def test_MLRs(region_sparse, region_dense, base_sparse, base_dense,
bias_sparse, bias_dense):
model_name = "MLRs"
_, y, region_feature_columns = get_test_data(
SAMPLE_SIZE,
sparse_feature_num=region_sparse,
dense_feature_num=region_dense,
prefix='region')
base_x, y, base_feature_columns = get_test_data(
SAMPLE_SIZE,
sparse_feature_num=region_sparse,
dense_feature_num=region_dense,
prefix='base')
bias_x, y, bias_feature_columns = get_test_data(
SAMPLE_SIZE,
sparse_feature_num=region_sparse,
dense_feature_num=region_dense,
prefix='bias')
model = MLR(region_feature_columns,
base_feature_columns,
bias_feature_columns=bias_feature_columns)
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
print(model_name + " test pass!")
def test_MLRs(region_sparse, region_dense, base_sparse, base_dense, bias_sparse, bias_dense):
model_name = "MLRs"
region_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [region_sparse, region_dense]):
if name == "sparse":
for i in range(num):
region_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
region_fd[name].append(name + '_' + str(i))
base_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [base_sparse, base_dense]):
if name == "sparse":
for i in range(num):
base_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
base_fd[name].append(name + '_' + str(i))
bias_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [bias_sparse, bias_dense]):
if name == "sparse":
for i in range(num):
bias_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
bias_fd[name].append(name + '_' + str(i))
model = MLR(region_fd, base_fd, bias_feature_dim_dict=bias_fd)
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
print(model_name + " test pass!")
def test_MLRs(region_sparse, region_dense, base_sparse, base_dense,
bias_sparse, bias_dense):
model_name = "MLRs"
region_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [region_sparse, region_dense]):
if name == "sparse":
for i in range(num):
region_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
region_fd[name].append(name + '_' + str(i))
base_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [base_sparse, base_dense]):
if name == "sparse":
for i in range(num):
base_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
base_fd[name].append(name + '_' + str(i))
bias_fd = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [bias_sparse, bias_dense]):
if name == "sparse":
for i in range(num):
bias_fd[name][name + '_' + str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
bias_fd[name].append(name + '_' + str(i))
model = MLR(region_fd, base_fd, bias_feature_dim_dict=bias_fd)
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
print(model_name + " test pass!")
def test_MLR():
model_name = "MLR"
sample_size = 64
feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
sparse_input = [np.random.randint(0, dim, sample_size)
for dim in feature_dim_dict['sparse'].values()]
dense_input = [np.random.random(sample_size)
for name in feature_dim_dict['dense']]
y = np.random.randint(0, 2, sample_size)
x = sparse_input + dense_input
model = MLR(feature_dim_dict)
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
print(model_name+" test train valid pass!")
model.save_weights(model_name + '_weights.h5')
model.load_weights(model_name + '_weights.h5')
print(model_name+" test save load weight pass!")
save_model(model, model_name + '.h5')
model = load_model(model_name + '.h5', custom_objects)
print(model_name + " test save load model pass!")
print(model_name + " test pass!")
def test_MLR():
model_name = "MLR"
sample_size = 64
feature_dim_dict = {
'sparse': [
SingleFeat('sparse_1', 2),
SingleFeat('sparse_2', 5),
SingleFeat('sparse_3', 10)
],
'dense': [
SingleFeat('dense_1', 0),
SingleFeat('dense_2', 0),
SingleFeat('dense_3', 0)
]
}
sparse_input = [
np.random.randint(0, dim, sample_size)
for feat, dim in feature_dim_dict['sparse']
]
dense_input = [
np.random.random(sample_size) for _ in feature_dim_dict['dense']
]
y = np.random.randint(0, 2, sample_size)
x = sparse_input + dense_input
model = MLR(feature_dim_dict)
check_model(model, model_name, x, y)
def test_MLR():
model_name = "MLR"
region_x, y, region_feature_columns = get_test_data(SAMPLE_SIZE,
3,
3,
prefix='region')
base_x, y, base_feature_columns = get_test_data(SAMPLE_SIZE,
3,
3,
prefix='base')
bias_x, y, bias_feature_columns = get_test_data(SAMPLE_SIZE,
3,
3,
prefix='bias')
model = MLR(region_feature_columns)
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
check_model(model, model_name, region_x, y)
print(model_name + " test pass!")
def test_MLR():
model_name = "MLR"
sample_size = 64
feature_dim_dict = {
'sparse': {
'sparse_1': 2,
'sparse_2': 5,
'sparse_3': 10
},
'dense': ['dense_1', 'dense_2', 'dense_3']
}
sparse_input = [
np.random.randint(0, dim, sample_size)
for dim in feature_dim_dict['sparse'].values()
]
dense_input = [
np.random.random(sample_size) for name in feature_dim_dict['dense']
]
y = np.random.randint(0, 2, sample_size)
x = sparse_input + dense_input
model = MLR(feature_dim_dict)
check_model(model, model_name, x, y)
