Code
library(tidyr)
library(dplyr)
library(ggplot2)
library(readr)
library(stringr)Data 607 Project 2: Data Transformation
Approach
For this project, I selected three datasets to practice transforming data from wide to tidy format using R. The datasets include simulated monthly patient visits for 15 community health clinics, fictional housing prices across the five New York City boroughs, and life expectancy data from the World Bank. These datasets provide an opportunity to work with different types of data and explore trends in healthcare utilization, housing, and public health. My plan is to import each dataset into R and examine its structure. I will use functions from tidyr and dplyr, to reshape the dataset into tidy format. I will also check for missing values, duplicate records, and inconsistencies in variable types. One challenge I anticipate is handling differences in how the datasets are organized. I will need to identify the appropriate columns to transform and ensure that the resulting variables have the correct data types. After cleaning and transforming the datasets, I plan to perform exploratory data analysis using descriptive statistics and visualizations. I will examine monthly patient visit trends, compare housing values across NYC boroughs, and explore changes in life expectancy across selected countries from 2015 to 2024.
Data Sources: Dataset 1: Community Health Clinic Visits - Simulated monthly patient visit data for 15 community health clinics during 2025 Dataset 2: NYC Housing Prices by Borough - Fictional housing data for the five NYC boroughs from 2024 to 2025, from dicussion board Dataset 3: World Bank Life Expectancy at birth, total(years) - https://data.worldbank.org/indicator/SP.DYN.LE00.IN?name_desc=false
Dataset 1: Community health clinic visits
This dataset contains simulated monthly patient visit counts for community health clinics during 2025. The purpose of this analysis is to examine how patient visits vary across clinics and months. The original dataset is in wide format, with each month represented by a separate column.
Data Import and Tidying
Code
clinic_wide <- read_csv("data/community_clinic_visits_wide.csv", show_col_types = FALSE)
dim(clinic_wide)[1] 15 14Code
names(clinic_wide) [1] "Clinic_ID" "Clinic_Name" "Jan" "Feb" "Mar"
[6] "Apr" "May" "Jun" "Jul" "Aug"
[11] "Sep" "Oct" "Nov" "Dec" Code
head(clinic_wide)# A tibble: 6 × 14
Clinic_ID Clinic_Name Jan Feb Mar Apr May Jun Jul Aug Sep
<chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 C001 Harbor Commun… 245 231 260 278 290 301 315 309 287
2 C002 Riverside Fam… 190 205 198 220 235 241 250 263 255
3 C003 Central Commu… 310 298 325 340 355 348 370 365 380
4 C004 Eastside Fami… 155 162 170 168 180 195 201 210 205
5 C005 Westview Comm… 270 265 280 295 310 320 318 330 342
6 C006 Northside Hea… 225 218 240 251 260 272 280 275 290
# ℹ 3 more variables: Oct <dbl>, Nov <dbl>, Dec <dbl>The original dataset contains 15 rows and 14 columns. Each row represents one community health clinic, while the columns include clinic ID, clinic name, and monthly patient visit counts from January through December 2025.
Transformation
Code
clinic_tidy <- clinic_wide %>%
pivot_longer(
cols = Jan:Dec,
names_to = "month",
values_to = "patient_visits"
) %>%
rename(clinic_id = Clinic_ID, clinic_name = Clinic_Name) %>%
mutate(
month = factor(month, levels = month.abb, ordered = TRUE),
patient_visits = as.numeric(patient_visits)
)
head(clinic_tidy)# A tibble: 6 × 4
clinic_id clinic_name month patient_visits
<chr> <chr> <ord> <dbl>
1 C001 Harbor Community Health Center Jan 245
2 C001 Harbor Community Health Center Feb 231
3 C001 Harbor Community Health Center Mar 260
4 C001 Harbor Community Health Center Apr 278
5 C001 Harbor Community Health Center May 290
6 C001 Harbor Community Health Center Jun 301Code
dim(clinic_tidy)[1] 180 4The original dataset contained 15 clinics with monthly patient visits stored in 12 separate columns. I used pivot_longer() to convert these columns into two variables: month and patient visits. I then renamed the clinic identifier variables using lowercase names for consistency and converted the month variable into an ordered factor to preserve chronological order. The resulting dataset contains 180 observations and four variables, with each row representing one clinic in one month.
