Front_MN_R_Cheatsheet.Rmd

---
title: ""
output: 
  html_document:
    css: "css/gray_style.css"
knit: pagedown::chrome_print     
---

```{r setup, include=F}
knitr::opts_chunk$set(echo=TRUE, eval=FALSE, error=F, message=F, warning=F)
library("rmarkdown")
htmltools::tagList(rmarkdown::html_dependency_font_awesome())
```

<div class="banner"><div class="left">
<h1 style="margin-left: 20px; color: #cfcfcf; margin-top: 10px; font-size: 58px;"> R <span style="font-size: 25px;"><i class="fas fa-cloud"></i><i class="fas fa-tint"></i><i class="fas fa-seedling"></i><i class="fas fa-tree"></i></span></h1>

<h2 style="margin-left: 20px; color: #cfcfcf; margin-top: -34px;"> for MINNESOTA </h2>
</div>

<div class="right" style="margin-left: 7%; width: 36%;">
<h5 style="margin-left: 20px; color: #cfcfcf; margin-top: 38px;"> Online @ <span style="font-size: 16px; color: white;">  github.com/tidy-mn/cheatsheets </span></h5>

<h5 style="margin-left: 20px; color: #cfcfcf;"> Use this reference to read data, clean column names, make plots, process dates, filter and summarize datfa, join tables, and more. </h5> 

![](images/porg_jump.png){style="float: left; width: 90px; margin-top: -100px; margin-left: -95px;"}

</div></div>

<div class="clearbox" style="clear: both;">
<div class="header"><i class="fas fa-rocket"></i> PROJECT LAUNCH  </div>
<div class="bluebox" style="width: 100%; color: white;">
<div class="in-header" style="color: white; margin-top: 4px;"> New Project </div>
`File` >`New Project` > `New Directory`
<div class="in-header" style="color: white; margin-top: 4px;"> New R script</div>
`File` > `New File` > `R Script`

<div class="in-header" style="color: white; margin-top: 0;"> Where am I? </div>
```{r}
# Show current working directory
getwd() 
# Set new working directory
setwd("C:/my-data-folder") 
```


<div class="in-header" style="color: white; margin-top: 2px;"> Install new packages </div>
```{r}
install.packages("readr")
library(readr)
```
</div></div>


<div class="clearbox" style="width 25.4%;">
<div class="header"> STORE VALUES </div>
<div class="linebox" style="padding-top: 24px; padding-bottom: 12px;">
```{r}
# Use the left-arrow
age <- 7.2

# Text goes in quotes
porg <- "Sunshine"

# Multiple values go inside c()
droids <- c("BB8", "R2D2", "C-3PO")

# Copy an object
my_droids <- droids

# Avoid numbers, spaces, & symbols
3-droids* <- "error_invalid_name"
```
</div></div>

<div class="clearbox" style="width: 28%; margin-left: 22px;">
<div class="header"> READ DATA </div>
<div class="linebox" style="padding-bottom: 1px;">
<div class="in-header"><i class="fa fa-file-text-o"></i> Text files _(.csv, .txt, .tab)_ 
</div>

```{r}
library(readr)
porgs <- read_csv("txt_file.csv")
```


<div class="in-header"><i class="fa fa-file-text"></i> Excel files _(.xlsx, .xls)_ 
</div>
```{r}
library(readxl)
porgs <- read_excel("Excel_file.xlsx")
```
</div>

<div class="header"> CLEAN NAMES <i class="fas fa-broom"></i> </div>
<div class="linebox" style="">
```{r}
# Simplify all column names
library(janitor)
porgs <- clean_names(porgs)

# Assign new names manually
library(dplyr)
# Put new name on left: new_name = oldName
rename(porgs, mass_kg = massKG)
```
</div>
</div>

<div class="clearbox" style="width: 19%;">
<div class="header">DESCRIBE DATA</div>
<div class="linebox">
```{r}
library(dplyr)
nrow(porgs)
names(porgs)
summary(porgs)
glimpse(porgs)
class(porgs)
# View unique column values
distinct(porgs, age)
## 5 6 11 12 3
```
</div>

<div class="header"> ADD COLUMNS </div>
<div class="linebox">
```{r}
library(dplyr)

# Add home planet column
mutate(porgs, 
       planet = "Earth")
# Add new calculated column
mutate(porgs, 
       growth = height / age)
```
</div>
</div>


