andreasvc

--- tiger_release_aug07.corrected.16012013.xml  2013-01-16 16:35:23.000000000 +0100
+++ tiger_2.2a.xml      2013-11-03 00:02:12.890306125 +0100
@@ -3097934,7 +3097934,6 @@
       <nt id="s46234_505" cat="PP">
         <edge label="AC" idref="s46234_24" />
         <edge label="NK" idref="s46234_25" />
-        <edge label="CJ" idref="s46234_135" />
       </nt>
       <nt id="s46234_506" cat="PP">
         <edge label="AC" idref="s46234_30" />

andreasvc

""" Run a set of XPath queries on a corpus of parse trees and compute precision
and recall with respect to a set of hand-picked sentences. """

from __future__ import print_function
import io
import os
import glob
import nltk
import alpinocorpus

andreasvc

""" Generate image with plot & rating for each movie in a directory. """
from __future__ import print_function
import os
import re
import sys
import glob
import json
import time
import urllib
import textwrap

andreasvc

""" Compare different strategies for adding a large number of small log
probabilities. """
from __future__ import print_function
from math import log, exp, fsum, isinf
from random import expovariate

N = 10000


def logprobadd(x, y):

andreasvc

""" Match lines in one file with those of another,
and produce line numbers. """
import io
import sys

USAGE = """Match lines in one file with those of another, and get line numbers.
usage: python %s sents text output
where sents and text are files with one sentence per line.
The result will be of the form "1|line", written to file "output".
Everything is assumed to be encoded with UTF-8.""" % sys.argv[0]

andreasvc

def cartpi(seq):
  """ A depth-first cartesian product for a sequence of iterables;
  i.e., all values of the last iterable are consumed before advancing the
  preceding ones. Like itertools.product(), but supports infinite sequences.

  >>> from itertools import islice, count
  >>> list(islice(cartpi([count(), count()]), 9))
  [(0, 0), (0, 1), (0, 2), (0, 3), (0, 4), (0, 5), (0, 6), (0, 7), (0, 8)]
  """
  if seq:

andreasvc

cdef extern from "macros.h":
    # test whether the b'th bit of array a is set:
    unsigned long TESTBIT(unsigned long a[], int b)

cdef unsigned long foo[2]
foo[0] = 281474976710656UL
foo[1] = 0

# what the macro does:
print foo[0] & (1UL << 48)

andreasvc

andreasvc

import sys, collections
def rotations(a):
    return {a[x:] + a [:x] for x in range(1, len(a))}

lexicon = collections.defaultdict(set)
for a in open(sys.argv[1]):
    lexicon[len(a) - 1].add(a.strip())
for length in sorted(lexicon):
    if length == 1:
        continue

andreasvc

The D 1 D@1-1 1 D@0-1 1
dog N 0.5   N@0-2 1
cat N@1-2 1 N 0.5
barks   V 0.5   V@0-4 1
meows   V 0.5   V@1-4 1
loudly  RB 1    RB@0-5 1    RB@1-5 1