From 6dd5145c4268eaa817f44fdf599ada3bfa62da35 Mon Sep 17 00:00:00 2001 From: wea_ondara Date: Sat, 11 Apr 2020 16:07:08 +0200 Subject: [PATCH] wip --- posthist.py | 17 ++-- text/2_relwork.tex | 2 +- text/4_datasets.tex | 189 ++++++++++++++++++++++++++++++++++++++++---- text/bib.bib | 12 +++ text/main.tex | 1 + 5 files changed, 197 insertions(+), 24 deletions(-) diff --git a/posthist.py b/posthist.py index 49f3574..472c624 100644 --- a/posthist.py +++ b/posthist.py @@ -154,15 +154,20 @@ def main(folder, intervl): plt.close(fig) #print data set stats - print("users: " + str(len(users))) - print("questions: " + str(len(posts))) - print("answers: " + str(sum(dmt(posts).map(lambda q: len(q['Answers'])).getresults()))) - print("active user last month: " + str(activeusercounts[-1])) + stats = "" + stats += "users: " + str(len(users)) + "\n" + stats += "questions: " + str(len(posts)) + "\n" + stats += "answers: " + str(sum(dmt(posts).map(lambda q: len(q['Answers'])).getresults())) + "\n" + stats += "active user last month: " + str(activeusercounts[-1]) + "\n" + useridmapping = {u['Id']: u for u in users} newuserposts = dmt(posts).filter(lambda q: q['CreationDate'] < useridmapping[q['OwnerUserId']]['CreationDate'] + timedelta(days=DAYS_NEW_USER)).getresults() newuserlist = set([q['OwnerUserId'] for q in newuserposts]) - print("questions from new users: " + str(len(newuserposts))) - print("questions from new users/new user: " + str(len(newuserposts) / len(newuserlist))) + stats += "questions from new users: " + str(len(newuserposts)) + "\n" + stats += "questions from new users/new user: " + str(len(newuserposts) / len(newuserlist)) + "\n" + print(stats) + with open(outputdir + "/stats.txt", "w") as file: + file.write(stats) if __name__ == "__main__": # execute only if run as a script diff --git a/text/2_relwork.tex b/text/2_relwork.tex index 113367b..e39405b 100644 --- a/text/2_relwork.tex +++ b/text/2_relwork.tex @@ -20,7 +20,7 @@ For each community on StackExchange a ``Meta'' page is offered where members of \begin{figure} \includegraphics[scale=0.47]{figures/stackoverflow_example_post} \label{soexamplepost} - \caption{A typically question on StackOverflow. In the top middle section of the page the question is stated. The question has 4 tags an 3 comments attached to it. Beneath the question all answers are listed by score in descending order (only one answer is visible in this screenshot). The accepted answer is marked by a green check mark. To the left of the question and answers the score (computed via votes) is indicated.} + \caption{A typically question on StackOverflow. In the top middle section of the page the question is stated. The question has 4 tags and 3 comments attached to it. Beneath the question all answers are listed by score in descending order (only one answer is visible in this screenshot). The accepted answer is marked by a green check mark. To the left of the question and answers the score (computed via votes) is indicated.} \end{figure} diff --git a/text/4_datasets.tex b/text/4_datasets.tex index beb8c33..dffc04c 100644 --- a/text/4_datasets.tex +++ b/text/4_datasets.tex @@ -10,40 +10,195 @@ %sections 1 per site -\section{StackOverflow.com} +\section{StackOverflow.com} %TODO insert values +StackOverflow is the largest and oldest community of the StackExchange platform. +The community has 165567 registered users of which 3467 were active in May of 2019. +Members asked 116797 questions in total and gave 202751 answers with an average answer density of 1.73 answers per question. +New users asked 42996 questions with an average of 1.129 questions per new user during their first week after registration. -\section{math.stackexchange.com} +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../stackoverflow.com/output/posthist/activeusers-i3.png} + \label{so_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../stackoverflow.com/output/posthist/postsanswers-i3.png} + \label{so_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} -\section{MathOverflow.com} +\section{math.stackexchange.com} +``Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields.'' \cite{mathstackexchangecom} +The community has 551397 registered users of which 18080 were active in May of 2019. +Members asked 1066979 questions in total and gave 1440948 answers with an average answer density of 1.35 answers per question. +New users asked 248867 questions with an average of 1.34 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../math.stackexchange.com/output/posthist/activeusers-i3.png} + \label{math_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../math.stackexchange.com/output/posthist/postsanswers-i3.png} + \label{math_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} + +\section{MathOverflow.net} +MathOverflow.net is a rather small community for professional mathematicians. +The community has 94559 registered users of which 1718 were active in May of 2019. +Members asked 100922 questions in total and gave 139077 answers with an average answer density of 1.378 answers per question. +New users asked 22794 questions with an average of 1.134 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../mathoverflow.net/output/posthist/activeusers-i3.png} + \label{matho_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../mathoverflow.net/output/posthist/postsanswers-i3.png} + \label{matho_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} \section{AskUbuntu.com} +AskUbuntu.com is a rather small community for Ubuntu users and developers. +The community has 783614 registered users of which 7033 were active in Feburary of 2020. +Members asked 334194 questions in total and gave 418051 answers with an average answer density of 1.25 answers per question. +New users asked 157018 questions with an average of 1.101 questions per new user during their first week after registration. -\section{ServerFault.com} +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../askubuntu.com/output/posthist/activeusers-i3.png} + \label{ubuntu_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../askubuntu.com/output/posthist/postsanswers-i3.png} + \label{ubuntu_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} + +\section{ServerFault.com} %TODO insert values +ServerFault.com is a rather small community for