final lab

Part:1- Davidson County showed to have the highest amount of renter-occupied households on the map. Rutherford County had the second highest amount with 34.8 percent. All other counties had at least 20 percent or under.

```{r}if (!require(“tidyverse”)) install.packages(“tidyverse”)} if (!require(“tidycensus”)) install.packages(“tidycensus”) if (!require(“sf”)) install.packages(“sf”) if (!require(“mapview”)) install.packages(“mapview”)

library(tidyverse) library(tidycensus) library(sf) library(mapview)

census_api_key(“4ed7968903abe3ded81b469e74ccc6bcd8cb1e24”)

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)

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)

Part 2: Text is the lowest amounts of viewers. Video has a higher amount of viewers than both photo and text.


```r
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 errors

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        1416

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  1952

options(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

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 0.0000002

Part 3: The theme I detected was jobs. It was an often mentioned term.

if (!require("tidyverse")) install.packages("tidyverse")
if (!require("tidytext")) install.packages("tidytext")

## Loading required package: tidytext

library(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)`