sangheestyle

import os
import json
import sys
from multiprocessing import Pool
from subprocess import call, check_output
from datetime import datetime, date, timedelta
from time import sleep
import github3 as github

"""

sangheestyle

import logging
import os
import zipfile
import multiprocessing
from subprocess import call

from gensim.corpora.textcorpus import TextCorpus
from gensim.corpora import Dictionary, MmCorpus
from gensim.models import TfidfModel
from gensim import utils

sangheestyle

scratchpad

sangheestyle

import os
from subprocess import check_output, CalledProcessError


def get_repo_paths(root=None):
    repo_paths = []
    for dir, _, _ in os.walk(root):
        if dir.endswith('/.git'):
            repo_paths.append(dir[:-5])
    return repo_paths

sangheestyle

from json import JSONEncoder

class MyEncoder(JSONEncoder):
    def default(self, o):
        temp = o.__dict__
        a = dict()
        for k, v in temp.iteritems():
            if v is not None:
                if type(v) is list:
                    v = [x for x in v if x is not None]

sangheestyle

Install NVidia driver

During installing debian, you need to set CMS disable at your BIOS menu. Also after installing done, press e on grub(recovery mode) and modify following line, and then press F10.

Go to linux line and then add following value

nouveau.modeset=0

sangheestyle

This scratch is for analyzing developers' relationship by analyzing commits such as same chunk modification.

sangheestyle

$ git log --grep="fix" --no-merges --format="%ae" | awk '{a[$0]++} END{for (i in a) if (a[i]>1) printf "%5.2f%%\t%s\n", 100*a[i]/NR, i}'| sort -nr
50.00%	[email protected]
21.43%	[email protected]
14.29%	[email protected]
 7.14%	[email protected]
$ git log --no-merges --format="%ae" | awk '{a[$0]++} END{for (i in a) if (a[i]>1) printf "%5.2f%%\t%s\n", 100*a[i]/NR, i}'| sort -nr
40.78%	[email protected]
22.57%	[email protected]
 6.53%	[email protected]
 2.52%	[email protected]

sangheestyle

Install Pandas on Debian from the scratch

a. install requirements

$ sudo apt-get install python-numpy python-scipy
$ sudo apt-get install libopenblas-base libatlas3-base

b. set symbolic link of libblas.so.3 and liblapack.so.3. This step affects performance of Numpy, Scipy, and Pandas. Check which implementation is better. Of course, it can spoil installing pandas with pip.

sangheestyle

from os import listdir, stat, sys
from os.path import isfile, join, basename
import time
import multiprocessing
import json
import networkx as nx
from sklearn.utils.graph import graph_shortest_path as gsp


def get_file_paths(root):