Problem Set 5

setwd("D:/R/Udacity/EDA_Course_Materials/lesson5")
library(ggplot2)

Price Histograms with Facet and Color

ggplot(diamonds, aes(x = price, fill = factor(cut))) +
    geom_histogram(binwidth = 200) +
    facet_wrap( ~ color) +
    scale_fill_brewer(type = 'qual')

Price vs. Table Colored by Cut

ggplot(diamonds, aes(x = table, y = price, color = cut)) +
    geom_point() +
    scale_color_brewer(type = 'qual') +
    scale_x_continuous(breaks = seq(50,80,2), lim = c(50,80)) 

## Warning: Removed 5 rows containing missing values (geom_point).

Price vs. Volume and Diamond Clarity

diamonds$volume = diamonds$x * diamonds$y * diamonds$z
ggplot(diamonds, aes(x = volume, y = price, color = clarity)) +
    geom_point() +
    scale_y_log10() +
    scale_color_brewer(type = 'div') +
    xlim(0, quantile(diamonds$volume, 0.99))

## Warning: Removed 540 rows containing missing values (geom_point).

Proportion of Friendships Initiated

Many interesting variables are derived from two or more others. For example, we might wonder how much of a person’s network on a service like Facebook the user actively initiated. Two users with the same degree (or number of friends) might be very different if one initiated most of those connections on the service, while the other initiated very few. So it could be useful to consider this proportion of existing friendships that the user initiated. This might be a good predictor of how active a user is compared with their peers, or other traits, such as personality (i.e., is this person an extrovert?).

pf <- read.csv('pseudo_facebook.tsv', sep = '\t')
pf$prop_initiated = pf$friendships_initiated / pf$friend_count

prop_initiated vs. tenure

pf$year_joined <- floor(2014 - pf$tenure/365)
pf$year_joined.bucket <- cut(pf$year_joined, c(2004, 2009, 2011, 2012, 2014))

ggplot(data = subset(pf, !is.na(year_joined.bucket)), aes(x = tenure, y = prop_initiated, color = year_joined.bucket)) +
    geom_line(stat = 'summary', fun.y = mean)

## Warning: Removed 1962 rows containing missing values (stat_summary).

Smoothing prop_initiated vs. tenure

ggplot(data = subset(pf, !is.na(year_joined.bucket)), aes(x = tenure, y = prop_initiated, color = year_joined.bucket)) +
    geom_line(stat = 'summary', fun.y = mean) +
    geom_smooth()

## Warning: Removed 1962 rows containing missing values (stat_summary).

## geom_smooth: method="auto" and size of largest group is >=1000, so using gam with formula: y ~ s(x, bs = "cs"). Use 'method = x' to change the smoothing method.

## Warning: Removed 5 rows containing missing values (stat_smooth).

## Warning: Removed 81 rows containing missing values (stat_smooth).

## Warning: Removed 408 rows containing missing values (stat_smooth).

## Warning: Removed 1468 rows containing missing values (stat_smooth).

Largest Group Mean prop_initiated

Proportion of friendships initated for the group with the largest proportion of friendships initiated is 0.66.

This group’s proportion is quite high because people who joined later (after 2012) initially have more friends to add because many of their friends are already on FB.

subs<-subset(pf, year_joined > 2012)
mean(subs$prop_initiated, na.rm = T)

## [1] 0.6653892

Price/Carat Binned, Faceted, & Colored

ggplot(diamonds, aes(x = cut, y = price/carat)) +
    geom_point(aes(color = diamonds$color), alpha = (1/2), position = position_jitter(width = 0.3)) +
    facet_wrap( ~ clarity) +
    scale_color_brewer(type = 'div')