library(readr)
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, union

Working on all given Homeworks

Homework1

Task: Importing data from different sources

In this task, we are required to import datasets from different sources into RStudio. Therefore, I am going to import datasets from Excel sheet, SPSS file, and CSV file. This process is important because data can come in different formats, and RStudio provides tools and packages that make it easy to load and analyze such data efficiently. By importing datasets from these sources, we can prepare the data for cleaning, analysis, and visualation.

1. Importing a csv file into RStudion 

dataset_1<-read.csv("C:\\Users\\NISR\\Desktop\\Women's waiting time dataset for dieudonne.csv")
#variable.names(dataset_1)
#library(dplyr)
#count(dataset_1)

2. Importing an Excel file into RStudion 

library(readxl)
dataset_2<- read_excel("C:\\Users\\NISR\\Desktop\\exercise.xlsx")
#variable.names(dataset_2)
#count(dataset_2)

3. Importing an SPSS file into RStudion 

library(haven)
dataset_3<- read_spss("C:\\Users\\NISR\\Desktop\\reberaha\\URGENT\\Waiting time Dataset.sav")
#variable.names(dataset_3)
#count(dataset_3)

4. Importing database into RStudion 

library(DBI)
library(RSQLite)
connection<-dbConnect(RSQLite::SQLite(),"auca_database.db")
#dbGetQuery(connection,"select * from gishushu")

Homework2

Task: How to merge datasets from two to three or more variables?

Data analysis often requires combining information from multiple datasets in order to create a complete and meaningful dataset for analysis. In RStudio, merging datasets is an important technique that allows researchers and analysts to integrate data based on common variables such as IDs, names, dates, or other related fields. Depending on the structure of the data, datasets can be merged using two, three, or even more variables to ensure accuracy and consistency. This task focuses on understanding how to merge datasets in RStudio using different variables, which helps improve data organization, reduce redundancy, and prepare datasets for further statistical analysis and visualization.

library(magrittr)
Kinyarwanda_and_Maths_marks <- data.frame(
   Names = c("Claude", "Mugisha", "Patrick", "Aimable"),
   Kinyarwanda    = c(92, 78, 87, 83),
   Maths     = c(67, 75, 81, 77)
 )
 
Kinyarwanda_and_Geoagraphy_marks<- data.frame(
   Names = c("Claude", "Mugisha", "Patrick", "Aimable"),
   Kinyarwanda = c(84, 83, 65, 78),
   Geography = c(90, 80, 79, 89)
 )

#Their is Difference Way we can make The Marging Their is

#merge
#inner_join
#left_join
#right_join
#full_join

 merge(Kinyarwanda_and_Maths_marks,Kinyarwanda_and_Geoagraphy_marks , by = c("Names","Kinyarwanda"))
## [1] Names       Kinyarwanda Maths       Geography  
## <0 rows> (or 0-length row.names)
 inner_join(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"))
## [1] Names       Kinyarwanda Maths       Geography  
## <0 rows> (or 0-length row.names)
 merge(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"), all.x = TRUE)
##     Names Kinyarwanda Maths Geography
## 1 Aimable          83    77        NA
## 2  Claude          92    67        NA
## 3 Mugisha          78    75        NA
## 4 Patrick          87    81        NA
 left_join(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"))
##     Names Kinyarwanda Maths Geography
## 1  Claude          92    67        NA
## 2 Mugisha          78    75        NA
## 3 Patrick          87    81        NA
## 4 Aimable          83    77        NA
 merge(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"), all.y = TRUE)
##     Names Kinyarwanda Maths Geography
## 1 Aimable          78    NA        89
## 2  Claude          84    NA        90
## 3 Mugisha          83    NA        80
## 4 Patrick          65    NA        79
 right_join(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"))
##     Names Kinyarwanda Maths Geography
## 1  Claude          84    NA        90
## 2 Mugisha          83    NA        80
## 3 Patrick          65    NA        79
## 4 Aimable          78    NA        89
 merge(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"), all = TRUE)
##     Names Kinyarwanda Maths Geography
## 1 Aimable          78    NA        89
## 2 Aimable          83    77        NA
## 3  Claude          84    NA        90
## 4  Claude          92    67        NA
## 5 Mugisha          78    75        NA
## 6 Mugisha          83    NA        80
## 7 Patrick          65    NA        79
## 8 Patrick          87    81        NA
 full_join(Kinyarwanda_and_Maths_marks, Kinyarwanda_and_Geoagraphy_marks, by = c("Names","Kinyarwanda"))
##     Names Kinyarwanda Maths Geography
## 1  Claude          92    67        NA
## 2 Mugisha          78    75        NA
## 3 Patrick          87    81        NA
## 4 Aimable          83    77        NA
## 5  Claude          84    NA        90
## 6 Mugisha          83    NA        80
## 7 Patrick          65    NA        79
## 8 Aimable          78    NA        89

Homework3

Task: group_by and %<%

In data analysis, organizing and summarizing data is an important step for understanding patterns and making decisions. In RStudio, the group_by() function and the pipe operator %>% from the dplyr package are widely used for data manipulation. The group_by() function helps to arrange data into groups based on one or more variables, while %>% allows commands to be connected in a clear and readable sequence. This task focuses on learning how to use group_by() together with %>% to perform operations such as summarizing, counting, and analyzing grouped data efficiently. These tools make data analysis simpler, faster, and easier to understand.

library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ tidyr::extract()   masks magrittr::extract()
## ✖ dplyr::filter()    masks stats::filter()
## ✖ dplyr::lag()       masks stats::lag()
## ✖ purrr::set_names() masks magrittr::set_names()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
Classss <- data.frame(
   Names = c("Claude", "Mugisha", "Patrick", "Aimable"),
   Kinyarwanda = c(84, 83, 65, 78),
   Geography = c(90, 80, 79, 89)
 )

