fnielsen

xs = [ float(i)/64.0 for i in range(-150, 41) ]
ys = [ float(i)/16.0 for i in range(-25,26) ]
for y in ys: 
    s = ''
    for x in xs:
        z = 0j; i = 0
        while i < 10:
            z = z**2 + x+y*1j
            if abs(z) > 2: 
                break   # Get out of inner loop

fnielsen

documents = [ dict(
            email=open("conference/%d.txt" % n).read().strip(), 
            category='conference') for n in range(1,372) ]
documents.extend([ dict( 
            email=open("job/%d.txt" % n).read().strip(),
            category='job') for n in range(1,275)])
documents.extend([ dict( 
            email=open("spam/%d.txt" % n).read().strip(), 
            category='spam') for n in range(1,799) ])

fnielsen

import matplotlib.pyplot as plt
import networkx as nx
from pysqlite2 import dbapi2

connection = dbapi2.Connection('bredewiki-templates.sqlite3')
sql = "SELECT DISTINCT pid FROM brede WHERE (template='paper' OR template='conference_paper');"
cursor = connection.cursor()
cursor.execute(sql)
pids = [ row[0] for row in cursor.fetchall() ]

fnielsen

# wget http://neuro.imm.dtu.dk/services/bredewiki/download/bredewiki-templates.sqlite3
import matplotlib.pyplot as plt
import networkx as nx
from pysqlite2 import dbapi2

connection = dbapi2.Connection('bredewiki-templates.sqlite3')
sql = "SELECT DISTINCT tid FROM brede WHERE (template='paper' OR template='conference_paper');"
cursor = connection.cursor()
cursor.execute(sql)
tids = [ row[0] for row in cursor.fetchall() ]

fnielsen

# wget http://neuro.imm.dtu.dk/services/bredewiki/download/bredewiki-templates.sqlite3
import matplotlib.pyplot as plt
import networkx as nx
from pysqlite2 import dbapi2

connection = dbapi2.Connection('bredewiki-templates.sqlite3')
sql = "SELECT DISTINCT tid FROM brede WHERE (template='paper' OR template='conference_paper');"
cursor = connection.cursor()
cursor.execute(sql)
tids = [ row[0] for row in cursor.fetchall() ]

fnielsen

# Code inspired and developed from: 
# http://streamhacker.com/2010/05/10/text-classification-sentiment-analysis-naive-bayes-classifier/

from __future__ import division
import nltk.classify, nltk.corpus, nltk.classify.util
from pylab import *

filebase = '/home/fn'

fnielsen

import urllib, urllib2
import simplejson as json
import dateutil.parser
import datetime
import matplotlib.dates
import matplotlib.finance
from matplotlib import pyplot as plt
import nltk.corpus 
import numpy as np
import re

fnielsen

# $Id: Nielsen2012Python_case.py,v 1.2 2012/09/02 16:55:25 fn Exp $

# Define a url as a Python string (note we are only getting 100 documents)
url = "http://wikilit.referata.com/" + \
    "wiki/Special:Ask/" + \
    "-5B-5BCategory:Publications-5D-5D/" + \
    "-3FHas-20author%3DAuthor(s)/-3FYear/" + \
    "-3FPublished-20in/-3FAbstract/-3FHas-20topic%3DTopic(s)/" + \
    "-3FHas-20domain%3DDomain(s)/" +  \
    "format%3D-20csv/limit%3D-20100/offset%3D0"

fnielsen

# python2.6

'Finn Årup Nielsen'

u'Finn Årup Nielsen'

unicode('Finn Årup Nielsen', 'utf-8')


# So what is wrong with that?}

fnielsen

#!/usr/bin/python

import math, sys                  #  Importing modules.

def formatresult(res):            # Define function. Remember colon!
    """This is the documentation for a function."""
    return "The result is %f" % res  # Percentage for formating

if len(sys.argv) < 3:              # Conditionals should be indended
    print("Too few input argument")