 21.5, 28.5, 18.8, 27.5, 27.3, 23.3...
## $ service <dbl> 17.0, 17.7, 16.1, 17.9, 14.1, 15.0, 16.6, 17.7, 14.5...
## $ office <dbl> 24.2, 27.1, 23.1, 17.8, 23.9, 19.7, 21.9, 24.2, 26.3...
## $ construction <dbl> 8.6, 10.8, 10.8, 19.0, 13.5, 20.1, 10.3, 10.5, 11.5,...
## $ production <dbl> 17.1, 11.2, 23.1, 23.7, 19.9, 26.4, 23.7, 20.4, 24.4...
## $ drive <dbl> 87.5, 84.7, 83.8, 83.2, 84.9, 74.9, 84.5, 85.3, 85.1...
## $ carpool <dbl> 8.8, 8.8, 10.9, 13.5, 11.2, 14.9, 12.4, 9.4, 11.9, 1...
## $ transit <dbl> 0.1, 0.1, 0.4, 0.5, 0.4, 0.7, 0.0, 0.2, 0.2, 0.2, 0....
## $ walk <dbl> 0.5, 1.0, 1.8, 0.6, 0.9, 5.0, 0.8, 1.2, 0.3, 0.6, 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....
## $ 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....
## $ mean_commute <dbl> 26.5, 26.4, 24.1, 28.8, 34.9, 27.5, 24.6, 24.1, 25.1...
## $ employed <dbl> 23986, 85953, 8597, 8294, 22189, 3865, 7813, 47401, ...
## $ private_work <dbl> 73.6, 81.5, 71.8, 76.8, 82.0, 79.5, 77.4, 74.1, 85.1...
## $ public_work <dbl> 20.9, 12.3, 20.8, 16.1, 13.5, 15.1, 16.2, 20.8, 12.1...
## $ self_employed <dbl> 5.5, 5.8, 7.3, 6.7, 4.2, 5.4, 6.2, 5.0, 2.8, 7.9, 4....
## $ family_work <dbl> 0.0, 0.4, 0.1, 0.4, 0.4, 0.0, 0.2, 0.1, 0.0, 0.5, 0....
## $ unemployment <dbl> 7.6, 7.5, 17.6, 8.3, 7.7, 18.0, 10.9, 12.3, 8.9, 7.9...There was a missing value in child poverty and income. Since there were so few missing values, the best method of dealing with them is to remove the observations associated with each. The following shows the summary of the data with the 2 NAs, followed by the code of how I removed them, then a second summary of the cleaned data with no missing values.
summary(data)## census_id state county total_pop
## Min. : 1001 Length:3142 Length:3142 Min. : 85
## 1st Qu.:18178 Class :character Class :character 1st Qu.: 11028
## Median :29176 Mode :character Mode :character Median : 25768
## Mean :30384 Mean : 100737
## 3rd Qu.:45081 3rd Qu.: 67552
## Max. :56045 Max. :10038388
##
## 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 : 51171 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 : 45111 Median :23577 Median :16.0
## Mean : 70804 Mean : 46830 Mean :24338 Mean :16.7
## 3rd Qu.: 50728 3rd Qu.: 52250 3rd Qu.:27138 3rd Qu.:20.3
## Max. :6046749 Max. :123453 Max. :65600 Max. :53.3
## NA's :1
## 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.:29.50 3rd Qu.:34.40 3rd Qu.:20.20 3rd Qu.:24.30
## Max. :72.30 Max. :74.00 Max. :36.60 Max. :35.40
## NA's :1
## 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
## data2 <- na.omit(data)
summary(data2)## census_id state county total_pop
## Min. : 1001 Length:3140 Length:3140 Min. : 267
## 1st Qu.:18179 Class :character Class :character 1st Qu.: 11036
## Median :29176 Mode :character Mode :character Median : 25793
## Mean :30383 Mean : 100801
## 3rd Qu.:45080 3rd Qu.: 67620
## Max. :56045 Max. :10038388
## men women hispanic white
## Min. : 136 Min. : 131 Min. : 0.000 Min. : 0.90
## 1st Qu.: 5551 1st Qu.: 5488 1st Qu.: 1.900 1st Qu.:65.67
## Median : 12838 Median : 12916 Median : 3.700 Median :84.65
## Mean : 49597 Mean : 51204 Mean : 8.819 Mean :77.31
## 3rd Qu.: 33328 3rd Qu.: 34123 3rd Qu.: 9.000 3rd Qu.:93.33
## 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 : 8.885 Mean : 1.763 Mean : 1.253 Mean : 0.07357
## 3rd Qu.:10.200 3rd Qu.: 0.600 3rd Qu.: 1.200 3rd Qu.: 0.00000
## Max. :85.900 Max. :92.100 Max. :41.600 Max. :11.10000
## citizen income income_per_cap poverty
## Min. : 199 Min. : 19328 Min. : 8292 Min. : 