Final Exam
Aysia King
2024-04-22
Part 1: Mapping
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: mapviewlibrary(tidyverse)
library(tidycensus)
library(sf)
library(mapview)
# Transmitting API key
census_api_key("634fb2ff81a5408504b8d902b244d17ae67ff1a8")## To install your API key for use in future sessions, run this function with `install = TRUE`.# Fetching ACS codebooks
DetailedTables <- load_variables(2022, "acs5", cache = TRUE)
SubjectTables <- load_variables(2022, "acs5/subject", cache = TRUE)
ProfileTables <- load_variables(2022, "acs5/profile", cache = TRUE)
# Double checking target variables
# Note the DP03_0062 variable name ##############################
ChosenVars <- filter(ProfileTables,name == "DP02_0001"|
name == "DP04_0047P")
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"# Specifying target variables
VariableList =
c(Renters_ = "DP04_0047P",
Households_ = "DP02_0001")
# Fetching data
# Note the state = "TN" mod
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%
|
|======= | 10%
|
|======= | 11%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|================ | 23%
|
|================= | 25%
|
|================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|============================== | 44%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================= | 48%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 49%
|
|=================================== | 50%
|
|=================================== | 51%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|======================================== | 58%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================= | 65%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 79%
|
|======================================================== | 80%
|
|======================================================== | 81%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 82%
|
|=========================================================== | 84%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================= | 88%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|=============================================================== | 91%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 98%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%# Reformatting data
mydata <-
separate_wider_delim(mydata,
NAME,
delim = ", ",
names = c("County", "State"))
# Filtering data
# Note the list of Tennessee counties ##############################
filtereddata <- mydata %>%
filter(County == "Cheatham County"|
County == "Davidson County"|
County == "Robertson County"|
County == "Rutherford County"|
County == "Sumner County"|
County == "Williamson County"|
County == "Wilson County")
# Plotting data
# Note the subtitle change ##############################
ggplot(filtereddata, aes(x = Renters_E, y = reorder(County, Renters_E))) +
geom_errorbarh(aes(xmin = Renters_E - Renters_M, xmax = Renters_E + Renters_M)) +
geom_point(size = 3, color = "darkblue") +
theme_minimal(base_size = 12.5) +
labs(title = "Median HH Renters",
subtitle = "Nashville-area counties. Brackets show error margins.",
x = "2018-2022 ACS estimate",
y = "")
# Mapping data
mapdata <- filtereddata %>%
rename(Renters = Renters_E,
Households = Households_E)
mapdata <- st_as_sf(mapdata)
mapviewOptions(basemaps.color.shuffle = FALSE)
mapview(mapdata, zcol = "Renters",
layer.name = "Renters",
popup = TRUE)From the map shown above you can see that Davidson County is mostly rented and the most rented area in the Nashville area at an estimated 46%.
Part 2: Statistics
# Install and load tidyverse
if (!require("tidyverse"))
install.packages("tidyverse")
library(tidyverse)
# Read the data
# NOTE: You may edit the URL to load a different dataset
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/SocialData.csv")
head(mydata,10)## ID Type Impressions
## 1 1 Photo 695
## 2 2 Text 940
## 3 3 Photo 1196
## 4 4 Photo 936
## 5 5 Photo 1389
## 6 6 Photo 857
## 7 7 Text 797
## 8 8 Photo 1810
## 9 9 Photo 1086
## 10 10 Video 1416# Specify the DV and IV
# NOTE: You may edit the FGP and Team variable names
mydata$DV <- mydata$Impressions
mydata$IV <- mydata$Type
# Graph the group distributions and averages
averages <- group_by(mydata, IV) %>%
summarise(mean = mean(DV, na.rm = TRUE))
ggplot(mydata, aes(x = DV)) +
geom_histogram() +
facet_grid(IV ~ .) +
geom_histogram(color = "black", fill = "#1f78b4") +
geom_vline(data = averages, aes(xintercept = mean, ))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
# Calculate and show the group counts, means, standard
# deviations, minimums, and maximums
group_by(mydata, IV) %>%
summarise(
count = n(),
mean = mean(DV, na.rm = TRUE),
sd = sd(DV, na.rm = TRUE),
min = min(DV, na.rm = TRUE),
max = max(DV, na.rm = TRUE))## # A tibble: 3 × 6
## IV count mean sd min max
## <chr> <int> <dbl> <dbl> <int> <int>
## 1 Photo 58 1035. 297. 397 1810
## 2 Text 43 999. 278. 515 1746
## 3 Video 39 1370. 307. 829 1952options(scipen = 999)
oneway.test(mydata$DV ~ mydata$IV,
var.equal = FALSE)##
## One-way analysis of means (not assuming equal variances)
##
## data: mydata$DV and mydata$IV
## F = 19.119, num df = 2.000, denom df = 85.525, p-value = 0.000000137# If the ANOVA detects significant difference, run
# this post-hoc procedure to learn which
# group pairs differed significantly.
anova_1 <- aov(mydata$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 0.0000002I was able to conclude that video does perform better than text and photos due to reasons other than randomness.
Part 3: Text Analysis
# Load packages
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)
# Read the data
mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/WhiteHouse.csv")
# Extract individual words to a "tidytext" data frame
tidy_text <- mydata %>%
unnest_tokens(word,Full.Text) %>%
count(word, sort = TRUE)
# Delete standard stop words
data("stop_words")
tidy_text <- tidy_text %>%
anti_join(stop_words)## Joining with `by = join_by(word)`# Delete custom stop words
my_stopwords <- tibble(word = c("https",
"t.co",
"rt"))
tidy_text <- tidy_text %>%
anti_join(my_stopwords)## Joining with `by = join_by(word)`# Define search terms and count items that include them
# "Biden" terms are used as an example
searchterms <- "Biden|Joe|president|administration"
mydata$Biden <- ifelse(grepl(searchterms,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$Biden)## [1] 3391I chose to analyze Biden as no suprise most of the White House correspondence has been about Biden with 29% of their tweets including the man in some form.