Math Club Meeting: Dating with Data

class: center, middle, inverse, title-slide

# Math Club Meeting: Dating with Data
## Exploratory Data Analysis - Job Analysis
### Ying-Ju Tessa Chen, PhD <a href="https://github.com/Ying-Ju">  Ying-Ju</a> <a href="mailto:ychen4@udayton.edu">  ychen4@udayton.edu</a> 
### October 5, 2021

---

# Ad: Undergraduate Mathematics Day

- Date: **Saturday, November 6, 2021**

- An undergraduate mathematics conference

- Contributed **15-minute talks**, primarily by undergraduate students, on mathematics research, the learning and teaching of mathematics, the history of mathematics, and applications to disciplines related to mathematics

- Talks are delivered **face to face or virtually**

- Two invited addresses
  * Suzanne Lenhart, University of Tennessee (One Health: Connecting Humans, Animals and the Environment)
  * Jennifer White, Saint Vincent College (The Crossings of Art, History, and Mathematics)
  
- Submit articles (based on talks presented) for publication in refereed online Conference Proceedings

-	No registration fee, complimentary lunch
  * Registration and information at [UndergradMathDayRegistration](https://udayton.edu/artssciences/academics/mathematics/events/undergrad-math-day/index.php)
  * deadline: **Sunday, October 31, 2021**.

---
.pull-left[
## Why dating with data?

- Understand what you are working on
  * Size of the data
  * Type of variables
  * Any missing values?
  * Any outliers? what to do with them?

- Summarize the data
  * Characteristics of variables
  
- Find interesting pattern

- **What** can the data tell us?

- **Why** are things good to know?

- **How** to present the story?
]

.pull-right[
<img src="wordcloud.jpg" width="480" height="480" />
]

---

# Google Job Skills

- Google published all of their jobs at [https://careers.google.com/](https://careers.google.com/).

- The data are collected using Selenium by scraping all of the jobs text from the Google Career site and provided in [kaggle.com](https://www.kaggle.com/niyamatalmass/google-job-skills?) by [Niyamat Ullah](https://www.kaggle.com/niyamatalmass).

- Available variables

* **Title**: The title of the job

* **Category**: Category of the job

* **Location**: Location of the job

* **Responsibilities**: Responsibilities for the job

* **Minimum Qualifications**: Minimum Qualifications for the job

* **Preferred Qualifications**: Preferred Qualifications for the job

---

### Let's check out the data set first.

```r
df <- read_csv("job_skills.csv")
plot_intro(df, ggtheme = theme_minimal(base_size = 18))
```

---

### Which variables have missing values?

```r
plot_missing(df, ggtheme = theme_minimal(base_size = 18))
```

---

### Get a glimpse of the data

```r
glimpse(df)
```

```
## Rows: 1,250
## Columns: 7
## $ Company <chr> "Google", "Google", "Google", "Google", "Goog~
## $ Title <chr> "Google Cloud Program Manager", "Supplier Dev~
## $ Category <chr> "Program Management", "Manufacturing & Supply~
## $ Location <chr> "Singapore", "Shanghai, China", "New York, NY~
## $ Responsibilities <chr> "Shape, shepherd, ship, and show technical pr~
## $ Minimum_Qualifications <chr> "BA/BS degree or equivalent practical experie~
## $ Preferred_Qualifications <chr> "Experience in the business technology market~
```

```r
table(df$Company)
```

```
## 
##  Google YouTube 
##    1227      23
```

---

### Find what you need to get a job at Google

Since there are only 23 jobs from YouTube, we will focus on the job skills needed in Google.

```r
df <- df %>% filter(Company=="Google") %>% select(-Company)
```

#### Here is a list of things we would like to know:

- Popular job categories

- Popular job titles

- Where their offices are located

- Which location(s) that Google needs more employee

- Academic degree

- Years of experience

- Programming languages

- Popular subjects

---

**Popular Job Categories**

```r
ggplot(data=df) + geom_bar(aes(x=reorder(Category, Category, function(x) length(x))),
                  fill=daytonred, position=position_dodge(width=1)) + 
                  coord_flip() + theme(legend.position = "none") +
                  labs(x="Job Category", y="Number of Jobs") + theme_minimal(base_size = 18)
```