1.4
## 1st Qu.: 8276 1st Qu.: 38826 1st Qu.:20470 1st Qu.:12.0
## Median : 19454 Median : 45095 Median :23575 Median :16.0
## Mean : 70849 Mean : 46824 Mean :24331 Mean :16.7
## 3rd Qu.: 50795 3rd Qu.: 52248 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 :31.05 Mean :18.25 Mean :22.13
## 3rd Qu.:29.50 3rd Qu.:34.42 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. : 5.2 Min. : 0.00
## 1st Qu.: 9.80 1st Qu.:11.50 1st Qu.:76.6 1st Qu.: 8.50
## Median :12.20 Median :15.40 Median :80.6 Median : 9.90
## Mean :12.75 Mean :15.82 Mean :79.1 Mean :10.33
## 3rd Qu.:15.00 3rd Qu.:19.40 3rd Qu.:83.6 3rd Qu.:11.90
## Max. :40.30 Max. :55.60 Max. :94.6 Max. :29.90
## transit walk other_transp work_at_home
## Min. : 0.0000 Min. : 0.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 0.1000 1st Qu.: 1.400 1st Qu.: 0.90 1st Qu.: 2.800
## Median : 0.4000 Median : 2.400 Median : 1.30 Median : 4.000
## Mean : 0.9681 Mean : 3.294 Mean : 1.61 Mean : 4.694
## 3rd Qu.: 0.8000 3rd Qu.: 4.000 3rd Qu.: 1.90 3rd Qu.: 5.700
## Max. :61.7000 Max. :71.200 Max. :39.10 Max. :37.200
## mean_commute employed private_work public_work
## Min. : 4.90 Min. : 166 Min. :29.50 Min. : 5.80
## 1st Qu.:19.30 1st Qu.: 4532 1st Qu.:70.90 1st Qu.:13.07
## Median :22.90 Median : 10657 Median :75.85 Median :16.10
## Mean :23.15 Mean : 46416 Mean :74.45 Mean :17.33
## 3rd Qu.:26.60 3rd Qu.: 29272 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 : 7.922 Mean :0.2917 Mean : 7.815
## 3rd Qu.: 9.400 3rd Qu.:0.3000 3rd Qu.: 9.700
## Max. :36.600 Max. :9.8000 Max. :29.400After looking at the summary statistics, the only unusual numbers is in the variable employed. This is supposed to be a percentage whereas I believe these are counts of employed population. In order to make them the percent of the population, I divided the employed by the population and multiplied by 100. The new summary shows the correct values.
summary(data2)## census_id state county total_pop
## Min. : 1001 Length:3140 Length:3140 Min. : 267
## 1st Qu.:18179 Class :character Class :character 1st Qu.: 11036
## Median :29176 Mode :character Mode :character Median : 25793
## Mean :30383 Mean : 100801
## 3rd Qu.:45080 3rd Qu.: 67620
## Max. :56045 Max. :10038388
## men women hispanic white
## Min. : 136 Min. : 131 Min. : 0.000 Min. : 0.90
## 1st Qu.: 5551 1st Qu.: 5488 1st Qu.: 1.900 1st Qu.:65.67
## Median : 12838 Median : 12916 Median : 3.700 Median :84.65
## Mean : 49597 Mean : 51204 Mean : 8.819 Mean :77.31
## 3rd Qu.: 33328 3rd Qu.: 34123 3rd Qu.: 9.000 3rd Qu.:93.33
## 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 : 8.885 Mean : 1.763 Mean : 1.253 Mean : 0.07357
## 3rd Qu.:10.200 3rd Qu.: 0.600 3rd Qu.: 1.200 3rd Qu.: 0.00000
## Max. :85.900 Max. :92.100 Max. :41.600 Max. :11.10000
## citizen income income_per_cap poverty
## Min. : 199 Min. : 19328 Min. : 8292 Min. : 1.4
## 1st Qu.: 8276 1st Qu.: 38826 1st Qu.:20470 1st Qu.:12.0
## Median : 19454 Median : 45095 Median :23575 Median :16.0
## Mean : 70849 Mean : 46824 Mean :24331 Mean :16.7
## 3rd Qu.: 50795 3rd Qu.: 52248 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 :31.05 Mean :18.25 Mean :22.13
## 3rd Qu.:29.50 3rd Qu.:34.42 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. : 5.2 Min. : 0.00
## 1st Qu.: 9.80 1st Qu.:11.50 1st Qu.:76.6 1st Qu.: 8.50
## Median :12.20 Median :15.40 Median :80.6 Median : 9.90
## Mean :12.75 Mean :15.82 Mean :79.1 Mean :10.33
## 3rd Qu.:15.00 3rd Qu.:19.40 3rd Qu.:83.6 3rd Qu.:11.90
## Max. :40.30 Max. :55.60 Max. :94.6 Max. :29.90
## transit walk other_transp work_at_home
## Min. : 0.0000 Min. : 0.