def _load_URM(self, filePath, header=False, separator="::"):
URM_builder = IncrementalSparseMatrix(auto_create_col_mapper=True,
auto_create_row_mapper=True)
fileHandle = open(filePath, "r")
numCells = 0
if header:
fileHandle.readline()
for line in fileHandle:
numCells += 1
if (numCells % 1000000 == 0):
print("Processed {} cells".format(numCells))
if (len(line)) > 1:
line = line.split(separator)
line[-1] = line[-1].replace("\n", "")
if not line[2] == "0" and not line[2] == "NaN":
user_id = line[0]
item_id = line[1]
rating = float(line[2])
URM_builder.add_data_lists([user_id], [item_id], [rating])
fileHandle.close()
return URM_builder
def test_IncrementalSparseMatrix_add_rows(self):
import numpy as np
n_rows = 100
n_cols = 200
randomMatrix = sps.random(n_rows, n_cols, density=0.01, format='csr')
incrementalMatrix = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols)
for row in range(n_rows):
row_data = randomMatrix.indices[randomMatrix.indptr[row]:randomMatrix.indptr[row+1]]
incrementalMatrix.add_single_row(row,
row_data,
5.0)
randomMatrix.data = np.ones_like(randomMatrix.data)*5.0
randomMatrix_incremental = incrementalMatrix.get_SparseMatrix()
assert sparse_are_equals(randomMatrix, randomMatrix_incremental)
def test_IncrementalSparseMatrix_add_lists(self):
n_rows = 100
n_cols = 200
randomMatrix = sps.random(n_rows, n_cols, density=0.01, format='coo')
incrementalMatrix = IncrementalSparseMatrix(n_rows=n_rows, n_cols=n_cols)
incrementalMatrix.add_data_lists(randomMatrix.row.copy(),
randomMatrix.col.copy(),
randomMatrix.data.copy())
randomMatrix_incremental = incrementalMatrix.get_SparseMatrix()
assert sparse_are_equals(randomMatrix, randomMatrix_incremental)