%% Machine Learning Online Class
% Exercise 8 | Anomaly Detection and Collaborative Filtering
%
% Instructions
% ------------
%
% This file contains code that helps you get started on the
% exercise. You will need to complete the following functions:
%
% estimateGaussian.m
% selectThreshold.m
% cofiCostFunc.m
%
% For this exercise, you will not need to change any code in this file,
% or any other files other than those mentioned above.
%
%% Initialization
clear ; close all; clc
%% ================== Part 1: Load Example Dataset ===================
% We start this exercise by using a small dataset that is easy to
% visualize.
%
% Our example case consists of 2 network server statistics across
% several machines: the latency and throughput of each machine.
% This exercise will help us find possibly faulty (or very fast) machines.
%
fprintf('Visualizing example dataset for outlier detection.nn');
% The following command loads the dataset. You should now have the
% variables X, Xval, yval in your environment
load('ex8data1.mat');
% Visualize the example dataset
plot(X(:, 1), X(:, 2), 'bx');
axis([0 30 0 30]);
xlabel('Latency (ms)');
ylabel('Throughput (mb/s)');
fprintf('Program paused. Press enter to continue.n');
pause
%% ================== Part 2: Estimate the dataset statistics ===================
% For this exercise, we assume a Gaussian distribution for the dataset.
%
% We first estimate the parameters of our assumed Gaussian distribution,
% then compute the probabilities for each of the points and then visualize
% both the overall distribution and where each of the points falls in
% terms of that distribution.
%
fprintf('Visualizing Gaussian fit.nn');
% Estimate my and sigma2
[mu sigma2] = estimateGaussian(X);
% Returns the density of the multivariate normal at each data point (row)
% of X
p = multivariateGaussian(X, mu, sigma2);
% Visualize the fit
visualizeFit(X, mu, sigma2);
xlabel('Latency (ms)');
ylabel('Throughput (mb/s)');
fprintf('Program paused. Press enter to continue.n');
pause;
%% ================== Part 3: Find Outliers ===================
% Now you will find a good epsilon threshold using a cross-validation set
% probabilities given the estimated Gaussian distribution
%
pval = multivariateGaussian(Xval, mu, sigma2);
[epsilon F1] = selectThreshold(yval, pval);
fprintf('Best epsilon found using cross-validation: %en', epsilon);
fprintf('Best F1 on Cross Validation Set: %fn', F1);
fprintf(' (you should see a value epsilon of about 8.99e-05)n');
fprintf(' (you should see a Best F1 value of 0.875000)nn');
% Find the outliers in the training set and plot the
outliers = find(p < epsilon);
% Draw a red circle around those outliers
hold on
plot(X(outliers, 1), X(outliers, 2), 'ro', 'LineWidth', 2, 'MarkerSize', 10);
hold off
fprintf('Program paused. Press enter to continue.n');
pause;
%% ================== Part 4: Multidimensional Outliers ===================
% We will now use the code from the previous part and apply it to a
% harder problem in which more features describe each datapoint and only
% some features indicate whether a point is an outlier.
%
% Loads the second dataset. You should now have the
% variables X, Xval, yval in your environment
load('ex8data2.mat');
% Apply the same steps to the larger dataset
[mu sigma2] = estimateGaussian(X);
% Training set
p = multivariateGaussian(X, mu, sigma2);
% Cross-validation set
pval = multivariateGaussian(Xval, mu, sigma2);
% Find the best threshold
[epsilon F1] = selectThreshold(yval, pval);
fprintf('Best epsilon found using cross-validation: %en', epsilon);
fprintf('Best F1 on Cross Validation Set: %fn', F1);
fprintf(' (you should see a value epsilon of about 1.38e-18)n');
fprintf(' (you should see a Best F1 value of 0.615385)n');
fprintf('# Outliers found: %dnn', sum(p < epsilon));
ex8_cofi.m
代码语言：javascript复制
%% Machine Learning Online Class
% Exercise 8 | Anomaly Detection and Collaborative Filtering
%
% Instructions
% ------------
%
% This file contains code that helps you get started on the
% exercise. You will need to complete the following functions:
%
% estimateGaussian.m
% selectThreshold.m
% cofiCostFunc.m
%
% For this exercise, you will not need to change any code in this file,
% or any other files other than those mentioned above.
%
%% =============== Part 1: Loading movie ratings dataset ================
% You will start by loading the movie ratings dataset to understand the
% structure of the data.
%
fprintf('Loading movie ratings dataset.nn');
% Load data
load ('ex8_movies.mat');
% Y is a 1682x943 matrix, containing ratings (1-5) of 1682 movies on
% 943 users
%
% R is a 1682x943 matrix, where R(i,j) = 1 if and only if user j gave a
% rating to movie i
% From the matrix, we can compute statistics like average rating.
fprintf('Average rating for movie 1 (Toy Story): %f / 5nn', ...
mean(Y(1, R(1, :))));
% We can "visualize" the ratings matrix by plotting it with imagesc
imagesc(Y);
ylabel('Movies');
xlabel('Users');
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ============ Part 2: Collaborative Filtering Cost Function ===========
% You will now implement the cost function for collaborative filtering.
% To help you debug your cost function, we have included set of weights
% that we trained on that. Specifically, you should complete the code in
% cofiCostFunc.m to return J.
