Final Exam
Conner Smith
2024-04-24
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("34881bb6b9c7be69140a4398f7232bf90dbceaf0")## 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)
All_ACS_Variables <- bind_rows (DetailedTables, ProfileTables)
All_ACS_Variables <- bind_rows (All_ACS_Variables, SubjectTables)
rm (DetailedTables, SubjectTables, ProfileTables)VariableList =
c(Estimate_ = "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%
|
|===== | 6%
|
|===== | 7%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|========= | 13%
|
|========== | 14%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 22%
|
|================ | 23%
|
|================ | 24%
|
|================= | 24%
|
|================= | 25%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 28%
|
|===================== | 30%
|
|===================== | 31%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 46%
|
|================================= | 47%
|
|=================================== | 50%
|
|=================================== | 51%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 53%
|
|===================================== | 54%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 56%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 62%
|
|============================================ | 63%
|
|============================================ | 64%
|
|============================================= | 64%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|===================================================== | 75%
|
|===================================================== | 76%
|
|======================================================== | 80%
|
|======================================================== | 81%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================= | 88%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 89%
|
|=============================================================== | 90%
|
|=============================================================== | 91%
|
|================================================================ | 91%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 96%
|
|==================================================================== | 97%
|
|==================================================================== | 98%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 99%
|
|======================================================================| 100%mydata <-
separate_wider_delim(mydata,
NAME,
delim = ", ",
names = c("County", "State"))
mydata <- mydata %>%
filter(County == "Cheatham County"|
County == "Davidson County"|
County == "Robertson County"|
County == "Rutherford County"|
County == "Sumner County"|
County == "Williamson County"|
County == "Wilson County")mapdata <- mydata %>%
rename(Estimate = Estimate_E, Estimate_MOE = Estimate_M)
mapdata <- st_as_sf(mapdata)
mapviewOptions(basemaps.color.shuffle = FALSE)
mapview(mapdata, zcol = "Estimate",
layer.name = "Pct. with Estimate",
popup = TRUE)CSVdata <- st_drop_geometry(mapdata)
write.csv(CSVdata, "mydata.csv", row.names = FALSE)Summary: The data shows that in more cities there are more renters than people who own their own house.
Part 2
if (!require("tidyverse"))
install.packages("tidyverse")
library(tidyverse)
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 1416mydata$DV <- mydata$Impressions
mydata$IV <- mydata$Typeaverages <- 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 0.0000002Summary: Looking at the study, pictures and videos are what they post the most and get the most interactions.
Part 3
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)mydata <- read.csv("https://raw.githubusercontent.com/drkblake/Data/main/WhiteHouse.csv")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 <- "Date|URL|Author|Full.Text."
mydata$WhiteHouse <- ifelse(grepl(searchterms,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$WhiteHouse)## [1] 172Summary: Pretty much all of the post’s are basically PR and hyping up the people in office.