a-paxton

# preliminaries
from pymongo import MongoClient
from nltk.corpus import stopwords
from string import ascii_lowercase
import pandas as pd
import gensim, os, re, pymongo, itertools, nltk, snowballstemmer

# set the location where we'll save our model
savefolder = '/data'

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

stulacy

"""
    MAUCpy
    ~~~~~~

    Contains two equations from Hand and Till's 2001 paper on a multi-class
    approach to the AUC. The a_value() function is the probabilistic approximation
    of the AUC found in equation 3, while MAUC() is the pairwise averaging of this
    value for each of the classes. This is equation 7 in their paper.
"""

jkbradley

/*
This example uses Scala.  Please see the MLlib documentation for a Java example.

Try running this code in the Spark shell.  It may produce different topics each time (since LDA includes some randomization), but it should give topics similar to those listed above.

This example is paired with a blog post on LDA in Spark: http://databricks.com/blog
Spark: http://spark.apache.org/
*/

import scala.collection.mutable

tokestermw

import json
import urlparse
from itertools import chain
flatten = chain.from_iterable

from nltk import word_tokenize

from gensim.corpora import Dictionary
from gensim.models.ldamodel import LdaModel
from gensim.models.tfidfmodel import TfidfModel

shanebutler

# sql.export.rf(): save a randomForest model as SQL
# v0.04
# Copyright (c) 2013-2014 Shane Butler <shane dot butler at gmail dot com>
# 
# sql.export.rf is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 2 of the License, or
# (at your option) any later version.
#
# sql.export.rf is distributed in the hope that it will be useful, but

erogol

def linear_model_ensemble(X, y, X_test, fold_num, fold_num_sec, grid_search_range, oobe=True, x_val=True ):

      '''
      X         - Train set 
    
      y         - Train set labels with. Labels are 1 for pos instances and -1 for neg instances
    
      fold_num1 - Fold size for the first step X-validation to set the hyper-params
                and feature selectors
    

shanebutler

# sql.export.gbm(): save a GBM model as SQL
# v0.11
# Copyright (c) 2013-2014 Shane Butler <shane dot butler at gmail dot com>
# 
# sql.export.gbm is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 2 of the License, or
# (at your option) any later version.
#
# sql.export.gbm is distributed in the hope that it will be useful, but

iamatypeofwalrus

What

Roll your own iPython Notebook server with Amazon Web Services (EC2) using their Free Tier.

What are we using? What do you need?

• An active AWS account. First time sign-ups are eligible for the free tier for a year
• One Micro Tier EC2 Instance
• With AWS we will use the stock Ubuntu Server AMI and customize it.
• Anaconda for Python.
• Coffee/Beer/Time

justinvw

# Delete the possibly existing autocomplete test index
curl -X DELETE localhost:9200/autocomplete_test

# Put the config of the autocomplete index
curl -X PUT localhost:9200/autocomplete_test -d '
{
  "settings" : {
    "index" : {
      "analysis" : {
        "analyzer" : {