def __init__(self, URM_train, ICM, S_matrix_target): super(CFW_D_Similarity_Linalg, self).__init__(URM_train) if (URM_train.shape[1] != ICM.shape[0]): raise ValueError( "Number of items not consistent. URM contains {} but ICM contains {}" .format(URM_train.shape[1], ICM.shape[0])) if (S_matrix_target.shape[0] != S_matrix_target.shape[1]): raise ValueError( "Items imilarity matrix is not square: rows are {}, columns are {}" .format(S_matrix_target.shape[0], S_matrix_target.shape[1])) if (S_matrix_target.shape[0] != ICM.shape[0]): raise ValueError( "Number of items not consistent. S_matrix contains {} but ICM contains {}" .format(S_matrix_target.shape[0], ICM.shape[0])) self.S_matrix_target = check_matrix(S_matrix_target, 'csr') self.ICM = check_matrix(ICM, 'csr') self.n_items = self.URM_train.shape[1] self.n_users = self.URM_train.shape[0] self.n_features = self.ICM.shape[1] self.sparse_weights = True
def fit(self, topK=50, shrink=100, similarity='cosine', normalize=True, feature_weighting="none", **similarity_args): self.topK = topK self.shrink = shrink if feature_weighting not in self.FEATURE_WEIGHTING_VALUES: raise ValueError( "Value for 'feature_weighting' not recognized. Acceptable values are {}, provided was '{}'" .format(self.FEATURE_WEIGHTING_VALUES, feature_weighting)) if feature_weighting == "BM25": self.URM_train = self.URM_train.astype(np.float32) self.URM_train = okapi_BM_25(self.URM_train.T).T self.URM_train = check_matrix(self.URM_train, 'csr') elif feature_weighting == "TF-IDF": self.URM_train = self.URM_train.astype(np.float32) self.URM_train = TF_IDF(self.URM_train.T).T self.URM_train = check_matrix(self.URM_train, 'csr') similarity = Compute_Similarity(self.URM_train.T, shrink=shrink, topK=topK, normalize=normalize, similarity=similarity, **similarity_args) self.W_sparse = similarity.compute_similarity() self.W_sparse = check_matrix(self.W_sparse, format='csr')
def get_S_incremental_and_set_W(self): self.S_incremental = self.cythonEpoch.get_S() if self.train_with_sparse_weights: self.W_sparse = self.S_incremental self.W_sparse = check_matrix(self.W_sparse, format='csr') else: self.W_sparse = similarityMatrixTopK(self.S_incremental, k = self.topK) self.W_sparse = check_matrix(self.W_sparse, format='csr')
def fit(self, lambda_user=10, lambda_item=25): self.lambda_user = lambda_user self.lambda_item = lambda_item self.n_items = self.URM_train.shape[1] # convert to csc matrix for faster column-wise sum self.URM_train = check_matrix(self.URM_train, 'csc', dtype=np.float32) # 1) global average self.mu = self.URM_train.data.sum( dtype=np.float32) / self.URM_train.data.shape[0] # 2) item average bias # compute the number of non-zero elements for each column col_nnz = np.diff(self.URM_train.indptr) # it is equivalent to: # col_nnz = X.indptr[1:] - X.indptr[:-1] # and it is **much faster** than # col_nnz = (X != 0).sum(axis=0) URM_train_unbiased = self.URM_train.copy() URM_train_unbiased.data -= self.mu self.item_bias = URM_train_unbiased.sum(axis=0) / (col_nnz + self.lambda_item) self.item_bias = np.asarray(self.item_bias).ravel( ) # converts 2-d matrix to 1-d array without anycopy # 3) user average bias # NOTE: the user bias is *useless* for the sake of ranking items. We just show it here for educational purposes. # first subtract the item biases from each column # then repeat each element of the item bias vector a number of times equal to col_nnz # and subtract it from the data vector URM_train_unbiased.data -= np.repeat(self.item_bias, col_nnz) # now convert the csc matrix to csr for efficient row-wise computation URM_train_unbiased_csr = URM_train_unbiased.tocsr() row_nnz = np.diff(URM_train_unbiased_csr.indptr) # finally, let's compute the bias self.user_bias = URM_train_unbiased_csr.sum( axis=1).ravel() / (row_nnz + self.lambda_user) # 4) precompute the item ranking by using the item bias only # the global average and user bias won't change the ranking, so there is no need to use them #self.item_ranking = np.argsort(self.bi)[::-1] self.URM_train = check_matrix(self.URM_train, 'csr', dtype=np.float32)
