Lesson 8: Problem Set: Explore Many Variables

library(ggplot2)
ggplot(aes(x = log(price)), data = diamonds) + 
  geom_histogram(aes(fill = cut)) + 
  facet_wrap( ~ color) + 
  scale_fill_brewer(type = 'qual')

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(data = diamonds, aes(x = table, y = price)) + 
  geom_point(aes(colour = cut)) +
  scale_color_brewer(type = 'qual')

volume <- diamonds$x*diamonds$y*diamonds$z
ggplot(data = diamonds, aes(x = volume, y = price)) + 
  geom_point(aes(colour = clarity)) + 
  scale_y_log10() + 
  coord_cartesian(xlim=c(0,quantile(volume, 0.99))) +
  scale_color_brewer(type = 'div')

pf <- read.csv('pseudo_facebook.tsv', sep = '\t')
pf$prop_initiated = pf$friendships_initiated / pf$friend_count
pf$prop_initiated[is.nan(pf$prop_initiated)] <- 0

pf$year_joined <- floor(2014 - pf$tenure/365)
pf$year_joined.bucket <- cut(pf$year_joined, c(2004, 2009, 2011, 2012, 2014))
ggplot(data = pf, aes(x = tenure, y = prop_initiated)) + 
  geom_line(aes(color = year_joined.bucket), stat = 'summary', fun.y = median)

## Warning: Removed 2 rows containing non-finite values (stat_summary).

ggplot(data = pf, aes(x = tenure, y = prop_initiated)) + 
  geom_line(aes(color = year_joined.bucket), stat = 'summary', fun.y = median) +
  geom_smooth()

## Warning: Removed 2 rows containing non-finite values (stat_summary).

## `geom_smooth()` using method = 'gam'

## Warning: Removed 2 rows containing non-finite values (stat_smooth).

by(pf$prop_initiated, pf$year_joined.bucket, summary)

## pf$year_joined.bucket: (2004,2009]
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.3415  0.4669  0.4665  0.5909  1.0000 
## -------------------------------------------------------- 
## pf$year_joined.bucket: (2009,2011]
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.3894  0.5342  0.5273  0.6744  1.0000 
## -------------------------------------------------------- 
## pf$year_joined.bucket: (2011,2012]
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.4500  0.6154  0.5911  0.7600  1.0000 
## -------------------------------------------------------- 
## pf$year_joined.bucket: (2012,2014]
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.5000  0.6912  0.6430  0.8438  1.0000

#by(pf$prop_initiated, pf$year_joined.bucket, mean, na.rm=T)
#summary(subset(pf, year_joined.bucket=='(2012,2014]')$prop_initiated)

ggplot(data = diamonds, aes(x = cut, y = price/carat)) + 
  geom_jitter(aes(colour = color)) + 
  facet_wrap(~ clarity) + 
  scale_color_brewer(type = 'div')