## ----intror:ggplot_weather, eval=FALSE-----------------------------------
## install.packages(c("ggplot2", "rattle"))
## library(ggplot2)
## library(rattle)
## qplot(data=weatherAUS, x=MinTemp, y=MaxTemp)

## ----intror:install.packages, eval=FALSE---------------------------------
## # Install a package from a CRAN repository.
## 
## install.packages(pkgs="dplyr")

## ----intror:data_glimpse-------------------------------------------------
# Review the dataset.

dplyr::glimpse(x=rattle::weatherAUS)

## ----intror:attach_dplyr_rattle, message=FALSE---------------------------
# Load packages from the local library into the R session.

library(package=dplyr)
library(package=rattle)

## ----intror:attach_dplyr_rattle_glimpse, message=FALSE-------------------
# Review the dataset.

glimpse(x=weatherAUS)

## ----intror:weather_glimpse, message=FALSE-------------------------------
# Load packages from the local library into the R session.

library(dplyr)
library(rattle)

# Review the dataset.

glimpse(weatherAUS)

## ----intror:attach_packages, message=FALSE-------------------------------
# Load packages required for this script.

library(rattle)   # The weatherAUS dataset and normVarNames().
library(readr)    # Efficient reading of CSV data.
library(dplyr)    # Data wrangling and glimpse().
library(ggplot2)  # Visualise data.
library(magrittr) # Pipes %>%, %<>%, %T>%, %$%.

## ----intror:data_sum_function--------------------------------------------
# Add two numbers.

sum(1, 2)

## ----intror:assignment_operator------------------------------------------
# Add two numbers and assign the result into a variable.

v <- sum(1, 2)

## ----intror:assignment_results-------------------------------------------
# Print the value stored in a variable.

v
print(v)

## ----intror:assignment_results_index-------------------------------------
# Access a particular value from a vector of data.

v[1]
v[2]

## ----intror:data_library_command-----------------------------------------
# Load package from the local library into the R session.

library(rattle)

## ----intror:data_library_command_visible, out.lines=NULL-----------------
# Demonstrate that library() returns a value invisibly.

print(library(rattle))

## ----intror:index_vector_library_command---------------------------------
# Load a package and save the value returned.

l <- library(rattle)

# Review one of the returned values.

l[7]

## ----intror:data_plus_infix_function-------------------------------------
# Add two numbers using an infix operator.

1 + 2

## ----intror:data_plus_function-------------------------------------------
# Add two numbers using the equivalent functional form.

`+`(1, 2)

## ----intror:weather_print, out.lines=3-----------------------------------
# Review the dataset of weather observations.

weatherAUS

## ----intror:weather_select-----------------------------------------------
# Select variables from the dataset.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine)

## ----intror:weather_select_summary, out.lines=7--------------------------
# Select variables from the dataset and summarise the result.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  summary()

## ----intror:weather_select_filter----------------------------------------
# Select specific variables and observations from the dataset.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall >= 1)

## ----intror:weather_select_filter_assign_normal--------------------------
# Select variables/observations and save the result.

rainy.days <- 
  weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall >= 1)

## ----intror:weather_select_filter_assign---------------------------------
# Demonstrate use of the forward assignment operator.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall >= 1) ->
  rainy.days

## ----intror:weather_select_filter_assign_unindent------------------------
# Best to unindent the final assigned variable for clarity.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall >= 1) ->
rainy.days

## ----intror:weather_select_filter_summary, out.lines=7-------------------
# Summarise subset of variables for observations with rainfall.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall >= 1) %>%
  summary()

## ----intror:weather_select_filter_summary_no_rain, out.lines=7-----------
# Summarise observations with little or no rainfall.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall < 1) %>%
  summary()

## ----intror:weather_select_filter_summary_no_rain_with_pipe, out.lines=7----
# Summarise observations with little or no rainfall.

weatherAUS %>% 
  select(MinTemp, MaxTemp, Rainfall, Sunshine) %>%
  filter(Rainfall < 1) %>%
  summary()

## ----intror:weather_select_filter_summary_no_rain_no_pipe, out.lines=7----
# Functional form equivalent to the pipeline above.

summary(filter(select(weatherAUS, 
                      MinTemp, MaxTemp, Rainfall, Sunshine),
               Rainfall < 1))

## ----intror:weather_assignment_pipe--------------------------------------
# Copy the dataset into the variable ds.

ds <- weatherAUS

# Report on the dimensions of the dataset.

dim(ds)

# Demonstrate an assignment pipeline.

ds %<>% 
  filter(Rainfall==0) %>%
  select(MinTemp, MaxTemp, Sunshine)

# Confirm that the dataset has changed.

dim(ds)

## ----intror:weather_assignment_no_pipe, eval=FALSE-----------------------
## # Functional form equivalent to the pipeline above.
## 
## ds <- select(filter(weatherAUS, Rainfall==0),
##              MinTemp, MaxTemp, Sunshine)

## ----intror:tee_pipe, out.lines=NULL-------------------------------------
weatherAUS %>%
  select(Rainfall, MinTemp, MaxTemp, Sunshine) %>%
  filter(Rainfall==0) %T>%
  head() %>%
  select(MinTemp, MaxTemp, Sunshine) %>%
  summary()

## ----intror:tee_pipe_print-----------------------------------------------
# Demonstrate usage of a tee-pipe.

no.rain <-
  weatherAUS %>%
  filter(Rainfall==0) %T>%
  print()

## ----intror:tee_pipe_print_alternatives----------------------------------
# Equivalent alternatives to the above tee-pipe example.

