def test_weights_categorical():
'''
This should get :
["{test-guid-1}", "{test-guid-2}", "{test-guid-3}", "{test-guid-4}"],
["{test-guid-9}", "{test-guid-10}", "{test-guid-11}", "{test-guid-12}"]
from the first two entries in the sample data where the geo_city
data
'''
# Create a new instance of a SimilarityRecommender.
ctx = create_cat_test_ctx()
ctx2 = create_cts_test_ctx()
wrapped = ctx2.wrap(ctx)
r = SimilarityRecommender(wrapped)
# In the ensemble method recommendations should be a sorted list of tuples
# containing [(guid, weight), (guid, weight)... (guid, weight)].
recommendation_list = r.recommend(generate_a_fake_taar_client(), 2)
assert len(recommendation_list) == 2
# Make sure the structure of the recommendations is correct and that we recommended the the right addons.
for recommendation, weight in recommendation_list:
assert isinstance(recommendation, six.string_types)
assert isinstance(weight, float)
# Test that sorting is appropriate.
rec0 = recommendation_list[0]
rec1 = recommendation_list[1]
rec0_weight = rec0[1]
rec1_weight = rec1[1]
assert rec0_weight > rec1_weight > 0
def test_soft_fail(test_ctx, caplog):
# Create a new instance of a SimilarityRecommender.
with mock_install_no_data(test_ctx):
r = SimilarityRecommender(test_ctx)
# Don't recommend if the source files cannot be found.
assert not r.can_recommend({})
def test_weights_continuous():
# Create a new instance of a SimilarityRecommender.
ctx = create_cts_test_ctx()
r = SimilarityRecommender(ctx)
# In the ensemble method recommendations should be a sorted list of tuples
# containing [(guid, weight), (guid, weight)... (guid, weight)].
recommendation_list = r.recommend(generate_a_fake_taar_client(), 2)
with open('/tmp/similarity_recommender.json', 'w') as fout:
fout.write(json.dumps(recommendation_list))
# Make sure the structure of the recommendations is correct and
# that we recommended the the right addons.
assert len(recommendation_list) == 2
for recommendation, weight in recommendation_list:
assert isinstance(recommendation, six.string_types)
assert isinstance(weight, float)
# Test that sorting is appropriate.
rec0 = recommendation_list[0]
rec1 = recommendation_list[1]
rec0_weight = rec0[1]
rec1_weight = rec1[1]
# Duplicate presence of test-guid-1 should mean rec0_weight is double
# rec1_weight, and both should be greater than 1.0
assert rec0_weight > rec1_weight > 1.0
def test_weights_continuous(mock_s3_continuous_data):
# Create a new instance of a SimilarityRecommender.
r = SimilarityRecommender()
# In the ensemble method recommendations shoudl be a sorted list of tuples
# containing [(guid, weight), (guid, weight)... (guid, weight)].
recommendation_list = r.recommend(generate_a_fake_taar_client(), 2)
with open('/tmp/similarity_recommender.json', 'w') as fout:
fout.write(json.dumps(recommendation_list))
# Make sure the structure of the recommendations is correct and
# that we recommended the the right addons.
assert len(recommendation_list) == 2
for recommendation, weight in recommendation_list:
assert isinstance(recommendation, str)
assert isinstance(weight, float)
# Test that sorting is appropriate.
rec0 = recommendation_list[0]
rec1 = recommendation_list[1]
rec0_weight = rec0[1]
rec1_weight = rec1[1]
assert rec0_weight == rec1_weight > 0
def test_soft_fail(test_ctx, caplog):
# Create a new instance of a SimilarityRecommender.
ctx = install_no_data(test_ctx)
r = SimilarityRecommender(ctx)
# Don't recommend if the source files cannot be found.
assert not r.can_recommend({})
assert not check_matrix_built(caplog)
def test_soft_fail():
# Create a new instance of a SimilarityRecommender.
ctx = Context()
ctx['utils'] = MockNoDataUtils()
ctx['clock'] = Clock()
ctx['cache'] = JSONCache(ctx)
r = SimilarityRecommender(ctx)
# Don't recommend if the source files cannot be found.
assert not r.can_recommend({})
def test_compute_clients_dist(test_ctx):
# Test the distance function computation.
with mock_install_continuous_data(test_ctx):
r = SimilarityRecommender(test_ctx)
test_clients = [
{
"client_id": "test-client-002",
"activeAddons": [],
"geo_city": "sfo-us",
"subsession_length": 1,
"locale": "en-US",
"os": "windows",
"bookmark_count": 1,
"tab_open_count": 1,
"total_uri": 1,
"unique_tlds": 1,
},
{
"client_id": "test-client-003",
"activeAddons": [],
"geo_city": "brasilia-br",
"subsession_length": 1,
"locale": "br-PT",
"os": "windows",
"bookmark_count": 10,
"tab_open_count": 1,
"total_uri": 1,
"unique_tlds": 1,
},
{
"client_id": "test-client-004",
"activeAddons": [],
"geo_city": "brasilia-br",
"subsession_length": 100,
"locale": "br-PT",
"os": "windows",
"bookmark_count": 10,
"tab_open_count": 10,
"total_uri": 100,
"unique_tlds": 10,
},
]
per_client_test = []
