fnielsen

wget https://dumps.wikimedia.org/other/pagecounts-all-sites/2015/2015-05/pagecounts-20150501-000000.gz

gzip -cd pagecounts-20150501-000000.gz | grep "^da " | perl -anle "print @F[2] . ' ' . @F[1] unless @F[1] =~ /(Bruger|Brugerdiskussion|da|Diskussion|Fil|Hj\%C3\%A6lp|Hj\%C3\%A6lp-diskussion|Kategori|Kategoridiskussion|MediaWiki|Portal|Skabelon|Skabelondiskussion|Speciel|Wikipedia|Wikipedia-diskussion):/i" | sort -nr | less

fnielsen

fnielsen

fnielsen

s = u"""DTU course 02819 is taught by Mr. Finn Årup Nielsen,
Ph.D. Some of aspects of the course are: machine learning and web
2.0. The telephone to Finn is (+45) 4525 3921, and his email is
[email protected]. A book published by O'Reilly called 'Programming
Collective Intelligence' might be useful. It costs $39.99 or 285.00
kroner in Polyteknisk Boghandle. Is 'Text Processing in Python'
appropriate for the course? Perhaps! The constructor function in
Python is called "__init__()". fMRI will not be a topic of the
course."""  

fnielsen

from collections import Counter
from nltk.corpus import brown
from pytagcloud import create_tag_image, make_tags
from PIL import Image

# Developed from https://pypi.python.org/pypi/pytagcloud
create_tag_image(make_tags(Counter(brown.words()).most_common(150), maxsize=300), 'cloud.png', size=(900, 600), fontname='Lobster')

Image.open('cloud.png').show()

fnielsen

fnielsen

fnielsen

fnielsen

import re
import requests
import pandas as pd
import matplotlib.pyplot as plt

pd.Series({re.findall('^(.+)\n', section)[0]: len(re.findall('^\*', section, flags=re.MULTILINE)) for section in re.split('^##[^#]', requests.get('https://raw.githubusercontent.com/josephmisiti/awesome-machine-learning/master/README.md').text, flags=re.MULTILINE)[1:-1]}).plot(kind='barh', title="'Awesome' machine learning links")

plt.show()

fnielsen

from math import exp
import numpy as np
import matplotlib.pyplot as plt


def sigmoid(x):
    return 1.0 / (1.0 + exp(-x))


def implication(a, b):