Introduction to R Data Analysis - Part 2
+Introduction to R Data Analysis
+Part 2
Natalie Elphick
-January 23rd, 2024
+May 21st, 2024
- Rows = observations, columns = variables
head(mpg)
-
-
-
-
+| -manufacturer - | --model - | --displ - | --year - | --cyl - | --trans - | --drv - | --cty - | --hwy - | --fl - | --class - | -
|---|---|---|---|---|---|---|---|---|---|---|
| -audi - | --a4 - | --1.8 - | --1999 - | --4 - | --auto(l5) - | --f - | --18 - | --29 - | --p - | --compact - | -
| -audi - | --a4 - | --1.8 - | --1999 - | --4 - | --manual(m5) - | --f - | --21 - | --29 - | --p - | --compact - | -
| -audi - | --a4 - | --2.0 - | --2008 - | --4 - | --manual(m6) - | --f - | --20 - | --31 - | --p - | --compact - | -
| -audi - | --a4 - | --2.0 - | --2008 - | --4 - | --auto(av) - | --f - | --21 - | --30 - | --p - | --compact - | -
| -audi - | --a4 - | --2.8 - | --1999 - | --6 - | --auto(l5) - | --f - | --16 - | --26 - | --p - | --compact - | -
| -audi - | --a4 - | --2.8 - | --1999 - | --6 - | --manual(m5) - | --f - | --18 - | --26 - | --p - | --compact - | -
# A tibble: 6 × 11
+ manufacturer model displ year cyl trans drv cty hwy fl class
+ <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
+1 audi a4 1.8 1999 4 auto(l5) f 18 29 p compa…
+2 audi a4 1.8 1999 4 manual(m5) f 21 29 p compa…
+3 audi a4 2 2008 4 manual(m6) f 20 31 p compa…
+4 audi a4 2 2008 4 auto(av) f 21 30 p compa…
+5 audi a4 2.8 1999 6 auto(l5) f 16 26 p compa…
+6 audi a4 2.8 1999 6 manual(m5) f 18 26 p compa…Creating ggplots
-
Plot Example
-ggplot(data = mpg, # Input dataframe
- mapping = aes(x = cty, y = hwy)) + # Aesthetic mapping
- geom_point() # Point graph
ggplot(data = mpg, # Input dataframe
+ mapping = aes(x = cty, y = hwy)) + # Aesthetic mapping
+ geom_point() # Point graph
Adding and Modifying Layers
-ggplot(data = mpg,
- mapping = aes(x = class, y = cty, fill = class)) +
- geom_violin() +
- geom_boxplot(width = 0.1,
- fill = "white")
ggplot(data = mpg,
+ mapping = aes(x = cty, y = hwy)) +
+ geom_point() +
+ geom_smooth(formula = y ~ x, method = "lm")
10 min break
+
@@ -3879,17 +3063,317 @@ modified by adding layers
@@ -5064,20 +4562,18 @@ NA
-
-
-
-
-
10:00
- PanTHERIA
-
-
- A global species-level data set of key life-history, ecological and -geographical traits of all known extant and recently extinct mammals -compiled from the literature -
- Macroecological and macroevolutionary research projects +
- A global species-level data set of key traits of all known extant +and recently extinct mammals compiled from literature +
- Used in macroecological and macroevolutionary research projects
- Data is organized by taxonomic rank
Taxonomic Rank
-
@@ -131,8 +133,6 @@ feature rich graphical user interface (GUI) ## Variable definition - Variables store information that is referenced and manipulated in a computer program -- In contrast to the mathematical definition of a variable, -variables in computer science are _mutable_ - There are 3 ways to define variables in R, but one is preferred: ```{r} x <- 1 # Preferred way @@ -141,7 +141,59 @@ x = 1 print(x) ``` -## Variable naming +## Example +- Run the following in the R console: + +```{r} +x <- 1 +y <- 4 +z <- y +x + y + z +``` + +# Error and Warning Messages + +## Errors +- **Errors**: Stop the execution of your code and must be fixed for the code to run successfully + +```{r, eval=FALSE} +x <- 5 +y <- 10 +z <- x + a +``` + +```{r,echo=FALSE} +message("Error: object 'a' not found") +``` + + +## Common Errors + +- **Syntax Error:** Invalid R code syntax (e.g. misplaced parentheses) +```{r,echo=FALSE} +message('Error: unexpected ")"') +``` + +- **Object not found:** This variable is not defined (e.g. misspelled variables) + +```{r,echo=FALSE} +message('Error: object "a" not found') +``` + + +See this [article](https://statsandr.com/blog/top-10-errors-in-r/) for more common errors and how to fix them. + +## Warnings +- Do not stop the execution but indicate potential issues that you should be aware of and might need to address + +```{r} +a <- c(1, 2, 3, 4, 5) +b <- c(6, 7, 8, 9) +result <- a + b +``` + + +## Variable Naming - Variables names must start with a letter and can contain underscores and periods @@ -176,7 +228,7 @@ DogBreeds <- c("Labrador Retriever", "Akita", "Bulldog") ## Data Types - Integer - - Whole numbers (in R denote with L ex. 1L,2L) + - Whole numbers (in R denoted with L ex. 1L,2L) - Numeric - Decimal numbers - Logical @@ -191,7 +243,7 @@ DogBreeds <- c("Labrador Retriever", "Akita", "Bulldog") **Which of these is not the correct data type for the value?** 1. 1.5 - Numeric -2. "Labrador Retriever" - Character +2. "1" - Character 3. NA - Logical 4. 1 - Integer @@ -227,6 +279,8 @@ DogBreeds <- c("Labrador Retriever", "Akita", "Bulldog") countdown::countdown(minutes = 10, seconds = 0, color_border = "black", + color_running_background = "#47d193", + color_finished_background = "#a3184e", padding = "50px", margin = "5%", font_size = "5em", @@ -297,6 +351,7 @@ x & !y execution of code ```{r} +dog_breeds <- c("Labrador Retriever", "Akita", "Bulldog") if ("Akita" %in% dog_breeds) { print("dog_breeds already contains Akita") } else { @@ -379,11 +434,17 @@ library(ggplot2) # Makes all of the ggplot2 functions available - The tidyverse is a collection of commonly used data analysis packages - Learning curve is less steep - - Lots of useful packages for data analysis + - Lots of useful packages for cleaning and "wrangling" data into the correct format -## +## Why use Tidyverse Packages? - +- Most of the work in data analysis is getting data into the correct format to create outputs +- The tidyverse collection of packages simplifies this process + - Intuitive syntax + - Comprehensive (data manipulation, cleaning, modeling and graphics) + - Consistent data structure + - Strong community support + # End of Part 1 @@ -392,11 +453,8 @@ packages ## Upcoming Workshops -1. [Introduction to Statistics, Experimental Design, and Hypothesis Testing](https://gladstone.org/index.php/events/introduction-statistics-experimental-design-and-hypothesis-testing-0) - - Jan 25, 2024 (Session 1 - 10am–12pm) (Session 2 - 1pm–3pm) - - Jan 26, 2024 (Session 3 - 10am–12pm) +[Single Cell ATAC-Seq Data Analysis Part 2](https://gladstone.org/events/single-cell-atac-seq-data-analysis-part-2-1) -2. [Intermediate RNA-Seq Analysis Using R](https://gladstone.org/index.php/events/intermediate-rna-seq-analysis-using-r-4) - - Feb 1, 2024 (9:30am-12:00pm) +- Check [this link](https://gladstone.org/events?series=data-science-training-program) at the end of the summer for out fall workshop schedule diff --git a/intro-r-data-analysis/Intro_to_R_data_analysis_part_2.Rmd b/intro-r-data-analysis/Intro_to_R_data_analysis_part_2.Rmd index 2e1218e..a950c3d 100644 --- a/intro-r-data-analysis/Intro_to_R_data_analysis_part_2.Rmd +++ b/intro-r-data-analysis/Intro_to_R_data_analysis_part_2.Rmd @@ -1,7 +1,8 @@ --- -title: "Introduction to R Data Analysis - Part 2" +title: "Introduction to R Data Analysis" +subtitle: "Part 2" author: "Natalie Elphick" -date: "January 23rd, 2024" +date: "May 21st, 2024" knit: (function(input, ...) { rmarkdown::render( input, @@ -19,6 +20,7 @@ library(kableExtra) library(tidyverse) library(readxl) theme_set(theme_grey(base_size = 16)) +knitr::opts_chunk$set(comment = "") ``` ## @@ -29,7 +31,10 @@ theme_set(theme_grey(base_size = 16)) **Natalie Elphick** Bioinformatician I -**Yihang Xin (TA)** +**Michela Traglia (In Person TA)** +Senior Statistician + +**Yihang Xin (Online TA)** Software Engineer III # Schedule @@ -46,11 +51,11 @@ Software Engineer III - The tidyverse packages work well together because they share common data representations and design principles - Rows = observations, columns = variables -- [ggplot2](), for data visualization. -- [dplyr](), for data manipulation. -- [tidyr](), for data tidying. -- [readr](), for data import. -- [purrr](), for iteration. +- [ggplot2](https://ggplot2.tidyverse.org/), for data visualization. +- [dplyr](https://dplyr.tidyverse.org/), for data manipulation. +- [tidyr](https://tidyr.tidyverse.org/), for data tidying. +- [readr](https://readr.tidyverse.org/), for data import. +- [purrr](https://purrr.tidyverse.org/), for iteration. - and more.. ## dplyr @@ -67,66 +72,38 @@ common data representations and design principles ## Example Dataframe - mpg is a dataframe built into the ggplot2 package -```{r, eval = FALSE} +```{r} head(mpg) ``` -```{r, echo = FALSE} -head(mpg) |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") -``` ## Select Columns -```{r, eval = FALSE} +```{r} select(.data = mpg, year, cty, hwy, manufacturer) ``` -```{r, echo = FALSE} -select(.data = mpg, - year, cty, hwy, manufacturer) |> - head() |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") -``` - ## Filter Rows -```{r, eval = FALSE} +```{r} filter(.data = mpg, year == 2008) ``` -```{r, echo = FALSE} -filter(.data = mpg, - year == 2008) |> - head() |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") -``` + ## Arrange Rows - desc() is used to arrange rows in descending order, the default is ascending -```{r, eval = FALSE} +```{r} arrange(.data = mpg, - desc(cyl)) + desc(cty)) ``` -```{r, echo = FALSE} -arrange(.data = mpg, - desc(cyl)) |> - head(n = 3) |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") -``` + + ## Summarising data - The dplyr **summarise()** function computes a table of summaries for a data frame @@ -136,6 +113,9 @@ variable(s) different categorical groupings ## Group and Summarise + +- Get the mean and median city mileage within manufacturer + ```{r, eval = FALSE} summarise(group_by(.data = mpg, manufacturer), @@ -144,37 +124,27 @@ summarise(group_by(.data = mpg, ``` ```{r, echo = FALSE} -summarise(group_by(.data = mpg, +summarise(.data = group_by(.data = mpg, manufacturer), mean_cty = mean(cty), median_cty = median(cty)) |> - head() |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") + head(10) ``` + + ## The pipe operator |> - Allows "chaining" of function calls to make code more readable -```{r, eval = FALSE} -mpg |> - group_by(manufacturer) |> - summarise(mean_cty = mean(cty), - median_cty = median(cty)) -``` - -```{r, echo = FALSE} +```{r} mpg |> group_by(manufacturer) |> summarise(mean_cty = mean(cty), median_cty = median(cty)) |> - head(n = 4) |> - kable() |> - kable_styling("striped") |> - scroll_box(width = "100%") + head(5) ``` + # Plotting ## ggplot2 @@ -204,11 +174,10 @@ ggplot(data = mpg, # Input dataframe ## Adding and Modifying Layers ```{r, fig.dim=c(10,4)} -ggplot(data = mpg, - mapping = aes(x = class, y = cty, fill = class)) + - geom_violin() + - geom_boxplot(width = 0.1, - fill = "white") +ggplot(data = mpg, + mapping = aes(x = cty, y = hwy)) + + geom_point() + + geom_smooth(formula = y ~ x, method = "lm") ``` @@ -221,6 +190,8 @@ ggplot(data = mpg, countdown::countdown(minutes = 10, seconds = 0, color_border = "black", + color_running_background = "#47d193", + color_finished_background = "#a3184e", padding = "50px", margin = "5%", font_size = "5em", @@ -234,8 +205,8 @@ countdown::countdown(minutes = 10, ## Dataset Description - PanTHERIA - - A global species-level data set of key life-history, ecological and geographical traits of all known extant and recently extinct mammals compiled from the literature - - Macroecological and macroevolutionary research projects + - A global species-level data set of key traits of all known extant and recently extinct mammals compiled from literature + - Used in macroecological and macroevolutionary research projects - Data is organized by taxonomic rank ## Taxonomic Rank @@ -252,10 +223,20 @@ read_xlsx("Intro_to_R_workshop_materials/PanTHERIA.xlsx") |> scroll_box(width = "100%") ``` +## Hands-on Analysis +- We will read in the data and explore if the trophic level has a significant impact on the adult body mass of mammals + + +Steps: +1. Combine and clean the data +2. Visualize adult body mass by trophic level +3. Check for overrepresented groups +4. Fit a simple linear model ## Hands-on Analysis - Open part_2.Rmd +- If you just want to follow along and not run code, open part2_filled_out.html @@ -263,63 +244,34 @@ read_xlsx("Intro_to_R_workshop_materials/PanTHERIA.xlsx") |> ## General Tips +- Follow any relevant institutional guidelines on using LLMs - Always confirm ChatGPT's outputs are correct - Provide as much detail as possible about the problem in the 1st prompt - Use separate chats for separate tasks/projects -- Try the 'Custom Instructions' function that adds additional information to every prompt -- Can visit webpages (GPT 4 only), which can help get more specific answers +- Try the 'Custom Instructions' function ## Code Tips -- Commented R code yields better responses in my experience +- Commented R code yields better responses - Provide the code and error message in the same prompt - ChatGPT can work well to convert syntax and improve your code: - "Turn this loop into a function : [your code]" - "Is there a better way to do this : [your code]" - Check out the file: `example_code/1_convert_syntax_example.R` for an example use case -# Finding R Packages - -## Key Questions - -- What assay was the package designed for? -- When was the last release? -- Is it maintained (frequent updates)? -- Does it work on all operating systems? -- Are other people using it? (citations) -- Do they respond to github issues? -- Is there a benchmarking paper? - -## BioConductor and CRAN - -- Both of these have stringent requirements for packages they host (eg. for BioConductor they have to run on all major operating systems) - -- Prefer BioConductor packages if available over CRAN - -- Prefer CRAN packages over ones only hosted on GitHub - -## Start with the Assay - -- Click [here](https://www.bioconductor.org/packages/release/BiocViews.html#___Sequencing) to go to BioC views -- Pick the assay you want to analyse -- Pick the type of analysis you want to do -- Find a package that does it -- Find benchmarking papers to narrow the list of packages down -- Find the vignette on the package page and refer to the manual for any questions not covered by it - # Additional Resources ## R - -- [R Markdown: The Definitive Guide](https://bookdown.org/yihui/rmarkdown/how-to-read-this-book.html) : Excellent R markdown reference - - [R for Data