<div style="clear: both; margin-top: -10px;"></div>

<div class="clearbox" style="width: 48.6%; margin-top: -156px;">
<div class="header"> PLOTS </div>
<div class="linebox" style="width: 100%;">
<div style="float: left; width: 61.4%;">
<div class="in-header"> Scatterplot </div>
```{r}
library(ggplot2)

ggplot(porgs, aes(x = name, y = age)) +
  geom_point(size = 8, color = "hotpink")
```


<div class="in-header"> Add titles & lines </div>
```{r}
ggplot(porgs, aes(x = name, y = age)) +
  geom_point(size = 8, color = "hotpink") +
  geom_hline(yintercept = 5, 
             linetype   = "dashed") +
  labs(title    = "Porgs",
       subtitle = "Sampled on planet Ahch-To", 
       caption  = "data from New Republic")
```


<div class="in-header"> Facet by group </div>
```{r}
ggplot(porgs, aes(x = name, y = age)) +
  geom_point(aes(color = color), size = 8) +
  facet_wrap(~color) +
  scale_color_manual(values = c("gray", "yellow")) + 
  theme_dark()
```

</div>


<div style="float: left; width: 36%; margin-left: 12px;">
<div class="linebox" style="margin-top: 16px; border: 0; background-color: white; padding-bottom: 2px; padding-left: 0;">

![](images/scatter_porgs_blue.png){style="height: 122px; width: 244px;"}

<br>

![](images/titles_porgs_blue.png){style="margin-top: -18px; height: 160px;"}

<br>

![](images/facet_porgs_dark2.png){style="margin-top: -8px; height: 150px;"}

</div></div></div></div>


<div class="clearbox" style="margin-left: 22px; width: 28%; margin-top: -30px;">
<div class="header"> FILTER </div>
<div class="linebox" style="padding-bottom: 7px; padding-top: 8px;">
```{r}
library(dplyr)
# Keep only Porgs older than 3
filter(porgs, age > 3)
# Keep rows with name Jumpity
filter(porgs, name == "Jumpity")
# Keep Porgs named Jumpity OR Chicken
filter(porgs, name %in% c("Jumpity", "Chicken"))
```
</div>


<div class="header"> SUMMARIZE </div>
<div class="linebox" style="padding-bottom: 7px; padding-top: 8px;">
```{r}
library(dplyr)
# Summarize the age for the entire table
summarize(porgs, avg_age = mean(age))
# Summarize the age for each color group
group_by(porgs, color) %>%
    summarize(avg_age = mean(age))
```
</div>
</div>


<div class="clearbox" style="width: 19%; margin-top: -30px; margin-left: 2px;">
<div class="header"> COMPARISONS </div>
<div class="fullbox">

| Symbol | Comparison               |
|:-------|:-------------------------|
| `>`    | greater than             |
| `>=`   | greater than or equal to |
| `<`    | less than                |
| `<=`   | less than or equal to    |
| `==`   | equal to                 |
| `!=`   | NOT equal to             |
| `%in%` | is value X in list: `X %in% c(1,3,5)`|
| `is.na(...)`   | is the value missing?        |
</div>
</div>


![](images/readr_hex.png){style="width: 70px; top: 157px; left: 1192px; float: left; position: absolute;"}

![](images/dplyr_hex.png){style="width: 64px; top: 696px; left: 1192px; float: left; position: absolute;"}

```{r, echo=F, eval=F}
library(tidyverse)
# Porgs for plotting
porgs <- read_csv("https://itep-r.netlify.com/data/porg_data.csv")

p_names <- read_csv("https://itep-r.netlify.com/data/porg_names.csv")

porgs <- left_join(porgs, p_names)

porgs$color[3:4] <- "gray"

porgs$name[2] <- "Chicken"

# Scatter
ggplot(porgs, aes(x = name, y = age)) +
  geom_point(color = "#008EAA", size = 8) +
   theme_minimal(base_size=26)

ggsave("images/scatter_porgs_blue.png", scale = 4)

# Facet
ggplot(porgs, aes(x = name, y = age)) +
    geom_point(aes(color = color), size = 8, show.legend = F) +
    facet_wrap(~color, scales = "free_x", drop = T) +
    scale_color_manual(values=c("#5D295F", "#FFC845")) +
    theme_dark(base_size = 26)

ggsave("images/facet_porgs_dark2.png", scale = 4)

# Titles
ggplot(porgs, aes(x = name, y = age)) +
  geom_point(color = "#008EAA", size = 8) +
  geom_hline(yintercept = 5, 
             linetype = "dashed") +
  labs(title    = "Porgs",
       subtitle = "Observed on planet Earth", 
       caption  = "source: MN DNR") +
  theme_minimal(base_size = 26)

ggsave("images/titles_porgs_blue.png", scale = 4)
```