在R中使用Bins进行基本概率分析

Question

我不是一个统计学家，但我确实想使用基本概率来理解我的数据发生了什么。

我已经创建了一种繁琐但非常有用的方法，可以使用直方图查看特定存储箱中的数据，然后将我感兴趣的不同组与整个组进行比较。它向我们展示了我们公司的一些令人难以置信的洞察力，很容易解释图表中发生的事情。话虽如此，但它相当单调乏味，而且这种类型的分析如此有用，以至于其他人已经为它创建了一个函数，这是有道理的。

下面是我的代码。函数中是否已经存在这种类型的分析？我还使用了logi.hist.plot()，它做了类似的事情，但它可能会有问题，我更喜欢使用这种数据的“原始视图”。

library(dplyr)
library(ggplot2)

#Create the data
set.seed(84102)
daba <- data.frame(YES_NO = c(0,0,1,1,1,1,0,0,0,1,0,1,0,1,0,1,0,0,0,1))
daba$UserCount <-     c(23,43,45,65,32,10,34,68,65,75,43,24,37,54,73,29,87,32,21,12)

#Create the bins using hist(), clean up bins and make them integers
hist_breaks <- cut(daba$UserCount, breaks = hist(daba$UserCount, breaks =     20)$breaks)
daba$Breaks <- hist_breaks
daba$Breaks <- sub(".*,","",daba$Breaks)
daba$Breaks <- sub("]","",daba$Breaks)
daba$Breaks[is.na(daba$Breaks)] <- 0
daba$Breaks <- as.integer(daba$Breaks)

#Create two data groups to be compared
daba_NO  <- filter(daba, daba$YES_NO == 0)
daba_YES <- filter(daba, daba$YES_NO == 1)

#Aggregate user count into histogram bins using aggregate()
daba_NOAgg <- aggregate(data = daba_NO, daba_NO$Breaks~daba_NO$UserCount, sum)
daba_YESAgg <- aggregate(data = daba_YES, daba_YES$Breaks~daba_YES$UserCount, sum)

#Rename the columns to clean it up
colnames(daba_NOAgg) <- c("UserCountNo", "Breaks")
colnames(daba_YESAgg) <- c("UserCountYes", "Breaks")

#Merge the two groups back together
daba_SUMAgg <- merge(x = daba_NOAgg, y = daba_YESAgg, by.x = "Breaks", by.y = "Breaks")

#Generate basic probability for Yes group of users
daba_SUMAgg$Probability <-     (daba_SUMAgg$UserCountYes/(daba_SUMAgg$UserCountNo+daba_SUMAgg$UserCountYes))*100

#Graph the data
ggplot(data = daba_SUMAgg)+
  geom_point(alpha = 0.4, mapping = aes(y = daba_SUMAgg$Probability, x =     daba_SUMAgg$Breaks))+
  labs( x = "BINS", y = "PROBABILITY", title = "PROBABILITY ANALYSIS USING     BINS")


daba_SUMAgg

Answer 1

当你有dplyr的group_by时，不需要拆分你的数据集。不需要从要绘制的范围中创建数值。我认为你的流程遗漏了一些东西(参见我上面的评论)。

我建议使用

library(dplyr)
library(ggplot2)

#Create the data
set.seed(84102)
daba <- data.frame(YES_NO = c(0,0,1,1,1,1,0,0,0,1,0,1,0,1,0,1,0,0,0,1))
daba$UserCount <-     c(23,43,45,65,32,10,34,68,65,75,43,24,37,54,73,29,87,32,21,12)

daba %>%
  mutate(Breaks = cut(UserCount, breaks = hist(UserCount, breaks = 20)$breaks, right = F)) %>%  # create your breaks (use right = F other wise you miss the value 10)
  group_by(Breaks, YES_NO) %>%                             # for every range and YES_NO value
  summarise(UserCount = sum(UserCount)) %>%                # get sum of counts
  mutate(Prc = UserCount/sum(UserCount)) %>%               # get the probability / percentage
  ungroup() %>%                                            # forget the grouping
  mutate(YES_NO = factor(YES_NO)) %>%                      # change this to factor for the plot
  ggplot(aes(Breaks, Prc, col=YES_NO, group=YES_NO)) +     # plot
  geom_point() +
  geom_line()

逐步运行管道流程，以查看数据处理的工作方式以及数据集在绘制之前的外观。