Code
colSums(is.na(clinic_tidy)) clinic_id clinic_name month patient_visits
0 0 0 0 Code
clinic_tidy %>%
filter(is.na(patient_visits))# A tibble: 0 × 4
# ℹ 4 variables: clinic_id <chr>, clinic_name <chr>, month <ord>,
# patient_visits <dbl>Code
clinic_tidy %>%
count(clinic_id, month) %>%
filter(n >1)# A tibble: 0 × 3
# ℹ 3 variables: clinic_id <chr>, month <ord>, n <int>Code
clinic_tidy %>%
filter(patient_visits < 0)# A tibble: 0 × 4
# ℹ 4 variables: clinic_id <chr>, clinic_name <chr>, month <ord>,
# patient_visits <dbl>I checked the dataset for missing values using is.na(). No missing patient visit counts were identified, so no observations needed to be removed or imputed. I also checked for duplicate clinic month records and negative patient visit counts. No duplicate records or invalid negative values were identified. Therefore, all observations were retained for analysis.
Analysis
The analysis used descriptive statistics to examine monthly patient visit trends across the 15 community health clinics. Total and average monthly visits were calculated for each clinic to compare patient visit volumes. Monthly totals were also calculated to examine changes throughout 2025. Finally, the difference between January and December visits was calculated for each clinic to identify which clinics experienced the largest and smallest increases in patient visits.
Patient Visits by Clinic
Code
clinic_summary <- clinic_tidy %>%
group_by(clinic_name) %>%
summarise(total_visits = sum(patient_visits, na.rm = TRUE),
average_monthly_visits = mean(patient_visits, na.rm = TRUE),
.groups = "drop") %>%
arrange(desc(total_visits))
clinic_summary# A tibble: 15 × 3
clinic_name total_visits average_monthly_visits
<chr> <dbl> <dbl>
1 Metro Family Health Clinic 4507 376.
2 Central Community Health Center 4299 358.
3 Lakeside Community Clinic 4054 338.
4 Oakwood Community Health Center 3942 328.
5 Westview Community Health Center 3815 318.
6 Maplewood Family Health Center 3567 297.
7 Harbor Community Health Center 3446 287.
8 Northside Health Clinic 3229 269.
9 Parkview Health Center 2984 249.
10 Riverside Family Health Clinic 2875 240.
11 Sunrise Community Health Clinic 2851 238.
12 Greenwood Family Health Center 2667 222.
13 Valley Community Health Center 2633 219.
14 Hillcrest Community Clinic 2498 208.
15 Eastside Family Clinic 2319 193.This calculates the total number of patient visits and the average monthly visits for each clinic. The clinics are sorted from highest to lowest total visits.
Monthly Patient Visit Trends
Code
monthly_summary <- clinic_tidy %>%
group_by(month) %>%
summarise(
total_visits = sum(patient_visits, na.rm = TRUE),
.groups = "drop"
)
monthly_summary# A tibble: 12 × 2
month total_visits
<ord> <dbl>
1 Jan 3455
2 Feb 3413
3 Mar 3647
4 Apr 3832
5 May 4005
6 Jun 4146
7 Jul 4269
8 Aug 4345
9 Sep 4432
10 Oct 4581
11 Nov 4694
12 Dec 4867Change in Patient Visits from January to December
Code
clinic_changes <- clinic_tidy %>%
group_by(clinic_name) %>%
summarise(
january_visits = patient_visits[month == "Jan"],
december_visits = patient_visits[month == "Dec"],
change_in_visits = december_visits - january_visits,
.groups = "drop"
) %>%
arrange(desc(change_in_visits))
clinic_changes# A tibble: 15 × 4
clinic_name january_visits december_visits change_in_visits
<chr> <dbl> <dbl> <dbl>
1 Metro Family Health Clinic 320 440 120
2 Central Community Health Cen… 310 415 105
3 Lakeside Community Clinic 290 395 105
4 Oakwood Community Health Cen… 280 385 105
5 Westview Community Health Ce… 270 375 105
6 Maplewood Family Health Cent… 250 350 100
7 Northside Health Clinic 225 315 90
8 Riverside Family Health Clin… 190 280 90
9 Sunrise Community Health Cli… 195 285 90
10 Valley Community Health Cent… 175 265 90
11 Parkview Health Center 205 292 87
12 Greenwood Family Health Cent… 180 265 85
13 Hillcrest Community Clinic 165 250 85
14 Harbor Community Health Cent… 245 325 80
15 Eastside Family Clinic 155 230 75Visualizations
Code
ggplot(
monthly_summary, aes(x = month, y = total_visits, group = 1)) +
geom_line(color = "blue", linewidth = 1) +
geom_point(color = "blue", size = 2) +
labs(title = "Monthly Patient Visits Across Community Health Clinics, 2025",
x = "Month",
y = "Total Patient Visits") +
theme_minimal()
This line graph illustrates changes in total monthly patient visits across 15 community health clinics during 2025. Each point represents the combined number of visits across all clinics for a particular month. Total visits decreased slightly from 3,455 in January to 3,413 in February before increasing steadily throughout the remainder of the year. December had the highest number of visits at 4,867. Overall, the graph shows an upward trend in monthly patient visits throughout 2025.
