#Tahra Cartwright MidTerm Submission
#Task1 response: For line 4-9, We are asking R Studio to install tidyverse (library that will help visualize data), followed by assing variables with unique names
# INC2022 = district’s estimated median household income in 2022.
# INC2017 = district’s estimated median household income in 2017.
if(!require(tidyverse))install.packages("tidyverse")## Loading required package: tidyverse## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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 errorslibrary(tidyverse)
Inc2022 <- read.csv("https://drkblake.com/wp-content/uploads/2024/02/Inc2022.csv")
Inc2017 <- read.csv("https://drkblake.com/wp-content/uploads/2024/02/Inc2017.csv")
#Task2 response: Line 13-19, Our data frame will be from Inc2017 to Inc2022.
# We are then merging HHInc2017 and HHInc2022 to for our key variable of IncomeINC
IncomeINC <- left_join(Inc2017,
Inc2022,
by = join_by(GEOID == GEOID))
head(IncomeINC, 10)## GEOID HHInc2017 District County HHInc2022 Significance
## 1 4702190022 44091 District 1 Cheatham County 59741 Significant
## 2 4702190212 55247 District 2 Cheatham County 73634 Significant
## 3 4702190402 73802 District 3 Cheatham County 89861 Nonsignificant
## 4 4702190592 49731 District 4 Cheatham County 73293 Significant
## 5 4702190782 60793 District 5 Cheatham County 78380 Significant
## 6 4702190972 66750 District 6 Cheatham County 92305 Significant
## 7 4703790038 56258 District 1 Davidson County 75038 Significant
## 8 4703790228 32487 District 2 Davidson County 54346 Significant
## 9 4703790418 49402 District 3 Davidson County 67953 Significant
## 10 4703790608 79381 District 4 Davidson County 106260 Significant #Task3 Change is our assigned variable ( This is the total from HHINC2022-HHInc2017)
Change <- IncomeINC %>%
mutate(Change = HHInc2022 - HHInc2017)
head(Change, 10)## GEOID HHInc2017 District County HHInc2022 Significance
## 1 4702190022 44091 District 1 Cheatham County 59741 Significant
## 2 4702190212 55247 District 2 Cheatham County 73634 Significant
## 3 4702190402 73802 District 3 Cheatham County 89861 Nonsignificant
## 4 4702190592 49731 District 4 Cheatham County 73293 Significant
## 5 4702190782 60793 District 5 Cheatham County 78380 Significant
## 6 4702190972 66750 District 6 Cheatham County 92305 Significant
## 7 4703790038 56258 District 1 Davidson County 75038 Significant
## 8 4703790228 32487 District 2 Davidson County 54346 Significant
## 9 4703790418 49402 District 3 Davidson County 67953 Significant
## 10 4703790608 79381 District 4 Davidson County 106260 Significant
## Change
## 1 15650
## 2 18387
## 3 16059
## 4 23562
## 5 17587
## 6 25555
## 7 18780
## 8 21859
## 9 18551
## 10 26879 #Task4 Level is our assigned variable (Change is assigned 3 vaules equaling assigned lables)
Level <- Change %>%
mutate(Level = case_when(Change < 100000 ~ ">$100k",
Change == 100000 ~ "$100k",
Change > 100000 ~ "$100k+",
.default = "Error"))
head(Level, 10)## GEOID HHInc2017 District County HHInc2022 Significance
## 1 4702190022 44091 District 1 Cheatham County 59741 Significant
## 2 4702190212 55247 District 2 Cheatham County 73634 Significant
## 3 4702190402 73802 District 3 Cheatham County 89861 Nonsignificant
## 4 4702190592 49731 District 4 Cheatham County 73293 Significant
## 5 4702190782 60793 District 5 Cheatham County 78380 Significant
## 6 4702190972 66750 District 6 Cheatham County 92305 Significant
## 7 4703790038 56258 District 1 Davidson County 75038 Significant
## 8 4703790228 32487 District 2 Davidson County 54346 Significant
## 9 4703790418 49402 District 3 Davidson County 67953 Significant
## 10 4703790608 79381 District 4 Davidson County 106260 Significant
## Change Level
## 1 15650 >$100k
## 2 18387 >$100k
## 3 16059 >$100k
## 4 23562 >$100k
## 5 17587 >$100k
## 6 25555 >$100k
## 7 18780 >$100k
## 8 21859 >$100k
## 9 18551 >$100k
## 10 26879 >$100k #Task 5 We are aggrigating data. We are aggregating Level to come out with County and level being compaired
Level <- group_by(Level, County, Level)
