/// <summary>Read binary relation data from file</summary>
/// <remarks>
/// The expected (sparse) line format is:
/// ENTITY_ID space/tab/comma ENTITY_ID
/// for the relations that hold.
/// </remarks>
/// <param name="reader">a StreamReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the relation data</returns>
static public IBooleanMatrix Read(StreamReader reader, IMapping mapping)
{
var matrix = new SparseBooleanMatrix();
string line;
while ((line = reader.ReadLine()) != null)
{
// ignore empty lines
if (line.Length == 0)
{
continue;
}
string[] tokens = line.Split(Constants.SPLIT_CHARS);
if (tokens.Length != 2)
{
throw new FormatException("Expected exactly 2 columns: " + line);
}
int entity1_id = mapping.ToInternalID(tokens[0]);
int entity2_id = mapping.ToInternalID(tokens[1]);
matrix[entity1_id, entity2_id] = true;
}
return(matrix);
}
/// <summary>Read in rating data which will be interpreted as implicit feedback data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">the IDataReader to be read from</param>
/// <param name="rating_threshold">the minimum rating value needed to be accepted as positive feedback</param>
/// <param name="user_mapping">user <see cref="IMapping"/> object</param>
/// <param name="item_mapping">item <see cref="IMapping"/> object</param>
/// <returns>a <see cref="IPosOnlyFeedback"/> object with the user-wise collaborative data</returns>
static public IPosOnlyFeedback Read(IDataReader reader, float rating_threshold, IMapping user_mapping, IMapping item_mapping)
{
var feedback = new PosOnlyFeedback <SparseBooleanMatrix>();
if (reader.FieldCount < 3)
{
throw new FormatException("Expected at least 3 columns.");
}
Func <string> get_user_id = reader.GetStringGetter(0);
Func <string> get_item_id = reader.GetStringGetter(1);
Func <float> get_rating = reader.GetFloatGetter(2);
while (reader.Read())
{
int user_id = user_mapping.ToInternalID(get_user_id());
int item_id = item_mapping.ToInternalID(get_item_id());
float rating = get_rating();
if (rating >= rating_threshold)
{
feedback.Add(user_id, item_id);
}
}
return(feedback);
}
/// <summary>Read binary relation data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">an IDataReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the relation data</returns>
static public IBooleanMatrix Read(IDataReader reader, IMapping mapping)
{
if (reader.FieldCount < 2)
{
throw new FormatException("Expected at least 2 columns.");
}
var matrix = new SparseBooleanMatrix();
Func <string> get_e1_id = reader.GetStringGetter(0);
Func <string> get_e2_id = reader.GetStringGetter(1);
while (!reader.Read())
{
int entity1_id = mapping.ToInternalID(get_e1_id());
int entity2_id = mapping.ToInternalID(get_e2_id());
matrix[entity1_id, entity2_id] = true;
}
return(matrix);
}
private IRatings ReadData(string path, IMapping usersMap, IMapping itemsMap)
{
var ratings = new MyMediaLite.Data.Ratings();
File.ReadAllLines(path).Select(l =>
{
var parts = l.Split(new string[] { "::" }, StringSplitOptions.RemoveEmptyEntries);
return(new { User = parts[0], Item = parts[1], Rating = float.Parse(parts[2]) });
}).ToList()
.ForEach(r =>
ratings.Add(usersMap.ToInternalID(r.User), itemsMap.ToInternalID(r.Item), r.Rating));
return(ratings);
}
/// <summary>Read binary relation data from file</summary>
/// <remarks>
/// The expected (sparse) line format is:
/// ENTITY_ID space/tab/comma ENTITY_ID
/// for the relations that hold.