(
  weatherAUS %>%
    filter(Rainfall==0) ->
  no.rain
)

## ----intror:tee_pipe_print_alternatives_print----------------------------
print(no.rain)

## ----intror:tee_pipe_usage, eval=FALSE-----------------------------------
## fpath <- "data"
## files <- dir(fpath, "*.csv.gz")
## ds <- data.frame()
## for (i in seq_len(length(files)))
## {
##   ds <- fpath %>%
##     file.path(files[i]) %T>%
##     cat("\n") %>%
##     readr::read_csv() %>%
##     rbind(ds, .)
## }

## ----intror:magrittr_fly-------------------------------------------------
# List the levels of a factor.

levels(weatherAUS$WindGustDir)

# 

weatherAUS %>%
  filter(Rainfall>0) %T>%
  { 
    lvls <<- select(., WindGustDir, MaxTemp) %>%
      group_by(WindGustDir) %>% 
      summarise(MaxMaxTemp=max(MaxTemp)) %>%
      arrange(MaxMaxTemp) %>%
      pull(WindGustDir)
  } %>%
  mutate(WindGustDir=factor(WindGustDir, levels=lvls)) %$%
  levels(WindGustDir)

## ----intror:exposition_pipe----------------------------------------------
weatherAUS %>%
  filter(Rainfall==0) %$%
  cor(MinTemp, MaxTemp)

## ----intror:exposition_pipe_alternative----------------------------------
weatherAUS %>%
  filter(Rainfall==0) %>%
  with(cor(MinTemp, MaxTemp))

## ----intror:example_figure, eval=FALSE-----------------------------------
## cities <- c("Canberra", "Darwin", "Melbourne", "Sydney")
## 
## weatherAUS %>%
##   filter(Location %in% cities) %>%
##   filter(Temp3pm %>% is.na() %>% not()) %>%
##   ggplot(aes(x=Temp3pm, colour=Location, fill=Location)) +
##   geom_density(alpha=0.55) +
##   labs(title = "Density Distributions of the 3pm Temperature",
##        x     = "Temperature Recorded at 3pm",
##        y     = "Density")

## ----intror:example_figure, fig.pos='h', fig.height=3, fig.width=8, out.width="\\textwidth", echo=FALSE----
cities <- c("Canberra", "Darwin", "Melbourne", "Sydney")

weatherAUS %>% 
  filter(Location %in% cities) %>%
  filter(Temp3pm %>% is.na() %>% not()) %>%
  ggplot(aes(x=Temp3pm, colour=Location, fill=Location)) +
  geom_density(alpha=0.55) +
  labs(title = "Density Distributions of the 3pm Temperature",
       x     = "Temperature Recorded at 3pm", 
       y     = "Density")

## ----intror:load_sa4_ports_data, echo=FALSE, message=FALSE---------------
avgdis <- read_csv("data/SA4_AvgDis_PoR_PoW.csv")

## ----intror:sydney_distance_travel, fig.pos='h', fig.height=4, fig.width=8, out.width="\\textwidth"----
avgdis %>%
  filter(GCCSA_CODE_2011=="1GSYD") %>%
  select(O_SA4name, O_Avg_KM, D_Avg_KM) %>%
  mutate(O_SA4name=str_replace(O_SA4name, "^Sydney - ", "")) %$%
  {
    nms <<- O_SA4name[order(O_Avg_KM)] ; .
  } %>%
  mutate(O_SA4name=factor(O_SA4name, levels=nms)) %>%
  gather("OD", "Distance", -O_SA4name) %>%
  arrange(O_SA4name) %$%
  {
    lbls <<- data.frame(x   = sort(c(seq(0.75, 14.75), seq(1.2, 15.2))+0.02),
                        y   = (Distance-0.75),
                        lbl = round(Distance,1)) ; .
  } %>%
  ggplot(aes(x=O_SA4name, y=Distance)) +
    geom_bar(stat="identity", position="dodge", aes(fill=OD)) +
    geom_text(data=lbls, aes(x=x, y=y, label=lbl), colour="white",
              size=3, hjust=0.5) +
    theme(axis.text.x=element_text(angle=45, hjust=1, size=10)) +
    theme(legend.position=c(.15, .9)) +
    scale_fill_manual(values=c(rgb(246, 160,  26, max=255), 
                               rgb(  0, 101, 164, max=255)),
                      labels=c("By SA4 of residence", "By SA4 of work")) +
    theme(legend.title=element_text(colour="transparent"),
          legend.background=element_rect(fill="transparent"),
          legend.direction="horizontal") +
    labs(x="Sydney", y="Average Distance (KM)")

## ----intror:tee_pipe_id_1------------------------------------------------
weatherAUS %>%
  select(Rainfall, MinTemp, MaxTemp, Sunshine) %>%
  {.}

## ----intror:tee_pipe_id_2, out.lines=NULL--------------------------------
weatherAUS %>%
  select(Rainfall, MinTemp, MaxTemp, Sunshine) %>%
  summary() %>%
  {.}