Activity-9

Sujith Prakash Parsa

2022-11-03

Setup

Loading all the required libraries

library(tidyverse)
library(skimr)
library(ggthemes)

Importing all the data sets

# Observed annual average temperatures for the Lower 48 states
tempState <- read_csv("https://raw.githubusercontent.com/washingtonpost/data-2C-beyond-the-limit-usa/main/data/processed/climdiv_state_year.csv")

# Observed annual average temperatures for counties in the Lower 48 states
tempCounty <- read_csv("https://raw.githubusercontent.com/washingtonpost/data-2C-beyond-the-limit-usa/main/data/processed/climdiv_county_year.csv")

# Temperature change estimates for each of the Lower 48 states
tempChangeState <- read_csv("https://github.com/washingtonpost/data-2C-beyond-the-limit-usa/raw/main/data/processed/model_state.csv")

# Temperature change estimates for counties in the contiguous U.S.
tempChangeCounty <- read_csv("https://github.com/washingtonpost/data-2C-beyond-the-limit-usa/raw/main/data/processed/model_county.csv")

Using skim and glimpse

skim(tempState)
Data summary
Name tempState
Number of rows 6000
Number of columns 4
_______________________
Column type frequency:
character 1
numeric 3
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
fips 0 1 2 2 0 48 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1 1957.00 36.09 1895.00 1926.00 1957.00 1988.00 2019.00 ▇▇▇▇▇
temp 0 1 51.62 8.01 34.90 45.18 50.77 57.56 73.36 ▃▇▇▅▁
tempc 0 1 10.90 4.45 1.61 7.32 10.43 14.20 22.98 ▃▇▇▅▁ 
glimpse(tempState)
## Rows: 6,000
## Columns: 4
## $ fips  <chr> "01", "01", "01", "01", "01", "01", "01", "01", "01", "01", "01"…
## $ year  <dbl> 1895, 1896, 1897, 1898, 1899, 1900, 1901, 1902, 1903, 1904, 1905…
## $ temp  <dbl> 61.64167, 64.26667, 64.19167, 62.98333, 63.10000, 63.40833, 61.3…
## $ tempc <dbl> 16.46759, 17.92593, 17.88426, 17.21296, 17.27778, 17.44907, 16.3…
skim(tempCounty)
Data summary
Name tempCounty
Number of rows 388375
Number of columns 4
_______________________
Column type frequency:
character 1
numeric 3
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
fips 0 1 5 5 0 3107 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1 1957.00 36.08 1895.00 1926.00 1957.00 1988.00 2019.00 ▇▇▇▇▇
temp 0 1 54.00 8.43 30.51 47.65 53.91 60.53 78.82 ▁▆▇▆▁
tempc 0 1 12.22 4.68 -0.83 8.69 12.17 15.85 26.01 ▁▆▇▆▁ 
glimpse(tempCounty)
## Rows: 388,375
## Columns: 4
## $ fips  <chr> "01001", "01001", "01001", "01001", "01001", "01001", "01001", "…
## $ year  <dbl> 1895, 1896, 1897, 1898, 1899, 1900, 1901, 1902, 1903, 1904, 1905…
## $ temp  <dbl> 62.63333, 65.34167, 65.15000, 63.81667, 63.92500, 64.17500, 62.2…
## $ tempc <dbl> 17.01852, 18.52315, 18.41667, 17.67593, 17.73611, 17.87500, 16.8…
skim(tempChangeCounty)
Data summary
Name tempChangeCounty
Number of rows 3107
Number of columns 9
_______________________
Column type frequency:
character 4
numeric 5
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
fips 0 1 5 5 0 3107 0
max_warming_season 0 1 4 6 0 4 0
CTYNAME 0 1 10 27 0 1842 0
STNAME 0 1 4 20 0 49 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Fall 0 1 0.54 0.54 -0.85 0.15 0.50 0.90 2.53 ▂▇▇▂▁
Spring 0 1 0.83 0.54 -0.61 0.44 0.83 1.21 2.79 ▂▇▇▂▁
Summer 0 1 0.46 0.62 -0.94 -0.01 0.34 0.87 2.58 ▂▇▅▂▁
Winter 0 1 1.41 0.71 -0.20 0.95 1.32 1.80 3.74 ▂▇▆▂▁
Annual 0 1 0.81 0.55 -0.57 0.40 0.74 1.20 2.54 ▂▇▇▃▁ 
glimpse(tempChangeCounty)
## Rows: 3,107
## Columns: 9
## $ fips               <chr> "01001", "01003", "01005", "01007", "01009", "01011…
## $ Fall               <dbl> -0.248564374, 0.049693122, 0.179485009, -0.39816578…
## $ Spring             <dbl> -0.073735450, 0.060035273, 0.127492063, -0.21007407…
## $ Summer             <dbl> -0.307132275, -0.007407407, -0.061220459, -0.576084…
## $ Winter             <dbl> 0.2700388, 0.4445855, 0.8911323, 0.5307937, 0.73578…
## $ max_warming_season <chr> "Winter", "Winter", "Winter", "Winter", "Winter", "…
## $ Annual             <dbl> -0.079968254, 0.142994709, 0.300250441, -0.15266666…
## $ CTYNAME            <chr> "Autauga County", "Baldwin County", "Barbour County…
## $ STNAME             <chr> "Alabama", "Alabama", "Alabama", "Alabama", "Alabam…
skim(tempChangeState)
Data summary
Name tempChangeState
Number of rows 48
Number of columns 10
_______________________
Column type frequency:
character 5
numeric 5
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
fips 0 1 2 2 0 48 0
max_warming_season 0 1 4 6 0 2 0
STUSAB 0 1 2 2 0 48 0
STATE_NAME 0 1 4 14 0 48 0
STATENS 0 1 8 8 0 48 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Fall 0 1 0.79 0.52 -0.20 0.36 0.77 1.16 1.66 ▅▇▆▇▇
Spring 0 1 1.00 0.48 -0.11 0.72 1.07 1.36 1.76 ▂▂▃▇▅
Summer 0 1 0.77 0.63 -0.33 0.21 0.87 1.28 2.11 ▇▇▆▇▂
Winter 0 1 1.67 0.71 0.34 1.19 1.51 2.27 3.15 ▂▇▃▃▃
Annual 0 1 1.06 0.55 -0.04 0.64 1.10 1.52 2.04 ▃▅▆▇▃ 
glimpse(tempChangeState)
## Rows: 48
## Columns: 10
## $ fips               <chr> "01", "04", "05", "06", "08", "09", "10", "12", "13…
## $ Fall               <dbl> -0.19566843, 1.20395062, -0.04253968, 1.57092063, 1…
## $ Spring             <dbl> -0.1058624, 1.3844797, 0.2663986, 1.4492416, 1.4369…
## $ Summer             <dbl> -0.32500882, 1.27445503, 0.05859612, 1.47833510, 1.…
## $ Winter             <dbl> 0.4585256, 1.3883880, 0.5322469, 1.4124303, 1.83875…
## $ max_warming_season <chr> "Winter", "Winter", "Winter", "Fall", "Winter", "Wi…
## $ Annual             <dbl> -0.03504762, 1.31988007, 0.21407407, 1.48056085, 1.…
## $ STUSAB             <chr> "AL", "AZ", "AR", "CA", "CO", "CT", "DE", "FL", "GA…
## $ STATE_NAME         <chr> "Alabama", "Arizona", "Arkansas", "California", "Co…
## $ STATENS            <chr> "01779775", "01779777", "00068085", "01779778", "01…

