# ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 1)

The data visualization package lattice is part of the base R distribution, and like ggplot2 is built on Grid graphics engine. Deepayan Sarkar’s (the developer of lattice) book Lattice: Multivariate Data Visualization with R gives a detailed overview of how the package works. All the figures and code used to produce them is also available on the book website.

In order to give those interested an option to compare graphs produced by ggplot2 and lattice, I will attempt to recreate the book’s lattice graphs in ggplot2. There are 14 chapters in the book, so this means that there would be at least 13 more posts on the subject.

The output of both packages can be tweaked so that the graphs would look similar if not the same, however for the purposes of comparison, the standard settings (at least in ggplot2) are used when possible. The code used to create the images is in separate paragraphs, allowing easy comparison, and by clicking on the thumbnail, a bigger image file is also available.

## Chapter 1 – Introduction

**Topics covered:**

- Basic usage; high level functions
- Conditioning
- Superposition (a.k.a. grouping)
- “trellis” objects

### Figure 1.1

> library(lattice) > library(ggplot2) > data(Chem97, package = "mlmRev") |

`lattice`

> pl <- histogram(~gcsescore | factor(score), data = Chem97) > print(pl) |

`ggplot2`

> pg <- ggplot(Chem97, aes(gcsescore)) + geom_histogram(binwidth = 0.5) + + facet_wrap(~score) > print(pg) |

Note |
ggplot2 uses counts, not percentages by default. |

Note |
ggplot2 plots the facets starting from top-left, lattice starts from bottom-left. |

### Figure 1.2

`lattice`

> pl <- densityplot(~gcsescore | factor(score), data = Chem97, + plot.points = FALSE, ref = TRUE) > print(pl) |

`ggplot2`

> pg <- ggplot(Chem97, aes(gcsescore)) + stat_density(geom = "path", + position = "identity") + facet_wrap(~score) > print(pg) |

### Figure 1.3

`lattice`

> pl <- densityplot(~gcsescore, data = Chem97, groups = score, + plot.points = FALSE, ref = TRUE, auto.key = list(columns = 3)) > print(pl) |

`ggplot2`

> pg <- ggplot(Chem97, aes(gcsescore)) + stat_density(geom = "path", + position = "identity", aes(colour = factor(score))) > print(pg) |

### Trackbacks

- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 5) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 6) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 7) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 8) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 9) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 10) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 11) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 13) « Learning R
- ggplot2 Version of Figures in “Lattice: Multivariate Data Visualization with R” (Part 13) « Learning R
- Time for Some Lattice « Amanda's Tea Room 阿勳茶室
- The R-Podcast Episode 8: Visualization with ggplot2 » The R-Podcast
- The R-Podcast Screencast 2: Visualization with ggplot2 » The R-Podcast
- Graphics: an important issue to communicate | FreshBiostats
- Multivariate weather statistics | Europe by numbeRs
- Comparing lattice and ggplot | Diogo Ferrari
- Curated list of R tutorials for Data Science – the data science blog

Awesome idea! Thanks for doing this.

I concur with Hadley. I’ve been doing most of my R graphics with the help of this book, so seeing the ggplot2 versions is a very good learning tool!

+1 awesome!!!

Much appreciate. This is very helpful.

Thank you! this is brilliant

This series is excellent, thanks for making the effort.

Hello.

Could you show an easy way to produce a scatter plot with error bars associated to each point, please?

From a dataframe with 4 columns: X, Y, errX, errY.

I’ve only seen complicated methods.

It would be great to see a newer version (specially in pdf) updated with lattice, latticeextra, ggplot and ggextra, things such as themes, error bars…

fantastic – was just starting to convert those in both Bates excellent Lme4 book chapter 4 and also some of those in another excellent book Galecki & Burzykowski’s Linear mixed effect models