Code
ggplot(
clinic_tidy, aes(x = month, y = patient_visits, color = clinic_name, group = clinic_name)
) +
geom_line(linewidth = 1) +
geom_point(size = 1.5) +
labs(
title = "Monthly Patient Visits by Clinic, 2025",
x = "Month",
y = "Number of Patient Visits",
color = "Clinic"
) + theme_minimal()
This line graph compares monthly patient visits across the 15 community health clinics in 2025. Although patient visit volumes varied between clinics, most showed an overall upward trend throughout 2025, with some monthly fluctuations. Metro Family Health Clinic consistently had the highest number of patient visits, increasing from 320 in January to 440 in December. Eastside Family Clinic had the lowest visit volume, increasing from 155 in January to 230 in December.
Conclusions
The analysis showed an overall increase in patient visits across the 15 community health clinics during 2025. Total monthly visits increased from 3,455 in January to 4,867 in December, with February having the lowest number of visits (3,413). Although there were some monthly fluctuations, patient visit volumes generally increased throughout the year. Metro Family Health Clinic had the highest number of visits (4,507), averaging approximately 376 visits per month. In contrast, Eastside Family Clinic had the lowest total (2,319) averaging approximately 193 visits per month. When comparing January and December, all 15 clinics experienced an increase in patient visits. Metro Family Health Clinic had the largest increase with 120 additional visits, while Eastside Family Clinic had the smallest increase, with 75 additional visits. Overall, the findings suggest a consistent upward trend in patient visit volume across the clinics, although the number of visits varied by location. Since this dataset contains simulated patient visit counts, these findings illustrate how data tidying and analysis can be used to examine healthcare utilization patterns rather than representing actual patient activity.
Dataset 2: New York housing by borough
This dataset was provided by my classmate and contains fictional average housing prices for the five New York City boroughs from January 2024 through December 2025. The purpose of this analysis is to compare average housing prices across boroughs, examine monthly and yearly trends, and identify which boroughs have the highest and lowest prices.
Data Import and Tidying
Code
housing_raw <- read_csv("data/nyc_housing_wide.csv",
skip = 1,
show_col_types = FALSE,
col_types = cols(.default = col_character()))
nrow(housing_raw)[1] 24Code
names(housing_raw)[1] "Year" "Month" "Bronx" "Brooklyn"
[5] "Manhattan" "Queens" "Staten Island"Code
head(housing_raw)# A tibble: 6 × 7
Year Month Bronx Brooklyn Manhattan Queens `Staten Island`
<chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 2024 Jan 565 948 1,108 650 675
2 2024 Feb 568 952 1,112 654 678
3 2024 Mar 572 958 1,118 660 683
4 2024 Apr 575 965 1,122 663 688
5 2024 May 579 972 1,128 668 693
6 2024 Jun 582 978 1,132 671 697 Transformation
Code
housing_tidy <- housing_raw %>%
pivot_longer(cols = c(Bronx, Brooklyn, Manhattan, Queens, `Staten Island`),
names_to = "borough", values_to = "housing_value") %>%
mutate(
year = as.integer(Year),
month = factor(Month, levels = month.abb, ordered = TRUE),
housing_value = parse_number(housing_value)
) %>%
select(year, month, borough, housing_value)
head(housing_tidy)# A tibble: 6 × 4
year month borough housing_value
<int> <ord> <chr> <dbl>
1 2024 Jan Bronx 565
2 2024 Jan Brooklyn 948
3 2024 Jan Manhattan 1108
4 2024 Jan Queens 650
5 2024 Jan Staten Island 675
6 2024 Feb Bronx 568Code
dim(housing_tidy)[1] 120 4The original dataset contains 24 rows and seven columns, with each row representing a month from 2024 through 2025. I used pivot_longer() to transform the borough columns into two variables: borough and housing value. I also used parse_number() to convert values containing commas into numeric format and converted the year and month variables into appropriate data types. The resulting tidy dataset contains 120 observations and four variables, with each row representing one borough during a particular month and year.