def applyAdjustedCosine(self): """ Remove from every data point the average for the corresponding row :return: """ self.dataMatrix = check_matrix(self.dataMatrix, 'csr') interactionsPerRow = np.diff(self.dataMatrix.indptr) nonzeroRows = interactionsPerRow > 0 sumPerRow = np.asarray(self.dataMatrix.sum(axis=1)).ravel() rowAverage = np.zeros_like(sumPerRow) rowAverage[nonzeroRows] = sumPerRow[nonzeroRows] / interactionsPerRow[nonzeroRows] # Split in blocks to avoid duplicating the whole data structure start_row = 0 end_row= 0 blockSize = 1000 while end_row < self.n_rows: end_row = min(self.n_rows, end_row + blockSize) self.dataMatrix.data[self.dataMatrix.indptr[start_row]:self.dataMatrix.indptr[end_row]] -= \ np.repeat(rowAverage[start_row:end_row], interactionsPerRow[start_row:end_row]) start_row += blockSize
def remove_empty_rows_and_cols(URM, ICM=None): URM = check_matrix(URM, "csr") rows = URM.indptr numRatings = np.ediff1d(rows) user_mask = numRatings >= 1 URM = URM[user_mask, :] cols = URM.tocsc().indptr numRatings = np.ediff1d(cols) item_mask = numRatings >= 1 URM = URM[:, item_mask] removedUsers = np.arange(0, len(user_mask))[np.logical_not(user_mask)] removedItems = np.arange(0, len(item_mask))[np.logical_not(item_mask)] if ICM is not None: ICM = ICM[item_mask, :] return URM.tocsr(), ICM.tocsr(), removedUsers, removedItems return URM.tocsr(), removedUsers, removedItems
def applyPearsonCorrelation(self): """ Remove from every data point the average for the corresponding column :return: """ self.dataMatrix = check_matrix(self.dataMatrix, 'csc') interactionsPerCol = np.diff(self.dataMatrix.indptr) nonzeroCols = interactionsPerCol > 0 sumPerCol = np.asarray(self.dataMatrix.sum(axis=0)).ravel() colAverage = np.zeros_like(sumPerCol) colAverage[nonzeroCols] = sumPerCol[nonzeroCols] / interactionsPerCol[nonzeroCols] # Split in blocks to avoid duplicating the whole data structure start_col = 0 end_col= 0 blockSize = 1000 while end_col < self.n_columns: end_col = min(self.n_columns, end_col + blockSize) self.dataMatrix.data[self.dataMatrix.indptr[start_col]:self.dataMatrix.indptr[end_col]] -= \ np.repeat(colAverage[start_col:end_col], interactionsPerCol[start_col:end_col]) start_col += blockSize
def __init__(self, URM_train, verbose=True): super(BaseRecommender, self).__init__() self.URM_train = check_matrix(URM_train.copy(), 'csr', dtype=np.float32) self.URM_train.eliminate_zeros() self.n_users, self.n_items = self.URM_train.shape self.verbose = verbose self.filterTopPop = False self.filterTopPop_ItemsID = np.array([], dtype=np.int) self.items_to_ignore_flag = False self.items_to_ignore_ID = np.array([], dtype=np.int) self._cold_user_mask = np.ediff1d(self.URM_train.indptr) == 0 if self._cold_user_mask.any(): self._print("URM Detected {} ({:.2f} %) cold users.".format( self._cold_user_mask.sum(), self._cold_user_mask.sum() / self.n_users * 100)) self._cold_item_mask = np.ediff1d(self.URM_train.tocsc().indptr) == 0 if self._cold_item_mask.any(): self._print("URM Detected {} ({:.2f} %) cold items.".format( self._cold_item_mask.sum(), self._cold_item_mask.sum() / self.n_items * 100))
def fit(self, URM_train): self.URM_train = URM_train.tocsr() if self.feature_weighting == "TF-IDF": self.URM_train = self.URM_train.astype(np.float32) self.URM_train = TF_IDF(self.URM_train.T).T self.URM_train = check_matrix(self.URM_train, 'csr') self.SM_item = self.get_similarity_matrix() self.RM = self.URM_train.dot(self.SM_item)
def _build_confidence_matrix(self, confidence_scaling): if confidence_scaling == 'linear': self.C = self._linear_scaling_confidence() else: self.C = self._log_scaling_confidence() self.C_csc = check_matrix(self.C.copy(), format="csc", dtype=np.float32)
