Presentation 3- Cassidy Longoria

How To access a column in R: We have a dataset of a survey containing multiple columns of information. We are interested in the isolating the satisfaction scores of the survey:

So, we need to extract the data from the Satisfaction column:

# Question 1 & 2
# Q1: Mean and Median of Satisfaction Ratings
# Q2: Find the average age of someone working in HR

# Extracts the satisfaction column from our data set creating vector now referred to as "Sat"
Sat<-SatisfactionSurvey$Satisfaction

# Creating a vector containing the ages of those in the HR Department
HR_Ages<- SatisfactionSurvey$Age[SatisfactionSurvey$Department == "HR"]

# Average age of those in the HR department
mean(HR_Ages)

[1] 30

# Calculates the mean and median of the Satisfaction variable
mean(Sat)

[1] 6.75

median(Sat)

[1] 7

# Creates a histogram and boxplot displaying Satisfaction scores
hist(Sat,
     col = rainbow(5),
     border = "grey",
     main = "Satisfaction Distribution",
     xlab = "Satisfaction Score",
  )

boxplot(Sat,
        col = "lightsteelblue3",
        border = "black",
        main = "Boxplot of Satisfaction",
        ylab = "Satisfaction Score")

Converting columns within the data set into matrices:

Determining the average satisfaction rating of each age group.

# Question 3
# Extracts the satisfaction from our data set creating vector now referred to as "Sat"
Sat <- SatisfactionSurvey

# Creates a matrix containing columns Age and Satisfaction scores
Age_Sat_Matrix <- as.matrix(Sat[, c("Age", "Satisfaction")])


Age_Mean_Sat <- tapply(Age_Sat_Matrix[, 2],
                       Age_Sat_Matrix[, 1],
                       mean,na.rm = TRUE)

# Creates data frame using our matrix
Age_Mean_Sat_df <- data.frame(
                   Age = as.numeric(names(Age_Mean_Sat)),
                   "Mean Satisfaction" = as.numeric(Age_Mean_Sat)
)

# Makes a cleaner version of our data
names(Age_Mean_Sat_df) <- c("Age", "Mean Satisfaction")

# Displays data frame
Age_Mean_Sat_df

Creating a matrix sorting named elements and a numberic value:

Determining the average satisfaction score per department:

# Question 4

# Keeps full data set
Sat <- SatisfactionSurvey

# Mean Satisfaction per Department
Department_Mean_Sat <- tapply(Sat$Satisfaction, 
                               Sat$Department,
                               mean,na.rm = TRUE)

# Convert to matrix with departments as columns
Department_Sat_Matrix <- matrix(Department_Mean_Sat,
                                nrow = 1,
                                dimnames = list(NULL, names(Department_Mean_Sat)))

# Transposes matrix into departments as rows
Department_Sat_Matrix_T <- t(Department_Sat_Matrix)

# Rename column name for clarity
colnames(Department_Sat_Matrix_T) <- c("Mean Satisfaction")

# View Matrix
Department_Sat_Matrix_T

          Mean Satisfaction
Finance                 6.4
HR                      7.8
IT                      6.4
Marketing               6.4

Analyzing Data frames:

Summarizing the Gender and Department columns:

Filtering the Data frame to only measure the Satisfaction Scores of those aged 30-40:

# Question 5 & 6

# Keeps full data set
Sat <- SatisfactionSurvey

# Columns and Rows of data set
dim(Sat)

[1] 20  5

nrow(Sat)

[1] 20

ncol(Sat)

[1] 5

# Converting values to factors
Sat$Gender <- as.factor(Sat$Gender)
Sat$Department <- as.factor(Sat$Department)

# Summary of columns
message("Demographics: Gender and Department Demographics")
summary(Sat$Gender)

    Female       Male Non-binary 
         8          8          4 

summary(Sat$Department)

  Finance        HR        IT Marketing 
        5         5         5         5 

# Mean of filtered data
message("Average Satisfaction for individuals aged 30-40")
Filtered_Sat <- Sat[Sat$Age >= 30 & Sat$Age <= 40, ]
mean(Filtered_Sat$Satisfaction, na.rm = TRUE)

[1] 6.666667

Histogram Distribution:

The range of different columns within the data set (Age, Satisfaction)

# Question 7 & 8

# Keeps full data set
Sat <- SatisfactionSurvey

# Making the Histogram
hist(Sat$Age,
     col = primary.colors(30),
     border = "grey",
     main = "Employee Age Distribution",
     xlab = "Age",
)

hist(Sat$Satisfaction,
     col = primary.colors(30),
     border = "grey",
     main = "Satisfaction Distribution",
     xlab = "Satisfaction Scores",
)

#

Distribution analysis through box plots:

Assessing data spread through box plot, determining IQR to identify outliers.

# Question 9-12

# Keeps full data set
Sat <- SatisfactionSurvey

# Satisfaction across Departments
boxplot(Sat_Dep,
        data = Sat,
        col = c("orchid3", "plum4", "lightpink3", "lightsteelblue"),
        border = "grey",
        main = "Satisfaction Ratings by Department",
        xlab = "Department",
        ylab = "Satisfaction Score"
)

#Age Distribution across Gender
boxplot(Sat$Age ~ Sat$Gender,
        data = Sat,
        col = c("pink2", "skyblue2", "springgreen2"),
        border = "grey",
        main = "Different Age Range by Gender",
        xlab = "Gender",
        ylab = "Ages"
)

# Overall Satisfaction Scores
boxplot(Sat$Satisfaction,
        col = "lightsteelblue3",
        border = "black",
        main = "Boxplot of Satisfaction",
        ylab = "Satisfaction Score")

# Explaining findings- overall satisfaction
message("IQR and Outliers")
cat("Satisfaction Scores:",
    "\nIQR:", IQR(Sat$Satisfaction, na.rm = TRUE),
    "\nQ1: 6, Q3: 8",
    "\nRange: 3-11")

Satisfaction Scores: 
IQR: 2 
Q1: 6, Q3: 8 
Range: 3-11

# Explaining Satisfaction per Department
cat("\nSatisfaction Scores per Department:",
    "\nIQR per Department:\n")

Satisfaction Scores per Department: 
IQR per Department:

# breakdown per department
tapply(Sat$Satisfaction, Sat$Department, IQR, na.rm = TRUE)

  Finance        HR        IT Marketing 
        1         1         1         2 

cat("Ranges per Department:",
    "\nFinance & IT : 4.5-8.5",
    "\nHR: 5.5-9.5",
    "\nMarketing: 2-9")

Ranges per Department: 
Finance & IT : 4.5-8.5 
HR: 5.5-9.5 
Marketing: 2-9