gistfile1.py

import pandas
import urllib2

feature_names_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.names'
feature_names = [
    line.strip().split(':')[0] 
    for line in urllib2.urlopen(feature_names_url).readlines()[33:]
]

spam_data = pandas.read_csv(
    'https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.data',
    header=None, names=(feature_names + ['spam'])
)

X, y = spam_data.ix[:, :-1].values, spam_data.ix[:, -1].values

spam_data.head()