def fit(self, W_sparse, selectTopK=False, topK=100): assert W_sparse.shape[0] == W_sparse.shape[1],\ "ItemKNNCustomSimilarityRecommender: W_sparse matrice is not square. Current shape is {}".format(W_sparse.shape) assert self.URM_train.shape[1] == W_sparse.shape[0],\ "ItemKNNCustomSimilarityRecommender: URM_train and W_sparse matrices are not consistent. " \ "The number of columns in URM_train must be equal to the rows in W_sparse. " \ "Current shapes are: URM_train {}, W_sparse {}".format(self.URM_train.shape, W_sparse.shape) if selectTopK: W_sparse = similarityMatrixTopK(W_sparse, k=topK) self.W_sparse = check_matrix(W_sparse, format='csr')
def removeFeatures(ICM, minOccurrence=5, maxPercOccurrence=0.30, reconcile_mapper=None): """ The function eliminates the values associated to feature occurring in less than the minimal percentage of items or more then the max. Shape of ICM is reduced deleting features. :param ICM: :param minPercOccurrence: :param maxPercOccurrence: :param reconcile_mapper: DICT mapper [token] -> index :return: ICM :return: deletedFeatures :return: DICT mapper [token] -> index """ ICM = check_matrix(ICM, 'csc') n_items = ICM.shape[0] cols = ICM.indptr numOccurrences = np.ediff1d(cols) feature_mask = np.logical_and( numOccurrences >= minOccurrence, numOccurrences <= n_items * maxPercOccurrence) ICM = ICM[:, feature_mask] deletedFeatures = np.arange( 0, len(feature_mask))[np.logical_not(feature_mask)] print( "RemoveFeatures: removed {} features with less then {} occurrencies, removed {} features with more than {} occurrencies" .format(sum(numOccurrences < minOccurrence), minOccurrence, sum(numOccurrences > n_items * maxPercOccurrence), int(n_items * maxPercOccurrence))) if reconcile_mapper is not None: reconcile_mapper = reconcile_mapper_with_removed_tokens( reconcile_mapper, deletedFeatures) return ICM, deletedFeatures, reconcile_mapper return ICM, deletedFeatures
def fit(self, l1_ratio=0.1, positive_only=True, topK=500, workers=multiprocessing.cpu_count()): assert 0 <= l1_ratio <= 1, "SLIM_ElasticNet: l1_ratio must be between 0 and 1, provided value was {}".format( l1_ratio) self.l1_ratio = l1_ratio self.positive_only = positive_only self.topK = topK self.workers = workers self.URM_train = check_matrix(self.URM_train, 'csc', dtype=np.float32) n_items = self.URM_train.shape[1] # fit item's factors in parallel #oggetto riferito alla funzione nel quale predefinisco parte dell'input _pfit = partial(self._partial_fit, X=self.URM_train, topK=self.topK) #creo un pool con un certo numero di processi pool = Pool(processes=self.workers) #avvio il pool passando la funzione (con la parte fissa dell'input) #e il rimanente parametro, variabile res = pool.map(_pfit, np.arange(n_items)) # res contains a vector of (values, rows, cols) tuples values, rows, cols = [], [], [] for values_, rows_, cols_ in res: values.extend(values_) rows.extend(rows_) cols.extend(cols_) # generate the sparse weight matrix self.W_sparse = sps.csr_matrix((values, (rows, cols)), shape=(n_items, n_items), dtype=np.float32)
def _log_scaling_confidence(self): C = check_matrix(self.URM_train, format="csr", dtype=np.float32) C.data = 1.0 + self.alpha * np.log(1.0 + C.data / self.epsilon) return C
def _linear_scaling_confidence(self): C = check_matrix(self.URM_train, format="csr", dtype=np.float32) C.data = 1.0 + self.alpha * C.data return C
