#Homework1: Import data from statistical package and from data management system
library(readr)
liste_of_students_okk <- read_csv("~/MASTERS NOTES AND ASSIGNEMENT/R PROGRAMING/PRACTICAL/INTRO/intro/liste of students okk.xlsx")## Multiple files in zip: reading '[Content_Types].xml'
## Rows: 1 Columns: 1
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(liste_of_students_okk)
head(liste_of_students_okk)## # A tibble: 1 × 1
## `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>`
## <chr>
## 1 "<Types xmlns=\"http://schemas.openxmlformats.org/package/2006/content-types\…summary(liste_of_students_okk)## <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
## Length : 1
## N.unique : 1
## N.blank : 0
## Min.nchar:1227
## Max.nchar:1227# Import second dataset
library(readr)
covid_19_clean_complete <- read_csv("~/MASTERS NOTES AND ASSIGNEMENT/R PROGRAMING/PRACTICAL/INTRO/intro/covid_19_clean_complete.csv")## Rows: 49068 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Province/State, Country/Region, WHO Region
## dbl (6): Lat, Long, Confirmed, Deaths, Recovered, Active
## date (1): Date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(covid_19_clean_complete)
head(covid_19_clean_complete)## # A tibble: 6 × 10
## `Province/State` `Country/Region` Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <date> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 0 0
## 2 <NA> Albania 41.2 20.2 2020-01-22 0 0
## 3 <NA> Algeria 28.0 1.66 2020-01-22 0 0
## 4 <NA> Andorra 42.5 1.52 2020-01-22 0 0
## 5 <NA> Angola -11.2 17.9 2020-01-22 0 0
## 6 <NA> Antigua and Barbuda 17.1 -61.8 2020-01-22 0 0
## # ℹ 3 more variables: Recovered <dbl>, Active <dbl>, `WHO Region` <chr>summary(covid_19_clean_complete)## Province/State Country/Region Lat Long
## Length :49068 Length :49068 Min. :-51.796 Min. :-135.00
## N.unique : 78 N.unique : 187 1st Qu.: 7.873 1st Qu.: -15.31
## N.blank : 0 N.blank : 0 Median : 23.634 Median : 21.75
## Min.nchar: 5 Min.nchar: 2 Mean : 21.434 Mean : 23.53
## Max.nchar: 28 Max.nchar: 32 3rd Qu.: 41.204 3rd Qu.: 80.77
## NAs :34404 Max. : 71.707 Max. : 178.06
## Date Confirmed Deaths Recovered
## Min. :2020-01-22 Min. : 0 Min. : 0.0 Min. : 0
## 1st Qu.:2020-03-08 1st Qu.: 4 1st Qu.: 0.0 1st Qu.: 0
## Median :2020-04-24 Median : 168 Median : 2.0 Median : 29
## Mean :2020-04-24 Mean : 16885 Mean : 884.2 Mean : 7916
## 3rd Qu.:2020-06-10 3rd Qu.: 1518 3rd Qu.: 30.0 3rd Qu.: 666
## Max. :2020-07-27 Max. :4290259 Max. :148011.0 Max. :1846641
## Active WHO Region
## Min. : -14 Length :49068
## 1st Qu.: 0 N.unique : 6
## Median : 26 N.blank : 0
## Mean : 8085 Min.nchar: 6
## 3rd Qu.: 606 Max.nchar: 21
## Max. :2816444Summary: This code imports the student dataset into R using the read_csv() function from the readr package. It then allows inspection of the data structure using functions like View(), head(), and summary().and also, This code imports the COVID-19 dataset into R from a CSV file using read_csv(). It then displays and summarizes the dataset to understand its structure and main characteristics.
# Homework2: Merge two datasets
# Import first dataset
library(readr)
Life_Expectancy_Data <- read_csv("~/MASTERS NOTES AND ASSIGNEMENT/R PROGRAMING/PRACTICAL/INTRO/ASSIGNEMENT/archive (10)/Life Expectancy Data.csv")## Rows: 2938 Columns: 22
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Country, Status
## dbl (20): Year, Life expectancy, Adult Mortality, infant deaths, Alcohol, pe...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(Life_Expectancy_Data)
library(readr)
X2020_2025 <- read_csv("~/MASTERS NOTES AND ASSIGNEMENT/R PROGRAMING/PRACTICAL/INTRO/ASSIGNEMENT/archive (11)/2020-2025.csv")## Rows: 196 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Country
## dbl (6): 2020, 2021, 2022, 2023, 2024, 2025
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View(X2020_2025)
colnames(Life_Expectancy_Data)## [1] "Country" "Year"
## [3] "Status" "Life expectancy"
## [5] "Adult Mortality" "infant deaths"
## [7] "Alcohol" "percentage expenditure"
## [9] "Hepatitis B" "Measles"
## [11] "BMI" "under-five deaths"
## [13] "Polio" "Total expenditure"
## [15] "Diphtheria" "HIV/AIDS"
## [17] "GDP" "Population"
## [19] "thinness 1-19 years" "thinness 5-9 years"
## [21] "Income composition of resources" "Schooling"colnames(X2020_2025)## [1] "Country" "2020" "2021" "2022" "2023" "2024" "2025"# Convert X2020_2025 to LONG format
library(tidyr)
library(dplyr)##
## Attaching package: 'dplyr'
##
## The following objects are masked from 'package:stats':
##
## filter, lag
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionX2020_2025_long <- X2020_2025 %>%
pivot_longer(
cols = -Country,
names_to = "Year",
values_to = "Value"
)
# Fix Year type
X2020_2025_long$Year <- as.numeric(X2020_2025_long$Year)
# Lets merge
merged_data <- Life_Expectancy_Data %>%
inner_join(X2020_2025_long, by = c("Country", "Year"))Explanation of the Merge Process
In this assignment, two datasets were imported into R: Life Expectancy Data and 2020–2025 data. The Life Expectancy dataset was already in a long format, containing variables such as Country and Year.
