Data Science for Economists

class: center, middle, inverse, title-slide

# Data Science for Economists
## Lecture 1: Introduction
### Grant McDermott
### University of Oregon | <a href="https://github.com/uo-ec607">EC 607</a>

---

# Table of contents

1. [Prologue](#prologue)

2. [Syllabus highlights](#syllabus)

3. [Getting started](#started)

4. [R for data science](#r4ds)

5. [Data visualization with ggplot2](#ggplot2)

---
class: inverse, center, middle
name: prologue

# Prologue

---

# Introductions

### Course

You'll soon receive access to a quarter-specific copy of this repo, where we 
submit assignments, upload presentations, etc.

### Me

### You

A quick roundtable of names, fields/interests, and coding background.

---
class: inverse, center, middle
name: syllabus

# Syllabus highlights

(Read the full document [here](https://github.com/uo-ec607/syllabus/blob/master/syllabus.pdf).)

---

# Why this course?

Fill in the gaps left by traditional econometrics and methods classes.

- Practical skills that tools that will benefit your dissertation and future career.
- Neglected skills like how to actually find datasets in the wild and clean them.

Data science skills are largely distinct from (and complementary to) the core 'metrics oeuvre familiar to economists.

- Data viz, cleaning and wrangling; programming; cloud computation; relational databases; machine learning; etc.

> *"In short, we will cover things that I wish someone had taught me when I was starting out in graduate
school."*

---

# You, at the end of this course

---
# Grading

| Component                           | Weight |
|:-|-:|
| 4 × homework assignments (20% each) | 80% |
| 2 × short presentations (5% each)		| 10% |
| 1 × OSS contribution				        | 10% |

- You can swap out one homework assignment for an (approved) final presentation of your own research.
- [Short presentations](https://github.com/uo-ec607/presentations) summarize either a key lecture reading, or an (approved) software package/platform.
- We'll get to OSS contribution later in the course, but I particularly encourage contributions to [LOST](lost-stats.github.io/).

</br>

PS &mdash; I'll also award a class participation bonus (2.5%) at my discretion.

---
# Lecture outline

### Data science basics

- Introduction: Motivation, software installation, and data visualization
- Version control with Git(Hub)
- Learning to love the shell
- R language basics
- Data cleaning and wrangling: 1) tidyverse and 2) data.table
- Webscraping: (1) Server-side and CSS
- Webscraping: (2) Client-side and APIs

### Analysis and programming

- Regression analysis in R
- Spatial analysis in R
- Functions in R: (1) Introductory concepts
- Functions in R: (2) Advanced concepts
- Parallel programming

---
# Lecture outline (cont.)

### Scaling up: Big data and cloud computation

- Docker
- Cloud computing with Google Compute Engine
- High performance computing (Talapas cluster) 
- Databases: SQL(ite) and BigQuery
- Spark
- **Options**
  - Project workflow and automation
  - Machine learning
  - Peer-review and student project presentations (demand dependent)

---
class: inverse, center, middle
name: started

# Getting started

---

# Software installation and registration

1. Download [R](https://www.r-project.org/).

2. Download [RStudio](https://www.rstudio.com/products/rstudio/download/preview/).

3. Download [Git](https://git-scm.com/downloads).

4. Create an account on [GitHub](https://github.com/) and register for a student/educator [discount](https://education.github.com/discount_requests/new).
  - You will soon receive an invitation to the quarter-specific course org. on GitHub, as well as [GitHub classroom](https://classroom.github.com), which is how we'll disseminate and submit assignments, receive feedback and grading, etc.

If you had trouble completing any of these steps, please raise your hand.
- My go-to place for installation guidance and troubleshooting is Jenny Bryan's http://happygitwithr.com.

---

# Some OS-specific extras

I'll detail further software requirements as and when the need arises. However, to help smooth some software installation issues further down the road, please also do the following (depending on your OS):

- **Windows:** Install [Rtools](https://cran.r-project.org/bin/windows/Rtools/). I also recommend that you install [Chocolately](https://chocolatey.org/).
- **Mac:** Install [Homebrew](https://brew.sh/). I also recommend that you configure/open your C++ toolchain (see [here](https://github.com/rmacoslib/r-macos-rtools#installer-package-for-macos-r-toolchain-).)
- **Linux:** None (you should be good to go).

