## HW 2 Example R code:

library(mdsr)
library(tidyverse)

#Problem 1, Chapter 3 Exercises:

library(babynames)
BabynamesDist <- make_babynames_dist()
#BabynamesDist

## creating a data frame called 'angelica' with only the female Angelicas:
angelica <- BabynamesDist %>%
  filter(name == "Angelica" & sex == "F")
name_plot <- ggplot(data = angelica, aes(x = year))  # basic ggplot object (with x-axis) to build on


## adding line plot with proportions of Angelicas BORN each year.
name_plot <- name_plot + 
  geom_line(aes(y = prop), size = 2)


## Adding a y-axis label
name_plot <- name_plot +
  ylab("Proportion of People") + 
  xlab(NULL)

name_plot


#Problem 2, Chapter 3 Exercises:

install.packages("nasaweather")
library(nasaweather)

# Simple scatterplot using geom_point
g <- ggplot(data = storms, aes(y = wind, x = pressure))
g + geom_point(size = 3)
# Addition of information on a third variable (categorical) using the Color aesthetic
g + geom_point(aes(color = type), size = 3)


#Problem 3, Chapter 3 Exercises:

library(mosaicData)

head(Marriage)

# (a)

##

## boxplot of 
ggplot(
  data = Marriage, 
  aes(
    x = race, 
    y = age
  )
) + 
  geom_boxplot() +
  xlab("Race") + 
  ylab("Age (in years) at Marriage")

#or:

ggplot(
  data = Marriage, 
  aes(
    x = officialTitle, 
    y = age
  )
) + 
  geom_boxplot() +
  xlab("Type of Officiant") + 
  ylab("Age (in years) at Marriage") +
coord_flip()


# (c)

# Simple scatterplot using geom_point
g3 <- ggplot(data = Marriage, aes(y = age, x = dob))
# Addition of information on other variables using the Size, Color aesthetics and facets:
g3 + geom_point(data=Marriage, aes(color = officialTitle), size = Marriage$prevcount+1) + facet_wrap(~ race)


#Problem 7, Chapter 3 Exercises:

## Creating a basic ggplot object
g7 <- ggplot(
  data = RailTrail, 
  aes(x = hightemp, y = volume)
) + 
  geom_point()
g7

## Plotting 2 separate scatterplots for the two weekday categories 
g7 + facet_wrap(~ weekday)

## Plotting it as a scatterplot with a trend line:
g7 <- g7 + 
  geom_smooth(method = "lm", se = FALSE) +     # Note "lm" will show a LINEAR trend
  xlab("High Temperature") +
  ylab("Number of Crossings")

## Plotting 2 separate scatterplots for the two weekday categories (now with trend lines)
g7 + facet_wrap(~ weekday)