def fit(self, l1_ratio=0.1, alpha=1.0, positive_only=True, topK=100): assert 0 <= l1_ratio <= 1, "{}: l1_ratio must be between 0 and 1, provided value was {}".format( self.RECOMMENDER_NAME, l1_ratio) self.l1_ratio = l1_ratio self.positive_only = positive_only self.topK = topK # Display ConvergenceWarning only once and not for every item it occurs warnings.simplefilter("once", category=ConvergenceWarning) # initialize the ElasticNet model self.model = ElasticNet(alpha=alpha, l1_ratio=self.l1_ratio, positive=self.positive_only, fit_intercept=False, copy_X=False, precompute=True, selection='random', max_iter=100, tol=1e-4) URM_train = check_matrix(self.URM_train, 'csc', dtype=np.float32) n_items = URM_train.shape[1] # Use array as it reduces memory requirements compared to lists dataBlock = 10000000 rows = np.zeros(dataBlock, dtype=np.int32) cols = np.zeros(dataBlock, dtype=np.int32) values = np.zeros(dataBlock, dtype=np.float32) numCells = 0 start_time = time.time() start_time_printBatch = start_time # fit each item's factors sequentially (not in parallel) for currentItem in range(n_items): # get the target column y = URM_train[:, currentItem].toarray() # set the j-th column of X to zero start_pos = URM_train.indptr[currentItem] end_pos = URM_train.indptr[currentItem + 1] current_item_data_backup = URM_train.data[start_pos:end_pos].copy() URM_train.data[start_pos:end_pos] = 0.0 # fit one ElasticNet model per column self.model.fit(URM_train, y) # self.model.coef_ contains the coefficient of the ElasticNet model # let's keep only the non-zero values # Select topK values # Sorting is done in three steps. Faster then plain np.argsort for higher number of items # - Partition the data to extract the set of relevant items # - Sort only the relevant items # - Get the original item index nonzero_model_coef_index = self.model.sparse_coef_.indices nonzero_model_coef_value = self.model.sparse_coef_.data local_topK = min(len(nonzero_model_coef_value) - 1, self.topK) relevant_items_partition = ( -nonzero_model_coef_value ).argpartition(local_topK)[0:local_topK] relevant_items_partition_sorting = np.argsort( -nonzero_model_coef_value[relevant_items_partition]) ranking = relevant_items_partition[ relevant_items_partition_sorting] for index in range(len(ranking)): if numCells == len(rows): rows = np.concatenate( (rows, np.zeros(dataBlock, dtype=np.int32))) cols = np.concatenate( (cols, np.zeros(dataBlock, dtype=np.int32))) values = np.concatenate( (values, np.zeros(dataBlock, dtype=np.float32))) rows[numCells] = nonzero_model_coef_index[ranking[index]] cols[numCells] = currentItem values[numCells] = nonzero_model_coef_value[ranking[index]] numCells += 1 # finally, replace the original values of the j-th column URM_train.data[start_pos:end_pos] = current_item_data_backup elapsed_time = time.time() - start_time new_time_value, new_time_unit = seconds_to_biggest_unit( elapsed_time) if time.time( ) - start_time_printBatch > 300 or currentItem == n_items - 1: self._print( "Processed {} ( {:.2f}% ) in {:.2f} {}. Items per second: {:.2f}" .format(currentItem + 1, 100.0 * float(currentItem + 1) / n_items, new_time_value, new_time_unit, float(currentItem) / elapsed_time)) sys.stdout.flush() sys.stderr.flush() start_time_printBatch = time.time() # generate the sparse weight matrix self.W_sparse = sps.csr_matrix( (values[:numCells], (rows[:numCells], cols[:numCells])), shape=(n_items, n_items), dtype=np.float32)
def fit(self, alpha=1., beta=0.6, min_rating=0, topK=100, implicit=False, normalize_similarity=True): self.alpha = alpha self.beta = beta self.min_rating = min_rating self.topK = topK self.implicit = implicit self.normalize_similarity = normalize_similarity # if X.dtype != np.float32: # print("RP3beta fit: For memory usage reasons, we suggest to use np.float32 as dtype for the dataset") if self.min_rating > 0: self.URM_train.data[self.URM_train.data < self.min_rating] = 0 self.URM_train.eliminate_zeros() if self.implicit: self.URM_train.data = np.ones(self.URM_train.data.size, dtype=np.float32) #Pui is the row-normalized urm Pui = normalize(self.URM_train, norm='l1', axis=1) #Piu is the column-normalized, "boolean" urm transposed X_bool = self.URM_train.transpose(copy=True) X_bool.data = np.ones(X_bool.data.size, np.float32) # Taking the degree of each item to penalize top popular # Some rows might be zero, make sure their degree remains zero X_bool_sum = np.array(X_bool.sum(axis=1)).ravel() degree = np.zeros(self.URM_train.shape[1]) nonZeroMask = X_bool_sum != 0.0 degree[nonZeroMask] = np.power(X_bool_sum[nonZeroMask], -self.beta) #ATTENTION: axis is still 1 because i transposed before the normalization Piu = normalize(X_bool, norm='l1', axis=1) del (X_bool) # Alfa power if self.alpha != 1.: Pui = Pui.power(self.alpha) Piu = Piu.power(self.alpha) # Final matrix is computed as Pui * Piu * Pui # Multiplication unpacked for memory usage reasons block_dim = 200 d_t = Piu # Use array as it reduces memory requirements compared to lists dataBlock = 10000000 rows = np.zeros(dataBlock, dtype=np.int32) cols = np.zeros(dataBlock, dtype=np.int32) values = np.zeros(dataBlock, dtype=np.float32) numCells = 0 start_time = time.time() start_time_printBatch = start_time for current_block_start_row in range(0, Pui.shape[1], block_dim): if current_block_start_row + block_dim > Pui.shape[1]: block_dim = Pui.shape[1] - current_block_start_row similarity_block = d_t[ current_block_start_row:current_block_start_row + block_dim, :] * Pui similarity_block = similarity_block.toarray() for row_in_block in range(block_dim): row_data = np.multiply(similarity_block[row_in_block, :], degree) row_data[current_block_start_row + row_in_block] = 0 best = row_data.argsort()[::-1][:self.topK] notZerosMask = row_data[best] != 0.0 values_to_add = row_data[best][notZerosMask] cols_to_add = best[notZerosMask] for index in range(len(values_to_add)): if numCells == len(rows): rows = np.concatenate( (rows, np.zeros(dataBlock, dtype=np.int32))) cols = np.concatenate( (cols, np.zeros(dataBlock, dtype=np.int32))) values = np.concatenate( (values, np.zeros(dataBlock, dtype=np.float32))) rows[numCells] = current_block_start_row + row_in_block cols[numCells] = cols_to_add[index] values[numCells] = values_to_add[index] numCells += 1 if time.time() - start_time_printBatch > 60: self._print( "Processed {} ( {:.2f}% ) in {:.2f} minutes. Rows per second: {:.0f}" .format( current_block_start_row, 100.0 * float(current_block_start_row) / Pui.shape[1], (time.time() - start_time) / 60, float(current_block_start_row) / (time.time() - start_time))) sys.stdout.flush() sys.stderr.flush() start_time_printBatch = time.time() self.W_sparse = sps.csr_matrix( (values[:numCells], (rows[:numCells], cols[:numCells])), shape=(Pui.shape[1], Pui.shape[1])) if self.normalize_similarity: self.W_sparse = normalize(self.W_sparse, norm='l1', axis=1) if self.topK != False: self.W_sparse = similarityMatrixTopK(self.W_sparse, k=self.topK) self.W_sparse = check_matrix(self.W_sparse, format='csr') self.RM = self.URM_train.dot(self.W_sparse)
def fit(self, URM_train, verbose=True): self.URM_train = URM_train self.verbose = verbose # # if X.dtype != np.float32: # print("P3ALPHA fit: For memory usage reasons, we suggest to use np.float32 as dtype for the dataset") if self.min_rating > 0: self.URM_train.data[self.URM_train.data < self.min_rating] = 0 self.URM_train.eliminate_zeros() if self.implicit: self.URM_train.data = np.ones(self.URM_train.data.size, dtype=np.float32) # Pui is the row-normalized urm Pui = normalize(self.URM_train, norm='l1', axis=1) # Piu is the column-normalized, "boolean" urm transposed X_bool = self.URM_train.transpose(copy=True) X_bool.data = np.ones(X_bool.data.size, np.float32) # ATTENTION: axis is still 1 because i transposed before the normalization Piu = normalize(X_bool, norm='l1', axis=1) del X_bool # Alfa power if self.alpha != 1.: Pui = Pui.power(self.alpha) Piu = Piu.power(self.alpha) # Final matrix is computed as Pui * Piu * Pui # Multiplication unpacked for memory usage reasons