public void TestReadIgnoreLine()
{
string s = @"# first line
5951,50,5
5951,223,5
5951,260,5
5951,293,5
5951,356,4
5951,364,3
5951,457,3
";
IDataSet data = ItemDataRatingThreshold.Read(new StringReader(s), 0, null, null, true);
Assert.AreEqual(7, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 5, null, null, true);
Assert.AreEqual(4, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 4, null, null, true);
Assert.AreEqual(5, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 3, null, null, true);
Assert.AreEqual(7, data.Count);
}
public void TestRead()
{
string s = @"5951,50,5
5951,223,5
5951,260,5
5951,293,5
5951,356,4
5951,364,3
5951,457,3
";
IDataSet data = ItemDataRatingThreshold.Read(new StringReader(s), 0);
Assert.AreEqual(7, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 5.0f);
Assert.AreEqual(4, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 4);
Assert.AreEqual(5, data.Count);
data = ItemDataRatingThreshold.Read(new StringReader(s), 3);
Assert.AreEqual(7, data.Count);
}
protected override void LoadData()
{
TimeSpan loading_time = Wrap.MeasureTime(delegate() {
base.LoadData();
// training data
training_data = double.IsNaN(rating_threshold)
? ItemData.Read(training_file, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE)
: ItemDataRatingThreshold.Read(training_file, rating_threshold, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE);
// test data
if (test_ratio == 0)
{
if (test_file != null)
{
test_data = double.IsNaN(rating_threshold)
? ItemData.Read(test_file, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE)
: ItemDataRatingThreshold.Read(test_file, rating_threshold, user_mapping, item_mapping, file_format == ItemDataFileFormat.IGNORE_FIRST_LINE);
}
}
else
{
var split = new PosOnlyFeedbackSimpleSplit <PosOnlyFeedback <SparseBooleanMatrix> >(training_data, test_ratio);
training_data = split.Train[0];
test_data = split.Test[0];
}
if (user_prediction)
{
// swap file names for test users and candidate items
var ruf = test_users_file;
var rif = candidate_items_file;
test_users_file = rif;
candidate_items_file = ruf;
// swap user and item mappings
var um = user_mapping;
var im = item_mapping;
user_mapping = im;
item_mapping = um;
// transpose training and test data
training_data = training_data.Transpose();
// transpose test data
if (test_data != null)
{
test_data = test_data.Transpose();
}
}
for (int i = 0; i < recommenders.Count; i++)
{
if (recommenders[i] is MyMediaLite.ItemRecommendation.ItemRecommender)
{
((ItemRecommender)recommenders[i]).Feedback = training_data;
}
}
// test users
if (test_users_file != null)
{
test_users = user_mapping.ToInternalID(File.ReadLines(Path.Combine(data_dir, test_users_file)).ToArray());
}
else
{
test_users = test_data != null ? test_data.AllUsers : training_data.AllUsers;
}
// if necessary, perform user sampling
if (num_test_users > 0 && num_test_users < test_users.Count)
{
var old_test_users = new HashSet <int>(test_users);
var new_test_users = new int[num_test_users];
for (int i = 0; i < num_test_users; i++)
{
int random_index = MyMediaLite.Random.GetInstance().Next(old_test_users.Count - 1);
new_test_users[i] = old_test_users.ElementAt(random_index);
old_test_users.Remove(new_test_users[i]);
}
test_users = new_test_users;
}
// candidate items
if (candidate_items_file != null)
{
candidate_items = item_mapping.ToInternalID(File.ReadLines(Path.Combine(data_dir, candidate_items_file)).ToArray());
}
else if (all_items)
{
candidate_items = Enumerable.Range(0, item_mapping.InternalIDs.Max() + 1).ToArray();
}
if (candidate_items != null)
{
eval_item_mode = CandidateItems.EXPLICIT;
}
else if (in_training_items)
{
eval_item_mode = CandidateItems.TRAINING;
}
else if (in_test_items)
{
eval_item_mode = CandidateItems.TEST;
}
else if (overlap_items)
{
eval_item_mode = CandidateItems.OVERLAP;
}
else
{
eval_item_mode = CandidateItems.UNION;
}
});
//Salvar arquivos
List <string> linesToWrite = new List <string>();
for (int i = 0; i < training_data.UserMatrix.NumberOfRows; i++)
{
IList <int> columns = training_data.UserMatrix.GetEntriesByRow(i);
for (int j = 0; j < columns.Count; j++)
{
StringBuilder line = new StringBuilder();
line.Append(i.ToString() + " " + columns[j].ToString());
linesToWrite.Add(line.ToString());
}
}
System.IO.File.WriteAllLines("training.data", linesToWrite.ToArray());
linesToWrite = new List <string>();
for (int i = 0; i < test_data.UserMatrix.NumberOfRows; i++)
{
IList <int> columns = test_data.UserMatrix.GetEntriesByRow(i);
for (int j = 0; j < columns.Count; j++)
{
StringBuilder line = new StringBuilder();
line.Append(i.ToString() + " " + columns[j].ToString());
linesToWrite.Add(line.ToString());
}
}
System.IO.File.WriteAllLines("test.data", linesToWrite.ToArray());
/*
* List<string> linesToWrite = new List<string>();
* for (int rowIndex = 0; rowIndex < training_data.AllItems.Count; rowIndex++)
* {
*
* }*/
Console.Error.WriteLine(string.Format(CultureInfo.InvariantCulture, "loading_time {0,0:0.##}", loading_time.TotalSeconds));
Console.Error.WriteLine("memory {0}", Memory.Usage);
}