However, the 2020–2025 dataset was in a wide format, where each year (2020–2025) was stored as a separate column. To make both datasets compatible for merging, the second dataset was transformed into a long format using the pivot_longer() function from the tidyr package. This restructuring created two key columns: Year and Value.
The Year column was then converted to a numeric format to ensure consistency between both datasets.
Finally, the two datasets were merged using an inner join based on the common variables Country and Year, resulting in a single dataset that combines life expectancy information with the values from the 2020–2025 dataset.
# Homework3: Group by () and pipe %>%
Life_Expectancy_Data %>%
select(Country, Year, `Life expectancy`)## # A tibble: 2,938 × 3
## Country Year `Life expectancy`
## <chr> <dbl> <dbl>
## 1 Afghanistan 2015 65
## 2 Afghanistan 2014 59.9
## 3 Afghanistan 2013 59.9
## 4 Afghanistan 2012 59.5
## 5 Afghanistan 2011 59.2
## 6 Afghanistan 2010 58.8
## 7 Afghanistan 2009 58.6
## 8 Afghanistan 2008 58.1
## 9 Afghanistan 2007 57.5
## 10 Afghanistan 2006 57.3
## # ℹ 2,928 more rowslibrary(dplyr)
Life_Expectancy_Data %>%
group_by(Country) %>%
summarise(Average_Life_Expectancy = mean(`Life expectancy`, na.rm = TRUE))## # A tibble: 193 × 2
## Country Average_Life_Expectancy
## <chr> <dbl>
## 1 Afghanistan 58.2
## 2 Albania 75.2
## 3 Algeria 73.6
## 4 Angola 49.0
## 5 Antigua and Barbuda 75.1
## 6 Argentina 75.2
## 7 Armenia 73.4
## 8 Australia 81.8
## 9 Austria 81.5
## 10 Azerbaijan 70.7
## # ℹ 183 more rowsmerged_data %>%
group_by(Country) %>%
summarise(Average_Value = mean(Value, na.rm = TRUE))## # A tibble: 0 × 2
## # ℹ 2 variables: Country <chr>, Average_Value <dbl>Life_Expectancy_Data %>%
group_by(Country) %>%
summarise(Number_of_Records = n())## # A tibble: 193 × 2
## Country Number_of_Records
## <chr> <int>
## 1 Afghanistan 16
## 2 Albania 16
## 3 Algeria 16
## 4 Angola 16
## 5 Antigua and Barbuda 16
## 6 Argentina 16
## 7 Armenia 16
## 8 Australia 16
## 9 Austria 16
## 10 Azerbaijan 16
## # ℹ 183 more rows# use select(),filter(),arrange(),rename(),mutate()
library(dplyr)
students <- data.frame(
id = c(1, 2, 3, 4, 5),
name = c("Amina", "Brian", "Claire", "David", "Eva"),
age = c(19, 21, 20, 22, 19),
score = c(78, 85, 92, 60, 88),
city = c("Kigali", "Nairobi", "Kampala", "Kigali", "Nairobi")
)
#select()
students_select <- students %>%
select(name, age, score)
#filter()
students_filter <- students %>%
filter(score >= 80)
#arrange()
students_arranged <- students %>%
arrange(desc(score))
#rename()
students_renamed <- students %>%
rename(
student_name = name,
student_score = score
)
# mutate()
students_mutated <- students %>%
mutate(
grade = ifelse(score >= 80, "A", "B"),
score_plus_5 = score + 5
)
# all
students_final <- students %>%
filter(score >= 70) %>%
select(name, age, score) %>%
mutate(status = "passed") %>%
arrange(desc(score))Expalanation: The group_by() function in R is used to group data based on a specific variable such as Country or Year. The pipe operator %>% is used to connect multiple operations in a readable sequence. After grouping the data, the summarise() function is used to calculate summary statistics such as mean or count for each group. The data was analyzed in R using the dplyr package together with the pipe operator %>% to make the code easier to read and follow. The group_by() function was used to group the data by Country, and summarise() was used to calculate summary statistics such as the average life expectancy and the number of records for each country. These steps helped to understand differences between countries and summarize key patterns in both the original and merged datasets.
