mikejs

import os

try:
    from pypy.rlib.jit import JitDriver, purefunction, hint
except ImportError:
    # If pypy isn't importable then (presumably) we're not being translated,
    # so make JIT stuff no-ops.
    class JitDriver(object):
        def __init__(self, **kwargs):
            pass

mikejs

#!/bin/bash
mkdir merged
for f in "$@"
do
    if [ -f merged/merged.shp ]
    then
        ogr2ogr -f "esri shapefile" -update -append merged/merged.shp $f -nln Merged
    else
        ogr2ogr -f "esri shapefile" merged/merged.shp $f    
    fi

mikejs

def pagerank(matrix, d_factor=0.85):
    """
    Calculate the pagerank vector of a given adjacency matrix (using
    the power method).

    :param matrix: an adjacency matrix
    :param d_factor: the damping factor
    """
    size = len(matrix)
    epsilon = 0.0001

mikejs

from mongrel2.config import *

main = Server(
    uuid="cb69cc4f-59d0-4cdb-aefe-4dcbe83f4682",
    access_log="/logs/access.log",
    error_log="/logs/error.log",
    chroot="./",
    default_host="mikej.st",
    name="main",
    pid_file="/run/mongrel2.pid",

mikejs

# ddg -h
Usage: ddg [options] query

Options:
  --version   show program's version number and exit
  -h, --help  show this help message and exit
  -o, --open  open results in a browser
  -n N        number of results to show
  -d D        disambiguation choice

mikejs

# Check that nltk and strfry produce same levenshtein distance on
# a bunch of randomly generated strings
import strfry
import nltk.metrics
import random

for i in xrange(0, 10000):
    a = ''.join([chr(random.randint(1, 255)) for x in xrange(0, random.randint(0, 20))])
    b = ''.join([chr(random.randint(1, 255)) for x in xrange(0, random.randint(0, 20))])

mikejs

# Levenshtein Distance:
# NLTK: 446.74 usec/call
# strfry: 1.86 usec/call

import timeit

nltk_lev = timeit.Timer(stmt="nltk.metrics.edit_distance('this is a string', 'this is another string')",
                  setup="import nltk.metrics")

str_lev = timeit.Timer(stmt="strfry.levenshtein_distance('this is a string', 'this is another string')",

mikejs

import unicodedata

from pymongo.son import SON
from pymongo.son_manipulator import SONManipulator


class NormalizeUnicode(SONManipulator):
    def __init__(self, form="NFKD"):
        self.__form = form

mikejs

train <- read.csv("~/code/informs/TrainingData.csv", row.names=1, header=TRUE)
test <- read.csv("~/code/informs/ResultData.csv", row.names=1, header=TRUE)

for (col in c("Variable142OPEN", "Variable142LOW", "Variable142HIGH",
              "Variable142LAST", "Variable158OPEN", "Variable158LOW",
              "Variable158HIGH", "Variable158LAST")) {
  train[col] <- NULL
  test[col] <- NULL
}
train[is.na(train)] <- 0.0

mikejs

# Replace all of the lxml cssselect calls in a python script with
# equivalent xpath calls.
import re
import sys
import lxml.cssselect


def cssselect_replace(match):
    xpath = lxml.cssselect.css_to_xpath(match.group(2))
    xpath = xpath.replace("'", "\\'").replace('"', '\\"')