Last active
January 31, 2017 15:28
-
-
Save wangkuiyi/50fb3094d476c47b6628d0e9ee7763da to your computer and use it in GitHub Desktop.
Issues by month -- Open Source Deep Learning Platforms
This file contains 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
project="paddlepaddle/paddle" | |
if [[ $# -ne 0 ]]; then | |
project=$1 | |
fi | |
file=${project/\//-} | |
> $file.issues | |
issues_per_page=25 | |
page=1 | |
until [ $issues_per_page -lt 25 ]; do | |
echo Parsing page: $page >&2 | |
url=$(printf 'https://github.com/%s/issues?page=%d' $project $page) | |
url=$url+'&q=is%3Aissue' | |
echo $url >&2 | |
issues_per_page=$(curl -s "$url" | grep 'relative-time' | sed "s/^.*datetime=\"\([^T]*\).*$/\1/" | tee -a $file.issues | wc -l) | |
if [[ $issues_per_page -eq 0 ]]; then | |
sleep 61 # work around the Github abuse detection mechanism. | |
issues_per_page=$(curl -s "$url" | grep 'relative-time' | sed "s/^.*datetime=\"\([^T]*\).*$/\1/" | tee -a $file.issues | wc -l) | |
fi | |
echo issues per page: $issues_per_page >&2 | |
let page=page+1 | |
sleep 2 # work around the Github abuse detection mechanism. | |
done | |
cat $file.issues | sort | cut -f1,2 -d '-' | uniq -c | gawk \ | |
'BEGIN { | |
year=2015; | |
month=6; | |
current=sprintf("%04d-%02d", year, month); | |
cum=0; | |
} | |
{ | |
while (current < $2) { | |
printf("%s-30,%d\n", current, cum); | |
month++; | |
if (month > 12) { | |
month=1; | |
year++; | |
} | |
current=sprintf("%04d-%02d", year, month); | |
} | |
if (current > $2) { | |
cum+=$1; | |
} | |
if (current == $2) { | |
cum+=$1; | |
printf("%s-30,%d\n", current, cum); | |
month++; | |
if (month > 12) { | |
month=1; | |
year++; | |
} | |
current=sprintf("%04d-%02d", year, month); | |
} | |
} | |
' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Above script can download all issues of an open source repo and count the cumulative number of issues by month. It outputs a .csv file that can be imported to Google Docs and be visualized there.
Here is an example that compares the number of issues of paddlepaddle/paddle and dmlc/mxnet. The figure was drawn using Google Docs is as follows:
To run the script with a Github repo, say dmlc/mxnet: