FINAL
Noah McLane
2024-04-24
Part I:
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 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUEif (!require("mapview")) install.packages("mapview")## Loading required package: mapviewlibrary(tidyverse)
library(tidycensus)
library(sf)
library(mapview)
census_api_key("eeef83e543a37e20cdbb5c2acfd18d8c6998354f")## 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%
|
|=== | 4%
|
|=== | 5%
|
|==== | 5%
|
|==== | 6%
|
|===== | 6%
|
|===== | 7%
|
|===== | 8%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|======= | 11%
|
|======== | 11%
|
|======== | 12%
|
|========= | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============ | 18%
|
|============= | 18%
|
|============= | 19%
|
|============== | 19%
|
|============== | 20%
|
|============== | 21%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================ | 24%
|
|================= | 24%
|
|================= | 25%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 26%
|
|=================== | 27%
|
|=================== | 28%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 29%
|
|===================== | 30%
|
|====================== | 32%
|
|======================= | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 35%
|
|========================= | 36%
|
|========================== | 36%
|
|========================== | 37%
|
|========================== | 38%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================== | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|=============================== | 45%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 49%
|
|=================================== | 50%
|
|==================================== | 52%
|
|===================================== | 52%
|
|===================================== | 53%
|
|===================================== | 54%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 55%
|
|======================================= | 56%
|
|============================================ | 63%
|
|============================================= | 65%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 66%
|
|=============================================== | 67%
|
|=============================================== | 68%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 69%
|
|================================================= | 70%
|
|================================================= | 71%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 75%
|
|====================================================== | 77%
|
|=========================================================== | 84%
|
|=============================================================== | 90%
|
|=============================================================== | 91%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 92%
|
|================================================================= | 93%
|
|================================================================= | 94%
|
|================================================================== | 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 = "Estimate",
popup = TRUE)CSVdata <- st_drop_geometry(mapdata)
write.csv(CSVdata, "mydata.csv", row.names = FALSE)Summary: The map rendered by this code shows viewers the percent of households occupied by renters. Nashville sees the highest rate of renters while less than one in five Cheatam County residents rent.
Part II:
# Install and load tidyverse
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$IV <- mydata$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 0.0000002Summary: Video averaged more than 300 more impression than photos and close to 400 more average impressions than text posts. This data, if presented, would create a clear and sturdy argument for keeping the videographer on board.
Part III:
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("tidytext")) install.packages("tidytext")## Loading required package: tidytextlibrary(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 <- "Immigration|taxes|gender|race"
mydata$Biden <- ifelse(grepl(searchterms,
mydata$Full.Text,
ignore.case = TRUE),1,0)
sum(mydata$Biden)## [1] 137Summary: Family, jobs, health, inflation. While sifting through the mmost used words, the four above this text stood out the most to me because they signify the administration sees those topics as worth talking about. I think this is an expansion of the Democratic platform because those topics are things everyday Americans are often most concerned about.