---

# Checklist

☑ Do you have the most recent version of R?
  
  ```r
  version$version.string
  ```
  
  ```
  ## [1] "R version 4.0.4 (2021-02-15)"
  ```

☑ Do you have the most recent version of RStudio? (The [preview version](https://www.rstudio.com/products/rstudio/download/preview/) is fine.)
  
  ```r
  RStudio.Version()$version
  ## Requires an interactive session but should return something like "[1] ‘1.4.1100’"
  ```

☑ Have you updated all of your R packages? 
  
  ```r
  update.packages(ask = FALSE, checkBuilt = TRUE)
  ```
  
---

# Checklist (cont.)

Open up the [shell](http://happygitwithr.com/shell.html#shell).
- Windows users, make sure that you installed a Bash-compatible version of the shell. If you installed [Git for Windows](https://gitforwindows.org), then you should be good to go.

☑ Which version of Git have you installed?
  
  ```bash
  git --version
  ```
  
  ```
  ## git version 2.30.1
  ```

☑ Did you introduce yourself to Git? (Substitute in your details.)
  
  ```bash
  git config --global user.name 'Grant McDermott'
  git config --global user.email 'grantmcd@uoregon.edu'
  git config --global --list
  ```

☑ Did you register an account in GitHub?

---

# Checklist (cont.)

We will make sure that everything is working properly with your R and GitHub setup next lecture.

For the rest of today's lecture, I want to go over some very basic R concepts.

</br>

PS — Just so you know where we're headed: We'll return to these R concepts (and delve much deeper) next week after a brief, but important detour to the lands of Git(Hub) and the shell.
- Don't worry, it will all make sense. You'll see.

---
class: inverse, center, middle
name: r4ds

# R for data science
<html><div style='float:left'></div><hr color='#EB811B' size=1px width=796px></html>

---
name: whyr

# Why R and RStudio? (cont.)
<img src="01-Intro_files/figure-html/indeeddotcom-1.svg" style="display: block; margin: auto;" />

---

# Why R and RStudio? (cont.)

### Data science positivism

- Alongside Python, R has become the *de facto* language for data science.
  - See: [*The Impressive Growth of R*](https://stackoverflow.blog/2017/10/10/impressive-growth-r/), [*The Popularity of Data Science Software*](http://r4stats.com/articles/popularity/)
- Open-source (free!) with a global user-base spanning academia and industry.
  - "Do you want to be a profit source or a cost center?"

### Bridge to applied economics and other tools

- Already has all of the statistics and econometrics support, and is amazingly adaptable as a “glue” language to other
programming languages and APIs.
- The RStudio IDE and ecosystem allow for further, seemless integration.

### Path dependency

- It's also the language that I know best.
--

- (Learning multiple languages is a good idea, though.)

---

# Some R basics

1. Everything is an object.

2. Everything has a name.

3. You do things using functions.

4. Functions come pre-written in packages (i.e. "libraries"), although you can — and should — write your own functions too.

</br>

Points 1. and 2. can be summarised as an [object-orientated programming](https://en.wikipedia.org/wiki/Object-oriented_programming) (OOP) approach.
  - This may sound super abstract now, but we'll see *lots* of examples over the coming weeks that will make things clear.

---

# R vs Stata

If you're coming from Stata, some additional things worth emphasizing:

- Multiple objects (e.g. data frames) can exist happily in the same workspace. 
   - No more `keep`, `preserve`, `restore` hackery. (Though, props to [Stata 16](https://www.stata.com/new-in-stata/multiple-datasets-in-memory/).)
   - This is a direct consequence of the OOP approach.

- You will load packages at the start of every new R session. Make peace with this.
  - "Base" R comes with tons of useful in-built functions. It also provides all the tools necessary for you to write your own functions. 
  - However, many of R's best data science functions and tools come from external packages written by other users.