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 0.1000 1st Qu.: 1.400 1st Qu.: 0.90 1st Qu.: 2.800
## Median : 0.4000 Median : 2.400 Median : 1.30 Median : 4.000
## Mean : 0.9681 Mean : 3.294 Mean : 1.61 Mean : 4.694
## 3rd Qu.: 0.8000 3rd Qu.: 4.000 3rd Qu.: 1.90 3rd Qu.: 5.700
## Max. :61.7000 Max. :71.200 Max. :39.10 Max. :37.200
## mean_commute employed private_work public_work
## Min. : 4.90 Min. : 166 Min. :29.50 Min. : 5.80
## 1st Qu.:19.30 1st Qu.: 4532 1st Qu.:70.90 1st Qu.:13.07
## Median :22.90 Median : 10657 Median :75.85 Median :16.10
## Mean :23.15 Mean : 46416 Mean :74.45 Mean :17.33
## 3rd Qu.:26.60 3rd Qu.: 29272 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 : 7.922 Mean :0.2917 Mean : 7.815
## 3rd Qu.: 9.400 3rd Qu.:0.3000 3rd Qu.: 9.700
## Max. :36.600 Max. :9.8000 Max. :29.400data2$employed <- (data2$employed/data2$total_pop) * 100
summary(data2$employed)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 16.57 39.01 43.66 43.36 48.19 76.24There are 1,984 counties that have more women than men.
nrow(data2[data2$women > data2$men, ])## [1] 1984There are 2,419 counties that have an unemployment rate lower than 10%.
nrow(data2[data2$unemployment < 10, ])## [1] 2419data3 <- arrange(data2, desc(mean_commute))
data3 <- data3[,c(1,2,3,29)]
dplyr::top_n(data3, 10)## # A tibble: 10 x 4
## census_id state county mean_commute
## <dbl> <chr> <chr> <dbl>
## 1 42103 Pennsylvania Pike 44
## 2 36005 New York Bronx 43
## 3 24017 Maryland Charles 42.8
## 4 51187 Virginia Warren 42.7
## 5 36081 New York Queens 42.6
## 6 36085 New York Richmond 42.6
## 7 51193 Virginia Westmoreland 42.5
## 8 8093 Colorado Park 42.4
## 9 36047 New York Kings 41.7
## 10 54015 West Virginia Clay 41.4data2$pct_women <- data2$women/data2$total_pop
data4 <- data2[,c(1,2,3,36)]
data5 <- arrange(data4,pct_women)
dplyr::top_n(data5, 10)## # A tibble: 10 x 4
## census_id state county pct_women
## <dbl> <chr> <chr> <dbl>
## 1 29117 Missouri Livingston 0.549
## 2 35011 New Mexico De Baca 0.551
## 3 51790 Virginia Staunton city 0.551
## 4 48137 Texas Edwards 0.552
## 5 51091 Virginia Highland 0.553
## 6 51620 Virginia Franklin city 0.555
## 7 28125 Mississippi Sharkey 0.555
## 8 1119 Alabama Sumter 0.557
## 9 13235 Georgia Pulaski 0.580
## 10 51720 Virginia Norton city 0.594All counties and states have exactly 100% of all races as expected.
data2$pct_race <- (data2$hispanic + data2$white + data2$black +
data2$native + data2$asian + data2$pacific)
data6 <- data2[,c(1,2,3,37)]
data7 <- arrange(data6,pct_race)
dplyr::top_n(data7, 10)## # A tibble: 11 x 4
## census_id state county pct_race
## <dbl> <chr> <chr> <dbl>
## 1 28021 Mississippi Claiborne 100.
## 2 48131 Texas Duval 100.
## 3 48261 Texas Kenedy 100.
## 4 48263 Texas Kent 100.
## 5 48377 Texas Presidio 100.
## 6 49001 Utah Beaver 100.
## 7 31125 Nebraska Nance 100.
## 8 31091 Nebraska Hooker 100.
## 9 48017 Texas Bailey 100.
## 10 48137 Texas Edwards 100.
## 11 31073 Nebraska Gosper 100.All counties and states have exactly 100% of all races as expected.
All counties and states have exactly 100% of all races as expected.
All counties and states have exactly 100% of all races as expected.
Having Trouble - kept receiving error when trying to sort by top 10
data2$carpool_rank <- data2 %>%
select(carpool) %>%
mutate(carpool_rank = percent_rank(desc(carpool)))
data8 <- data2[,c(1,2,3,38)]
data9 <- arrange(data8,desc(carpool_rank))