Affairs Shown with Graphs

This is a dataset that was previously used and was found on kaggle.com. I want to re-visit the data and graph the information to see what type of story can be concluded from it.

Exploring the Data

library(ggplot2)
library(ggthemes)
library(Zelig)
library(ggrepel)
library(HistData)
library(tidyverse)
library(dplyr)

options(dplyr.show_progress = FALSE)

affairs<- read.csv("C:/Users/Jessica/Desktop/712/affairs.csv")
head(affairs)
##   affairs gender age yearsmarried children religiousness education
## 1       0   male  37        10.00       no             3        18
## 2       0 female  27         4.00       no             4        14
## 3       0 female  32        15.00      yes             1        12
## 4       0   male  57        15.00      yes             5        18
## 5       0   male  22         0.75       no             2        17
## 6       0 female  32         1.50       no             2        17
##   occupation rating
## 1          7      4
## 2          6      4
## 3          1      4
## 4          6      5
## 5          6      3
## 6          5      5
g1 <- ggplot(affairs, aes(x = gender)) + geom_bar(color ="Blue", fill = "Blue")
gender <- g1 + labs(title = "Gender Count") + ylab("Count") + xlab("Gender") 
plot(gender)

Dividing into the variables.

affairs <- affairs%>%
  mutate(age_group=ifelse(age >= 17 & age <= 25, "17-25 years old",
                          ifelse(age >=26 & age <= 35, "26-35 years old",
                                 ifelse(age>= 36 & age <= 45, "36-45 years old",
                                        ifelse(age >=46 & age <= 55, "46-55 years old",
                                               ifelse(age>=56, "56-65 years old", NA))))))

g <- ggplot(affairs, aes(x = age_group)) + geom_bar(color ="Blue", fill = "Red")
ggplotagegroup <- g + labs(title = "Affairs by Age Group") + ylab("Count") + xlab("Age Group")
plot(ggplotagegroup)

Focusing on The Number of Years Married

g1 <- ggplot(affairs, mapping = aes(x = yearsmarried, y = affairs)) 

g2 <- g1 + geom_bin2d()+ggtitle("Years Married vs. Number of Affairs")
g2

g3 <- g1 + geom_smooth() +ggtitle("Years Married vs. Number of Affairs")
g3

Adding gender into the mix to look closer

qplot(yearsmarried, data = affairs, fill = gender, ylab = "Affairs", xlab = " Years Married ") + scale_fill_manual("gender", values = c("male" = "blue", "female" = "orange"))

qplot(religiousness, data = affairs, fill = gender, ylab = "Affairs", xlab = " Religiousness") + scale_fill_manual("gender", values = c("male" = "red", "female" = "green"))

qplot(rating, data = affairs, fill = gender, ylab = "Affairs", xlab = " Rating") + scale_fill_manual("gender", values = c("male" = "red", "female" = "blue"))

qplot(rating, affairs, data = affairs, colour = gender)