From f9ec6ff60e9f6e6c17f78f0542802aae75c0f523 Mon Sep 17 00:00:00 2001
From: Laurent Modolo <laurent@modolo.fr>
Date: Wed, 23 Oct 2019 17:01:19 +0200
Subject: [PATCH] session_2/slides.Rmd, example with full data set
---
session_2/slides.Rmd | 251 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 251 insertions(+)
create mode 100644 session_2/slides.Rmd
diff --git a/session_2/slides.Rmd b/session_2/slides.Rmd
new file mode 100644
index 0000000..92e3747
--- /dev/null
+++ b/session_2/slides.Rmd
@@ -0,0 +1,251 @@
+---
+title: "R#2: introduction to Tidyverse"
+author: "Laurent Modolo [laurent.modolo@ens-lyon.fr](mailto:laurent.modolo@ens-lyon.fr)"
+date: "24 Oct 2019"
+output:
+ beamer_presentation:
+ theme: metropolis
+ slide_level: 3
+ fig_caption: no
+ df_print: tibble
+ highlight: tango
+ latex_engine: xelatex
+ slidy_presentation:
+ highlight: tango
+---
+
+```{r setup, include=FALSE, cache=TRUE}
+knitr::opts_chunk$set(echo = FALSE)
+library(tidyverse)
+tmp <- tempfile(fileext = ".zip")
+download.file("http://www.fueleconomy.gov/feg/epadata/vehicles.csv.zip",
+ tmp,
+ quiet = TRUE)
+unzip(tmp, exdir = "data-raw")
+read_csv("data-raw/vehicles.csv") %>%
+ select(
+ "id",
+ "make",
+ "model",
+ "year",
+ "VClass",
+ "trany",
+ "drive",
+ "cylinders",
+ "displ",
+ "fuelType",
+ "highway08",
+ "city08"
+ ) %>%
+ rename(
+ "class" = "VClass",
+ "trans" = "trany",
+ "drive" = "drive",
+ "cyl" = "cylinders",
+ "displ" = "displ",
+ "fuel" = "fuelType",
+ "hwy" = "highway08",
+ "cty" = "city08"
+ ) %>%
+ filter(drive != "") %>%
+ drop_na() %>%
+ arrange(make, model, year) %>%
+ write_csv("2_data.csv")
+```
+
+## Tidyverse
+
+The tidyverse is a collection of R packages designed for data science.
+
+All packages share an underlying design philosophy, grammar, and data structures.
+
+```{r install_tidyverse, cache = TRUE, eval = FALSE}
+install.packages("tidyverse")
+```
+
+```{r load_tidyverse, cache = TRUE}
+library("tidyverse")
+```
+
+
+## Toy data set `mpg`
+
+This dataset contains a subset of the fuel economy data that the EPA makes available on **http://fueleconomy.gov**. It contains only models which had a new release every year between 1999 and 2008.
+
+
+```{r mpg_inspect, cache = TRUE, eval=FALSE}
+?mpg
+mpg
+dim(mpg)
+View(mpg)
+```
+
+## Updated version of the data
+
+`mpg` is loaded with tidyverse, we want to be able to read our own data from
+**http://perso.ens-lyon.fr/laurent.modolo/R/2_data.csv**
+
+```{r mpg_download, cache=TRUE, message=FALSE}
+new_mpg <- read_csv(
+ "http://perso.ens-lyon.fr/laurent.modolo/R/2_data.csv"
+ )
+```
+
+## First plot with `ggplot2`
+
+Relationship between engine size `displ` and fuel efficiency `hwy`.
+```{r new_mpg_plot_a, cache = TRUE, fig.width=8, fig.height=4.5}
+ggplot(data = new_mpg) +
+ geom_point(mapping = aes(x = displ, y = hwy))
+```
+
+## Composition of plot with `ggplot2`
+
+Composition of plot with `ggplot2`
+
+```R
+ggplot(data = <DATA>) +
+ <GEOM_FUNCTION>(mapping = aes(<MAPPINGS>))
+```
+
+- you begin a plot with the function `ggplot()`
+- you complete your graph by adding one or more layers
+- `geom_point()` adds a layer with a scatterplot
+- each geom function in `ggplot2` takes a `mapping` argument
+- the `mapping` argument is always paired with `aes()`
+
+
+## First challenge
+
+- Run `ggplot(data = new_mpg)`. What do you see?
+- How many rows are in `new_mpg`? How many columns?
