No data set. Matrix is empty!I about python-recsys HOT 6 CLOSED

Hi,

You don't need this code bit:

from recsys.utils.svdlibc import SVDLIBC
svdlibc = SVDLIBC('/usr/local/python-recsys-master/recsys/data/movielens/ratings.dat')
svdlibc.to_sparse_matrix(sep='::', format={'col':0, 'row':1, 'value':2, 'ids': int})
svdlibc.compute(k=100)
svd = svdlibc.export()

svd can be created using either divisi2 SVD (default), or by calling SVDLIBC, the external C library, that runs faster, and uses less memory.

Looking at your code, you're doing both things, and you only need to do one.
You can have a look here for (quick start example): http://ocelma.net/software/python-recsys/build/html/quickstart.html (step 8 is an alternative version of step 2).

I hope this helps!

from python-recsys.

thank you very much！another question...now i get the svd model and i save it to '/tmp/Svd_model'

how could i get the RMSE and MAE of this model?under the path /python-recsys-master/python-recsys-master/draft,there is a code named test_svd.py ,but everytime i run it ,there is no result in a long time....Is there alternate way to get the model's Evaluation?thanks a lot for you kindly reply!

from python-recsys.

Regarding your RMSE and MAE question, try this:

#Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
    try:
        pred_rating = svd.predict(item_id, user_id)
        rmse.add(rating, pred_rating)
        mae.add(rating, pred_rating)
        print 'RMSE=%s' % rmse.compute()
        print 'MAE=%s' % mae.compute()
    except KeyError:
        continue

print 'Final RMSE=%s' % rmse.compute()
print 'Final MAE=%s' % mae.compute()

from python-recsys.

According to your guide,i write a code named MySVDNeiStart.py,in order to compute the RMSE and MAE of My SVD++ Model,but After 30 minutes ,it still has no result,could you help me?

import recsys.algorithm
from recsys.algorithm.factorize import SVD,SVDNeighbourhood
from recsys.datamodel.data import Data
recsys.algorithm.VERBOSE = True
filename = '/usr/local/python-recsys-master/recsys/data/movielens/ratings.dat'
data = Data()
format = {'col':0, 'row':1, 'value':2, 'ids': int}
data.load(filename, sep='::', format=format)
train, test = data.split_train_test(percent=80) # 80% train, 20% test

svd = SVDNeighbourhood()
svd.set_data(train)
svd.compute(k=100, min_values=5, pre_normalize=None, mean_center=True, post_normalize=True, savefile='/tmp/svd_neig')

#Evaluation using prediction-based metrics

from recsys.algorithm.factorize import SVD
from recsys.evaluation.prediction import RMSE, MAE
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = svd.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue

print 'Final RMSE=%s' % rmse.compute()
print 'Final MAE=%s' % mae.compute()

from python-recsys.

instead writing a single file to run, i use python console to check code. It work perfect like charm 💯

from python-recsys.

Perfect. Glad to hear that it worked fine!

from python-recsys.