block_dim = 200 d_t = Piu # Use array as it reduces memory requirements compared to lists dataBlock = 10000000 rows = np.zeros(dataBlock, dtype=np.int32) cols = np.zeros(dataBlock, dtype=np.int32) values = np.zeros(dataBlock, dtype=np.float32) numCells = 0 start_time = time.time() start_time_printBatch = start_time for current_block_start_row in range(0, Pui.shape[1], block_dim): if current_block_start_row + block_dim > Pui.shape[1]: block_dim = Pui.shape[1] - current_block_start_row similarity_block = d_t[current_block_start_row:current_block_start_row + block_dim, :] * Pui similarity_block = similarity_block.toarray() for row_in_block in range(block_dim): row_data = similarity_block[row_in_block, :] row_data[current_block_start_row + row_in_block] = 0 best = row_data.argsort()[::-1][:self.topK] notZerosMask = row_data[best] != 0.0 values_to_add = row_data[best][notZerosMask] cols_to_add = best[notZerosMask] for index in range(len(values_to_add)): if numCells == len(rows): rows = np.concatenate((rows, np.zeros(dataBlock, dtype=np.int32))) cols = np.concatenate((cols, np.zeros(dataBlock, dtype=np.int32))) values = np.concatenate((values, np.zeros(dataBlock, dtype=np.float32))) rows[numCells] = current_block_start_row + row_in_block cols[numCells] = cols_to_add[index] values[numCells] = values_to_add[index] numCells += 1 if time.time() - start_time_printBatch > 60: self._print("Processed {} ( {:.2f}% ) in {:.2f} minutes. Rows per second: {:.0f}".format( current_block_start_row, 100.0 * float(current_block_start_row) / Pui.shape[1], (time.time() - start_time) / 60, float(current_block_start_row) / (time.time() - start_time))) sys.stdout.flush() sys.stderr.flush() start_time_printBatch = time.time() self.SM = sps.csr_matrix((values[:numCells], (rows[:numCells], cols[:numCells])), shape=(Pui.shape[1], Pui.shape[1])) if self.normalize_similarity: self.SM = normalize(self.SM, norm='l1', axis=1) if self.topK: self.SM = similarityMatrixTopK(self.SM, k=self.topK) self.SM = check_matrix(self.SM, format='csr') self.RM = self.URM_train.dot(self.SM)
def _generateTrainData_low_ram(self): print(self.RECOMMENDER_NAME + ": Generating train data") start_time_batch = time.time() # Here is important only the structure self.similarity = Compute_Similarity(self.ICM.T, shrink=0, topK=self.topK, normalize=False) S_matrix_contentKNN = self.similarity.compute_similarity() S_matrix_contentKNN = check_matrix(S_matrix_contentKNN, "csr") self._writeLog( self.RECOMMENDER_NAME + ": Collaborative S density: {:.2E}, nonzero cells {}".format( self.S_matrix_target.nnz / self.S_matrix_target.shape[0]**2, self.S_matrix_target.nnz)) self._writeLog( self.RECOMMENDER_NAME + ": Content S density: {:.2E}, nonzero cells {}".format( S_matrix_contentKNN.nnz / S_matrix_contentKNN.shape[0]**2, S_matrix_contentKNN.nnz)) if self.normalize_similarity: # Compute sum of squared sum_of_squared_features = np.array( self.ICM.T.power(2).sum(axis=0)).ravel() sum_of_squared_features = np.sqrt(sum_of_squared_features) num_common_coordinates = 0 estimated_n_samples = int(S_matrix_contentKNN.nnz * (1 + self.add_zeros_quota) * 1.2) self.row_list = np.zeros(estimated_n_samples, dtype=np.int32) self.col_list = np.zeros(estimated_n_samples, dtype=np.int32) self.data_list = np.zeros(estimated_n_samples, dtype=np.float64) num_samples = 0 for row_index in range(self.n_items): start_pos_content = S_matrix_contentKNN.indptr[row_index] end_pos_content = S_matrix_contentKNN.indptr[row_index + 1] content_coordinates = S_matrix_contentKNN.indices[ start_pos_content:end_pos_content] start_pos_target = self.S_matrix_target.indptr[row_index] end_pos_target = self.S_matrix_target.indptr[row_index + 1] target_coordinates = self.S_matrix_target.indices[ start_pos_target:end_pos_target] # Chech whether the content coordinate is associated to a non zero