NOTES FROM LECTURE TODAY
Below is the Data science workflow with Tidyverse from R for Data Science
Import –> Tidy –> transform –> visualise <–> model –> communicate
- Import (readr, haven, readxl)
- Tidy (tidyr)
- transform (dplyr)
- Visualise (purr, ggplot2)
- Model (broom)
- communicate (knitr, rmarkdown)
- others
- Dealing with Factors (forcats)
- Dealing with data.frames (tibble)
- Dealing with string (stringr)
use r cheatsheets to get the syntax
Pike %>% - super important connector
Installing and loading required libraries
- Loading multiple packages at one go
Show code
packages = c('ggplot2', 'tidyverse', 'ggrepel')
for(p in packages){
if(!require(p, character.only = T)){
install.packages(p)
}
library(p, character.only = T)
}
Importing data into R
- Data should be same level as the rmarkdown file to use the relative file path below
Show code
exam_data <-read_csv("data/Exam_data.csv")
summary(exam_data)
ID CLASS GENDER
Length:322 Length:322 Length:322
Class :character Class :character Class :character
Mode :character Mode :character Mode :character
RACE ENGLISH MATHS SCIENCE
Length:322 Min. :21.00 Min. : 9.00 Min. :15.00
Class :character 1st Qu.:59.00 1st Qu.:58.00 1st Qu.:49.25
Mode :character Median :70.00 Median :74.00 Median :65.00
Mean :67.18 Mean :69.33 Mean :61.16
3rd Qu.:78.00 3rd Qu.:85.00 3rd Qu.:74.75
Max. :96.00 Max. :99.00 Max. :96.00 - using read.csv instead of read_csv may result in messy column names
Visualisation using ggplot2 package
ggplot2 is used for Visual Data exploration purpose
using R graphics to plot histogram vs using ggplot.
Show code
hist(exam_data$MATHS)
Note the longer coding but more powerful customisation
Show code
ggplot(data=exam_data,
aes(x = MATHS)) +
geom_histogram(bins=10,
boundary = 100,
colour = "black",
fill="grey") +
ggtitle("Distribution of Maths scores")
GGPLOT2 elements
- Data
- Aesthetics (aes =df$variablename)
- Geometrics (bar or pie or line or histogram)
- Facets (columns x rows eg. 2 x 5) / grids
- statistics (sum, average etc..)
- Coordinates (x and Y axis)
- Theme (colour/ format of the graph)
Note that the default grom_histogram default bin is 30
adding theme
Show code
ggplot(data=exam_data,
aes(x = MATHS)) +
geom_histogram(bins=10,
boundary = 100,
colour = "black",
fill="grey") +
ggtitle("Distribution of Maths scores") +
theme_dark()
adding facet
Show code
ggplot(data=exam_data,
aes(x = MATHS)) +
geom_histogram(bins=10,
boundary = 100,
colour = "black",
fill="blue") +
ggtitle("Distribution of Maths scores") +
facet_grid(cols = vars(RACE))
putting GENDER variable as a fill filter
Show code
ggplot(data=exam_data,
aes(x = MATHS,
fill = GENDER)) +
geom_histogram(bins=10,
boundary = 100,
colour = "black") +
ggtitle("Distribution of Maths scores") +
facet_grid(cols = vars(RACE))
putting GENDER variable as a fill filter
Show code
ggplot(data=exam_data,
aes(y = MATHS,
x = GENDER)) +
geom_boxplot(notch = TRUE)
combining boxplot and geompoint together
Show code
ggplot(data=exam_data,
aes(y = MATHS,
x = GENDER)) +
geom_boxplot() +
geom_point(position = "jitter",
size = 0.5)
volin plot is good to compliment boxplot, got error - cannot find dunction geom_volin
####```{r echo = TRUE} ggplot(data=exam_data, aes(y = MATHS, x = GENDER)) + geom_boxplot(alpha = 0.5) + geom_volin (fill = “light blue”)
####``` ### note the 2 syntax below gives the same result though the code is different.Show code
ggplot(data=exam_data,
aes(y = MATHS, x = GENDER)) +
geom_boxplot() +
geom_point (stat = "summary",
fun.y = "mean",
colour = "red",
size = 4)
Show code
ggplot(data=exam_data,
aes(y = MATHS, x = GENDER)) +
geom_boxplot() +
stat_summary (geom = "point",
fun.y = "mean",
colour = "red",
size = 4)