% Load pre-trained weights (X, Theta, num_users, num_movies, num_features)
load ('ex8_movieParams.mat');
% Reduce the data set size so that this runs faster
num_users = 4; num_movies = 5; num_features = 3;
X = X(1:num_movies, 1:num_features);
Theta = Theta(1:num_users, 1:num_features);
Y = Y(1:num_movies, 1:num_users);
R = R(1:num_movies, 1:num_users);
% Evaluate cost function
J = cofiCostFunc([X(:) ; Theta(:)], Y, R, num_users, num_movies, ...
num_features, 0);
fprintf(['Cost at loaded parameters: %f '...
'n(this value should be about 22.22)n'], J);
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ============== Part 3: Collaborative Filtering Gradient ==============
% Once your cost function matches up with ours, you should now implement
% the collaborative filtering gradient function. Specifically, you should
% complete the code in cofiCostFunc.m to return the grad argument.
%
fprintf('nChecking Gradients (without regularization) ... n');
% Check gradients by running checkNNGradients
checkCostFunction;
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ========= Part 4: Collaborative Filtering Cost Regularization ========
% Now, you should implement regularization for the cost function for
% collaborative filtering. You can implement it by adding the cost of
% regularization to the original cost computation.
%
% Evaluate cost function
J = cofiCostFunc([X(:) ; Theta(:)], Y, R, num_users, num_movies, ...
num_features, 1.5);
fprintf(['Cost at loaded parameters (lambda = 1.5): %f '...
'n(this value should be about 31.34)n'], J);
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ======= Part 5: Collaborative Filtering Gradient Regularization ======
% Once your cost matches up with ours, you should proceed to implement
% regularization for the gradient.
%
%
fprintf('nChecking Gradients (with regularization) ... n');
% Check gradients by running checkNNGradients
checkCostFunction(1.5);
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ============== Part 6: Entering ratings for a new user ===============
% Before we will train the collaborative filtering model, we will first
% add ratings that correspond to a new user that we just observed. This
% part of the code will also allow you to put in your own ratings for the
% movies in our dataset!
%
movieList = loadMovieList();
% Initialize my ratings
my_ratings = zeros(1682, 1);
% Check the file movie_idx.txt for id of each movie in our dataset
% For example, Toy Story (1995) has ID 1, so to rate it "4", you can set
my_ratings(1) = 4;
% Or suppose did not enjoy Silence of the Lambs (1991), you can set
my_ratings(98) = 2;
% We have selected a few movies we liked / did not like and the ratings we
% gave are as follows:
my_ratings(7) = 3;
my_ratings(12)= 5;
my_ratings(54) = 4;
my_ratings(64)= 5;
my_ratings(66)= 3;
my_ratings(69) = 5;
my_ratings(183) = 4;
my_ratings(226) = 5;
my_ratings(355)= 5;
fprintf('nnNew user ratings:n');
for i = 1:length(my_ratings)
if my_ratings(i) > 0
fprintf('Rated %d for %sn', my_ratings(i), ...
movieList{i});
end
end
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ================== Part 7: Learning Movie Ratings ====================
% Now, you will train the collaborative filtering model on a movie rating
% dataset of 1682 movies and 943 users
%
fprintf('nTraining collaborative filtering...n');
% Load data
load('ex8_movies.mat');
% Y is a 1682x943 matrix, containing ratings (1-5) of 1682 movies by
% 943 users
%
% R is a 1682x943 matrix, where R(i,j) = 1 if and only if user j gave a
% rating to movie i
% Add our own ratings to the data matrix
Y = [my_ratings Y];
R = [(my_ratings ~= 0) R];
% Normalize Ratings
[Ynorm, Ymean] = normalizeRatings(Y, R);
% Useful Values
num_users = size(Y, 2);
num_movies = size(Y, 1);
num_features = 10;
% Set Initial Parameters (Theta, X)
X = randn(num_movies, num_features);
Theta = randn(num_users, num_features);
initial_parameters = [X(:); Theta(:)];
% Set options for fmincg
options = optimset('GradObj', 'on', 'MaxIter', 100);
% Set Regularization
lambda = 10;
theta = fmincg (@(t)(cofiCostFunc(t, Ynorm, R, num_users, num_movies, ...
num_features, lambda)), ...
initial_parameters, options);
% Unfold the returned theta back into U and W
X = reshape(theta(1:num_movies*num_features), num_movies, num_features);
Theta = reshape(theta(num_movies*num_features 1:end), ...
num_users, num_features);
fprintf('Recommender system learning completed.n');
fprintf('nProgram paused. Press enter to continue.n');
pause;
%% ================== Part 8: Recommendation for you ====================
% After training the model, you can now make recommendations by computing
% the predictions matrix.
%
p = X * Theta';
my_predictions = p(:,1) Ymean;
movieList = loadMovieList();
[r, ix] = sort(my_predictions, 'descend');
fprintf('nTop recommendations for you:n');
for i=1:10
j = ix(i);
fprintf('Predicting rating %.1f for movie %sn', my_predictions(j), ...
movieList{j});
end
fprintf('nnOriginal ratings provided:n');
for i = 1:length(my_ratings)
if my_ratings(i) > 0
fprintf('Rated %d for %sn', my_ratings(i), ...
movieList{i});
end
end