target value # If true, the content coordinate has a collaborative non-zero value # if false, the content coordinate has a collaborative zero value is_common = np.in1d(content_coordinates, target_coordinates) num_common_in_current_row = is_common.sum() num_common_coordinates += num_common_in_current_row for index in range(len(is_common)): if num_samples == estimated_n_samples: dataBlock = 1000000 self.row_list = np.concatenate( (self.row_list, np.zeros(dataBlock, dtype=np.int32))) self.col_list = np.concatenate( (self.col_list, np.zeros(dataBlock, dtype=np.int32))) self.data_list = np.concatenate( (self.data_list, np.zeros(dataBlock, dtype=np.float64))) if is_common[index]: # If cell exists in target matrix, add its value # Otherwise it will remain zero with a certain probability col_index = content_coordinates[index] self.row_list[num_samples] = row_index self.col_list[num_samples] = col_index new_data_value = self.S_matrix_target[row_index, col_index] if self.normalize_similarity: new_data_value *= sum_of_squared_features[ row_index] * sum_of_squared_features[col_index] self.data_list[num_samples] = new_data_value num_samples += 1 elif np.random.rand() <= self.add_zeros_quota: col_index = content_coordinates[index] self.row_list[num_samples] = row_index self.col_list[num_samples] = col_index self.data_list[num_samples] = 0.0 num_samples += 1 if time.time( ) - start_time_batch > 30 or num_samples == S_matrix_contentKNN.nnz * ( 1 + self.add_zeros_quota): print(self.RECOMMENDER_NAME + ": Generating train data. Sample {} ( {:.2f} %) ".format( num_samples, num_samples / S_matrix_contentKNN.nnz * (1 + self.add_zeros_quota) * 100)) sys.stdout.flush() sys.stderr.flush() start_time_batch = time.time() self._writeLog( self.RECOMMENDER_NAME + ": Content S structure has {} out of {} ( {:.2f}%) nonzero collaborative cells" .format(num_common_coordinates, S_matrix_contentKNN.nnz, num_common_coordinates / S_matrix_contentKNN.nnz * 100)) # Discard extra cells at the left of the array self.row_list = self.row_list[:num_samples] self.col_list = self.col_list[:num_samples] self.data_list = self.data_list[:num_samples] data_nnz = sum(np.array(self.data_list) != 0) data_sum = sum(self.data_list) collaborative_nnz = self.S_matrix_target.nnz collaborative_sum = sum(self.S_matrix_target.data) self._writeLog( self.RECOMMENDER_NAME + ": Nonzero collaborative cell sum is: {:.2E}, average is: {:.2E}, " "average over all collaborative data is {:.2E}".format( data_sum, data_sum / data_nnz, collaborative_sum / collaborative_nnz))
def compute_similarity(self, start_col=None, end_col=None, block_size = 100): """ Compute the similarity for the given dataset :param self: :param start_col: column to begin with :param end_col: column to stop before, end_col is excluded :return: """ values = [] rows = [] cols = [] start_time = time.time() start_time_print_batch = start_time processedItems = 0 if self.adjusted_cosine: self.applyAdjustedCosine() elif self.pearson_correlation: self.applyPearsonCorrelation() elif self.tanimoto_coefficient or self.dice_coefficient or self.tversky_coefficient: self.useOnlyBooleanInteractions() # We explore the matrix column-wise self.dataMatrix = check_matrix(self.dataMatrix, 'csc') # Compute sum of squared values to be used in normalization # Along Column sumOfSquared = np.array(self.dataMatrix.power(2).sum(axis=0)).ravel() # Tanimoto does not require the square root to be applied if not (self.tanimoto_coefficient or self.dice_coefficient or self.tversky_coefficient): sumOfSquared = np.sqrt(sumOfSquared) if self.asymmetric_cosine: sumOfSquared_to_1_minus_alpha = np.power(sumOfSquared, 2 * (1 - self.asymmetric_alpha)) sumOfSquared_to_alpha = np.power(sumOfSquared, 2 * self.asymmetric_alpha) self.dataMatrix = check_matrix(self.dataMatrix, 'csc') start_col_local = 0 end_col_local = self.n_columns