Line Chart

tempChangeState %>% select(fips, STATE_NAME) %>% 
  right_join(tempState) %>% filter(STATE_NAME %in% c("Michigan", "Minnesota")) %>% 
  ggplot(aes(x = year, y = temp, color = STATE_NAME)) +
  geom_line() +
  scale_color_colorblind() +
  labs(title = "Temperature of Michigan and Minnesota, 1895 - 2019",
       x = "Year",
       y = "Temperature (F)",
       caption = "Data source: The Washington Post and the NOAA nClimDiv and nClimGrid data sets") +
  theme_bw() +
  theme(legend.position = "bottom")

Pivoting to long format

tempChangeStateLong <- tempChangeState %>%  pivot_longer(cols = c(Fall:Winter, Annual) ,
                                                         names_to = "Period",
                                                         values_to = "Change")

tempChangeCountyLong <- tempChangeCounty %>%  pivot_longer(cols = c(Fall:Winter, Annual) ,
                                                         names_to = "Period",
                                                         values_to = "Change")

tempChangeCountyLong %>% arrange(desc(Change)) %>% slice_head(n = 10)

Creating side by side box plots

tempChangeStateLong %>% ggplot(aes(x = Period,
                                   y = Change)) +
    geom_boxplot(fill = "dodgerblue") +
  labs(title = "State-level temperature changes", 
       subtitle = "The lower 48 contiguous United States, 1895-2019", 
       x = "",
       y = "Temperature change(F)",
       caption = "Data source: The Washington Post and the NOAA nClimDiv and nClimGrid data sets",
       color = "") +
  theme_bw()
## Error in ggplot(., aes(x = Period, y = Change)): object 'tempChangeStateLong' not found

Poviting to wider format

Loading the us_rent_income data set and using glimpse() function

data(us_rent_income, package = "tidyr")
glimpse(us_rent_income)
## Rows: 104
## Columns: 5
## $ GEOID    <chr> "01", "01", "02", "02", "04", "04", "05", "05", "06", "06", "…
## $ NAME     <chr> "Alabama", "Alabama", "Alaska", "Alaska", "Arizona", "Arizona…
## $ variable <chr> "income", "rent", "income", "rent", "income", "rent", "income…
## $ estimate <dbl> 24476, 747, 32940, 1200, 27517, 972, 23789, 709, 29454, 1358,…
## $ moe      <dbl> 136, 3, 508, 13, 148, 4, 165, 5, 109, 3, 109, 5, 195, 5, 247,…
us_rent_income_wide <- us_rent_income %>% pivot_wider(id_cols = GEOID:NAME,
                                                      names_from = variable,
                                                      values_from = c(estimate, moe))

Creating a bar chart

ratios <- us_rent_income_wide %>%
  mutate(rent_income_ratio = estimate_rent / estimate_income)

ratios %>% slice_min(rent_income_ratio, n = 10) %>%
  bind_rows(ratios %>% slice_max(rent_income_ratio, n = 10)) %>%
  ggplot(aes(x = fct_reorder(NAME, rent_income_ratio), y = rent_income_ratio))+
  geom_col(fill = "dodgerblue", color = "black")+
  labs(title = "Rent to income ratio, United States, 2017",
       x = "",
       y = "Median rent to median income ratio",
       caption = "Data source: The tidycensus R package & the American Community Survey")+
  coord_flip()+
  theme_bw()