Lets import data on Food insecurity in the US
Map_data <- read.csv('https://raw.githubusercontent.com/Kingtilon1/DATA608/main/mapdata2022%20-%20Map%20Data%20%20-%20mapdata2022%20-%20Map%20Data%20(1)%20(1).csv')
glimpse(Map_data)
## Rows: 52
## Columns: 7
## $ State <chr> "U.S.", "AK", "AL", "AR", "AZ", "CA"…
## $ Number.of.households <chr> "131,744,000", "273,000", "2,062,000…
## $ Interviewed <chr> "96,426", "1,155", "1,806", "1,748",…
## $ Food.insecurity.Prevalence <dbl> 11.2, 9.5, 12.4, 16.6, 10.2, 10.3, 8…
## $ Margin.of.error2 <dbl> 0.20, 2.20, 2.02, 1.75, 1.62, 0.62, …
## $ Very.low.food.security.Prevalence <dbl> 4.3, 4.2, 4.7, 6.5, 4.0, 3.8, 3.4, 3…
## $ Margin.of.error2.1 <dbl> 0.13, 1.25, 1.07, 0.98, 0.95, 0.43, …
sorted_data <- Map_data[order(-Map_data$Food.insecurity.Prevalence), ]
fig <- plot_ly(sorted_data, x = ~State, y = ~Food.insecurity.Prevalence, type = "bar") %>%
layout(title = "Food Insecurity Prevalence by State",
xaxis = list(title = "State"),
yaxis = list(title = "Food Insecurity Prevalence"))
table_data <- head(sorted_data[, c("State", "Food.insecurity.Prevalence", "Very.low.food.security.Prevalence")], 5)
fig
table_data
## State Food.insecurity.Prevalence Very.low.food.security.Prevalence
## 4 AR 16.6 6.5
## 45 TX 15.5 5.8
## 27 MS 15.3 5.3
## 20 LA 15.2 6.1
## 42 SC 14.5 6.8
Notice how Arkansas ranks the highest in food insecurity,followed by TEXAS, Based off of th e heat map we see that states towards the south have the higher value in terms of food insecurity, this can be due to poverty rates, which tend to be higher in southern states, or unemployment.
Map_data$Full_State <- state.name[match(Map_data$State, state.abb)]
fig <- plot_geo(Map_data, locationmode = "USA-states") %>%
add_trace(
z = ~Food.insecurity.Prevalence,
locations = ~State,
text = ~paste("State: ", Full_State,
"<br>Food Insecurity Prevalence: ", Food.insecurity.Prevalence,
"<br>Very Low Food Security Prevalence: ", Very.low.food.security.Prevalence,
"<br>Number of Households: ", Number.of.households),
colorscale = "Viridis",
colorbar = list(title = "Food Insecurity Prevalence")
) %>%
layout(
title = "Food Insecurity Prevalence by State",
geo = list(scope = "usa", projection = list(type = "albers usa"))
)
fig
Poverty_rate <- read.csv('https://raw.githubusercontent.com/Kingtilon1/DATA608/main/poverty-rate-by-state-2024.csv')
Poverty_rate <- Poverty_rate %>%
mutate(State = state.abb[match(state, state.name)]) %>%
select(State, everything())
Poverty_rate <- Poverty_rate %>%
select(-state)
# Drop rows where the 'State' column is NA
Poverty_rate <- na.omit(Poverty_rate)
sorted_data <- Poverty_rate[order(-Poverty_rate$PovertyRatesPercentOfPopulationBelowPovertyLevel), ]
head(sorted_data)
## State PovertyRatesPopulationBelowPovertyLevel
## 19 LA 883236
## 25 MS 554152
## 32 NM 382798
## 49 WV 291930
## 18 KY 721878
## 4 AR 480153
## PovertyRatesPercentOfPopulationBelowPovertyLevel
## 19 19.6
## 25 19.4
## 32 18.4
## 49 16.8
## 18 16.5
## 4 16.3
Display the data as a heat map
Poverty_rate$Full_State <- state.name[match(Poverty_rate$State, state.abb)]
fig <- plot_geo(Poverty_rate, locationmode = "USA-states") %>%
add_trace(
z = ~PovertyRatesPercentOfPopulationBelowPovertyLevel,
locations = ~State,
text = ~paste("State: ", Full_State),
colorscale = "Viridis",
colorbar = list(title = "Poverty by State")
) %>%
layout(
title = "Poverty Rate Prevalence by State",
geo = list(scope = "usa", projection = list(type = "albers usa"))
)
fig
merged_data <- merge(Poverty_rate, Map_data, by = "State", all = TRUE)
plot_ly(merged_data, x = ~PovertyRatesPercentOfPopulationBelowPovertyLevel, y = ~Food.insecurity.Prevalence, type = "scatter", mode = "markers",
marker = list(color = "blue")) %>%
layout(title = "Poverty Rate vs. Food Insecurity Prevalence",
xaxis = list(title = "Poverty Rate"),
yaxis = list(title = "Food Insecurity Prevalence"))
## Warning: Ignoring 2 observations
The scatter plot shows a clear positive trend between poverty rate and food insecurity prevalence. As poverty rate increases, so does food insecurity. This suggests a strong relationship between socioeconomic factors and access to food resources. Addressing poverty is crucial for reducing food insecurity.
Store data frame
Food_by_age <- read.csv('https://raw.githubusercontent.com/Kingtilon1/DATA608/main/Food%20insecurity%20by%20gender%2C%20and%20age%20-%20US.csv')
Increasing_age <- read.csv('https://raw.githubusercontent.com/Kingtilon1/DATA608/main/age%20-%20Sheet1.csv')
colnames(Food_by_age) <- NULL
# Assign the first row as the new header
colnames(Food_by_age) <- Food_by_age[1, ]
# Remove the first row (since it's now the header)
Food_by_age <- Food_by_age[-1, ]
colnames(Food_by_age)[1] <- "categories"
colnames(Food_by_age)[2] <- "total"
male_data <- subset(Food_by_age, categories == "Male")
female_data <- subset(Food_by_age, categories == "Female")
Increasing_age <- Increasing_age[Increasing_age$Age != "Total", ]
Increasing_age$Age <- factor(Increasing_age$Age, levels = unique(Increasing_age$Age))
fig <- plot_ly(Increasing_age, x = ~Age, y = ~Number.of.SNAP.participants..Millions., type = 'scatter', mode = 'line')
fig <- fig %>% layout(
xaxis = list(title = 'Age', type = 'category'),
yaxis = list(title = 'Number of SNAP participants (Millions)'),
title = 'Trend of SNAP Participants by Age'
)
fig
This graph illustrates the age distribution of individuals participating in the Supplemental Nutrition Assistance Program (SNAP), providing a valuable benchmark for assessing support needs as individuals age.