ggplot2 绘图

# 保存最近一次生成的图片
ggsave('priceHistogram.png')
# ggsave currently recognises the extensions eps/ps, tex (pictex),
# pdf, jpeg, tiff, png, bmp, svg and wmf (windows only).

facet_wrap(formula)
facet_wrap(~variable)

facet_grid(formula)
facet_grid(vertical ~ horizontal)

# 方法一
pf <- read.csv('pseudo_facebook.tsv', sep = '\t')
# 方法二
pf <- read.delim('pseudo_facebook.tsv')

# 分面处理
qplot(x=dob_day, data=pf) + 
  scale_x_continuous(breaks = 1:31) +
  facet_wrap(~dob_month, ncol = 3)

# 限制x轴：方法一
qplot(x=friend_count, data=pf, xlim=c(0, 1000))

# 方法二
qplot(x=friend_count, data=pf) +
  scale_x_continuous(limits = c(0, 1000))

# 设置每组的宽度
qplot(x = friend_count, data = pf, binwidth = 10) +
  scale_x_continuous(limits = c(0, 1000),
                     breaks = seq(0, 1000, 50))

# 按照性别拆分直方图
qplot(x = friend_count, data = pf, binwidth = 10) +
  scale_x_continuous(limits = c(0, 1000), breaks = seq(0, 1000, 50)) +
  facet_wrap(~gender)

# 删除 NA Values
qplot(x = friend_count, data=subset(pf, !is.na(gender)), binwidth = 10) +
  scale_x_continuous(limits = c(0, 1000), breaks = seq(0, 1000, 50)) + 
  facet_wrap(~gender)

# 按照性别统计 friend 平均值
> by(pf$friend_count, pf$gender, summary)
pf$gender: female
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      0      37      96     242     244    4923 
--------------------------------------------------------- 
pf$gender: male
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      0      27      74     165     182    4917

分析：女性的平均 friend_count 要高于男性，不管是中位数还是均值都大于男性。应该注意，中位数 指标比 均值 指标更可靠、稳定：因为friend_count 是右偏的，当右侧有很离谱的 friend_count 时，均值很容易会被拉向右方，而中位数却不受影响。

> summary(pf$tenure)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
    0.0   226.0   412.0   537.9   675.0  3139.0       2 

# 设置颜色
qplot(x = tenure, data = pf,
      color = I('black'), fill = I('#099dd9'))

# create a histogram of tenure by year
qplot(x = tenure/365, data = pf, binwidth = .25, 
      color = I('black'), fill = I('#f79420')) + 
  scale_x_continuous(breaks = seq(0, 7, 1), limits = c(0, 7))

# 增加x轴，y轴标签
qplot(x = tenure/365, data = pf, binwidth = .25,
      xlab = 'Number of years using Facebook',
      ylab = 'Number of users in sample',
      color = I('black'), fill = I('#f79420')) + 
  scale_x_continuous(breaks = seq(0, 7, 1), limits = c(0, 7))

> summary(pf$age)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  13.00   20.00   28.00   37.28   50.00  113.00 

# 绘制年龄直方图
qplot(x=age, data = pf, binwidth = 1,
      color=I('black'), fill=I('#5760ab')) +
  scale_x_continuous(breaks = seq(0, 113, 5))

# 分面时，使y轴按需要调节
qplot(x = price, data = diamonds) + facet_wrap(~cut, scales = "free") 

# 分面时，使y轴按需要调节，对横坐标轴进行对数转换
# 对于长尾分布，你可以添加一个 ggplot 图层（如：scale_x_log10()）来转换变量。
qplot(x = price/carat, data = diamonds) + 
  scale_x_log10() + 
  facet_wrap(~cut, scales = "free")