def get_linear_logit(features,
linear_feature_columns,
units=1,
use_bias=False,
seed=1024,
prefix='linear',
l2_reg=0):
features = features
linear_feature_columns = linear_feature_columns
units = 1
use_bias = False
seed = 1024
prefix = 'linear'
l2_reg = 0
for i in range(len(linear_feature_columns)):
if linear_feature_columns[i]['feat_cat'] == 'sparse':
linear_feature_columns[i]['embedding_dim'] = 3
linear_feature_columns[i]['embeddings_initializer'] = Zeros()
linear_emb_list = [
input_from_feature_columns(features,
linear_feature_columns,
l2_reg,
seed,
prefix=prefix + str(i))[0]
for i in range(units)
]
_, dense_input_list = input_from_feature_columns(features,
linear_feature_columns,
l2_reg,
seed,
prefix=prefix)
linear_logit_list = []
for i in range(units):
if len(linear_emb_list[i]) > 0 and len(dense_input_list) > 0:
sparse_input = concat_func(linear_emb_list[i])
dense_input = concat_func(dense_input_list)
linear_logit = Linear(l2_reg, mode=2, use_bias=use_bias,
seed=seed)([sparse_input, dense_input])
elif len(linear_emb_list[i]) > 0:
sparse_input = concat_func(linear_emb_list[i])
linear_logit = Linear(l2_reg, mode=0, use_bias=use_bias,
seed=seed)(sparse_input)
elif len(dense_input_list) > 0:
dense_input = concat_func(dense_input_list)
linear_logit = Linear(l2_reg, mode=1, use_bias=use_bias,
seed=seed)(dense_input)
else:
# raise NotImplementedError
return add_func([])
linear_logit_list.append(linear_logit)
return concat_func(linear_logit_list)
def get_linear_logit(features,
feature_columns,
units=1,
use_bias=False,
seed=1024,
prefix='linear',
l2_reg=0):
linear_feature_columns = copy(feature_columns)
for i in range(len(linear_feature_columns)):
if isinstance(linear_feature_columns[i], SparseFeat):
linear_feature_columns[i] = linear_feature_columns[i]._replace(
embedding_dim=1, embeddings_initializer=Zeros())
if isinstance(linear_feature_columns[i], VarLenSparseFeat):
linear_feature_columns[i] = linear_feature_columns[i]._replace(
sparsefeat=linear_feature_columns[i].sparsefeat._replace(
embedding_dim=1, embeddings_initializer=Zeros()))
linear_emb_list = [
input_from_feature_columns(features,
linear_feature_columns,
l2_reg,
seed,
prefix=prefix + str(i))[0]
for i in range(units)
]
_, dense_input_list = input_from_feature_columns(features,
linear_feature_columns,
l2_reg,
seed,
prefix=prefix)
linear_logit_list = []
for i in range(units):
if len(linear_emb_list[i]) > 0 and len(dense_input_list) > 0:
sparse_input = concat_func(linear_emb_list[i])
dense_input = concat_func(dense_input_list)
linear_logit = Linear(l2_reg, mode=2, use_bias=use_bias,
seed=seed)([sparse_input, dense_input])
elif len(linear_emb_list[i]) > 0:
sparse_input = concat_func(linear_emb_list[i])
linear_logit = Linear(l2_reg, mode=0, use_bias=use_bias,
seed=seed)(sparse_input)
elif len(dense_input_list) > 0:
dense_input = concat_func(dense_input_list)
linear_logit = Linear(l2_reg, mode=1, use_bias=use_bias,
seed=seed)(dense_input)
else:
# raise NotImplementedError
return add_func([])
linear_logit_list.append(linear_logit)
return concat_func(linear_logit_list)
#########################################################################################################
print('group_embedding_dict',group_embedding_dict)
print('dense_value_list',dense_value_list)
cc=[]
for k, v in group_embedding_dict.items():
cc.append(v)
cc1=concat_func(cc[0], axis=1)
cc2=FM()(cc1)
# cc=[FM()(concat_func(v, axis=1))
# for k, v in group_embedding_dict.items() if k in fm_group]
fm_logit = add_func([cc2])
dnn_input = combined_dnn_input(list(chain.from_iterable(
group_embedding_dict.values())), dense_value_list)
dnn_output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(dnn_input)
dnn_logit = tf.keras.layers.Dense(
1, use_bias=False, kernel_initializer=tf.keras.initializers.glorot_normal(seed=seed))(dnn_output)
final_logit = add_func([linear_logit, fm_logit, dnn_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
def DeepFM(linear_feature_columns,
dnn_feature_columns,
fm_group=[DEFAULT_GROUP_NAME],
dnn_hidden_units=(128, 128),
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
l2_reg_dnn=0,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
task='binary'):
"""Instantiates the DeepFM Network architecture.
:param linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
:param fm_group: list, group_name of features that will be used to do feature interactions.
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN
:param l2_reg_linear: float. L2 regularizer strength applied to linear part
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
#构建模型的输入张量
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
print("#" * 10)
print(features)
inputs_list = list(features.values())
# 构建线性张量
linear_logit = get_linear_logit(features,
linear_feature_columns,
seed=seed,
prefix='linear',
l2_reg=l2_reg_linear)
group_embedding_dict, dense_value_list = input_from_feature_columns(
features,
dnn_feature_columns,
l2_reg_embedding,
seed,
support_group=True)
print('group_embedding_dict', group_embedding_dict)
print('dense_value_list', dense_value_list)
fm_logit = add_func([
FM()(concat_func(v, axis=1)) for k, v in group_embedding_dict.items()
if k in fm_group
])
dnn_input = combined_dnn_input(
list(chain.from_iterable(group_embedding_dict.values())),
dense_value_list)
dnn_output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(dnn_input)
dnn_logit = tf.keras.layers.Dense(
1,
use_bias=False,
kernel_initializer=tf.keras.initializers.glorot_normal(
seed=seed))(dnn_output)
final_logit = add_func([linear_logit, fm_logit, dnn_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model