distribution of dataset size
This commit is contained in:
parent
f89a323b76
commit
a11de07f88
|
|
@ -90,4 +90,41 @@ Publications focusing Tool development account for ***.
|
|||
\includegraphics[width=0.45\textwidth]{resources/type_statics.png}
|
||||
\caption{Distribution of publications per research types.}
|
||||
\label{fig:venue}
|
||||
\end{figure}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\subsection{Statistics of datasize}
|
||||
|
||||
\begin{figure}[h]
|
||||
\centering
|
||||
\includegraphics[width=0.45\textwidth]{resources/prj_numbers.png}
|
||||
\caption{Distribution of the number of studied projects.}
|
||||
\label{fig:venue}
|
||||
\end{figure}
|
||||
|
||||
\begin{figure}[h]
|
||||
\centering
|
||||
\includegraphics[width=0.45\textwidth]{resources/pr_numbers.png}
|
||||
\caption{Distribution of the number of studied PRs.}
|
||||
\label{fig:venue}
|
||||
\end{figure}
|
||||
|
||||
|
||||
|
||||
|
||||
\begin{table}[h]
|
||||
|
||||
\centering
|
||||
\caption{The statistics of dataset size}
|
||||
\begin{tabular}{@{}l ccccc c @{}}
|
||||
\toprule
|
||||
Studied ***&\textbf{Min} &\textbf{25\%} &\textbf{Median} &\textbf{75\%} &\textbf{Max} &\textbf{Mean} \\ \midrule
|
||||
\#Project & 1 & 1 & 2 & 3 & 35 & 2.30 \\
|
||||
\#PR & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\#Interviewee & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\#Survey respondents & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\label{tab:dtsize}
|
||||
|
||||
\end{table}
|
||||
|
|
@ -57,7 +57,7 @@ The most popular topic is ***.
|
|||
\subsubsection{Submission practice}
|
||||
\subsubsection{Factors affecting PR submission}
|
||||
|
||||
\begin{table*}[h]
|
||||
\begin{table*}[h!]
|
||||
|
||||
\centering
|
||||
\caption{Topic studied in previous research. (The number following each topic and category indicating the publication count)}
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ as well as one of the studies using the metric.
|
|||
|
||||
|
||||
\newcommand{\tabincell}[2]{\begin{tabular}{@{}#1@{}}#2\end{tabular}}
|
||||
\begin{table*}[htb]
|
||||
\begin{table*}[h!]
|
||||
|
||||
\centering
|
||||
\caption{Metrics studied in previous research - Part I.}
|
||||
|
|
|
|||
|
|
@ -1,18 +1,2 @@
|
|||
\section{Dataset size}
|
||||
|
||||
\begin{table}[h]
|
||||
|
||||
\centering
|
||||
\caption{The statistics of dataset size}
|
||||
\begin{tabular}{@{}l ccccc c @{}}
|
||||
\toprule
|
||||
Studied ***&\textbf{Min} &\textbf{25\%} &\textbf{Median} &\textbf{75\%} &\textbf{Max} &\textbf{Mean} \\ \midrule
|
||||
\#Project & 1 & 1 & 2 & 3 & 35 & 2.30 \\
|
||||
\#PR & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\#Interviewee & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\#Survey respondents & 1 & 2 & 3 & 6 & 148 & 5.68 \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\label{tab:dtsize}
|
||||
|
||||
\end{table}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,70 @@
|
|||
# coding: utf-8
|
||||
import xlrd
|
||||
|
||||
|
||||
data = xlrd.open_workbook('../data_extraction.xlsx')
|
||||
import matplotlib.pyplot as plt
|
||||
import pandas as pd
|
||||
|
||||
import math
|
||||
def prj_sts():
|
||||
table = data.sheet_by_name('sheet1')
|
||||
prjs = table.col_values(8)
|
||||
|
||||
prj_counts = []
|
||||
for prj in prjs[1:]:
|
||||
prj = prj.strip()
|
||||
if len(prj) > 0:
|
||||
while prj.find(",")!=-1:
|
||||
prj = prj.replace(",","")
|
||||
print prj
|
||||
prj_counts.append(int(prj))
|
||||
print len(prj_counts)
|
||||
prjct = pd.Series(prj_counts)
|
||||
print prjct.describe()
|
||||
|
||||
# plt.xlabel("The number of publications",fontsize=10)
|
||||
plt.ylabel("The number of studied projects",fontsize=10)
|
||||
vp = plt.violinplot([math.log(item) for item in prjct], widths = 0.9, showmeans=False,showmedians=True)
|
||||
|
||||
plt.subplots_adjust(left=0.20,bottom=0.1,right=0.98,top=0.98)
|
||||
plt.savefig("../../resources/prj_numbers",dpi=200)
|
||||
plt.show()
|
||||
plt.close()
|
||||
|
||||
|
||||
def pr_sts():
|
||||
table = data.sheet_by_name('sheet1')
|
||||
prjs = table.col_values(9)
|
||||
|
||||
prj_counts = []
|
||||
for prj in prjs[1:]:
|
||||
print prj
|
||||
prj = prj.strip().lower()
|
||||
if len(prj) > 0:
|
||||
while prj.find(",")!=-1:
|
||||
prj = prj.replace(",","")
|
||||
while prj.find(" ")!=-1:
|
||||
prj = prj.replace(" ","")
|
||||
if prj == "2323 pairs" or prj=="2323pairs":
|
||||
prj = "4646"
|
||||
if prj.find("k") != -1:
|
||||
prj = prj.replace("k","000")
|
||||
print prj
|
||||
prj_counts.append(int(prj))
|
||||
print len(prj_counts)
|
||||
prjct = pd.Series(prj_counts)
|
||||
print prjct.describe()
|
||||
|
||||
# plt.xlabel("The number of publications",fontsize=10)
|
||||
plt.ylabel("The number of studied PRs",fontsize=10)
|
||||
vp = plt.violinplot([math.log(item) for item in prjct], widths = 0.9, showmeans=False,showmedians=True)
|
||||
|
||||
plt.subplots_adjust(left=0.20,bottom=0.1,right=0.98,top=0.98)
|
||||
plt.savefig("../../resources/pr_numbers",dpi=200)
|
||||
plt.show()
|
||||
plt.close()
|
||||
|
||||
if __name__ == "__main__":
|
||||
# prj_sts()
|
||||
pr_sts()
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 42 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 44 KiB |
Loading…
Reference in New Issue