def testStratifiedRecallAtk(self):
m = 20
n = 50
r = 3
alpha = 1
X, U, V = SparseUtilsCython.generateSparseBinaryMatrixPL((m, n),
r,
density=0.2,
alpha=alpha,
csarray=True)
itemCounts = numpy.array(X.sum(0) + 1, numpy.int32)
(indPtr, colInds) = X.nonzeroRowsPtr()
indPtr = numpy.array(indPtr, numpy.uint32)
colInds = numpy.array(colInds, numpy.uint32)
k = 5
orderedItems = numpy.random.randint(0, n, m * k)
orderedItems = numpy.reshape(orderedItems, (m, k))
orderedItems = numpy.array(orderedItems, numpy.int32)
beta = 0.5
recalls, denominators = MCEvaluatorCython.stratifiedRecallAtk(
indPtr, colInds, orderedItems, itemCounts, beta)
recalls2 = numpy.zeros(m)
#Now compute recalls from scratch
for i in range(m):
omegai = colInds[indPtr[i]:indPtr[i + 1]]
numerator = 0
for j in range(k):
if orderedItems[i, j] in omegai:
numerator += 1 / itemCounts[orderedItems[i, j]]**beta
denominator = 0
for j in omegai:
denominator += 1 / itemCounts[j]**beta
recalls2[i] = numerator / denominator
nptst.assert_array_equal(recalls, recalls2)
#Now try to match with normal recall
itemCounts = numpy.ones(n, numpy.int32)
recalls, denominators = MCEvaluatorCython.stratifiedRecallAtk(
indPtr, colInds, orderedItems, itemCounts, beta)
recalls2 = MCEvaluatorCython.recallAtk(indPtr, colInds, orderedItems)
nptst.assert_array_equal(recalls, recalls2)
def testStratifiedRecallAtk(self):
m = 20
n = 50
r = 3
alpha = 1
X, U, V = SparseUtilsCython.generateSparseBinaryMatrixPL((m,n), r, density=0.2, alpha=alpha, csarray=True)
itemCounts = numpy.array(X.sum(0)+1, numpy.int32)
(indPtr, colInds) = X.nonzeroRowsPtr()
indPtr = numpy.array(indPtr, numpy.uint32)
colInds = numpy.array(colInds, numpy.uint32)
k = 5
orderedItems = numpy.random.randint(0, n, m*k)
orderedItems = numpy.reshape(orderedItems, (m, k))
orderedItems = numpy.array(orderedItems, numpy.int32)
beta = 0.5
recalls, denominators = MCEvaluatorCython.stratifiedRecallAtk(indPtr, colInds, orderedItems, itemCounts, beta)
recalls2 = numpy.zeros(m)
#Now compute recalls from scratch
for i in range(m):
omegai = colInds[indPtr[i]:indPtr[i+1]]
numerator = 0
for j in range(k):
if orderedItems[i, j] in omegai:
numerator += 1/itemCounts[orderedItems[i, j]]**beta
denominator = 0
for j in omegai:
denominator += 1/itemCounts[j]**beta
recalls2[i] = numerator/denominator
nptst.assert_array_equal(recalls, recalls2)
#Now try to match with normal recall
itemCounts = numpy.ones(n, numpy.int32)
recalls, denominators = MCEvaluatorCython.stratifiedRecallAtk(indPtr, colInds, orderedItems, itemCounts, beta)
recalls2 = MCEvaluatorCython.recallAtk(indPtr, colInds, orderedItems)
nptst.assert_array_equal(recalls, recalls2)
def testGenerateSparseBinaryMatrixPL(self):
m = 200
n = 100
k = 3
density = 0.1
numpy.random.seed(21)
X, U, V = SparseUtilsCython.generateSparseBinaryMatrixPL((m,n), k, density=density, csarray=True)
#Just check that the distributions are roughtly power law
print(numpy.histogram(X.sum(0)))
print(numpy.histogram(X.sum(1)))
self.assertAlmostEqual(X.nnz/float(m*n), density, 2)
self.assertEquals(X.shape, (m, n))
import os
import sys
import sppy.io
import numpy
import logging
from sandbox.util.SparseUtilsCython import SparseUtilsCython
from sandbox.util.SparseUtils import SparseUtils
from sandbox.util.PathDefaults import PathDefaults
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
numpy.random.seed(21)
m = 600
n = 300
k = 8
density = 0.1
X, U, V = SparseUtilsCython.generateSparseBinaryMatrixPL((m,n), k, density=density, alpha=1, csarray=True)
X = SparseUtils.pruneMatrixRows(X, minNnzRows=10)
resultsDir = PathDefaults.getDataDir() + "syntheticRanking/"
if not os.path.exists(resultsDir):
os.mkdir(resultsDir)
matrixFileName = resultsDir + "dataset1.mtx"
sppy.io.mmwrite(matrixFileName, X)
logging.debug("Non-zero elements: " + str(X.nnz) + " shape: " + str(X.shape))
logging.debug("Saved file: " + matrixFileName)
