sangheestyle

#!/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 ..

sangheestyle

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))):

sangheestyle

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:

sangheestyle

nothing

sangheestyle

# 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

sangheestyle

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

sangheestyle

# origin: http://stackoverflow.com/questions/24662006/python-networkx-graph-different-colored-nodes-using-two-lists
## assign a node attribute, which I am going to color according to
for node in G.nodes():
    G.node[node]['category'] = my_category_dict[node]
## put together a color map, one color for a category
color_map = {'type_A':'b', 'type_B':'#FF0099', 'type_C':'#660066'} 
## construct a list of colors then pass to node_color
nx.draw(G, node_color=[color_map[G.node[node]['category']] for node in G])
plt.show()

sangheestyle

import csv

with open('ps03-4.csv','rb') as file:
    contents = csv.reader(file)
    matrix = list()
    for row in contents:
        matrix.append(row)

sangheestyle

from collections import defaultdict
from nltk.corpus import brown

print ">>> Procssing"
word_tag = defaultdict(set)
for word, tag in brown.tagged_words():
    word_tag[word].add(tag)

num_words_by_num_tags = defaultdict(int)
words_with_max_tags = [None, 0]

sangheestyle

words1 = "pa’Daq ghah taH tera’ngan ’e".replace("’","'").split()
tags1 = "N PRO V N PRO".split()

words2 = "ja’chuqmeH rojHom neH tera’ngan".replace("’","'").split()
tags2 = "V N V N".split()

words3 = "tera’ngan qIp puq ’eg puq qIp tera’ngan".replace("’","'").split()
tags3 = "N V N CONJ N V N".split()

train = []