This gist is part of a blog post. Check it out at:
http://jasonrudolph.com/blog/2011/08/09/programming-achievements-how-to-level-up-as-a-developer
""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" | |
" => General | |
""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" | |
" Sets how many lines of history VIM has to remember | |
set history=300 | |
" Enable filetype plugin | |
filetype plugin on | |
filetype indent on |
#!/usr/bin/env python2 | |
from nltk.corpus.reader import TaggedCorpusReader | |
from nltk.tokenize import RegexpTokenizer | |
from shogun.Kernel import CommUlongStringKernel | |
from shogun.Features import StringUlongFeatures, StringCharFeatures, RAWBYTE | |
from shogun.PreProc import SortUlongString | |
from scikits.learn.cluster import affinity_propagation | |
import numpy as np | |
def read_reviews(): |
import XMonad | |
import Data.List | |
import XMonad.Hooks.ManageHelpers | |
import XMonad.Util.EZConfig | |
import XMonad.Config.Gnome | |
import XMonad.Config.Desktop (desktopLayoutModifiers) | |
import XMonad.Layout.NoBorders (smartBorders) | |
import XMonad.Layout.PerWorkspace (onWorkspace) | |
import XMonad.Layout.CenteredMaster (centerMaster) | |
import XMonad.Layout.SimpleFloat (simpleFloat) |
#!/usr/bin/env python2 | |
import random | |
import nltk | |
from sklearn.linear_model import LogisticRegression | |
import numpy as np | |
from sklearn.feature_extraction.text import CountVectorizer | |
from nltk.corpus import movie_reviews | |
documents = [(movie_reviews.raw(fileid), category) |
from sklearn.datasets import load_svmlight_file | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.svm.sparse import LinearSVC | |
from sklearn.cross_validation import StratifiedKFold | |
from sklearn import metrics | |
import numpy as np | |
X, y = load_svmlight_file("fr.vec") | |
y[y == -1] = 0 | |
kf = StratifiedKFold(y, k = 10, indices=True) |
from sklearn.datasets import load_svmlight_file | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.cross_validation import StratifiedKFold | |
from sklearn import metrics | |
X, y = load_svmlight_file("mpqa_en.vec") | |
kf = StratifiedKFold(y, k = 10, indices=True) | |
clf = MultinomialNB() | |
for train_index, test_index in kf: | |
X_train, X_test = X[train_index], X[test_index] | |
y_train, y_test = y[train_index], y[test_index] |
from sklearn.naive_bayes import EMNB, MultinomialNB, BernoulliNB | |
from sklearn.cross_validation import KFold | |
from sklearn.datasets import load_svmlight_file | |
from scipy.sparse import vstack | |
import numpy as np | |
X, y = load_svmlight_file("mpqa_en.vec") | |
y = np.asarray(y, np.int32) | |
n_labeled = int(0.8 * X.shape[0]) | |
X_labeled = X[:n_labeled] |
"""http://stackoverflow.com/questions/6282432/load-sparse-array-from-npy-file | |
""" | |
import random | |
import scipy.sparse as sparse | |
import scipy.io | |
import numpy as np | |
def save_sparse_matrix(filename, x): | |
x_coo = x.tocoo() | |
row = x_coo.row |
This gist is part of a blog post. Check it out at:
http://jasonrudolph.com/blog/2011/08/09/programming-achievements-how-to-level-up-as-a-developer
#encoding:utf-8 | |
from java.io import FileInputStream | |
from java.io import ObjectInputStream | |
import sys | |
jarfiles = ["/opt/lingpipe-segmenter/lingpipe-4.0.1.jar", "/opt/lingpipe-segmenter/zhToksDemo.jar"] | |
for jar in jarfiles: | |
if jar not in sys.path: | |
sys.path.append(jar) |