kljensen

# -*- coding: utf-8 -*-
""" Small script that shows hot to do one hot encoding
    of categorical columns in a pandas DataFrame.

    See:
    http://scikit-learn.org/dev/modules/generated/sklearn.preprocessing.OneHotEncoder.html#sklearn.preprocessing.OneHotEncoder
    http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.DictVectorizer.html
"""
import pandas
import random

kljensen

"""
 If you're using Celery with the gevent worker and a Flask app,
 you may have noticed that you're unsuccessful in having the 
 tasks execute within your Flask app's app_context.  Normally,
 you can do this
 
 with app.app_context():
   celery.start()

 ...but...doesn't appear to work with the gevent worker pool.

kljensen

# First, find your broadcast address
#
ifconfig

# - Should return something like the below, where 192.168.1.255 is
# - the broadcast address
# -
# - eth0      Link encap:Ethernet  HWaddr b8:27:eb:19:c6:01  
# -           inet addr:192.168.1.109  Bcast:192.168.1.255  Mask:255.255.255.0
# -           UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1

kljensen

# If you want maximum shared memory of 1/5 of your RAM,
# leave FRACTION as 5
FRACTION=5
RAM=`cat /proc/meminfo|grep ^MemTotal|awk '{printf("%.f", $2*1024)}'`
SHMMAX=`echo "$RAM / $FRACTION" |bc`
PAGESIZE=`getconf PAGESIZE`
SHMALL=`echo "$SHMMAX / $PAGESIZE" |bc`

sudo sysctl -w kernel.shmmax=$SHMMAX
sudo sysctl -w kernel.shmall=$SHMALL

kljensen

#!/usr/bin/env bash

##########################################################
#
# This is a shell script for keeping a journal that is
#   * plaintext,
#   * time-stamped,
#   * encrypted, and
#   * edited with vim.
#

kljensen

GITX="/Applications/GitX.app/Contents/Resources/gitx"
if [[ -x  $GITX ]]; then
	gitx() { 
		if [[ ($# -eq 1) && ($1 != "-"*) ]]; then
			# If a single arg is given, assume that
			# arg is the directory to open.
			$GITX --git-dir=$1
		else
			# Otherwise pass args to gitx.
			$GITX "$@"

kljensen

autoload -Uz vcs_info
zstyle ':vcs_info:*' check-for-changes true
zstyle ':vcs_info:*' enable git svn hg

### git: Show marker (T) if there are untracked files in repository
# Make sure you have added staged to your 'formats':  %c
function +vi-git-untracked(){
    if [[ $(git rev-parse --is-inside-work-tree 2> /dev/null) == 'true' ]] && \
        git status --porcelain | grep '??' &> /dev/null ; then

kljensen

#!/usr/bin/env python
# encoding: utf-8
"""
fingerprint_cluster.py
Based on http://code.google.com/p/google-refine/wiki/ClusteringInDepth
Created by Kyle Jensen on 2010-12-15.
"""

import re

kljensen

# Make a new virtual env
# named ninjakitten
mkvirtualenv ninjakitten
cdvirtualenv

# Install readline binary
easy_install -a readline

# Install ipython
pip install -E . ipython

kljensen

class HighBaseEncoder(object):
    """docstring for HighBaseEncoder
       http://stackoverflow.com/questions/1119722/base-62-conversion-in-python
    """

    def __init__(self):
        super(HighBaseEncoder, self).__init__()
        
    ALPHABET = "23456789abcdefghijkmnpqrstuvwxyzABCDEFGHJKLMNPQRSTUVWXYZ"