Intro to R - Ch 10.R

############################################################
# R script to accompany Intro to R for Business, Chapter 10#
# Written by Troy Adair                                    #
############################################################

# Clear out Console and Enviroment
rm(list=ls(all=TRUE))
cat("\014")

library(here)

## Get subsample from YT_Sample_Validated ready for graphing
# Load the previously referenced data frame in 
# "YT_Sample_Validated.RData", copy it to "DF",
# and remove "YT_Sample_Validated" from memory
load(here("Data","YT_Sample_Validated.RData"))
DF <- YT_Sample_Validated
rm(YT_Sample_Validated)

# Reform DF with only the "good" observations
DF<-DF[which(DF$total_amount >0 &
               DF$fare_amount <100000 &
               DF$fare_amount >= 0 &
               DF$trip_distance < 100),]

# Reformat passenger_count as factor and store data frame as DF
DF$passenger_count <- as.factor(DF$passenger_count)

# Select a random subsample of 10,000 rows
set.seed(10)
index <- sample(1:nrow(DF), 10000, replace=FALSE)
# Copy the row numbers for the sample only into DF
DF <- DF[index,]
##################################################

# Install and load ggplot2 package
if (!require("ggplot2")) install.packages("ggplot2")
library(ggplot2)

# Data set "diamonds" comes in ggplot2
data(diamonds)
dim(diamonds)
names(diamonds)

# Using R core plotting capabilities
plot (price ~ carat, data=diamonds)
plot(diamonds$carat, diamonds$price)
boxplot(diamonds$carat)
hist(diamonds$carat, main="Carat Histogram", xlab="Carat")

# Using ggplot2
ggplot(data = diamonds)
ggplot(data = diamonds)+geom_histogram(aes(x=carat))
ggplot(data = diamonds)+geom_density(aes(x=carat),fill='grey50')


ggplot(data=diamonds) + 
  geom_histogram(binwidth=500, aes(x=diamonds$price)) + 
  ggtitle("Diamond Price Distribution") + 
  xlab("Diamond Price U$") + 
  ylab("Frequency") + 
  theme_minimal()

ggplot(data=diamonds) + 
  geom_histogram(binwidth=500, aes(x=diamonds$price)) + 
  ggtitle("Diamond Price Distribution") + 
  xlab("Diamond Price U$ - Binwidth 500") + 
  ylab("Frequency") + 
  theme_minimal() + 
  xlim(0,2500)

ggplot(data=diamonds) + 
  geom_histogram(binwidth=100, aes(x=diamonds$price)) + 
  ggtitle("Diamond Price Distribution") + 
  xlab("Diamond Price U$- Binwidth 50") + 
  ylab("Frequency") + 
  theme_minimal() + 
  xlim(0,2500)

ggplot(data=diamonds) + 
  geom_histogram(binwidth=100, aes(x=diamonds$price)) + 
  ggtitle("Diamond Price Distribution by Cut") + 
  xlab("Diamond Price U$") + 
  ylab("Frequency") + 
  theme_minimal() + 
  facet_wrap(~cut)

ls(pattern = '^geom_', env = as.environment('package:ggplot2'))
help(aes)
help(aes_colour_fill_alpha)
help(aes_group_order)
help(aes_linetype_size_shape)
help(aes_position)

# Package devtools will be used to install latest ggplotgui
# from GitHub
if (!require("devtools")) install.packages("devtools")
library(devtools)

# Installing latest ggplotgui p[ackage from GitHub]
if (!require("ggplotgui")) devtools::install_github("gertstulp/ggplotgui")
library(ggplotgui)

# Running ggplot_shiny() with our data
ggplot_shiny(DF)

## This is where I put the code generated by ggplotgui

# You need the following package(s):
library("ggplot2")

# The code below will generate the graph:
graph <- ggplot(DF, aes(x = trip_distance, y = tip_amount, colour = passenger_count)) +
  geom_point()+
  geom_smooth(se = FALSE, method = 'lm')+
  scale_colour_brewer(palette = 'RdBu') +
  theme_bw()
graph

# If you want the plot to be interactive,
# you need the following package(s):
library("plotly")
ggplotly(graph)

# If you would like to save your graph, you can use:
ggsave('my_graph.pdf', graph, width = 14, height = 14, units = 'cm')