# This %>% We can Use it When you want to Count the Row of Row You have in your Table

Classss %>% tally()
##   n
## 1 4
# This is How we Group the Data with same Variable like here i use Country
Classss %>%
  group_by(Names) %>%
  summarise(
    average_gdp = mean(Geography),
    max_gdp = max(Geography),
    min_gdp = min(Geography)
  )
## # A tibble: 4 × 4
##   Names   average_gdp max_gdp min_gdp
##   <chr>         <dbl>   <dbl>   <dbl>
## 1 Aimable          89      89      89
## 2 Claude           90      90      90
## 3 Mugisha          80      80      80
## 4 Patrick          79      79      79

Homework4

Task: group_by and %<%

In R programming, debugging is an important process used to identify and fix errors in code. Two useful debugging tools in R are trace() and recover(). The trace() function allows programmers to monitor and inspect how a function is executed by inserting debugging code into a function. On the other hand, recover() helps users investigate errors by allowing them to browse function calls after an error occurs. These tools are helpful for understanding program behavior, locating mistakes, and improving code efficiency.

1. Using trace() in R

The trace() function is used to temporarily modify a function to print messages or run debugging commands.

# Create a function
add_numbers <- function(x, y) {
  result <- x + y
  return(result)
}

# Trace the function
trace(add_numbers)

# Run the function
add_numbers(5, 6)
## trace: add_numbers(5, 6)
## [1] 11

2.Using recover()

The recover() function is used for error handling and debugging. It allows you to inspect the environment where an error occurred.

options(error = recover)
add_one <- function(x) x + 1
double  <- function(x) add_one(x) * 2

double(5)   # "a" causes a crash
## [1] 12
options(error = NULL)

Homework5

Task: Create your own function that calculate summary statistics

In data analysis, summary statistics are important because they help describe and understand the main characteristics of a dataset. In R programming, functions can be created to automate calculations such as the mean, median, minimum, maximum, standard deviation, and other statistical measures. Creating a custom function allows users to save time, reduce repetition, and improve the efficiency of data analysis. In this task, the objective is to create a personal R function that calculates summary statistics for a dataset or selected variables, making data interpretation easier and more organized.

# ── Mean ──────────────────────────────────────────────
my_mean <- function(data) {
  sum(data) / length(data)
}

# ── Median ────────────────────────────────────────────
my_median <- function(data) {
  sorted_data <- sort(data)
  n <- length(sorted_data)
  mid <- floor(n / 2)
  
  if (n %% 2 == 0) {
    return((sorted_data[mid] + sorted_data[mid + 1]) / 2)
  } else {
    return(sorted_data[mid + 1])
  }
}

# ── Minimum ───────────────────────────────────────────
my_min <- function(data) {
  minimum <- data[1]
  for (x in data) {
    if (x < minimum) minimum <- x
  }
  minimum
}

# ── Maximum ───────────────────────────────────────────
my_max <- function(data) {
  maximum <- data[1]
  for (x in data) {
    if (x > maximum) maximum <- x
  }
  maximum
}

# ── Standard Deviation (Population) ──────────────────
my_sd <- function(data) {
  mean_val <- my_mean(data)
  variance <- sum((data - mean_val)^2) / length(data)
  sqrt(variance)
}

# ── All-in-one Summary Function ───────────────────────
summary_statistics <- function(data) {
  cat("================================\n")
  cat("       SUMMARY STATISTICS       \n")
  cat("================================\n")
  cat(sprintf("Mean:               %.4f\n", my_mean(data)))
  cat(sprintf("Median:             %.4f\n", my_median(data)))
  cat(sprintf("Minimum:            %.4f\n", my_min(data)))
  cat(sprintf("Maximum:            %.4f\n", my_max(data)))

  cat("================================\n")
}

# ── Test it ───────────────────────────────────────────
data <- c(8, 7, 7, 16, 6, 30, 5, 32, 13, 34)
summary_statistics(data)
## ================================
##        SUMMARY STATISTICS       
## ================================
## Mean:               15.8000
## Median:             10.5000
## Minimum:            5.0000
## Maximum:            34.0000
## ================================

Homework6

Task: Lapply(), Sapply(), Vapply()

  • lapply()
  • sapply()
  • vapply()

1. lapply() — Returns a List

numbers <- list(1, 2, 3, 4)

result <- lapply(numbers, function(x) x * 2)

print(result)
## [[1]]
## [1] 2
## 
## [[2]]
## [1] 4
## 
## [[3]]
## [1] 6
## 
## [[4]]
## [1] 8

2. sapply() — Simplifies Output

sapply() simplifies the result into vectors, matrices, or arrays whenever possible.

Example — Producing a Vector

numbers <- list(1, 2, 3, 4)

result <- sapply(numbers, function(x) x * 2)

print(result)
## [1] 2 4 6 8

Example — Producing a Matrix

numbers <- list(1, 2, 3)

result <- sapply(numbers, function(x) c(x, x^2))

print(result)
##      [,1] [,2] [,3]
## [1,]    1    2    3
## [2,]    1    4    9

3. vapply() — Safer Version of sapply()

vapply() requires specifying the expected output type.

Syntax

vapply(X, FUN, FUN.VALUE)

Example — Numeric Vector

numbers <- list(1, 2, 3, 4)

result <- vapply(
  numbers,
  function(x) x * 2,
  numeric(1)
)

print(result)
## [1] 2 4 6 8
#### Example — Character Output
words <- list("caw", "goat", "bird")

result <- vapply(
  words,
  toupper,
  character(1)
)

print(result)
## [1] "CAW"  "GOAT" "BIRD"