Final Exam
Jesse Jones
2024-04-26
PART 1
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 errorsif (!require("tidycensus")) install.packages("tidycensus")## Loading required package: tidycensusif (!require("sf")) install.packages("sf")## Loading required package: sf
## Linking to GEOS 3.11.2, GDAL 3.7.2, PROJ 9.3.0; sf_use_s2() is TRUEif (!require("mapview")) install.packages("mapview")## Loading required package: mapview## Warning: package 'mapview' was built under R version 4.3.3library(tidyverse)
library(tidycensus)
library(sf)
library(mapview)
census_api_key("74c3d1fe0a1e580a10119351a7382c1f9ceb8c34")## To install your API key for use in future sessions, run this function with `install = TRUE`.DetailedTables <- load_variables(2022, "acs5", cache = TRUE)
SubjectTables <- load_variables(2022, "acs5/subject", cache = TRUE)
ProfileTables <- load_variables(2022, "acs5/profile", cache = TRUE)
ChosenVars <- filter(ProfileTables,name == "DP04_0047P")
print(ChosenVars$name)## [1] "DP04_0047P"print(ChosenVars$label)## [1] "Percent!!HOUSING TENURE!!Occupied housing units!!Renter-occupied"print(ChosenVars$concept)## [1] "Selected Housing Characteristics"VariableList =
c(Households_ = "DP04_0047P")
mydata <- get_acs(
geography = "county",
state = "TN",
variables = VariableList,
year = 2022,
survey = "acs5",
output = "wide",
geometry = TRUE)## Getting data from the 2018-2022 5-year ACS
## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.
## Using the ACS Data Profile##
|
| | 0%
|
| | 1%
|
|= | 1%
|
|= | 2%
|
|== | 2%
|
|== | 3%
|
|=== | 4%
|
|=== | 5%
|
|==== | 5%
|
|==== | 6%
|
|===== | 7%
|
|===== | 8%
|
|====== | 8%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 22%
|
|================= | 24%
|
|================= | 25%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 39%
|
|============================ | 40%
|
|============================ | 41%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|============================== | 44%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|======================================== | 58%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 60%
|
|========================================== | 61%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 63%
|
|============================================ | 64%
|
|============================================= | 64%
|
|============================================= | 65%
|
|============================================== | 65%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 69%
|
|================================================= | 70%
|
|================================================= | 71%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 79%
|
|======================================================== | 80%
|
|======================================================== | 81%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 82%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|=================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|==================================================================== | 98%
|
|===================================================================== | 98%
|
|======================================================================| 99%
|
|======================================================================| 100%mydata <-
separate_wider_delim(mydata,
NAME,
delim = ", ",
names = c("County", "State"))
filtereddata <- mydata %>%
filter(County == "Davidson County"|
County == "Rutherford County"|
County == "Williamson County"|
County == "Cheatham County"|
County == "Robertson County"|
County == "Sumner County"|
County == "Wilson County")
mapdata <- st_as_sf(filtereddata)
mapviewOptions(basemaps.color.shuffle = FALSE)
mapview(mapdata, zcol = "Households_E",
layer.name = "Pct. Households Occupied by Renters",
popup = TRUE)The map shows how Davidson County is the outlier here, with 45.8% of the households being renter-occupied. The surrounding counties have a smaller percentage.
PART 2
if (!require("tidyverse"))
install.packages("tidyverse")
library(tidyverse)
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/SocialData.csv")
mydata$DV <- mydata$Impressions
mydata$IV <- mydata$Type
averages <- group_by(mydata, IV) %>%
summarise(mean = mean(DV, na.rm = TRUE))
ggplot(mydata, aes(x = DV)) +
geom_histogram() +
facet_grid(IV ~ .) +
geom_histogram(color = "black", fill = "#1f78b4") +
geom_vline(data = averages, aes(xintercept = mean, ))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
The averages data set shows that on average a post with a video has over
300 more impressions when compared to simple photos or text. The graph
supports the idea that video posts gain much more impressions, showing a
right-skew on the video bar graph. Therefore, you should not lay off the
videographer.
PART 3
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/WhiteHouse.csv")
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("tidytext")) install.packages("tidytext")## Loading required package: tidytext## Warning: package 'tidytext' was built under R version 4.3.3library(tidyverse)
library(tidytext)
tidy_text <- mydata %>%
unnest_tokens(word,Full.Text) %>%
count(word, sort = TRUE)
data("stop_words")
tidy_text <- tidy_text %>%
anti_join(stop_words)## Joining with `by = join_by(word)`my_stopwords <- tibble(word = c("https",
"t.co",
"rt"))
tidy_text <- tidy_text %>%
anti_join(my_stopwords)## Joining with `by = join_by(word)`searchterms <- "Biden|Joe|president|biden's|potus"
mydata$Biden <- ifelse(grepl(searchterms,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$Biden)## [1] 3357searchterms2 <- "inflation|economy|money|economic|dollars"
mydata$money <- ifelse(grepl(searchterms2,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$money)## [1] 920A large amount of the White House’s posts discuss Joe Biden, which is no surprise. At least 3357 of the 5508 observed tweets mention him. That’s about 61 percent! Another repeated topic I noticed was money or economy. 920 times the White House twitter mentions terms regarding money. That’s about 17 percent.
Thank you for everything!!!