def test_score_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
inp = [{"user": 10, "item": 100},
{"user": 10, "item": 110},
{"user": 12, "item": 120}]
inp = pd.DataFrame(inp)
tf.fit(inp)
uid = tf.data_map[tf.get_user_column()][10]
iid = tf.data_map[tf.get_item_column()][100]
tf.factors[0][uid, 0] = 0
tf.factors[0][uid, 1] = 1
tf.factors[1][iid, 0] = 1
tf.factors[1][iid, 1] = 5
self.assertEqual(0*1+1*5, tf.get_score(10, 100))
def test_tensor_score_against_testfm(self):
"""
[recommendation.models.TensorCoFi] Test tensorcofi scores with test.fm benchmark
"""
evaluator = Evaluator()
tc = TensorCoFi(n_users=len(self.df.user.unique()), n_items=len(self.df.item.unique()), n_factors=2)
ptc = PyTensorCoFi()
training, testing = testfm.split.holdoutByRandom(self.df, 0.9)
items = training.item.unique()
tc.fit(training)
ptc.fit(training)
tc_score = evaluator.evaluate_model(tc, testing, all_items=items)[0]
ptc_score = evaluator.evaluate_model(ptc, testing, all_items=items)[0]
assert abs(tc_score-ptc_score) < .15, \
"TensorCoFi score is not close enough to testfm benchmark (%.3f != %.3f)" % (tc_score, ptc_score)
def test_ids_returns_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
inp = [{"user": 10, "item": 100},
{"user": 10, "item": 110},
{"user": 12, "item": 120}]
inp = pd.DataFrame(inp)
tf.fit(inp)
# Test the id in map
uid = tf.data_map[tf.get_user_column()][10]
iid = tf.data_map[tf.get_item_column()][100]
self.assertEquals(uid, 0)
self.assertEquals(iid, 0)
# Test number of factors
self.assertEquals(len(tf.factors[0][uid, :]), tf.number_of_factors)
self.assertEquals(len(tf.factors[1][iid, :]), tf.number_of_factors)
def test_nogil_against_std_05(self):
"""
[EVALUATOR] Test the groups measure differences between python and c implementations for 5% training
"""
df = pd.read_csv(resource_filename(testfm.__name__, 'data/movielenshead.dat'),
sep="::", header=None, names=['user', 'item', 'rating', 'date', 'title'])
model = PyTensorCoFi()
ev = Evaluator(False)
ev_nogil = Evaluator()
results = {"implementation": [], "measure": []}
for i in range(SAMPLE_SIZE_FOR_TEST):
training, testing = testfm.split.holdoutByRandom(df, 0.05)
model.fit(training)
results["implementation"].append("Cython"), results["measure"].append(ev_nogil.evaluate_model(model, testing)[0])
results["implementation"].append("Python"), results["measure"].append(ev.evaluate_model(model, testing)[0])
#####################
# ANOVA over result #
#####################
assert_equality_in_groups(results, alpha=ALPHA, groups="implementation", test_var="measure")
def test_score_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
inp = [{
"user": 10,
"item": 100
}, {
"user": 10,
"item": 110
}, {
"user": 12,
"item": 120
}]
inp = pd.DataFrame(inp)
tf.fit(inp)
uid = tf.data_map[tf.get_user_column()][10]
iid = tf.data_map[tf.get_item_column()][100]
tf.factors[0][uid, 0] = 0
tf.factors[0][uid, 1] = 1
tf.factors[1][iid, 0] = 1
tf.factors[1][iid, 1] = 5
self.assertEqual(0 * 1 + 1 * 5, tf.get_score(10, 100))
def test_ids_returns_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
inp = [{
"user": 10,
"item": 100
}, {
"user": 10,
"item": 110
}, {
"user": 12,
"item": 120
}]
inp = pd.DataFrame(inp)
tf.fit(inp)
# Test the id in map
uid = tf.data_map[tf.get_user_column()][10]
iid = tf.data_map[tf.get_item_column()][100]
self.assertEquals(uid, 0)
self.assertEquals(iid, 0)
# Test number of factors
self.assertEquals(len(tf.factors[0][uid, :]), tf.number_of_factors)
self.assertEquals(len(tf.factors[1][iid, :]), tf.number_of_factors)
def test_fit_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
tf.fit(self.df)
#item and user are row vectors
self.assertEqual(len(self.df.user.unique()), tf.factors[0].shape[0])
self.assertEqual(len(self.df.item.unique()), tf.factors[1].shape[0])
def test_fit_for_python_version(self):
tf = PyTensorCoFi(n_factors=2)
tf.fit(self.df)
#item and user are row vectors
self.assertEqual(len(self.df.user.unique()), tf.factors[0].shape[0])
self.assertEqual(len(self.df.item.unique()), tf.factors[1].shape[0])
from testfm.evaluation.evaluator import Evaluator
from pkg_resources import resource_filename
from testfm.evaluation.parameter_tuning import ParameterTuning
if __name__ == "__main__":
eval = Evaluator(
) # Call this before loading the data to save memory (fork of process takes place)
# Prepare the data
df = pd.read_csv(resource_filename(testfm.__name__,
'data/movielenshead.dat'),
sep="::",
header=None,
names=['user', 'item', 'rating', 'date', 'title'])
print df.head()
training, testing = testfm.split.holdoutByRandom(df, 0.9)
print "Tuning the parameters."
tr, validation = testfm.split.holdoutByRandom(training, 0.7)
pt = ParameterTuning()
pt.set_max_iterations(100)
pt.set_z_value(90)
tf_params = pt.get_best_params(TensorCoFi, tr, validation)
print tf_params
tf = TensorCoFi()
tf.set_params(**tf_params)
tf.fit(training)
print tf.get_name().ljust(50),
print eval.evaluate_model(tf, testing, all_items=training.item.unique())