head(Level, 20)## # A tibble: 20 × 8
## # Groups: County, Level [2]
## GEOID HHInc2017 District County HHInc2022 Significance Change Level
## <dbl> <int> <chr> <chr> <int> <chr> <int> <chr>
## 1 4702190022 44091 District 1 Cheatha… 59741 Significant 15650 >$10…
## 2 4702190212 55247 District 2 Cheatha… 73634 Significant 18387 >$10…
## 3 4702190402 73802 District 3 Cheatha… 89861 Nonsignific… 16059 >$10…
## 4 4702190592 49731 District 4 Cheatha… 73293 Significant 23562 >$10…
## 5 4702190782 60793 District 5 Cheatha… 78380 Significant 17587 >$10…
## 6 4702190972 66750 District 6 Cheatha… 92305 Significant 25555 >$10…
## 7 4703790038 56258 District 1 Davidso… 75038 Significant 18780 >$10…
## 8 4703790228 32487 District 2 Davidso… 54346 Significant 21859 >$10…
## 9 4703790418 49402 District 3 Davidso… 67953 Significant 18551 >$10…
## 10 4703790608 79381 District 4 Davidso… 106260 Significant 26879 >$10…
## 11 4703790798 40220 District 5 Davidso… 71189 Significant 30969 >$10…
## 12 4703790988 50871 District 6 Davidso… 82996 Significant 32125 >$10…
## 13 4703791178 46594 District 7 Davidso… 72500 Significant 25906 >$10…
## 14 4703791368 39885 District 8 Davidso… 62232 Significant 22347 >$10…
## 15 4703791558 39769 District 9 Davidso… 54322 Significant 14553 >$10…
## 16 4703791748 47270 District 10 Davidso… 58338 Significant 11068 >$10…
## 17 4703791938 57086 District 11 Davidso… 73158 Significant 16072 >$10…
## 18 4703792128 61720 District 12 Davidso… 85559 Significant 23839 >$10…
## 19 4703792318 46435 District 13 Davidso… 63110 Significant 16675 >$10…
## 20 4703792508 53068 District 14 Davidso… 64380 Significant 11312 >$10…Level <- summarize(Level,Count = n ())## `summarise()` has grouped output by 'County'. You can override using the
## `.groups` argument.head(Level, 10)## # A tibble: 7 × 3
## # Groups: County [7]
## County Level Count
## <chr> <chr> <int>
## 1 Cheatham County >$100k 6
## 2 Davidson County >$100k 35
## 3 Robertson County >$100k 12
## 4 Rutherford County >$100k 21
## 5 Sumner County >$100k 12
## 6 Williamson County >$100k 12
## 7 Wilson County >$100k 25 #Task 6 aggregating data.RichDistricts = top earning districts
RichDistricts <- group_by(Level, Count = 100000)
head(Level, 10)## # A tibble: 7 × 3
## # Groups: County [7]
## County Level Count
## <chr> <chr> <int>
## 1 Cheatham County >$100k 6
## 2 Davidson County >$100k 35
## 3 Robertson County >$100k 12
## 4 Rutherford County >$100k 21
## 5 Sumner County >$100k 12
## 6 Williamson County >$100k 12
## 7 Wilson County >$100k 25 #Task7 I used setDT which sets values into decending order
library(data.table)##
## Attaching package: 'data.table'
##
## The following objects are masked from 'package:lubridate':
##
## hour, isoweek, mday, minute, month, quarter, second, wday, week,
## yday, year
##
## The following objects are masked from 'package:dplyr':
##
## between, first, last
##
## The following object is masked from 'package:purrr':
##
## transposesetDT(Level)[order(-Level)]## County Level Count
## 1: Cheatham County >$100k 6
## 2: Davidson County >$100k 35
## 3: Robertson County >$100k 12
## 4: Rutherford County >$100k 21
## 5: Sumner County >$100k 12
## 6: Williamson County >$100k 12
## 7: Wilson County >$100k 25#Task 8 A interesting pattern I noticed with this visulized data, Cheatham county is one of the overall riches county with 6 out of 7 entry being listed in our RichDistricts. I would like to also note that there is a income difference amongst davidsons districts.```