Science](https://r4ds.hadley.nz/) - +- [Top 10 R Errors and How to Fix them](https://statsandr.com/blog/top-10-errors-in-r/) +- [R Markdown: The Definitive Guide](https://bookdown.org/yihui/rmarkdown/how-to-read-this-book.html) : Excellent R markdown reference - [ggplot2: elegant graphics for data analysis](https://ggplot2-book.org/) - [Advanced R](https://adv-r.hadley.nz/) + + ## Statistics - [Data Analysis in R](https://bookdown.org/steve_midway/DAR) : This book has more statistics details than *R for Data Science* @@ -346,10 +298,9 @@ read_xlsx("Intro_to_R_workshop_materials/PanTHERIA.xlsx") |> ## Upcoming Workshops -1. [Introduction to Statistics, Experimental Design, and Hypothesis Testing](https://gladstone.org/index.php/events/introduction-statistics-experimental-design-and-hypothesis-testing-0) - - Jan 25, 2024 (Session 1 - 10am–12pm) (Session 2 - 1pm–3pm) - - Jan 26, 2024 (Session 3 - 10am–12pm) +[Single Cell ATAC-Seq Data Analysis Part 2](https://gladstone.org/events/single-cell-atac-seq-data-analysis-part-2-1) + +- Check [this link](https://gladstone.org/events?series=data-science-training-program) at the end of the summer for out fall workshop schedule + -2. [Intermediate RNA-Seq Analysis Using R](https://gladstone.org/index.php/events/intermediate-rna-seq-analysis-using-r-4) - - Feb 1, 2024 (9:30am-12:00pm) diff --git a/intro-r-data-analysis/renv.lock b/intro-r-data-analysis/renv.lock index 52c9d40..6812de9 100644 --- a/intro-r-data-analysis/renv.lock +++ b/intro-r-data-analysis/renv.lock @@ -22,7 +22,7 @@ }, "MASS": { "Package": "MASS", - "Version": "7.3-60", + "Version": "7.3-60.0.1", "Source": "Repository", "Repository": "CRAN", "Requirements": [ @@ -33,11 +33,11 @@ "stats", "utils" ], - "Hash": "a56a6365b3fa73293ea8d084be0d9bb0" + "Hash": "b765b28387acc8ec9e9c1530713cb19c" }, "Matrix": { "Package": "Matrix", - "Version": "1.6-1.1", + "Version": "1.6-5", "Source": "Repository", "Repository": "CRAN", "Requirements": [ @@ -50,7 +50,7 @@ "stats", "utils" ], - "Hash": "1a00d4828f33a9d690806e98bd17150c" + "Hash": "8c7115cd3a0e048bda2a7cd110549f7a" }, "R6": { "Package": "R6", @@ -872,7 +872,7 @@ }, "lattice": { "Package": "lattice", - "Version": "0.21-9", + "Version": "0.22-6", "Source": "Repository", "Repository": "CRAN", "Requirements": [ @@ -883,7 +883,7 @@ "stats", "utils" ], - "Hash": "5558c61e0136e247252f5f952cdaad6a" + "Hash": "cc5ac1ba4c238c7ca9fa6a87ca11a7e2" }, "learnr": { "Package": "learnr", @@ -977,7 +977,7 @@ }, "mgcv": { "Package": "mgcv", - "Version": "1.9-0", + "Version": "1.9-1", "Source": "Repository", "Repository": "CRAN", "Requirements": [ @@ -990,7 +990,7 @@ "stats", "utils" ], - "Hash": "086028ca0460d0c368028d3bda58f31b" + "Hash": "110ee9d83b496279960e162ac97764ce" }, "mime": { "Package": "mime", @@ -1033,7 +1033,7 @@ }, "nlme": { "Package": "nlme", - "Version": "3.1-163", + "Version": "3.1-164", "Source": "Repository", "Repository": "CRAN", "Requirements": [ @@ -1043,7 +1043,7 @@ "stats", "utils" ], - "Hash": "8d1938040a05566f4f7a14af4feadd6b" + "Hash": "a623a2239e642806158bc4dc3f51565d" }, "openssl": { "Package": "openssl", diff --git a/intro-r-data-analysis/style.css b/intro-r-data-analysis/style.css index 6e7ace6..9928aff 100644 --- a/intro-r-data-analysis/style.css +++ b/intro-r-data-analysis/style.css @@ -129,4 +129,14 @@ small { .big-picture img{ max-width: 70%; border: 1px solid black !important; -} \ No newline at end of file +} + +/* Chage link color to sky blue */ +.reveal a { + color: #0c74dc; +} + +/* Change link color to magenta on hover */ +.reveal a:hover { + color: #9c0366 !important; +}