Code
colSums(is.na(housing_tidy)) year month borough housing_value
0 0 0 0 Code
housing_tidy %>%
count(year, month, borough) %>%
filter(n > 1)# A tibble: 0 × 4
# ℹ 4 variables: year <int>, month <ord>, borough <chr>, n <int>Code
housing_tidy %>%
filter(housing_value < 0)# A tibble: 0 × 4
# ℹ 4 variables: year <int>, month <ord>, borough <chr>, housing_value <dbl>I checked the tidy dataset for missing values, duplicate year-month borough records, and negative housing values. No missing values, duplicate records, or negative values were identified. Therefore, all 120 observations were retained for analysis.
Analysis
The analysis used descriptive statistics to examine housing price patterns across the five NYC boroughs during 2024 and 2025. Average, minimum, and maximum housing prices were calculated for each borough to compare price difference. Average prices were also calculated by year and month to examine changes over time. Finally, the lowest-priced months were identified for each borough to explore when housing prices were relatively lower.
Average Housing Prices by borough
Code
housing_summary <- housing_tidy %>%
group_by(borough) %>%
summarise(average_price = mean(housing_value, na.rm = TRUE),
minimum_price = min(housing_value, na.rm = TRUE),
maximum_price = max(housing_value, na.rm = TRUE),
.groups = "drop") %>%
arrange(desc(average_price))
housing_summary# A tibble: 5 × 4
borough average_price minimum_price maximum_price
<chr> <dbl> <dbl> <dbl>
1 Manhattan 1153. 1108 1192
2 Brooklyn 1000. 948 1045
3 Staten Island 714. 675 750
4 Queens 687. 650 718
5 Bronx 595. 565 620I calculated the average, minimum, and maximum housing prices for each borough to compare housing costs across New York City. The boroughs were arranged from highest to lowest average price to identify which areas were the most and least expensive. The results show differences in average housing prices across the five NYC boroughs. Manhattan had the highest average housing price at $1,152.63, followed by Brooklyn at $1,000.08. The Bronx had the lowest average price at $594.63, followed by Queens at $686.83 and Staten Island at $714.50. Manhattan also had the highest maximum price at $1,192, while the Bronx had the lowest minimum price at $565. These findings suggest Manhattan was the most expensive borough and the Bronx was the least expensive during the period examined.
Average Housing Prices by Year and Borough
Code
housing_yearly <- housing_tidy %>%
group_by(year, borough) %>%
summarise(
average_price = mean(housing_value, na.rm = TRUE),
.groups = "drop"
) %>%
arrange(borough, year)
housing_yearly# A tibble: 10 × 3
year borough average_price
<int> <chr> <dbl>
1 2024 Bronx 581.
2 2025 Bronx 609.
3 2024 Brooklyn 975
4 2025 Brooklyn 1025.
5 2024 Manhattan 1130.
6 2025 Manhattan 1175.
7 2024 Queens 670.
8 2025 Queens 704
9 2024 Staten Island 696.
10 2025 Staten Island 733.The yearly analysis compares average housing prices across the five NYC boroughs in 2024 and 2025. The results indicate that average housing prices were higher in 2025 than in 2024 across the boroughs.
Monthly Housing Price Trends
Code
housing_monthly <- housing_tidy %>%
group_by(year, month) %>%
summarise(
average_price = mean(housing_value, na.rm = TRUE),
.groups = "drop"
) %>%
arrange(year, month)
housing_monthly# A tibble: 24 × 3
year month average_price
<int> <ord> <dbl>
1 2024 Jan 789.
2 2024 Feb 793.
3 2024 Mar 798.
4 2024 Apr 803.
5 2024 May 808
6 2024 Jun 812
7 2024 Jul 816.