/// </remarks>
/// <param name="reader">a StreamReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the relation data</returns>
static public IBooleanMatrix Read(StreamReader reader, IMapping mapping)
{
var matrix = new SparseBooleanMatrix();
string line;
while ((line = reader.ReadLine()) != null)
{
// ignore empty lines
if (line.Length == 0)
continue;
string[] tokens = line.Split(Constants.SPLIT_CHARS);
if (tokens.Length != 2)
throw new FormatException("Expected exactly 2 columns: " + line);
int entity1_id = mapping.ToInternalID(tokens[0]);
int entity2_id = mapping.ToInternalID(tokens[1]);
matrix[entity1_id, entity2_id] = true;
}
return matrix;
}
/// <summary>Read binary attribute data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">an IDataReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the attribute data</returns>
static public IBooleanMatrix Read(IDataReader reader, IMapping mapping)
{
if (reader.FieldCount < 2)
{
throw new Exception("Expected at least 2 columns.");
}
var matrix = new SparseBooleanMatrix();
while (!reader.Read())
{
int entity_id = mapping.ToInternalID(reader.GetString(0));
int attr_id = reader.GetInt32(1);
matrix[entity_id, attr_id] = true;
}
return(matrix);
}
Read(IDataReader reader, IMapping user_mapping, IMapping item_mapping)
{
var ratings = new Ratings();
if (reader.FieldCount < 3)
{
throw new FormatException("Expected at least 3 columns.");
}
Func <string> get_user_id = reader.GetStringGetter(0);
Func <string> get_item_id = reader.GetStringGetter(1);
Func <float> get_rating = reader.GetFloatGetter(2);
while (reader.Read())
{
int user_id = user_mapping.ToInternalID(get_user_id());
int item_id = item_mapping.ToInternalID(get_item_id());
float rating = get_rating();
ratings.Add(user_id, item_id, rating);
}
ratings.InitScale();
return(ratings);
}
/// <summary>Read in implicit feedback data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">the IDataReader to be read from</param>
/// <param name="user_mapping">user <see cref="IMapping"/> object</param>
/// <param name="item_mapping">item <see cref="IMapping"/> object</param>
/// <returns>a <see cref="IPosOnlyFeedback"/> object with the user-wise collaborative data</returns>
public static IPosOnlyFeedback Read(IDataReader reader, IMapping user_mapping, IMapping item_mapping)
{
var feedback = new PosOnlyFeedback<SparseBooleanMatrix>();
if (reader.FieldCount < 2)
throw new FormatException("Expected at least 2 columns.");
Func<string> get_user_id = reader.GetStringGetter(0);
Func<string> get_item_id = reader.GetStringGetter(1);
while (reader.Read())
{
int user_id = user_mapping.ToInternalID(get_user_id());
int item_id = item_mapping.ToInternalID(get_item_id());
feedback.Add(user_id, item_id);
}
return feedback;
}
/// <summary>Read in rating data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">the <see cref="IDataReader"/> to read from</param>
/// <param name="user_mapping">mapping object for user IDs</param>
/// <param name="item_mapping">mapping object for item IDs</param>
/// <returns>the rating data</returns>
public static IRatings Read(IDataReader reader, IMapping user_mapping, IMapping item_mapping)
{
var ratings = new Ratings();
if (reader.FieldCount < 3)
throw new FormatException("Expected at least 3 columns.");
Func<string> get_user_id = reader.GetStringGetter(0);
Func<string> get_item_id = reader.GetStringGetter(1);
Func<float> get_rating = reader.GetFloatGetter(2);
while (reader.Read())
{
int user_id = user_mapping.ToInternalID(get_user_id());
int item_id = item_mapping.ToInternalID(get_item_id());
float rating = get_rating();
ratings.Add(user_id, item_id, rating);
}
ratings.InitScale();
return ratings;
}
/// <summary>Read binary attribute data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">an IDataReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the attribute data</returns>
static public IBooleanMatrix Read(IDataReader reader, IMapping mapping)
{
if (reader.FieldCount < 2)
throw new Exception("Expected at least 2 columns.");
var matrix = new SparseBooleanMatrix();
while (!reader.Read())
{
int entity_id = mapping.ToInternalID(reader.GetString(0));
int attr_id = reader.GetInt32(1);
matrix[entity_id, attr_id] = true;
}
return matrix;
}
/// <summary>Read binary relation data from an IDataReader, e.g. a database via DbDataReader</summary>
/// <param name="reader">an IDataReader to be read from</param>
/// <param name="mapping">the mapping object for the given entity type</param>
/// <returns>the relation data</returns>
static public IBooleanMatrix Read(IDataReader reader, IMapping mapping)
{
if (reader.FieldCount < 2)
throw new FormatException("Expected at least 2 columns.");
var matrix = new SparseBooleanMatrix();
Func<string> get_e1_id = reader.GetStringGetter(0);
Func<string> get_e2_id = reader.GetStringGetter(1);
while (!reader.Read())
{
int entity1_id = mapping.ToInternalID(get_e1_id());
int entity2_id = mapping.ToInternalID(get_e2_id());
matrix[entity1_id, entity2_id] = true;
}
return matrix;
}
