Created
October 13, 2016 14:07
-
-
Save CerebralMastication/f5408672ac627511399d7a643eb297ef to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# query run here: https://data.stackexchange.com/stackoverflow/query/edit/543286 | |
# | |
# select | |
# TagName, | |
# str(DATEPART(yyyy, p.CreationDate )) + '-' + str(DATEPART(mm, p.CreationDate )) as postmonth, | |
# count(pt.PostId) as Num | |
# from | |
# Tags, | |
# PostTags pt, | |
# Posts as p | |
# where Tags.Id = pt.TagId | |
# and p.Id = pt.PostId | |
# AND tags.tagname = 'r' | |
# group by | |
# TagName , | |
# str(DATEPART(yyyy, p.CreationDate )) + '-' + str(DATEPART(mm, p.CreationDate )); | |
## data downloaded and saved to '~/Downloads/QueryResults-r.csv' | |
library(stringr) | |
library(ggplot2) | |
library(plyr) | |
soData <- read.csv('~/Downloads/QueryResults-r.csv') | |
soData$postmonth <- gsub("\\s+", " ", str_trim(soData$postmonth)) | |
soData$yearNum <- as.numeric(substr(soData$postmonth,1,4)) | |
soData$monthNum <- substr(soData$postmonth, nchar(soData$postmonth)-2 , nchar(soData$postmonth)) | |
soData$monthNum <- as.numeric(gsub('![[:alnum:]]*[[:space:]]|[[:punct:]]', '', soData$monthNum)) | |
soData$postmonth <- factor(soData$postmonth, levels = soData$postmonth) | |
theme_set(theme_gray(base_size = 18)) | |
ggplot(data = subset(soData, yearNum <= 2009), aes( x=postmonth, y=Num)) + | |
geom_bar(stat="identity") + | |
theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5) | |
) | |
ggplot(data = soData, aes( x=postmonth, y=Num)) + | |
geom_bar(stat="identity") + | |
theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5) | |
) | |
write.csv(soData, '~/Downloads/QueryResults-r-soData.csv' ) | |
## linear trend | |
soDataSubset <- subset(soData, yearNum >= 2012 & postmonth != '2016- 10') | |
soDataSubset$index <- 1:length(soDataSubset$Num) | |
reg <- lm(Num ~ index, data =soDataSubset ) | |
soDataSubset$modeled <- predict(reg) | |
# calculate percent deviation of modeled | |
soDataSubset$dev <- (soDataSubset$Num - soDataSubset$modeled) / soDataSubset$modeled | |
## plot errors | |
ggplot(data = soDataSubset, aes( x=postmonth, y=dev)) + | |
geom_bar(stat="identity") + | |
theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5) | |
) | |
monthlyAvgDev <- ddply(soDataSubset, 'monthNum', function(df)mean(df$dev) ) | |
colnames(monthlyAvgDev) <- c('monthNum','avgErr') | |
monthlyAvgDev$monthNum <- factor( monthlyAvgDev$monthNum ) | |
## plot average error by month | |
ggplot(data = monthlyAvgDev, aes( x=monthNum, y=avgErr)) + | |
geom_bar(stat="identity") + | |
theme(axis.text.x=element_text(angle=90,hjust=1,vjust=0.5) | |
) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment