Welcome to Intro to Data Science

# Welcome to Intro to Data Science

---

# Welcome!

---

## What is Data Science?

Data science is an emerging discipline that builds on tools from mathematics,
statistics, and computer science to extract knowledge from data.

## Course Objectives

- explore, visualize, and analyze data in a reproducible manner
- investigate patterns, model outcomes, and make predictions
- gain experience in data wrangling and munging, exploratory data analysis, predictive modeling, and data visualization
- work on problems and case studies inspired by real-world questions and data
- effectively communicate results

---

## Where to find information

#### Course Website: https://sta199-sp21-002.netlify.app/

.pull-left[
- slides and notes
- schedule
  ]
.pull-right[
- syllabus and course policies
- links to other resources
]

#### Sakai: https://sakai.duke.edu

- Gradebook
- Zoom links to live lecture, office hours, and labs
- recorded videos

#### GitHub: https://github.com/sta199-sp21-002/

- assignment repos

---

## Activities and Assessments

- **Homework (25%):** Five individual assignments combining conceptual and 
computational skills.

- **Labs (15%):** Nine individual or team assignments focusing on computing. 
Designed to be completed during the official lab session.

- **Exams (40%):** Two individual take-home exams.

- **Final Project (15%):** Team final project in which you use the data science
tools to answer a data-based research question.

- **Participation and Teamwork (2.5%):** Primarily completion of lecture notes. 
Due one week following the lecture date.

- **Statistics Experiences (2.5%):** Engage with statistics outside of the 
classroom and reflect on your experience.

---

## Course Structure

#### Lecture

- Focus on concepts behind data analysis
  - Recorded and posted online
  - A lecture notes R Markdown file will be created for you for each lecture
  
#### Lab

- Focus on computing in R `tidyverse` syntax
- Apply concepts from lecture to case study scenarios
- Work on labs individually or in teams of 3-4
- Designed to be completed during the scheduled lab time
- introductory portion will be recorded and posted online

---

## Some of what you will learn
.pull-left[
- Fundamentals of `R`

- Data visualization and wrangling with `ggplot2` and `dplyr` from the `tidyverse`

- Web scraping

- Web based applications with `RShiny`

- Spatial data visualization

]

- Version control with `GitHub`

- Reproducible reports with `R Markdown`

- Regression and classification

- Statistical inference

]

---

## Textbooks

- **[OpenIntro Statistics](https://www.openintro.org/book/os/)** 
  - Free online
  - Hard copies available for purchase
  - Assigned readings on statistical content

- **[R for Data Science](https://r4ds.had.co.nz/)**
  - Free online
  - Hard copies available for purchase
  - Assigned readings on R coding using `tidyverse` syntax

- **Occasional other readings**
  - Will be posted on the course webpage

---

## Where to find help in the course

- Attend **office hours** to meet with a member of the teaching team.
  - office hours begin Thursday Jan 21
  - stay after lecture if you have questions
- Use **Piazza** (free) for general questions about course content and/or assignments, since other students may benefit from the response.
- Use **chat** for questions during lecture.
- Use **email** for questions regarding personal matters and/or grades.

## Technical help this week

- Jan 21 6:30 - 8:30 PM
- Jan 22 8:00 - 10:00 AM

Will post links after class.

---

## Technology set-up

Complete into survey at the link below if you haven't already.

https://forms.gle/M6XLB7BoWcCLFbGa9

Accept the invitation to the GitHub organization when you receive it after 
class.

---

### How are you feeling right now?

---

## Zoom Mechanics

-Display your first and last name

-Raise your hand (under "Participants")

-Yes, No, Go slower, Go faster (under "Participants")

-Applause, Thumbs up (under "Reactions")

-Chat the last book you read.

- ask questions during lecture
  - answer questions during lecture
  - share links

---

# Toolkit

---

## What is R and RStudio?

- R is a statistical programming language

- RStudio is a convenient interface for R (an integrated development environment, IDE)

- At its simplest:*
 - R is like a car’s engine
 - RStudio is like a car’s dashboard

---

## tidyverse

- The [tidyverse](https://www.tidyverse.org/) is an **opinionated**\* collection of R packages designed for data science.

- All packages share an underlying philosophy and a common grammar.

.footnote[
Image from [Teaching in the Tidyverse 2020](https://education.rstudio.com/blog/2020/07/teaching-the-tidyverse-in-2020-part-1-getting-started/)
]

---

## RStudio

---

## RStudio

---

## Accessing RStudio

- Link: https://vm-manage.oit.duke.edu/containers/rstudio
  - also on Sakai
  - also on the course webpage
  
--

# Let's try!

---

## Reproducibility checklist

What does it mean for a data analysis to be "reproducible"?

**Near-term goals:**

`\(\checkmark\)` Are the tables and figures reproducible from the code and data?