if start_col is not None and 0 < start_col < self.n_columns: start_col_local = start_col if end_col is not None and start_col_local < end_col < self.n_columns: end_col_local = end_col start_col_block = start_col_local this_block_size = 0 # Compute all similarities for each item using vectorization while start_col_block < end_col_local: end_col_block = min(start_col_block + block_size, end_col_local) this_block_size = end_col_block-start_col_block # All data points for a given item # Prendi tutte le colonne nel range item_data = self.dataMatrix[:, start_col_block:end_col_block] item_data = item_data.toarray().squeeze() # If only 1 feature avoid last dimension to disappear if item_data.ndim == 1: item_data = np.atleast_2d(item_data) if self.use_row_weights: this_block_weights = self.dataMatrix_weighted.T.dot(item_data) else: # Compute item similarities this_block_weights = self.dataMatrix.T.dot(item_data) for col_index_in_block in range(this_block_size): if this_block_size == 1: this_column_weights = this_block_weights else: # Prendi una sola colonna all'index col_index_in_block this_column_weights = this_block_weights[:,col_index_in_block] # Ritorna sempre l'index della diagonale in questa colonna columnIndex = col_index_in_block + start_col_block # L'utente non deve sembrare come uguale a sé stesso this_column_weights[columnIndex] = 0.0 # Apply normalization and shrinkage, ensure denominator != 0 if self.normalize: if self.asymmetric_cosine: denominator = sumOfSquared_to_alpha[columnIndex] * sumOfSquared_to_1_minus_alpha + self.shrink + 1e-6 else: denominator = sumOfSquared[columnIndex] * sumOfSquared + self.shrink + 1e-6 this_column_weights = np.multiply(this_column_weights, 1 / denominator) # Apply the specific denominator for Tanimoto elif self.tanimoto_coefficient: denominator = sumOfSquared[columnIndex] + sumOfSquared - this_column_weights + self.shrink + 1e-6 this_column_weights = np.multiply(this_column_weights, 1 / denominator) elif self.dice_coefficient: denominator = sumOfSquared[columnIndex] + sumOfSquared + self.shrink + 1e-6 this_column_weights = np.multiply(this_column_weights, 1 / denominator) elif self.tversky_coefficient: denominator = this_column_weights + \ (sumOfSquared[columnIndex] - this_column_weights)*self.tversky_alpha + \ (sumOfSquared - this_column_weights)*self.tversky_beta + self.shrink + 1e-6 this_column_weights = np.multiply(this_column_weights, 1 / denominator) # If no normalization or tanimoto is selected, apply only shrink elif self.shrink != 0: this_column_weights = this_column_weights/self.shrink #this_column_weights = this_column_weights.toarray().ravel() # Sort indices and select TopK # Sorting is done in three steps. Faster then plain np.argsort for higher number of items # - Partition the data to extract the set of relevant items # - Sort only the relevant items # - Get the original item index # Trova gli indici dei primi TopK con valori più alti e tieni solo i primi 10 relevant_items_partition = (-this_column_weights).argpartition(self.TopK-1)[0:self.TopK] relevant_items_partition_sorting = np.argsort(-this_column_weights[relevant_items_partition]) top_k_idx = relevant_items_partition[relevant_items_partition_sorting] # Incrementally build sparse matrix, do not add zeros notZerosMask = this_column_weights[top_k_idx] != 0.0 numNotZeros = np.sum(notZerosMask) values.extend(this_column_weights[top_k_idx][notZerosMask]) rows.extend(top_k_idx[notZerosMask]) # Dato che scorro colonna per colonna, nella sps.coo_matrix alla fine questa avrà sempre lo stesso index cols.extend(np.ones(numNotZeros) * columnIndex) # Add previous block size processedItems += this_block_size start_col_block += block_size # End while on columns W_sparse = sps.csr_matrix((values, (rows, cols)), shape=(self.n_columns, self.n_columns), dtype=np.float32) return W_sparse