# Compute a different set of distances for each set of clients.
cache = r._get_cache({})
for tc in test_clients:
test_distances = r.compute_clients_dist(tc, cache)
assert len(test_distances) == len(CONTINUOUS_FEATURE_FIXTURE_DATA)
per_client_test.append(test_distances[2][0])
# Ensure the different clients also had different distances to a specific donor.
assert per_client_test[0] >= per_client_test[1] >= per_client_test[2]
def test_recommendations(test_ctx):
# Create a new instance of a SimilarityRecommender.
ctx = install_continuous_data(test_ctx)
r = SimilarityRecommender(ctx)
recommendation_list = r.recommend(generate_a_fake_taar_client(), 1)
assert isinstance(recommendation_list, list)
assert len(recommendation_list) == 1
recommendation, weight = recommendation_list[0]
# Make sure that the reported addons are the expected ones from the most similar donor.
assert "{test-guid-1}" == recommendation
assert type(weight) == np.float64
def test_recommendations(instantiate_mocked_s3_bucket):
# Create a new instance of a SimilarityRecommender.
r = SimilarityRecommender()
recommendations = r.recommend(generate_a_fake_taar_client(), 10)
# Make sure the structure of the recommendations is correct and that we recommended the the right addons.
assert isinstance(recommendations, list)
# Make sure that the reported addons are the expected ones from the most similar donor.
assert "{test-guid-9}" in recommendations
assert "{test-guid-10}" in recommendations
assert "{test-guid-11}" in recommendations
assert "{test-guid-12}" in recommendations
assert len(recommendations) == 4
def test_recommendations(mock_s3_continuous_data):
# Create a new instance of a SimilarityRecommender.
r = SimilarityRecommender()
# TODO: clobber the SimilarityRecommender::lr_curves
recommendation_list = r.recommend(generate_a_fake_taar_client(), 1)
assert isinstance(recommendation_list, list)
assert len(recommendation_list) == 1
recommendation, weight = recommendation_list[0]
# Make sure that the reported addons are the expected ones from the most similar donor.
assert "{test-guid-1}" == recommendation
assert type(weight) == np.float64
def test_get_lr(test_ctx):
# Tests that the likelihood ratio values are not empty for extreme values and are realistic.
with mock_install_continuous_data(test_ctx):
r = SimilarityRecommender(test_ctx)
cache = r._get_cache({})
assert r.get_lr(0.0001, cache) is not None
assert r.get_lr(10.0, cache) is not None
assert r.get_lr(0.001, cache) > r.get_lr(5.0, cache)
def test_distance_functions(test_ctx):
# Tests the similarity functions via expected output when passing
# modified client data.
with mock_install_continuous_data(test_ctx):
r = SimilarityRecommender(test_ctx)
# Generate a fake client.
test_client = generate_a_fake_taar_client()
recs = r.recommend(test_client, 10)
assert len(recs) > 0
# Make it a generally poor match for the donors.
test_client.update({
"total_uri": 10,
"bookmark_count": 2,
"subsession_length": 10
})
all_client_values_zero = test_client
# Make all categorical variables non-matching with any donor.
all_client_values_zero.update({
key: "zero"
for key in test_client.keys() if key in CATEGORICAL_FEATURES
})
recs = r.recommend(all_client_values_zero, 10)
assert len(recs) == 0
# Make all continuous variables equal to zero.
all_client_values_zero.update({
key: 0
for key in test_client.keys() if key in CONTINUOUS_FEATURES
})
recs = r.recommend(all_client_values_zero, 10)
assert len(recs) == 0
# Make all categorical variables non-matching with any donor.
all_client_values_high = test_client
all_client_values_high.update({
key: "one billion"
for key in test_client.keys() if key in CATEGORICAL_FEATURES
})
recs = r.recommend(all_client_values_high, 10)
assert len(recs) == 0
# Make all continuous variables equal to a very high numerical value.
all_client_values_high.update({
key: 1e60
for key in test_client.keys() if key in CONTINUOUS_FEATURES
})
recs = r.recommend(all_client_values_high, 10)
assert len(recs) == 0
# Test for 0.0 values if j_c is not normalized and j_d is fine.
j_c = 0.0
j_d = 0.42
assert abs(j_c * j_d) == 0.0
assert abs((j_c + 0.01) * j_d) != 0.0
def test_get_lr():
# Tests that the likelihood ratio values are not empty for extreme values and are realistic.
ctx = create_cts_test_ctx()
r = SimilarityRecommender(ctx)
assert r.get_lr(0.0001) is not None
assert r.get_lr(10.0) is not None
assert r.get_lr(0.001) > r.get_lr(5.0)
def test_get_lr(test_ctx):
