Final Exam
maja lakes
2024-04-22
This is my final exam script.
Part 1
This code creates a map of filtered data for specific nashville area counties and their percentages of households that are renter occupied. Davidson County has the highest percentage of renters at 45.8% of households. Cheatham county has the lowest percentage at 18.8% of households.
if (!require("tidyverse")) install.packages("tidyverse")## Loading required package: tidyverse## Warning: package 'tidyverse' was built under R version 4.3.3## ── 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("6fc0d69837f63fba2a26c30d3b4cacddd913742f")## 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"|
name == "DP02_0001")
print(ChosenVars$name)## [1] "DP02_0001" "DP04_0047P"print(ChosenVars$label)## [1] "Estimate!!HOUSEHOLDS BY TYPE!!Total households"
## [2] "Percent!!HOUSING TENURE!!Occupied housing units!!Renter-occupied"print(ChosenVars$concept)## [1] "Selected Social Characteristics in the United States"
## [2] "Selected Housing Characteristics"VariableList =
c(Rentals_ = "DP04_0047P",
Households_ = "DP02_0001")
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%
|
|====== | 9%
|
|======= | 9%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 19%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================ | 24%
|
|================= | 25%
|
|================== | 25%
|
|=================== | 27%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|====================== | 31%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|============================ | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================== | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================= | 48%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================= | 65%
|
|=============================================== | 66%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================= | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|====================================================== | 78%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 79%
|
|======================================================== | 80%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================= | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|=============================================================== | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 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")
ggplot(filtereddata, aes(x = Rentals_E, y = reorder(County, Rentals_E))) +
geom_errorbarh(aes(xmin = Rentals_E - Rentals_M, xmax = Rentals_E + Rentals_M)) +
geom_point(size = 3, color = "darkblue") +
theme_minimal(base_size = 12.5) +
labs(title = "Pct. households that are renter occupied",
subtitle = "Nashville-area counties. Brackets show error margins.",
x = "2018-2022 ACS estimate",
y = "")
mapdata <- filtereddata %>%
rename(Rentals = Rentals_E,
Households = Households_E)
mapdata <- st_as_sf(mapdata)
mapviewOptions(basemaps.color.shuffle = FALSE)
mapview(mapdata, zcol = "Rentals",
layer.name = "Pct. Renter Occupied",
popup = TRUE)CSVdata <- st_drop_geometry(mapdata)
write.csv(CSVdata, "mydata.csv", row.names = FALSE)Part 2
each plot shows a comparitive analysis of text,photo, or video. Video and text have the most significant difference between them in regards to number of impressions. Text and photo also differ but not at significantly as video and photo. the videographer in question does increase the impressions for the football teams social media accounts.
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/SocialData.csv")
if (!require("tidyverse"))
install.packages("tidyverse")
library(tidyverse)
mydata$DV <- mydata$Impressions
mydata$IV <- mydata$Type
averages <- group_by(mydata, IV) %>%
summarise(mean = mean(DV, na.rm = TRUE))
ggplot(mydata, aes(x = DV)) +
geom_histogram() +
facet_grid(IV ~ .) +
geom_histogram(color = "black", fill = "#1f78b4") +
geom_vline(data = averages, aes(xintercept = mean, ))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
group_by(mydata, IV) %>%
summarise(
count = n(),
mean = mean(DV, na.rm = TRUE),
sd = sd(DV, na.rm = TRUE),
min = min(DV, na.rm = TRUE),
max = max(DV, na.rm = TRUE))## # A tibble: 3 × 6
## IV count mean sd min max
## <chr> <int> <dbl> <dbl> <int> <int>
## 1 Photo 58 1035. 297. 397 1810
## 2 Text 43 999. 278. 515 1746
## 3 Video 39 1370. 307. 829 1952options(scipen = 999)
oneway.test(mydata$DV ~ mydata$IV,
var.equal = FALSE)##
## One-way analysis of means (not assuming equal variances)
##
## data: mydata$DV and mydata$IV
## F = 19.119, num df = 2.000, denom df = 85.525, p-value = 0.000000137anova_1 <- aov(mydata$DV ~ mydata$IV)
TukeyHSD(anova_1)## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = mydata$DV ~ mydata$IV)
##
## $`mydata$IV`
## diff lwr upr p adj
## Text-Photo -36.35605 -176.6202 103.9081 0.8126345
## Video-Photo 334.87710 190.5414 479.2128 0.0000005
## Video-Text 371.23315 217.1076 525.3587 0.0000002Part 3
I chose to search terms that were related to education. i used “student”, “loan”, “Education”, and”administration”. these terms appeared 1316 times throughout white house twitter communication. this gives the impression that the Biden/Harris administration values discussing these topics. 1,316 out of 5,508 tweets being about education is substantial and reflective of an important issue right now.
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 <- "Student|Loan|Education|administration"
mydata$Biden <- ifelse(grepl(searchterms,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$Biden)## [1] 1316