rstudio::conf(2018L)

class: center, middle, inverse, title-slide

# rstudio::conf(2018L)
### February 8, 2018

---

class: protecttext
background-image: url(assets/IMG_9539.jpg)
background-position: center
background-repeat: no-repeat
background-size: cover

# Introduction

## data scientist @powerley

## organizer @annarborrusergroup

### "... statistics starts once you have tidy data." - Di Cook

---
class: center, middle, inverse

# recap: To the Tidyverse and Beyond

## Di Cook

---
class: center, middle

<h1 style="color:#E69F00;">"[ggplot2] provides a tight connection between data and statistics, in order to do inference with data plots"</h1>

---
class: center, middle

<h1 style="color:#56B4E9;">"a statistic is a function of the data"</h1>

<h1 style="color:#009E73;">"[ggplot2] makes plots another type of statistic"</h1>

---
class: center, middle

<h1 style="color:#E69F00">Inference happens when you have information on a subset of data, and you want to make statements about the full set."</h1>

<h1 style="color:#0072B2">Typically, inference is done using the sample statistics, and what we know about the behaviour of that statistic over all possible subsets, of the same size."</h1>

---

# Nullabor example

```r
d <- lineup(null_permute("waiting"), faithful, n = 16)
qplot(eruptions, waiting, data = d) + facet_wrap(~ .sample)
```

---

# Download speed by time of day

---
class: center, middle, inverse

# recap: Understanding PCA Using Stack Overflow Data

## Julia Silge

---
class: center, middle

<div>
<blockquote class="twitter-tweet" data-conversation="none" data-lang="en"><p lang="en" dir="ltr">Every linear algebra class<br><br>Me: What are eigenvectors<br><br>Teacher: You can think of them as an n-dimensional kernel subspace<br><br>Me: No I can&#39;t</p>&mdash; David Robinson (@drob) <a href="https://twitter.com/drob/status/714559825116434432?ref_src=twsrc%5Etfw">March 28, 2016</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
</div>

---
class: center, middle

???

credit: https://chrisalbon.com

---

# User tag visits

```
## # A tibble: 6 x 3
##   AccountId Tag            Value
##       <dbl> <chr>          <dbl>
## 1   6461130 sass         0.00244
## 2   1044010 tsql         0.00179
## 3    405410 qt           0.00156
## 4   3224070 http-headers 0.00306
## 5  10525200 asp.net-mvc  0.00403
## 6   6349580 amazon-s3    0.00123
```

```r
sparse_tag_matrix <- user_tag_counts %>%
  tidytext::cast_sparse(AccountId, Tag, Percent)
tags_scaled <- scaled(sparse_tag_matrix)
tags_pca <- irlba::prcomp_irlba(tags_scaled, n = 64)
tidied_pca <- bind_cols(Tag = colnames(tag_scled),
                        tidy(tags_pca$rotation))
```

---

???

credit: https://speakerdeck.com/juliasilge/understanding-principal-component-analysis-using-stack-overflow-data

---

???

credit: https://speakerdeck.com/juliasilge/understanding-principal-component-analysis-using-stack-overflow-data

---
class: center, middle
background-color: #363A4C

---
class: center, middle

# Demo

---
class: center, middle, protecttext, lastslide
background-image: url(assets/IMG_E7538.JPG)
background-position: center
background-repeat: no-repeat
background-size: cover

# Thanks!

## @ellisvalentiner

### GitHub

### Twitter