sanealytics

# coding=UTF-8
from __future__ import division
import nltk
from collections import Counter

# This is a simple tool for adding automatic hashtags into an article title
# Created by Shlomi Babluki
# Sep, 2013

sanealytics

recommenderRegistry$get_entries(dataType = "realRatingMatrix")
# We have a few options

# Let's check some algorithms against each other
scheme <- evaluationScheme(MovieLense, method = "split", train = .9,
                           k = 1, given = 10, goodRating = 4)

scheme

algorithms <- list(

sanealytics

# What is the mean rating of each movie
qplot(colMeans(MovieLense), binwidth = .1, 
      main = "Mean rating of Movies", 
      xlab = "Rating", 
      ylab = "# of movies")

# The big spike on 1 suggests that this could also be intepreted as binary
# In other words, some people don't want to see certain movies at all.
# Same on 5 and on 3.
# We will give it the binary treatment later

sanealytics

# How many movies did people rate on average
qplot(rowCounts(MovieLense), binwidth = 10, 
      main = "Movies Rated on average", 
      xlab = "# of users", 
      ylab = "# of movies rated")
# Seems people get tired of rating movies at a logarithmic pace. But most rate some.

sanealytics

# How about after normalization?
qplot(getRatings(normalize(MovieLense, method = "Z-score")),
      main = "Histogram of normalized ratings", xlab = "Rating") 
summary(getRatings(normalize(MovieLense, method = "Z-score"))) # seems better
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# -4.8520 -0.6466  0.1084  0.0000  0.7506  4.1280 

sanealytics

# Visualizing ratings
qplot(getRatings(MovieLense), binwidth = 1, 
      main = "Histogram of ratings", xlab = "Rating")
summary(getRatings(MovieLense)) # Skewed to the right
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# 1.00    3.00    4.00    3.53    4.00    5.00

sanealytics

# Load required library
library(recommenderlab) # package being evaluated
library(ggplot2) # For plots

# Load the data we are going to work with
data(MovieLense)
MovieLense
# 943 x 1664 rating matrix of class ‘realRatingMatrix’ with 99392 ratings.

# Visualizing a sample of this