8 2024 Aug 814
9 2024 Sep 820
10 2024 Oct 823
# ℹ 14 more rowsCode
housing_lowest_months <- housing_monthly %>%
group_by(year) %>%
slice_min(average_price, n = 1, with_ties = TRUE) %>%
ungroup()
housing_lowest_months# A tibble: 2 × 3
year month average_price
<int> <ord> <dbl>
1 2024 Jan 789.
2 2025 Jan 830.The monthly analysis showed that average housing prices generally increased across the five NYC boroughs during 2024 and 2025, with some fluctuations. January had the lowest average housing price in both years at $789.20 in 2024 and $830.20 in 2025. These findings suggest that January was the least expensive month overall in each year within the dataset. However, prices may vary by borough, so borough-specific trends should also be examined.
Code
housing_lowest_by_borough <- housing_tidy %>%
group_by(year, borough) %>%
slice_min(housing_value, n = 1, with_ties = TRUE) %>%
ungroup() %>%
select(year, borough, month, housing_value)
housing_lowest_by_borough# A tibble: 10 × 4
year borough month housing_value
<int> <chr> <ord> <dbl>
1 2024 Bronx Jan 565
2 2024 Brooklyn Jan 948
3 2024 Manhattan Jan 1108
4 2024 Queens Jan 650
5 2024 Staten Island Jan 675
6 2025 Bronx Jan 594
7 2025 Brooklyn Jan 1001
8 2025 Manhattan Jan 1153
9 2025 Queens Jan 688
10 2025 Staten Island Jan 715The results show that January had the lowest housing prices across all five NYC boroughs in both 2024 and 2025. In 2024, the lowest prices ranged from $565 in the Bronx to $1,108 in Manhattan. In 2025, the lowest prices ranged from $594 in the Bronx to $1,153 in Manhattan. These findings suggest that January may be the most favorable month for finding lower housing prices across the five boroughs.
Visualizations
Code
ggplot(
housing_monthly, aes(x = month,
y = average_price,
color = factor(year),
group = factor(year))
) +
geom_line(linewidth = 1) +
geom_point(size = 2) +
labs(
title = "Monthly Average Housing Price in NYC, 2024 - 2025",
x = "Month",
y = "Average Housing Price",
color = "Year"
) + theme_minimal()
The line graph compares monthly average housing prices across the five NYC boroughs in 2024 and 2025. Average housing prices were consistently higher in 2025 than in 2024. Both years showed an overall upward trend, with slight decreases during certain months. January had the lowest average price in both years at $789.20 in 2024 and $830.20 in 2025. December had the highest average price in both years at $827 in 2024 and $865 in 2025.
Code
ggplot(housing_summary, aes(x = reorder(borough, average_price), y = average_price)) +
geom_col(fill = "blue") +
coord_flip() +
labs(
title = "Average Housing Prices by NYC Borough, 2024-2025",
x = "Borough",
y = "Average Housing Price"
) + theme_minimal()
The bar chart compares average housing prices across the five NYC boroughs during 2024 and 2025. Manhattan had the highest average housing price at $1,152.63, followed by Brooklyn at $1,000.08. The Bronx had the lowest average price at $594.63, followed by Queens at $686.83 and Staten Island at $714.50.
Conclusions
The analysis showed differences in average housing prices across the five NYC boroughs during 2024 and 2025. Manhattan had the highest average housing price at $1,152.63, followed by Brooklyn at $1,000.08, while the Bronx had the lowest average price at $594.63. Average housing prices were consistently higher in 2025 than in 2024. The monthly analysis also showed that January had the lowest average housing prices in both years. Further examination confirmed that January was the lowest-priced month for all five boroughs in 2024 and 2025. These findings indicate that January had the lowest housing values across all five boroughs in the fictional dataset.
Dataset 3: World Bank Life Expectancy at Birth
This dataset was obtained from the World Bank’s World Development Indicators database and contains life expectancy at birth estimates for countries and regional groups from 1960 through 2024. Life expectancy is measured in years. The purpose of this analysis is to examine changes in life expectancy over time and compare patterns across selected countries.
