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_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_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_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(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(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