system and network administrators. +The community has 165567 registered users of which 3467 were active in May of 2019. +Members asked 116797 questions in total and gave 202751 answers with an average answer density of 1.73 answers per question. +New users asked 42996 questions with an average of 1.129 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../serverfault.com/output/posthist/activeusers-i3.png} + \label{fault_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../serverfault.com/output/posthist/postsanswers-i3.png} + \label{fault_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} \section{SuperUser.com} +SuperUser.com is a rather small community for computer enthusiasts and power users. +The community has 766028 registered users of which 11643 were active in May of 2019. +Members asked 396611 questions in total and gave 561645 answers with an average answer density of 1.416 answers per question. +New users asked 147080 questions with an average of 1.091 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../superuser.com/output/posthist/activeusers-i3.png} + \label{super_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../superuser.com/output/posthist/postsanswers-i3.png} + \label{super_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} \section{electronic.stackexchange.com} electronic.stackexchange.com is a rather small community for electrical engeneering. -The community has X registered users of which X were active in X of Year. -Members asked X questions in total and gave X answers with an average answer density of X per question. -New users asked X questions with an average of X questione per new user during their first week after registration. +The community has 165567 registered users of which 3467 were active in May of 2019. +Members asked 116797 questions in total and gave 202751 answers with an average answer density of 1.73 answers per question. +New users asked 42996 questions with an average of 1.129 questions per new user during their first week after registration. -\begin{figure}[H] %TODO add line with total users - \includegraphics[scale=0.35]{../electronics.stackexchange.com/output/posthist/activeusers-i3.png} - \label{elec_activeusers} - \caption{Active users with activity in the last 3 months} -\end{figure} -\begin{figure}[H] %TODO add line with total users - \includegraphics[scale=0.35]{../electronics.stackexchange.com/output/posthist/activeusers-i3.png} - \label{elec_activeusers_t} - \caption{Active users with activity in the last 3 months} +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../electronics.stackexchange.com/output/posthist/activeusers-i3.png} + \label{elec_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../electronics.stackexchange.com/output/posthist/postsanswers-i3.png} + \label{elec_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} \end{figure} -\section{stats.stackexchange.com} +\section{stats.stackexchange.com (Cross Validated)} +``Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization.'' \cite{statsstackexchangecom} +The community has 202879 registered users of which 5252 were active in May of 2019. +Members asked 137318 questions in total and gave 135350 answers with an average answer density of 0.985 answers per question. +New users asked 52588 questions with an average of 1.113 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../stats.stackexchange.com/output/posthist/activeusers-i3.png} + \label{stats_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../stats.stackexchange.com/output/posthist/postsanswers-i3.png} + \label{stats_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} \section{tex.stackexchange.com} +tex.stackexchange.com is a rather small community for TEX and related type setting systems. +The community has 155352 registered users of which 3630 were active in May of 2019. +Members asked 173991 questions in total and gave 135350 answers with an average answer density of 0.777 answers per question. +New users asked 55313 questions with an average of 1.195 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../tex.stackexchange.com/output/posthist/activeusers-i3.png} + \label{tex_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../tex.stackexchange.com/output/posthist/postsanswers-i3.png} + \label{tex_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} \section{unix.stackexchange.com} +unix.stackexchange.com is a rather small community for Linux and Unix-like operating systems. +The community has 316144 registered users of which 4624 were active in May of 2019. +Members asked 158714 questions in total and gave 236797 answers with an average answer density of 0.67 answers per question. +New users asked 56211 questions with an average of 1.128 questions per new user during their first week after registration. + +\begin{figure}[H] + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../unix.stackexchange.com/output/posthist/activeusers-i3.png} + \label{unix_activeusers} + \subcaption{Active users with activity in the last 3 months} + \end{subfigure} + \begin{subfigure}[c]{0.5\textwidth} + \includegraphics[scale=0.35]{../unix.stackexchange.com/output/posthist/postsanswers-i3.png} + \label{unix_postsanswers} + \subcaption{Questions and answers counts over time} + \end{subfigure} +\end{figure} diff --git a/text/bib.bib b/text/bib.bib index f527fd3..757b3c2 100644 --- a/text/bib.bib +++ b/text/bib.bib @@ -257,6 +257,18 @@ journal={\url{https://meta.stackexchange.com/questions/314472/what-are-the-exact-criteria-for-the-new-contributor-indicator-to-be-shown}}, year={2018} } +@article{statsstackexchangecom, + title={Cross Validated Main page}, + author={}, + journal={\url{https://stats.stackexchange.com/}}, + year={} +} +@article{mathstackexchangecom, + title={Mathematics Stack Exchange Main page}, + author={}, + journal={\url{https://math.stackexchange.com/}}, + year={} +} @inproceedings{yanovsky2019one, title={One Size Does Not Fit All: Badge Behavior in Q\&A Sites}, author={Yanovsky, Stav and Hoernle, Nicholas and Lev, Omer and Gal, Kobi}, diff --git a/text/main.tex b/text/main.tex index 3272ac3..3642828 100644 --- a/text/main.tex +++ b/text/main.tex @@ -201,6 +201,7 @@ ]{biblatex} \usepackage[T1]{fontenc} \usepackage{float} +\usepackage{subcaption} \addbibresource{\mybiblatexfile}