Data Import and Tidying
Code
life_wide <- read_csv("data/API_SP.DYN.LE00.IN_DS2_en_csv_v2_1528.csv",
skip = 4,
show_col_types = FALSE)
dim(life_wide)[1] 266 71Code
names(life_wide) [1] "Country Name" "Country Code" "Indicator Name" "Indicator Code"
[5] "1960" "1961" "1962" "1963"
[9] "1964" "1965" "1966" "1967"
[13] "1968" "1969" "1970" "1971"
[17] "1972" "1973" "1974" "1975"
[21] "1976" "1977" "1978" "1979"
[25] "1980" "1981" "1982" "1983"
[29] "1984" "1985" "1986" "1987"
[33] "1988" "1989" "1990" "1991"
[37] "1992" "1993" "1994" "1995"
[41] "1996" "1997" "1998" "1999"
[45] "2000" "2001" "2002" "2003"
[49] "2004" "2005" "2006" "2007"
[53] "2008" "2009" "2010" "2011"
[57] "2012" "2013" "2014" "2015"
[61] "2016" "2017" "2018" "2019"
[65] "2020" "2021" "2022" "2023"
[69] "2024" "2025" "...71" Code
head(life_wide)# A tibble: 6 × 71
`Country Name` `Country Code` `Indicator Name` `Indicator Code` `1960` `1961`
<chr> <chr> <chr> <chr> <dbl> <dbl>
1 Aruba ABW Life expectancy… SP.DYN.LE00.IN 64.0 64.2
2 Africa Eastern… AFE Life expectancy… SP.DYN.LE00.IN 44.2 44.5
3 Afghanistan AFG Life expectancy… SP.DYN.LE00.IN 32.8 33.3
4 Africa Western… AFW Life expectancy… SP.DYN.LE00.IN 37.8 38.1
5 Angola AGO Life expectancy… SP.DYN.LE00.IN 37.9 36.9
6 Albania ALB Life expectancy… SP.DYN.LE00.IN 56.4 57.5
# ℹ 65 more variables: `1962` <dbl>, `1963` <dbl>, `1964` <dbl>, `1965` <dbl>,
# `1966` <dbl>, `1967` <dbl>, `1968` <dbl>, `1969` <dbl>, `1970` <dbl>,
# `1971` <dbl>, `1972` <dbl>, `1973` <dbl>, `1974` <dbl>, `1975` <dbl>,
# `1976` <dbl>, `1977` <dbl>, `1978` <dbl>, `1979` <dbl>, `1980` <dbl>,
# `1981` <dbl>, `1982` <dbl>, `1983` <dbl>, `1984` <dbl>, `1985` <dbl>,
# `1986` <dbl>, `1987` <dbl>, `1988` <dbl>, `1989` <dbl>, `1990` <dbl>,
# `1991` <dbl>, `1992` <dbl>, `1993` <dbl>, `1994` <dbl>, `1995` <dbl>, …Transformation
Code
life_tidy <- life_wide %>%
filter(`Country Name` %in% c(
"United States",
"Canada",
"Ghana",
"Japan"
)) %>%
pivot_longer(
cols = `2015`:`2024`,
names_to = "year",
values_to = "life_expectancy"
) %>%
rename(
country = `Country Name`,
country_code = `Country Code`
) %>%
mutate(
year = as.integer(year)
) %>%
select(country, country_code, year, life_expectancy)
head(life_tidy)# A tibble: 6 × 4
country country_code year life_expectancy
<chr> <chr> <int> <dbl>
1 Canada CAN 2015 81.8
2 Canada CAN 2016 81.9
3 Canada CAN 2017 81.8
4 Canada CAN 2018 81.8
5 Canada CAN 2019 82.2
6 Canada CAN 2020 81.5Code
dim(life_tidy)[1] 40 4The original World Bank dataset contains 266 rows and 71 columns, with countries and regional groups represented in rows and individual years represented in separate columns. I selected four countries: the United States, Canada, Ghana, and Japan, and restricted the analysis to 2015 through 2024. I used pivot_longer() to transform the year columns into two variables: year and life expectancy. I also converted the year variable to an integer and renamed the country identifier variables for consistency. The resulting dataset contains 40 observations and four variables, with each row representing one country in a particular year.
Code
colSums(is.na(life_tidy)) country country_code year life_expectancy
0 0 0 0 Code
life_tidy %>%
count(country, year) %>%
filter(n >1)# A tibble: 0 × 3
# ℹ 3 variables: country <chr>, year <int>, n <int>Code
life_tidy %>%
filter(life_expectancy <= 0 | life_expectancy > 120)# A tibble: 0 × 4
# ℹ 4 variables: country <chr>, country_code <chr>, year <int>,
# life_expectancy <dbl>After transforming the dataset, I checked for missing values, duplicate country-year observations, and invalid life expectancy values. No issues were identified in the selected observations.
Analysis
I calculated descriptive statistics for each country and compared life expectancy in 2019 and 2024 to examine changes relative to the pre-pandemic period.
Code
life_summary <- life_tidy %>%
group_by(country) %>%
summarise(
mean_life = mean(life_expectancy),
min_life = min(life_expectancy),
max_life = max(life_expectancy),
.groups = "drop"
) %>%
arrange(desc(mean_life))
life_summary# A tibble: 4 × 4
country mean_life min_life max_life
<chr> <dbl> <dbl> <dbl>
1 Japan 84.2 83.8 84.6
2 Canada 81.7 81.1 82.2
3 United States 78.1 76.3 78.9
4 Ghana 64.4 63.2 65.7The descriptive analysis revealed differences in life expectancy across the four selected countries from 2015 to 2024. Japan had the highest average life expectancy at 84.15 years, followed by Canada at 81.73 years and the United States at 78.12 years. Ghana had the lowest average life expectancy at 64.42 years.
Code
life_changes <- life_tidy %>%
filter(year %in% c(2019, 2024)) %>%
group_by(country) %>%
summarise(
life_2019 = life_expectancy[year == 2019],
life_2024 = life_expectancy[year == 2024],
change = life_2024 - life_2019,
.groups = "drop"
) %>%
arrange(desc(change))
life_changes# A tibble: 4 × 4
country life_2019 life_2024 change
<chr> <dbl> <dbl> <dbl>
1 Ghana 64.5 65.7 1.24
2 United States 78.8 78.9 0.102
3 Canada 82.2 82.1 -0.0505
4 Japan 84.4 84.0 -0.320 Comparing 2019 and 2024, Ghana experienced the largest increase in life expectancy, rising by 1.24 years from 64.46 to 65.70 years. The United States experienced a smaller increase of 0.10 years, from 78.79 to 78.89 years. In contrast, life expectancy declined slightly in Canada by 0.05 years and in Japan by 0.32 years.
Visualization
I created a line graph to visualize life expectancy trends across the four countries from 2015 through 2024.
Code
ggplot(life_tidy, aes(x = year, y = life_expectancy, color = country)) +
geom_line(linewidth = 1) +
geom_point(size = 2) +
scale_x_continuous(breaks = 2015:2024) +
labs(
title = "Life Expectancy Trends by Country, 2015-2024",
x = "Year",
y = "Life Expectancy at Birth (Years)",
color = "Country"
) + theme_minimal()
The line graph shows differences in life expectancy trends across the four countries from 2015 to 2024. Japan maintained the highest life expectancy throughout the study period, while Ghana had the lowest. The United States experienced a noticeable decline in life expectancy during 2020 and 2021, followed by a gradual recovery through 2024. Canada experienced smaller fluctuations, while Ghana showed an overall increasing trend.
Code
ggplot(
life_summary, aes(x = reorder(country, mean_life),
y = mean_life,
fill = country)) +
geom_col() +
coord_flip() +
labs(
title = "Average Life Expectancy by Country 2015-2024",
x = "Country",
y = "Average Life Expectancy (Years)"
) + theme_minimal() + theme(legend.position = "none")
The bar chart compares average life expectancy across the four countries. Japan had the highest average at 84.15 years, followed by Canada at 81.73 years and the United States at 78.12 years. Ghana had the lowest average at 64.42 years.
Conclusion
This analysis examined life expectancy trends across the United States, Canada, Ghana, and Japan from 2015 to 2024. The results showed that Japan had the highest average life expectancy at 84.15 years, while Ghana had the lowest at 64.42 years. However, Ghana experienced the largest increase in life expectancy between 2019 and 2024, gaining 1.24 years. The United States experienced a noticeable decline during 2020 and 2021 but recovered by 2024.
Data source: https://data.worldbank.org/indicator/SP.DYN.LE00.IN?name_desc=false
Project Conclusion
This project demonstrated how three datasets in wide format could be transformed into tidy format using R. Through pivot_longer(), data cleaning, descriptive statistics, and visualization, I was able to organize the datasets and examine patterns in clinic visits, housing values, and life expectancy. Although the datasets covered different topics, the same data-tidying techniques made them easier to analyze and interpret.