def readDBandSplit(dbfile):
r = reader.tabSepReader(dbfile)
fulltrain, testDict = split.split(
r.getR(), SEED1)
trainingDict, evalDict = split.split(
fulltrain, SEED2)
output = open("splits.npz", "wb")
cPickle.dump(r, output, -1)
cPickle.dump(trainingDict, output, -1)
cPickle.dump(fulltrain, output, -1)
cPickle.dump(testDict, output, -1)
cPickle.dump(evalDict, output, -1)
output.close()
return r, trainingDict, fulltrain, testDict, evalDict
# Reading a database file called "u.data"
import reader
r = reader.tabSepReader("u.data")
# Get 10 recommendations with simple algorithms
# for userid 201.
#import primitive
#import external
#rand = primitive.randomRec(r.getR())
#getRec = external.getExternalRec(rand.getRec, r)
#print getRec(97, 10)
#
## Train a MF model.
#import mf
#
#reg = 0.01 # Regularization constant
#ler = 0.1 # Learning rate
#features = 150 # number of features
#EPOCHS = 3 # number of epochs
#
#W, H = mf.learnModel(
# r.getMaxUid(), r.getMaxIid(),
# reg, reg, reg, ler, r.getR(),
# features, EPOCHS,
# r.numberOfTransactions,
# mf.logLoss, mf.dLogLoss) # With logLoss it will be BPRMF
#
## Get recommendations with a MF model.
#import test
#import external
#t = test.MFtest(W, H, r.getR())