# Homework4: How to use trace() and recover()
my_function <- function(x, y) {
result <- (x^2 + 2 * y)
return(result)
}
# Add tracing
trace(
"my_function",
quote(cat("Inside my_function: x =", x, ", y =", y, "\n")),
at = 1,
print = FALSE
)## [1] "my_function"my_function(2, 3)## Inside my_function: x = 2 , y = 3## [1] 10# Remove tracing afterward
untrace("my_function")
# Enable recover debugging on errors
options(error = recover)
# Example function with an error
my_function_debug <- function(x, y) {
result <- (x^2 + 2 * y)
stop("Test error")
return(result)
}
my_function_debug(2, 3)## Error in my_function_debug(2, 3): Test errorExplanation: The recover() function was used to debug errors in R by allowing interactive inspection of the environment where an error occurs. When an error is triggered, R pauses execution and provides options to explore the function stack. After testing, the error option was reset using options(error = NULL).
#Function for Summary Statistics
# Create summary statistics function
summary_stats <- function(x) {
result <- list(
Mean = mean(x),
Median = median(x),
SD = sd(x),
Minimum = min(x),
Maximum = max(x)
)
return(result)
}
# Example variable
scores <- c(12, 15, 18, 20, 22, 25)
# Apply function
summary_stats(scores)## $Mean
## [1] 18.66667
##
## $Median
## [1] 19
##
## $SD
## [1] 4.718757
##
## $Minimum
## [1] 12
##
## $Maximum
## [1] 25#Function for Two-Sample t-test
# Create two-sample t-test function
two_sample_ttest <- function(x, y) {
result <- t.test(x, y)
return(result)
}
# Example data
group1 <- c(12, 14, 15, 16, 18)
group2 <- c(20, 22, 24, 25, 27)
# Apply function
two_sample_ttest(group1, group2)##
## Welch Two Sample t-test
##
## data: x and y
## t = -5.4832, df = 7.7297, p-value = 0.0006587
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -12.238958 -4.961042
## sample estimates:
## mean of x mean of y
## 15.0 23.6Explanation: The summary_stats() function calculates basic descriptive statistics such as the mean, median, standard deviation, minimum, and maximum values of a dataset. The two_sample_ttest() function performs a two-sample t-test to compare the means of two groups and determine whether they are significantly different. In the examples above, the functions are applied to sample numeric data to demonstrate how user-defined functions can simplify statistical analysis in R.
#sapply()
# Create a list
numbers <- list(a = 1:5, b = 6:10, c = 11:15)
# Find mean of each list element
sapply(numbers, mean)## a b c
## 3 8 13#vapply()
# Create a list
numbers <- list(a = 1:5, b = 6:10, c = 11:15)
# Apply mean function
vapply(numbers, mean, numeric(1))## a b c
## 3 8 13#mapply()
# Two vectors
x <- 1:5
y <- 6:10
# Add corresponding values
mapply(function(a, b) a + b, x, y)## [1] 7 9 11 13 15#Map()
# Two vectors
x <- 1:5
y <- 6:10
# Multiply values
Map(function(a, b) a * b, x, y)## [[1]]
## [1] 6
##
## [[2]]
## [1] 14
##
## [[3]]
## [1] 24
##
## [[4]]
## [1] 36
##
## [[5]]
## [1] 50#split()
# Student scores
scores <- c(80, 75, 90, 85, 70, 95)
# Groups
group <- c("A", "A", "B", "B", "C", "C")
# Split scores by group
split(scores, group)## $A
## [1] 80 75
##
## $B
## [1] 90 85
##
## $C
## [1] 70 95#tapply()
# Student scores
scores <- c(80, 75, 90, 85, 70, 95)
# Groups
group <- c("A", "A", "B", "B", "C", "C")
# Find mean score for each group
tapply(scores, group, mean)## A B C
## 77.5 87.5 82.5sapply() applies the mean() function to each element in the list and returns the results as a vector. vapply() applies the mean() function and ensures the output is numeric. mapply() adds elements from two vectors position by position. Map() applies a function to multiple inputs and returns the result as a list. split() separates the scores according to their groups. tapply() calculates the mean score for each group separately. In summarry: sapply() applies a function to a list or vector and returns a simplified output like a vector or matrix. vapply() is similar to sapply() but requires specifying the output type for safer results. mapply() applies a function to multiple vectors or lists at the same time. Map() works like mapply() but returns the output as a list. split() divides data into groups based on a factor or category. tapply() applies a function to grouped data and summarizes the results.