+- What does the `cty` variable describe? Read the help for `?mpg` to find out.
+- Make a scatterplot of `hwy` vs `cyl`.
+- What happens if you make a scatterplot of `class` vs `drive`? Why is the plot not useful?
+
+### Run `ggplot(data = mpg)`. What do you see?
+
+```{r empty_plot, cache = TRUE, fig.width=8, fig.height=4.5}
+ggplot(data = new_mpg)
+```
+
+### How many rows are in `new_mpg`? How many columns?
+
+```{r size_of_mpg, cache = TRUE, fig.width=8, fig.height=4.5}
+new_mpg
+```
+
+### Make a scatterplot of `hwy` vs `cyl`.
+
+```{r new_mpg_plot_b, cache = TRUE, fig.width=8, fig.height=4.5}
+ggplot(data = new_mpg) +
+ geom_point(mapping = aes(x = hwy, y = cyl))
+```
+
+### What happens if you make a scatterplot of `class` vs `drive`?
+Why is the plot not useful?
+
+```{r new_mpg_plot_c, cache = TRUE, fig.width=8, fig.height=4.5}
+ggplot(data = new_mpg) +
+ geom_point(mapping = aes(x = class, y = drive))
+```
+
+## Aesthetic mappings
+
+
+```{r new_mpg_plot_b, cache = TRUE, fig.width=8, fig.height=4.5}
+new_mpg %>% pull(class) %>% as.factor() %>% levels()
+c(
+ "Compact Cars",
+ "Large Cars",
+ "Midsize Cars",
+ "Midsize Station Wagons",
+ "Midsize-Large Station Wagons",
+ "Minicompact Cars",
+ "Minivan - 2WD",
+ "Minivan - 4WD",
+ "Small Pickup Trucks",
+ "Small Pickup Trucks 2WD",
+ "Small Pickup Trucks 4WD",
+ "Small Sport Utility Vehicle 2WD",
+ "Small Sport Utility Vehicle 4WD",
+ "Small Station Wagons",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle 2WD",
+ "Special Purpose Vehicle 4WD",
+ "Special Purpose Vehicles",
+ "Special Purpose Vehicles/2wd",
+ "Special Purpose Vehicles/4wd",
+ "Sport Utility Vehicle - 2WD",
+ "Sport Utility Vehicle - 4WD",
+ "Standard Pickup Trucks",
+ "Standard Pickup Trucks 2WD",
+ "Standard Pickup Trucks 4WD",
+ "Standard Pickup Trucks/2wd",
+ "Standard Sport Utility Vehicle 2WD",
+ "Standard Sport Utility Vehicle 4WD",
+ "Subcompact Cars",
+ "Two Seaters",
+ "Vans",
+ "Vans Passenger",
+ "Vans, Cargo Type",
+ "Vans, Passenger Type"
+)
+new_class_level <- c(
+ "Compact Cars",
+ "Large Cars",
+ "Midsize Cars",
+ "Midsize Cars",
+ "Midsize Cars",
+ "Compact Cars",
+ "Minivan",
+ "Minivan",
+ "Pickup Trucks",
+ "Pickup Trucks",
+ "Pickup Trucks",
+ "Sport Utility Vehicle",
+ "Sport Utility Vehicle",
+ "Compact Cars",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle",
+ "Special Purpose Vehicle",
+ "Sport Utility Vehicle",
+ "Sport Utility Vehicle",
+ "Pickup Trucks",
+ "Pickup Trucks",
+ "Pickup Trucks",
+ "Pickup Trucks",
+ "Sport Utility Vehicle",
+ "Sport Utility Vehicle",
+ "Compact Cars",
+ "Two Seaters",
+ "Vans",
+ "Vans",
+ "Vans",
+ "Vans"
+)
+new_mpg %>% pull(fuel) %>% as.factor() %>% levels()
+new_fuel_level <- c(
+ "gas",
+ "Diesel",
+ "Regular",
+ "gas",
+ "gas",
+ "Regular",
+ "Regular",
+ "Hybrid",
+ "Hybrid",
+ "Regular",
+ "Regular",
+ "Hybrid",
+ "Hybrid"
+)
+new_mpg %>%
+ mutate(class = factor(as.factor(class), labels = new_class_level)) %>%
+ mutate(fuel = factor(as.factor(fuel), labels = new_fuel_level)) %>%
+ggplot() +
+ geom_point(mapping = aes(x = displ, y = hwy, color = class))
+```
\ No newline at end of file
--
GitLab