# Tests that the likelihood ratio values are not empty for extreme values and are realistic.
ctx = install_continuous_data(test_ctx)
r = SimilarityRecommender(ctx)
assert r.get_lr(0.0001) is not None
assert r.get_lr(10.0) is not None
assert r.get_lr(0.001) > r.get_lr(5.0)
def test_can_recommend(test_ctx, caplog):
caplog.set_level(logging.INFO)
# Create a new instance of a SimilarityRecommender.
ctx = install_continuous_data(test_ctx)
r = SimilarityRecommender(ctx)
assert check_matrix_built(caplog)
# Test that we can't recommend if we have not enough client info.
assert not r.can_recommend({})
# Test that we can recommend for a normal client.
assert r.can_recommend(generate_a_fake_taar_client())
# Check that we can not recommend if any required client field is missing.
required_fields = CATEGORICAL_FEATURES + CONTINUOUS_FEATURES
for required_field in required_fields:
profile_without_x = generate_a_fake_taar_client()
# Make an empty value in a required field in the client info dict.
profile_without_x[required_field] = None
assert not r.can_recommend(profile_without_x)
# Completely remove (in place) the entire required field from the dict.
del profile_without_x[required_field]
assert not r.can_recommend(profile_without_x)
def test_recompute_matrices(test_ctx, caplog):
caplog.set_level(logging.INFO)
# Create a new instance of a SimilarityRecommender.
ctx = install_continuous_data(test_ctx)
r = SimilarityRecommender(ctx)
# Reloading the donors pool should reconstruct the matrices
caplog.clear()
r._donors_pool.force_expiry()
r.donors_pool
assert check_matrix_built(caplog)
# Reloading the LR curves should reconstruct the matrices
caplog.clear()
r._lr_curves.force_expiry()
r.lr_curves
assert check_matrix_built(caplog)
def test_can_recommend(instantiate_mocked_s3_bucket):
# Create a new instance of a SimilarityRecommender.
r = SimilarityRecommender()
# Test that we can't recommend if we have not enough client info.
assert not r.can_recommend({})
# Test that we can recommend for a normal client.
assert r.can_recommend(generate_a_fake_taar_client())
# Check that we can not recommend if any required client field is missing.
required_fields = CATEGORICAL_FEATURES + CONTINUOUS_FEATURES
for required_field in required_fields:
profile_without_x = generate_a_fake_taar_client()
# Make an empty value in a required field in the client info dict.
profile_without_x[required_field] = None
assert not r.can_recommend(profile_without_x)
# Completely remove (in place) the entire required field from the dict.
del profile_without_x[required_field]
assert not r.can_recommend(profile_without_x)
def test_recommender_str():
# Tests that the string representation of the recommender is correct.
ctx = create_cts_test_ctx()
r = SimilarityRecommender(ctx)
assert str(r) == "SimilarityRecommender"
def test_soft_fail():
# Create a new instance of a SimilarityRecommender.
r = SimilarityRecommender()
# Don't recommend if the source files cannot be found.
assert not r.can_recommend({})
def test_get_lr(instantiate_mocked_s3_bucket):
# Tests that the likelihood ratio values are not empty for extreme values and are realistic.
r = SimilarityRecommender()
assert r.get_lr(0.0001) is not None
assert r.get_lr(10.0) is not None
assert r.get_lr(0.001) > r.get_lr(5.0)
def test_recommender_str(instantiate_mocked_s3_bucket):
# Tests that the string representation of the recommender is correct.
r = SimilarityRecommender()
assert str(r) == "SimilarityRecommender"
addons = client['installed_addons']
num_mask = get_num_masked(addons)
masked, unmasked = random_partition(addons, num_mask)
client['installed_addons'] = unmasked
client['masked_addons'] = masked
return client
training_masked = map(mask_addons, training)
recommenders = {
"collaborative": CollaborativeRecommender(),
"similarity": SimilarityRecommender(),
"locale": LocaleRecommender("./top_addons_by_locale.json"),
"legacy": LegacyRecommender()
}
def compute_features(client_data):
recommendations = []
matrix = []
for _, recommender in recommenders.items():
recommendations.append(recommender.get_weighted_recommendations(client_data))
for addon in whitelist:
matrix.append([features[addon] for features in recommendations])
return client_data, np.array(matrix)
def test_recommender_str(mock_s3_continuous_data):
# Tests that the string representation of the recommender is correct.
r = SimilarityRecommender()
assert str(r) == "SimilarityRecommender"
def test_get_lr(mock_s3_continuous_data):
# Tests that the likelihood ratio values are not empty for extreme values and are realistic.
r = SimilarityRecommender()
assert r.get_lr(0.0001) is not None
assert r.get_lr(10.0) is not None
assert r.get_lr(0.001) > r.get_lr(5.0)
def test_recommender_str(test_ctx):
# Tests that the string representation of the recommender is correct.
ctx = install_continuous_data(test_ctx)
r = SimilarityRecommender(ctx)
assert str(r) == "SimilarityRecommender"