R-basics.Rmd

---
title: "GitHub R Intro"
author: "Natalie Wiley"
date: "`r Sys.Date()`"
output: html_document
---

# Week 1 Intro Part 1

```{r}
source("setup.R")
```

```{r}
data("penguins")

penguins

class(penguins$species)
str(penguins$species)

myList<-list("apple", 1993, FALSE, penguins)
str(myList)
list(myList, list("more stuff here", list("and more")))
names(myList) <- c("fruit", "year", "logic", "data")
names(myList)



myList["fruit"]
penguins$flipper_length_mm
penguins[penguins$island=='Dream',]


unique(penguins$species, incomparables = FALSE,)

penguins_q3<-penguins[penguins$island=='Dream', c("species", "island", "flipper_length_mm")]

penguins_q4<-penguins[penguins$island=="Dream" & penguins$species== "Adelie",]
avg_flipper_length_mm<-mean(penguins_q4$flipper_length_mm)

```

## 6.3.1 Exercises

2.  There are 3 species of penguins in the data set
3.  #penguins_q3\<-penguins[penguins\$island=='Dream', c("species", "island", "flipper_length_mm")]
4.  Average flipper length is 189.73 mm

# 6.4 DPLYR Package

```{r}
filter(penguins, species == "Adelie")

filter(penguins, species != "Adelie")

filter(penguins, island %in% c("Dream", "Torgersen") & !is.na(bill_length_mm))

# Select two specific variables
select(penguins, species, sex)

# Select a range of variables
select(penguins, species:flipper_length_mm)

# Rename columns within select
select(penguins, genus = species, island)

# Select column variables that are recorded in mm
select(penguins, contains("mm"))


##Create new variables with mutate()

# New variable that calculates bill length in cm
mutate(penguins, bill_length_cm = bill_length_mm/10)

# mutate based on conditional statements
mutate(penguins, species_sex = if_else(sex == 'male', paste0(species,"_m"), paste0(species, "_f")))
```

# 6.4.1 The Pipe %\>%

```{r}
df1 <- filter(penguins, island == "Dream")
df2 <- mutate(df1, flipper_length_cm = flipper_length_mm/10)
df3 <- select(df2, species, year, flipper_length_cm)

print(df3)

#you can take the code above and do it an easier why by removing the need to create intermediate variables
penguins %>% 
  filter(island == "Dream") %>% 
  mutate(flipper_length_cm = flipper_length_mm/10) %>% 
  select(species, year, flipper_length_cm)

#Avg body mass for each species
penguins %>% 
  group_by(species) %>% 
  summarise(body_mass_avg = mean(body_mass_g, na.rm = TRUE))

#how many individuals were observed for each species each year
penguins %>% 
  group_by(species, year) %>% 
  summarise(n_observations = n())


```

# 6.3.2 Exercises

```{r}
# 1) Reorder the variables in penguins so that year is the first column followed by the rest (Hint: look into the use of everything()).
penguins<-penguins%>%
  select(year, everything())

# 2) Create a new column called ‘size_group’ where individuals with body mass greater than the overall average are called ‘large’ and those smaller are called ‘small’.
body_mass_avg<- mean(penguins$body_mass_g, na.rm = TRUE)
penguins<-penguins%>%
  mutate(size_group = if_else(body_mass_g>=body_mass_avg, paste('large'), paste('small')))

# 3) Find out which year for each species were individuals on average the largest according to body mass.

penguins%>%
  group_by(year)%>%
  summarise(body_mass_avg = mean(body_mass_g, na.rm = TRUE))


```

# 7. Visualize

```{r}
#explore the distribution of the variables. Example here:
ggplot(penguins) + 
  geom_histogram(mapping = aes(x = flipper_length_mm))

# Histogram example: flipper length by species
ggplot(penguins) +
  geom_histogram(aes(x = flipper_length_mm, fill = species), alpha = 0.5, position = "identity") +
  scale_fill_manual(values = c("darkorange","darkorchid","cyan4"))

#Another way to visualize across groups is with facet_wrap(), which will create a separate plot for each group, in this case species.
ggplot(penguins) +
  geom_histogram(aes(x = flipper_length_mm, fill = species), alpha = 0.5, position = "identity") +
  scale_fill_manual(values = c("darkorange","darkorchid","cyan4")) +
  facet_wrap(~species)

#Lets make a quick bar plot showing the total count of each species studied on each island
ggplot(penguins) +
  geom_bar(mapping = aes(x = island, fill = species))

#using ggplot2, This example builds on our simple bar plot
ggplot(penguins, aes(x = island, fill = species)) +
  geom_bar(alpha = 0.8) +
  scale_fill_manual(values = c("darkorange","purple","cyan4"), 
                    guide = FALSE) +
  theme_minimal() +
  facet_wrap(~species, ncol = 1) +
  coord_flip()

#using geom_point(), we want to visualize the relationship between penguin body mass and flipper length and color the point by species:
ggplot(penguins) +
  geom_point(mapping = aes(x = body_mass_g, y = flipper_length_mm, color = species))

```

# 7.1 Exercises