---

**Popular Job Titles**

```r
titles <- sort(table(df$Title), decreasing = T)[1:20]
df1 <- data.frame(titles)
ggplot(data=df1, aes(x=reorder(Var1, Freq), y=Freq)) + geom_bar(stat="identity", fill=daytonred, 
 position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") + 
 labs(x="Top 20 Popular Job Titles", y="Number of Jobs") + theme_minimal(base_size = 26)
```

---

**Which location(s) that Google needs more employee**

```r
locations <- sort(table(df$Location), decreasing = T)[1:20]
df2 <- data.frame(locations)
ggplot(data=df2, aes(x=reorder(Var1, Freq), y=Freq)) + geom_bar(stat="identity", fill=daytonred, 
 position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") +
 labs(x="Top 20 Popular Locations", y="Number of Jobs") + theme_minimal(base_size = 18)
```

---
**Academic Degree**

```r
ggplot(data=df3, aes(x=reorder(Degree, Count), y=Count)) + geom_bar(stat="identity", fill=daytonred,
      position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") +
      labs(x="Degree", y="Number of Jobs") + theme_minimal(base_size = 18)
```

---
**Years of Experience**

```r
ggplot(data=df4, aes(x=reorder(Year, Count), y=Count)) + geom_bar(stat="identity", fill=daytonred,
      position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") +
      labs(x="Years of Experience", y="Number of Jobs") + theme_minimal(base_size = 18)
```

<img src="analysis_files/figure-html/exp_years-1.png" width="65%" style="display: block; margin: auto;" />
---

**Programming Languages**

```r
ggplot(data=df5, aes(x=reorder(Language, Count), y=Count)) + geom_bar(stat="identity", fill=daytonred,
      position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") +
      labs(x="Programming Language", y="Number of Jobs") + theme_minimal(base_size = 18)
```

<img src="analysis_files/figure-html/job_languages-1.png" width="65%" style="display: block; margin: auto;" />
---

**Popular Subjects**

In the end, I am curious how popular certain subjects are when looking for a job in Google. Here, I only consider the following subjects: **Computer Science**, **Engineering**, **Mathematics**, and **Statistics**.

```r
ggplot(data=df6, aes(x=reorder(Subject, Count), y=Count)) + geom_bar(stat="identity", fill=daytonred,
      position=position_dodge(width=1)) + coord_flip() + theme(legend.position = "none") +
      labs(x="Subject", y="Number of Jobs") + theme_minimal(base_size = 18)
```

---
# Ad: MTH 490 Intro to Programming with R

- **Spring**, 2022

- 1 credit hour

- **5:05PM - 6:20PM on Mondays**

- Things you will learn in this course
  * Basic data types
  * Basic data structures
  * Managing data
  * Creating basic graphical displays
  * Data manipulation
  * Data visualization with two R packages: ggplot2, plotly
  * R markdown presentation
  * Dynamic programming (if time permits)

---

# Thanks

.pull-left[
- Please do not hesitate to contact Dr. Chen if you have questions pertaining to learning R or other languages. Please email me at <a href="mailto:ychen@udayton.edu">&nbsp; ychen4@udayton.edu</a>.

- The R code used in this presentation can be found [here](https://raw.githubusercontent.com/Ying-Ju/MathClub.github.io/main/job_analysis.R).

- Slides were created via the R package **xaringan**, with styling based on:  
  * [xariganthemer](https://cran.r-project.org/web/packages/xaringanthemer/vignettes/xaringanthemer.html) package, and  
  * Alison Hill's [@apreshill](https://github.com/apreshill/) CSS resources for customizing themes and fonts

- The formatting of slides is provided by Dr. Fadel M. Megahed [@fmegahed](https://github.com/fmegahed).

- The example data are provided in [kaggle.com](https://www.kaggle.com/niyamatalmass) by [Niyamat Ullah](https://www.kaggle.com/niyamatalmass). 
]

.pull-right[
<img src="https://www.verouden.net/slides/presentation-xaringan/img/questions.gif" width="350" height="350" />
]