##### Helicopter Data exploring & manipulation and starting graphs, D Jenkins 9 Sep 2021

# These two lines are handy to put at the start of any code
rm(list=ls()) # remove ALL objects to help make space - most helpful if you have been doing other R stuff before this
gc() # garbage collection - cleans those objects out of memory

setwd("~/Desktop") # set working directory to where the data will be - all subsequent work will also be saved there by default

# Install needed packages. This only needs to be done once - they will exist on your computer once this is done.
install.packages("readxl") 
install.packages("tidyverse") # this actually installs several packages, including dplyr, readr, and ggplot2
install.packages("ggthemes") 
install.packages("viridis")

# Now invoke those packages. You will need to do similar "library" or "require" commands to get needed packages every time you run R.
library(readxl) # to read Excel files
library(tidyverse) # to move data around with dplyr, start using pipelines ( %>% ), and graph with ggplot2
library(ggthemes) # some nice preloads of graph styles
library(viridis) # a popular color scheme

### Let's practice loading the data in a couple ways. Go to the class web page and download the helicopter data.csv AND helicopter data.xls files.
# Below I assume those files are now on your Desktop.
# First import the .csv file using readr:
copter.csv.data <- read_csv("~/Desktop/helicopter data.csv")
# That works great but automatically decides the kinds of data in columns. You may find problems in data some day due to importing as the wrong types.
# To customize details, go instead to Environment... Import Dataset... From Text (readr) and then Browse in the pop-up window to get the file...
# Click on a column heading to change data type. For example, copter ID is not a continuous number with decimal places, but only an integer for a design type.
# Change that from "double" to "integer" and click "Import" at the bottom.

### Now let's import straight from the Excel file, using readxl.
# The excel file contains two sheets - one with data and one with metadata (explanations). You want the data on the first sheet
copter.xl.data <- read_xls("~/Desktop/helicopter data.xls", 1)
# What if you want to see the metadata while in R - can you load the second sheet?
# What other options exist in readxl? Go to Packages (see right --->), scroll down to readxl, and click on the name. There is lots of info available about each package.

##### Let's squint at the data, using either the csv or the xl version.
# to use only one data file hereafter, use this command (convenient but also can cause problems if you later use multiple data files in a long script):
attach(copter.csv.data)
# What is the average copter "hang time" for each group?
groupmeans <- copter.csv.data %>% group_by(Group) %>% summarise(Group.mean = mean(Time, na.rm=T))
# Notice what that did? We grouped by student Groups, then summarized to get a mean time per group, after removing any NAs in the data.
# But what did you get?
groupmeans
# This is a short list, but what if you wanted to sort them in order descending means (so greatest was at the top)?
arrange(groupmeans, desc(Group.mean))

# How many copters were used per Design? Did we get a balanced experiment?
copter.csv.data$ID <- factor(copter.csv.data$ID) # here we convert the numeric ID into a non-numeric factor
designcounts <- copter.csv.data %>% group_by(ID) %>% count(WL)
designcounts
# What happens if we replace WL above with Time? Why is this different?

# How many unique copter designs were used?
number.of.designs <- length(unique(copter.csv.data$ID))
number.of.designs

# How about a graph? Let's first make a simple boxplot - Time as a function of categorical Groups
boxplot(copter.xl.data$Time~copter.xl.data$Group) # medians in the middle, box = quartiles, whiskers = 10 & 90 percentiles, dots = outliers
# Want a prettier one?
ggplot(copter.csv.data, aes(x=Group, y=Time, color = Group)) + 
  geom_boxplot()
# Wanna get rid of the gray background and change box colors?
ggplot(copter.csv.data, aes(x=Group, y=Time, color = Group)) + 
  geom_boxplot(aes(fill = Group)) +
  theme_classic() +
  scale_fill_viridis_d()

# Why is there so much scatter for any one Group? 
# Now try some other boxplots of your own - for example, Time ~ WL. And play with different themes in ggthemes

# Or how about a scatter plot between two numerical variables?
plot(Time~Step) # Notice that copter.xl.data$ was skipped this time? That is because we attached the data file. 
ggplot(copter.csv.data, aes(x=WL, y=Time)) + 
  geom_point(aes(color = Group)) +
  geom_smooth(aes(color = Group), method = "lm") + 
  theme_classic()

# Compare that to 
ggplot(copter.csv.data, aes(x=WL, y=Time)) + 
  geom_point(aes(color = Group)) +
  geom_smooth(method = "lm", color="black") + 
  theme_classic()
# Can you see code that made the difference? See how these two graphs help answer different questions?

# Why is there so much scatter for any one wing length? 
# Now try some other scatter plots of your own - for example, Time ~ WL and different themes in ggthemes

# So what did you accomplish today? You:
# learned about memory management (computer's  - not your's)
# loaded data in a couple different ways and learned about details of that process
# attached a data file and used dplyr to group and calculate means
# started seeing differences between categorical groups and relationships between continuous variables.
# started becoming a graphic artist

# Stats to be done later will examine multiple effects (Group, WL, BW, Fold, and Step) SIMULTANEOUSLY AND SEPARATE FROM OTHER EFFECTS