Renato Rocha Souza rsouza

Movies Recommendation:

MovieLens - Movie Recommendation Data Sets http://www.grouplens.org/node/73
Yahoo! - Movie, Music, and Images Ratings Data Sets http://webscope.sandbox.yahoo.com/catalog.php?datatype=r
Jester - Movie Ratings Data Sets (Collaborative Filtering Dataset) http://www.ieor.berkeley.edu/~goldberg/jester-data/
Cornell University - Movie-review data for use in sentiment-analysis experiments http://www.cs.cornell.edu/people/pabo/movie-review-data/

Music Recommendation:

	import hashlib as hasher
	import datetime as date

	# Define what a Snakecoin block is
	class Block:
	def __init__(self, index, timestamp, data, previous_hash):
	self.index = index
	self.timestamp = timestamp
	self.data = data
	self.previous_hash = previous_hash

	# -- coding: utf-8 --
	"""
	given a word and visualize near words
	original source code is https://github.com/nishio/mycorpus/blob/master/vis.py
	"""
	import word2vec_boostpython as w2v
	from sklearn.decomposition import PCA
	import matplotlib.pyplot as plt
	import matplotlib.font_manager

	#!/usr/bin/env python
	# encoding: utf-8
	"""
	linkedin-query.py

	Created by Thomas Cabrol on 2012-12-03.
	Customised by Rik Van Bruggen
	Copyright (c) 2012 dataiku. All rights reserved.

	Building the LinkedIn Graph

	// Word cloud layout by Jason Davies, http://www.jasondavies.com/word-cloud/
	// Algorithm due to Jonathan Feinberg, http://static.mrfeinberg.com/bv_ch03.pdf
	(function(exports) {
	function cloud() {
	var size = [256, 256],
	text = cloudText,
	font = cloudFont,
	fontSize = cloudFontSize,
	rotate = cloudRotate,
	padding = cloudPadding,

	# -- 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,

	# BM25F Model

	def bm25(idf, tf, fl, avgfl, B, K1):
	# idf - inverse document frequency
	# tf - term frequency in the current document
	# fl - field length in the current document
	# avgfl - average field length across documents in collection
	# B, K1 - free paramters

	return idf * ((tf * (K1 + 1)) / (tf + K1 * (1 - B + B * (fl / avgfl))))