public static void Test_CollaborativeFilteringRSCostFunction_Evaluate(double lambda)
{
int num_users = 4; int num_movies = 5; int num_features = 3;
List <List <double> > X = DblDataTableUtil.LoadDataSet("X.txt");
List <List <double> > Y = DblDataTableUtil.LoadDataSet("Y.txt");
List <List <int> > R = IntDataTableUtil.LoadDataSet("R.txt");
List <List <double> > Theta = DblDataTableUtil.LoadDataSet("Theta.txt");
X = DblDataTableUtil.SubMatrix(X, num_movies, num_features);
Y = DblDataTableUtil.SubMatrix(Y, num_movies, num_users);
R = IntDataTableUtil.SubMatrix(R, num_movies, num_users);
Theta = DblDataTableUtil.SubMatrix(Theta, num_users, num_features);
Matrix <double> Y_matrix = Convert2Matrix(Y);
Matrix <double> X_matrix = Convert2Matrix(X);
Matrix <double> Theta_matrix = Convert2Matrix(Theta);
int[,] R_matrix = IntDataTableUtil.Convert2DArray(R);
int dimension = num_movies * num_features + num_users * num_features; //total number of entries in X and Theta
double[] theta_x = new double[dimension];
CollaborativeFilteringRSCostFunction.UnrollMatrixIntoVector(Theta_matrix, X_matrix, theta_x);
CollaborativeFilteringRSCostFunction f = new CollaborativeFilteringRSCostFunction(Y_matrix, R_matrix, num_movies, num_features, dimension);
f.RegularizationLambda = lambda;
double J = f.Evaluate(theta_x);
Console.WriteLine("Cost at loaded parameters: {0} (this value should be about 22.22)", J);
}
private void ImportData(string X_filepath, string y_filepath)
{
mTrainingPercent = 100;
mTestingPercent = 0;
mCrossValidationPercent = 0;
lvTabularData.Items.Clear();
lvTabularData.Columns.Clear();
List <MLDataPoint> X_points = MLDataPointUtil.LoadDataSet(X_filepath);
List <List <int> > y_points = IntDataTableUtil.LoadDataSet(y_filepath);
List <CDataRecord> X = new List <CDataRecord>();
for (int i = 0; i < X_points.Count; ++i)
{
CDataRecord X_i = new CDataRecord(X_points[i].Dimension);
for (int j = 0; j < X_points[i].Dimension; ++j)
{
X_i[j + 1] = X_points[i][j];
}
X_i.Label = y_points[i][0].ToString();
X.Add(X_i);
}
lvTabularData.Columns.Add("#");
for (int i = 0; i < X[0].Dimension; ++i)
{
lvTabularData.Columns.Add(string.Format("X[{0}]", i));
}
lvTabularData.Columns.Add("Y");
lvTabularData.Columns.Add("Data Set");
lvTabularData.Columns.Add("Predicted Y");
int m = X.Count;
for (int i = 0; i < m; ++i)
{
CDataRecord X_i = X[i];
ListViewItem item = new ListViewItem();
item.Text = (lvTabularData.Items.Count + 1).ToString();
for (int j = 0; j < X_i.Dimension; ++j)
{
item.SubItems.Add(X_i[j].ToString());
}
item.SubItems.Add(X_i.Label.ToString());
item.SubItems.Add(X_i.DataSetType.ToString());
item.SubItems.Add(X_i.PredictedLabel.ToString());
item.Tag = X_i;
item.ForeColor = Color.Green;
lvTabularData.Items.Add(item);
}
}
public static void Run_Classify2()
{
List <MLDataPoint> X_points = MLDataPointUtil.LoadDataSet("X1.txt");
List <List <int> > y_points = IntDataTableUtil.LoadDataSet("y1.txt");
List <CDataRecord> X = new List <CDataRecord>();
for (int i = 0; i < X_points.Count; ++i)
{
CDataRecord X_i = new CDataRecord(X_points[i].Dimension);
for (int j = 0; j < X_points[i].Dimension; ++j)
{
X_i[i + 1] = X_points[i][j]; //X_i index must start at 1
}
X_i.Label = y_points[i][0].ToString();
X.Add(X_i);
}
LinearSVM <CDataRecord> algorithm = new LinearSVM <CDataRecord>();
algorithm.C = 100;
algorithm.Train(X);
}
public static void Test_Compute()
{
List <string> movie_titles = LoadMovies();
int num_movies = movie_titles.Count;
// Step 1: create my ratings with missing entries
double[] my_ratings = new double[num_movies];
int[] my_ratings_r = new int[num_movies];
for (int i = 0; i < num_movies; ++i)
{
my_ratings[i] = 0;
}
my_ratings[1] = 4;
my_ratings[98] = 2;
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;
for (int i = 0; i < num_movies; ++i)
{
my_ratings_r[i] = my_ratings[i] > 0 ? 1 : 0;
}
// Step 2: load the current ratings of all users, i.e., Y and R
List <List <double> > Y = DblDataTableUtil.LoadDataSet("Y.txt");
List <List <int> > R = IntDataTableUtil.LoadDataSet("R.txt");
int num_users;
DblDataTableUtil.GetSize(Y, out num_movies, out num_users);
// Step 3: insert my ratings into the existing Y and R (as the first column)
num_users++;
List <RatedItem> records = new List <RatedItem>();
for (int i = 0; i < num_movies; ++i)
{
double[] rec_Y = new double[num_users];
bool[] rec_R = new bool[num_users];
for (int j = 0; j < num_users; ++j)
{
if (j == 0)
{
rec_Y[j] = my_ratings[i];
rec_R[j] = my_ratings_r[i] == 1;
}
else
{
rec_Y[j] = Y[i][j - 1];
rec_R[j] = R[i][j - 1] == 1;
}
}
RatedItem rec = new RatedItem(null, rec_Y, rec_R);
records.Add(rec);
}
int num_features = 10;
double lambda = 10;
CollaborativeFilteringRS <RatedItem> algorithm = new CollaborativeFilteringRS <RatedItem>();
algorithm.Stepped += (s, step) =>
{
Console.WriteLine("#{0}: {1}", step, s.Cost);
};
algorithm.RegularizationLambda = lambda;
algorithm.MaxLocalSearchIteration = 100;
GradientDescent local_search = algorithm.LocalSearch as GradientDescent;
local_search.Alpha = 0.005;
double[] Ymean;
algorithm.DoMeanNormalization(records, out Ymean);
algorithm.Compute(records, num_features);
algorithm.UndoMeanNormalization(records, Ymean);
int userId = 0;
int topK = 10;
List <RatedItem> highest_ranks = algorithm.SelectHigestRanked(userId, records, topK);
for (int i = 0; i < highest_ranks.Count; ++i)
{
RatedItem rec = highest_ranks[i];
Console.WriteLine("#{0}: ({1}) {2}", i + 1, rec.UserRanks[0], movie_titles[rec.ItemIndex]);
}
}
