| OK, here is what you should do to use python pandas on Debian Wheezy, | |
| Step 1: Make a bootable image with usb key | |
| a. Get a usb key | |
| b. Download debian live ISO image (recommend xfce integrated image) | |
| c. Make a usb key as a ISO boot image (recommend using dd) | |
| Step 2: Install & Boot | |
| d. Boot up your machine with Debian usb key (recommend UEFI) | |
| e. Do configuration |
| # Reference: | |
| # http://networkx.github.io/documentation/networkx-1.9.1/ | |
| # reference/algorithms.centrality.html | |
| import operator | |
| import networkx as nx | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import itertools |
| nothing |
| import os | |
| import json | |
| summary_folder = "summary" | |
| summary = {} | |
| for path in os.listdir(summary_folder): | |
| path_summary = json.load(open(os.path.join(summary_folder, path), "r")) | |
| if not len(summary): | |
| summary = path_summary | |
| else: |
| import sys | |
| import json | |
| from os import listdir | |
| from os.path import isfile, join, basename | |
| def get_file_paths(root): | |
| file_paths = [] | |
| for f in listdir(root): | |
| if isfile((join(root, f))): |
| #!/bin/bash | |
| mkdir sssp | |
| cd sssp | |
| curl "https://dl.dropboxusercontent.com/u/7571776/facebook100_txt_only.zip" -o "facebook100_txt_only.zip" | |
| unzip facebook100_txt_only.zip | |
| curl https://gist.githubusercontent.com/sangheestyle/6335b209b4779dddc5ac/raw/47a803d6ccfa727efb80d5c32f5e7361d32c861a/ps16c.py > ps16c.py | |
| mkdir out | |
| python ps16c.py facebook100txt $1 $2 | |
| cd .. |
| 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): |
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.
| $ 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] |
This scratch is for analyzing developers' relationship by analyzing commits such as same chunk modification.