Import data from URL for BONUS
prison_data <- read.csv('https://raw.githubusercontent.com/wilsonvetdev/R_Bridge/main/texas.csv')
head(prison_data)
## X statefip year bmprison wmprison alcohol income ur poverty black
## 1 1 1 1985 6227 4210 1.90 11566 8.616667 20.6 25.86634
## 2 2 1 1986 6657 4423 1.90 12164 9.083334 23.8 25.82727
## 3 3 1 1987 7281 4803 1.89 12826 7.650000 21.3 25.77733
## 4 4 1 1988 7244 4605 1.89 13698 6.916667 19.3 25.73439
## 5 5 1 1989 8056 4998 1.87 14865 6.616667 18.9 25.69405
## 6 6 1 1990 9282 5421 1.92 15723 6.333333 19.2 25.59587
## perc1519 aidscapita state
## 1 8.461768 0.6795045 Alabama
## 2 8.473580 0.8516917 Alabama
## 3 8.397089 1.9672137 Alabama
## 4 8.280076 2.7581367 Alabama
## 5 8.088959 3.8459067 Alabama
## 6 7.868362 4.3703108 Alabama
1. Summary
summary(prison_data[c('bmprison', 'wmprison', 'poverty')])
## bmprison wmprison poverty
## Min. : 0.0 Min. : 76 Min. : 2.90
## 1st Qu.: 489.5 1st Qu.: 1734 1st Qu.:10.10
## Median : 3055.5 Median : 4176 Median :12.40
## Mean : 7625.8 Mean : 6324 Mean :13.06
## 3rd Qu.:11423.8 3rd Qu.: 7484 3rd Qu.:15.43
## Max. :61861.0 Max. :74992 Max. :27.20
## NA's :14
cat('The mean for black men in prison is:', mean(prison_data$bmprison))
## The mean for black men in prison is: 7625.753
cat('The median for black men in prison is:', median(prison_data$bmprison))
## The median for black men in prison is: 3055.5
cat('The mean for poverty is:', mean(prison_data$poverty))
## The mean for poverty is: 13.06164
cat('The median for poverty in prison is:', median(prison_data$poverty))
## The median for poverty in prison is: 12.4
2. Create new data drame
new_prison_data <- prison_data %>%
select(-statefip, -perc1519, -aidscapita) %>%
filter(year > 1990)
head(new_prison_data)
## X year bmprison wmprison alcohol income ur poverty black state
## 1 7 1991 10119 5579 1.76 16406 6.875000 18.8 25.70243 Alabama
## 2 8 1992 10660 5658 1.79 17327 6.883333 17.3 25.87369 Alabama
## 3 9 1993 11450 6011 1.86 17764 6.625000 17.4 26.02926 Alabama
## 4 10 1994 11996 6323 1.87 18606 5.383333 16.4 26.20609 Alabama
## 5 11 1995 12715 6654 1.81 19441 5.225000 20.1 26.35656 Alabama
## 6 12 1996 13397 6940 1.86 20081 4.491667 14.0 26.44337 Alabama
3. Update column names
new_prison_data <- new_prison_data %>% rename(
white_man_in_prison = wmprison,
black_man_in_prison = bmprison,
black_population_percentage = black,
unemployment_rate = ur
)
head(new_prison_data)
## X year black_man_in_prison white_man_in_prison alcohol income
## 1 7 1991 10119 5579 1.76 16406
## 2 8 1992 10660 5658 1.79 17327
## 3 9 1993 11450 6011 1.86 17764
## 4 10 1994 11996 6323 1.87 18606
## 5 11 1995 12715 6654 1.81 19441
## 6 12 1996 13397 6940 1.86 20081
## unemployment_rate poverty black_population_percentage state
## 1 6.875000 18.8 25.70243 Alabama
## 2 6.883333 17.3 25.87369 Alabama
## 3 6.625000 17.4 26.02926 Alabama
## 4 5.383333 16.4 26.20609 Alabama
## 5 5.225000 20.1 26.35656 Alabama
## 6 4.491667 14.0 26.44337 Alabama
4. Summary of new data frame
The new mean for this subset of data is higher than the original
data set for both black and white men in in prison. The avg poverty rate
is lowered when compared to the original data set.
summary(new_prison_data[c('black_man_in_prison', 'white_man_in_prison', 'poverty')])
## black_man_in_prison white_man_in_prison poverty
## Min. : 0.0 Min. : 76 Min. : 4.50
## 1st Qu.: 534.2 1st Qu.: 1950 1st Qu.: 9.90
## Median : 3936.5 Median : 4700 Median :12.10
## Mean : 9162.7 Mean : 7094 Mean :12.92
## 3rd Qu.:14648.0 3rd Qu.: 8332 3rd Qu.:15.40
## Max. :61861.0 Max. :74992 Max. :26.40
## NA's :12
cat('The mean for black men in prison is:', mean(new_prison_data$black_man_in_prison, na.rm = TRUE))
## The mean for black men in prison is: 9162.737
cat('The median for black men in prison is:', median(new_prison_data$black_man_in_prison, na.rm = TRUE))
## The median for black men in prison is: 3936.5
cat('The mean for poverty is:', mean(new_prison_data$poverty))
## The mean for poverty is: 12.91627
cat('The median for poverty in prison is:', median(new_prison_data$poverty))
## The median for poverty in prison is: 12.1
5. Rename values in a column.
new_prison_data <- new_prison_data %>% transmute(
year = year,
white_man_in_prison,
black_man_in_prison,
income,
unemployment_rate = format(round(unemployment_rate, 3), nsmall = 3),
black_population_percentage,
state,
poverty = format(round(poverty, 3), nsmall = 3), # shortened decimal places.
)
head(new_prison_data) # 6. display rows to see examples of all of steps 1 - 5 above.
## year white_man_in_prison black_man_in_prison income unemployment_rate
## 1 1991 5579 10119 16406 6.875
## 2 1992 5658 10660 17327 6.883
## 3 1993 6011 11450 17764 6.625
## 4 1994 6323 11996 18606 5.383
## 5 1995 6654 12715 19441 5.225
## 6 1996 6940 13397 20081 4.492
## black_population_percentage state poverty
## 1 25.70243 Alabama 18.800
## 2 25.87369 Alabama 17.300
## 3 26.02926 Alabama 17.400
## 4 26.20609 Alabama 16.400
## 5 26.35656 Alabama 20.100
## 6 26.44337 Alabama 14.000