def test_NFM():
name = "NFM"
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 = NFM(feature_dim_dict, embedding_size=8,
hidden_size=[32, 32], keep_prob=0.5, )
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
print(name+" test train valid pass!")
model.save_weights(name + '_weights.h5')
model.load_weights(name + '_weights.h5')
print(name+" test save load weight pass!")
save_model(model, name + '.h5')
model = load_model(name + '.h5', custom_objects)
print(name + " test save load model pass!")
print(name + " test pass!")
def test_NFM(hidden_size, sparse_feature_num):
model_name = "NFM"
sample_size = SAMPLE_SIZE
x, y, feature_columns = get_test_data(sample_size, sparse_feature_num=sparse_feature_num,
dense_feature_num=sparse_feature_num)
model = NFM(feature_columns, feature_columns, dnn_hidden_units=[8, 8], dnn_dropout=0.5)
check_model(model, model_name, x, y)
def test_NFM(hidden_size, sparse_feature_num):
model_name = "NFM"
sample_size = 64
x, y, feature_dim_dict = get_test_data(
sample_size, sparse_feature_num, sparse_feature_num)
model = NFM(feature_dim_dict, embedding_size=8,
hidden_size=[32, 32], keep_prob=0.5, )
check_model(model, model_name, x, y)
def test_NFM(hidden_size, sparse_feature_num):
model_name = "NFM"
sample_size = SAMPLE_SIZE
x, y, feature_dim_dict = get_test_data(sample_size, sparse_feature_num,
sparse_feature_num)
model = NFM(
feature_dim_dict,
embedding_size=8,
dnn_hidden_units=[32, 32],
dnn_dropout=0.5,
)
check_model(model, model_name, x, y)
def test_NFM(hidden_size, sparse_feature_num):
model_name = "NFM"
sample_size = 64
feature_dim_dict = {"sparse": {}, 'dense': []}
for name, num in zip(["sparse", "dense"], [sparse_feature_num, sparse_feature_num]):
if name == "sparse":
for i in range(num):
feature_dim_dict[name][name + '_' +
str(i)] = np.random.randint(1, 10)
else:
for i in range(num):
feature_dim_dict[name].append(name + '_' + str(i))
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 = NFM(feature_dim_dict, embedding_size=8,
hidden_size=[32, 32], keep_prob=0.5, )
check_model(model, model_name, x, y)
data[feature] = lbe.fit_transform(data[feature])
# 计算每个特征中的 不同特征值的个数
fixlen_feature_columns = [
SparseFeat(feature, data[feature].nunique()) for feature in sparse_features
]
linear_feature_columns = fixlen_feature_columns
dnn_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
# 将数据集切分成训练集和测试集
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name].values for name in feature_names}
test_model_input = {name: test[name].values for name in feature_names}
# 使用NFM进行训练
model = NFM(linear_feature_columns, dnn_feature_columns, task='regression')
model.compile(
"adam",
"mse",
metrics=['mse'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=1,
verbose=True,
validation_split=0.2,
)
# 使用NFM进行预测
pred_ans = model.predict(test_model_input, batch_size=256)
dnn_feature_columns = fixlen_feature_columns
linear_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(linear_feature_columns +
dnn_feature_columns)
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
# 4.Define Model,train,predict and evaluate
model = NFM(linear_feature_columns,
dnn_feature_columns,
task='binary',
dnn_hidden_units=(400, 400, 400),
dnn_dropout=0.5)
model.compile(
"adam",
"binary_crossentropy",
metrics=['binary_crossentropy'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=10,
verbose=2,
validation_split=0.2,