- R easily and infinitely parallelizes. For free.
  - Compare the cost of a [Stata/MP](https://www.stata.com/statamp/) license, nevermind the fact that you effectively pay per core...

- You don't need to `tset or xtset` your data. (Although you can too.)

---

# R code example (linear regression)

```r
fit = lm(mpg ~ wt, data = mtcars)
summary(fit)
```

```
## 
## Call:
## lm(formula = mpg ~ wt, data = mtcars)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -4.5432 -2.3647 -0.1252  1.4096  6.8727 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  37.2851     1.8776  19.858  < 2e-16 ***
## wt           -5.3445     0.5591  -9.559 1.29e-10 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.046 on 30 degrees of freedom
## Multiple R-squared:  0.7528,	Adjusted R-squared:  0.7446 
## F-statistic: 91.38 on 1 and 30 DF,  p-value: 1.294e-10
```

---

# Base R plot

```r
par(mar = c(4, 4, 1, .1)) ## Just for nice plot margins on this slide deck
plot(mtcars$wt, mtcars$mpg)
abline(fit, col = "red")
```

---

# ggplot2

```r
library(ggplot2)
ggplot(data = mtcars, aes(x = wt, y = mpg)) + 
  geom_smooth(method = "lm", col = "red") + 
  geom_point() 
```

---
class: inverse, center, middle
name: ggplot2

# More ggplot2
<html><div style='float:left'></div><hr color='#EB811B' size=1px width=796px></html>

---

# Install and load

Open up your laptops. For the remainder of this first lecture, we're going continue playing around with [ggplot2](https://ggplot2.tidyverse.org/) (i.e. livecoding).

If you don't have them already, install the `ggplot2` and `gapminder` packages via either:
- **Console:** Enter `install.packages(c("ggplot2", "gapminder"), dependencies=T)`.
- **RStudio:** Click the "Packages" tab in the bottom-right window pane. Then click "Install" and search for these two packages.
  
![](pics/install.gif)

---

# Install and load (cont.)

Once the packages are installed, load them into your R session with the `library()` function.

```r
library(ggplot2)
library(gapminder) ## We're just using this package for the gapminder data
```

Notice too that you don't need quotes around the package names any more. Reason: R now recognises these packages as defined objects with given names. ("Everything in R is an object and everything has a name.")

PS — A convenient way to combine the package installation and loading steps is with the [pacman package's](https://github.com/trinker/pacman) `p_load()` function. If you run `pacman::p_load(ggplot, gapminder)` it will first look to see whether it needs to install either package before loading them. Clever.
- We'll get to this next week, but if you want to run a function from an (installed) package without loading it, you can use the `PACKAGE::package_function()` syntax.

---

# Brief aside: The gapminder dataset

Because we're going to be plotting the [gapminder](https://github.com/jennybc/gapminder) dataset, it is helpful to know that it contains panel data on life expectancy, population size, and GDP per capita for 142 countries since the 1950s.

```r
gapminder
```

```
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows
```

---

# Elements of ggplot2

[Hadley Wickham's](http://hadley.nz/) ggplot2 is one of the most popular packages in the entire R canon. 
- It also happens to be built upon some deep visualization theory: i.e. Leland Wilkinson's [*The Grammar of Graphics*](https://www.amazon.com/Grammar-Graphics-Statistics-Computing/dp/0387245448).

There's a lot to say about ggplot2's implementation of this "grammar of graphics" approach, but the three key elements are:

1. Your plot ("the visualization") is linked to your variables ("the data") through various **aesthetic mappings**.

2. Once the aesthetic mappings are defined, you can represent your data in different ways by choosing different **geoms** (i.e. "geometric objects" like points, lines or bars).

3. You build your plot in **layers**.

</br>

That's kind of abstract. Let's review each element in turn with some actual plots.

---

# 1. Aesthetic mappings

```r
ggplot(data = gapminder, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point()
```

---