stucchio

from matplotlib import use

from pylab import *
from scipy.stats import beta, norm, uniform
from random import random
from numpy import *
import numpy as np
import os

# Input data

rjurney

register /me/Software/elephant-bird/pig/target/elephant-bird-pig-3.0.6-SNAPSHOT.jar
register /me/Software/pig/build/ivy/lib/Pig/json-simple-1.1.jar
set elephantbird.jsonloader.nestedLoad 'true'

set default_parallel 4

/* Remove files from previous runs */
rmf /tmp/prior_words.txt
rmf /tmp/prior_genres.txt
rmf /tmp/p_word_given_genre.txt

rjurney

DEFINE tf_idf(token_records, id_field, token_field) RETURNS out_relation {
   
  /* Calculate the term count per document */
  doc_word_totals = foreach (group $token_records by ($id_field, $token_field)) generate 
    FLATTEN(group) as ($id_field, token), 
    COUNT_STAR($token_records) as doc_total;
 
  /* Calculate the document size */
  pre_term_counts = foreach (group doc_word_totals by $id_field) generate
    group AS $id_field,

greeness

cat mysql-statement
> insert into mytable (k, v) values (1,2);
> insert into mytable (k, v) values (2,2);
> insert into mytable (k, v) values (3,2);
 
scp mysql-statement to an ec2 machine
ssh to the ec2 machine
 
$ mysql -h hostname -u username -p password database_name < mysql-statement

greeness

http://danzambonini.com/self-improving-bayesian-sentiment-analysis-for-twitter/

http://www.laurentluce.com/posts/twitter-sentiment-analysis-using-python-and-nltk/

[PDF] 
Sentiment Analysis of Twitter Data - Department of Computer ...
www.cs.columbia.edu/~julia/papers/Agarwaletal11.pdf

catawbasam

# -*- coding: utf-8 -*-
"""
LICENSE: BSD (same as pandas)
example use of pandas with oracle mysql postgresql sqlite
    - updated 9/18/2012 with better column name handling; couple of bug fixes.
    - used ~20 times for various ETL jobs.  Mostly MySQL, but some Oracle. 

    to do:  
            save/restore index (how to check table existence? just do select count(*)?), 
            finish odbc, 

mbostock

license: gpl-3.0