`\(\checkmark\)` Does the code actually do what you think it does?

`\(\checkmark\)` In addition to what was done, is it clear **why** it was done?

**Long-term goals:**

`\(\checkmark\)` Can the code be used for other data?

`\(\checkmark\)` Can you extend the code to do other things?

---

# R Markdown

---

## R Markdown

- Fully reproducible reports -- the analysis is run from the beginning each time you knit

- Simple [Markdown syntax](https://github.com/rstudio/cheatsheets/raw/master/rmarkdown-2.0.pdf) for text

- Code goes in chunks, defined by three backticks, narrative goes outside of chunks

## How will we use R Markdown?

- Every assignment / lab / project / etc. is an R Markdown document

- You'll always have a template R Markdown document to start with

- The amount of scaffolding in the template will decrease over the semester

---

---

---

# Let's try!

---

# Git and GitHub

---

## Version control

We will use GitHub as a platform for collaboration and version control.

##### Why do we need version control?

---

## What is versioning?

---

## What is versioning?

with human readable messages

---

- **Git** is a version control system -- like “Track Changes” features from Microsoft Word.

- **GitHub** is the home for your Git-based projects on the internet (like DropBox but much better).

- There are a lot of Git commands and very few people know them all. 99% of the time you will use git to stage, commit, push, and pull.

---

# Let's try!

---

## Outline of steps

- **repository (repo)**: contains files associated with a particular project and
each file's version history
- **pull**: update a local repository from a remote repo (GitHub)
- **stage**: prepare file for commit
- **commit**: save changes to local repository
- **push**: upload files to remote repository (gitHub)

- Step #1. Create / navigate to the repository on GitHub
- Step #2. Clone the GitHub repo & make a new RStudio project
- Step #3. Configure git
- Step #4. Change a file locally
- Step #5. Stage and commit
- Step #6. Push these changes to the repo on GitHub.

---

### Step #1. Create a repository on GitHub

.vocab[repository]: contains files associated with a particular project and each
file's version history

(a) Click the link below to create the repository for lecture notes #1.
  - https://classroom.github.com/a/2g5MiMkx
  
--

(b) When prompted, select "Accept this assignment".

(d) Click the link following "Your assignment repository has been created:".

**A private repository was just created for you.**

---

### Step #1. Create a repository on GitHub

---

### Step #2. Clone a GitHub repo & Make a new RStudio project

(a) In the repository that was just created, click the green "CODE" button, 
select "Use HTTPS" and click the clipboard icon to copy the repo URL.

---

### Step #2. Clone a GitHub repo & Make a new RStudio project

(b) In RStudio, click "File" `\(\rightarrow\)` "New Project" `\(\rightarrow\)` "Version Control" `\(\rightarrow\)` "Git".

(d) Click "Create Project" and enter your GitHub username and password when
prompted.

(e) The files from your GitHub repo should now be displayed in the "Files" pane
in RStudio.

The "Project" drop-down menu in the upper-right should show the project you are 
currently working on.

---

### Step #3. Configure Git

We need to make sure RStudio can communicate with GitHub.

(a) Type or paste the code below into the **console**.

```r
library(usethis)
use_git_config(
  user.name = "GitHub username", 
  user.email="your email"
)
```

But fill in your GitHub username and the email associated with GitHub (mine is
below). Click **ENTER** to run the code in the console.

```r
library(usethis)
use_git_config(
  user.name = "rdeisinger", 
  user.email="robert.eisinger@duke.edu"
)
```

---

### Step #3. Configure Git

If if worked, your console should look like the screenshot below.

---

### Step #4. Change a file locally

(a) Click the R Markdown file named lecture01.Rmd in the lower-right pane.

(b) Change the author name to your name.

Examine this file. What changed?

---

### Step #5. Stage and Commit

(a) Open the "Git" pane in the top-right panel.

(b) Click on the .Rmd file

(d) If you're happy with the changes, stage them by checking the box next to the file.

(e) Write a meaningful commit message "changed author" in the commit message box.

(f) Click commit.

---

### Step #6. Push these changes to the repo on GitHub.

- .vocab[push]: upload files to remote repository (gitHub)

(a) Click "Push".

- Now go to the repo on GitHub. What do you notice?

---

## Vocabulary

- **pull**: update a local repository from a remote repo (GitHub)
- **stage**: prepare file for commit
- **commit**: save changes to local repository
- **push**: upload files to remote repository (gitHub)

As you work on a data science project, you should periodically knit, stage, 
commit, and push.

If you are working on a team, there may be updates to your GitHub repo that 
aren't in your local repo. To make sure you are starting with the most up-to-date
files, click "Pull" to update your local repo before adding any new work.

Submit your lecture notes for credit by pushing before the deadline.

---

## Review of steps