def test_DIN_att():
model_name = "DIN_att"
x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
model = DIN(
feature_dim_dict,
behavior_feature_list,
hist_len_max=4,
embedding_size=8,
use_din=True,
hidden_size=[4, 4, 4],
keep_prob=0.6,
)
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x, y, verbose=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!")
# try:
# save_model(model, name + '.h5')
# model = load_model(name + '.h5', custom_objects)
# print(name + " test save load model pass!")
# except:
# print("【Error】There is a bug when save model use Dice---------------------------------------------------")
print(model_name + " test pass!")
def test_DIN_sum():
model_name = "DIN_sum"
x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
model = DIN(feature_dim_dict,
behavior_feature_list,
hist_len_max=4,
embedding_size=8,
use_din=False,
hidden_size=[4, 4, 4],
keep_prob=0.6,
activation="sigmoid")
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x, y, verbose=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_DIN_att():
model_name = "DIN_att"
x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
model = DIN(feature_dim_dict, behavior_feature_list, hist_len_max=4, embedding_size=8,
use_din=True, hidden_size=[4, 4, 4], keep_prob=0.6,)
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x, y, verbose=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!")
# try:
# save_model(model, name + '.h5')
# model = load_model(name + '.h5', custom_objects)
# print(name + " test save load model pass!")
# except:
# print("【Error】There is a bug when save model use Dice---------------------------------------------------")
print(model_name + " test pass!")
def example_din():
"""
1. 生成训练数据为txt格式的，逗号分割字段
2. 转换成tfrecord
3. 读取数据，区分dense, sparse, VarLenSparse, 用户行为序列特征
4. 分别喂到模型中，看看会怎么样
:return:
"""
# x, y, feature_columns, behavior_feature_list = get_xy_fd() #说一下哪几列是当前的item需要和历史的行为进行attention的。所以之后就可以尝试，还是像之前一样读数据，然后只是把需要attention的列名单拿出来，放到list中就可以了
x, y, feature_columns, behavior_feature_list = get_xy_from_txt(
) #说一下哪几列是当前的item需要和历史的行为进行attention的。所以之后就可以尝试，还是像之前一样读数据，然后只是把需要attention的列名单拿出来，放到list中就可以了
# dataset = tf.data.Dataset.from_tensor_slices((x.values, y.values))
model = DIN(feature_columns, behavior_feature_list)
model.compile(
'adam',
keras.losses.binary_crossentropy,
metrics=[keras.metrics.AUC(), keras.metrics.categorical_accuracy])
history = model.fit(x, y, verbose=1, epochs=10, validation_split=0.5)
# history = model.fit(dataset, verbose=1, epochs=10, validation_data=(x,y))
# history = model.fit(dataset, verbose=1, epochs=10, validation_split=0.5)
print("history: ", history)
def get_xy_fd():
feature_dim_dict = {"sparse": [SingleFeat('user', 3), SingleFeat(
'gender', 2), SingleFeat('item', 3+1), SingleFeat('item_gender', 2+1)], "dense": [SingleFeat('score', 0)]}
behavior_feature_list = ["item", "item_gender"]
uid = np.array([0, 1, 2])
ugender = np.array([0, 1, 0])
iid = np.array([1, 2, 3]) # 0 is mask value
igender = np.array([1, 2, 1]) # 0 is mask value
score = np.array([0.1, 0.2, 0.3])
hist_iid = np.array([[1, 2, 3, 0], [1, 2, 3, 0], [1, 2, 0, 0]])
hist_igender = np.array([[1, 1, 2, 0], [2, 1, 1, 0], [2, 1, 0, 0]])
feature_dict = {'user': uid, 'gender': ugender, 'item': iid, 'item_gender': igender,
'hist_item': hist_iid, 'hist_item_gender': hist_igender, 'score': score}
x = [feature_dict[feat.name] for feat in feature_dim_dict["sparse"]] + [feature_dict[feat.name]
for feat in feature_dim_dict["dense"]] + [feature_dict['hist_'+feat] for feat in behavior_feature_list]
y = [1, 0, 1]
return x, y, feature_dim_dict, behavior_feature_list
if __name__ == "__main__":
x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
model = DIN(feature_dim_dict, behavior_feature_list, hist_len_max=4,)
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
history = model.fit(x, y, verbose=1, epochs=10, validation_split=0.5)
# 组装train_model_input，得到feature names，将train_X转换为字典格式
feature_names = list(train_X.columns)
train_model_input = {name: train_X[name].values for name in get_feature_names(feature_columns)}
print("########################################")
# histroy输入必须是二维数组
from tqdm import tqdm
for fea in ['hist_merchant_id', 'hist_action_type']:
list = []
for i in tqdm(train_model_input[fea]):
list.append(i)
train_model_input[fea] = np.array(list)
history = model.fit(train_model_input, train_y.values, verbose=True, epochs=10, validation_split=0.2, batch_size=512)
# 转换test__model_input
test_data['action_type'] = 3
test_model_input = {name: test_data[name].values for name in feature_names}
from tqdm import tqdm
for fea in ['hist_merchant_id', 'hist_action_type']:
list = []
for i in tqdm(test_model_input[fea]):
list.append(i)
test_model_input[fea] = np.array(list)
# 得到预测结果
prob = model.predict(test_model_input)
submission['prob'] = prob
del train_input_pos
del train_input_neg
del train_label_pos
del train_label_neg
n = 10
length_train = len(train_input[0])
length_train = int(length_train / n + 1)
for i in range(n):
train_input_slice = [
column[i * length_train:(i + 1) * length_train]
for column in train_input
]
hist_ = model.fit(
train_input_slice,
train_label[i * length_train:(i + 1) * length_train],
batch_size=BATCH_SIZE,
epochs=1,
initial_epoch=0,
verbose=1,
)
# pred_ans = model.predict(test_input, BATCH_SIZE)
#AUC = round(roc_auc_score(test_label, pred_ans), 4)
#if AUC > best_AUC:
# best_AUC = AUC
# model.save_weights(model_dir+'/ckpt.h5')
#print("epoch : ",e,"----date : ",date,"----test AUC : ",AUC)
user_age = np.array([1, 2, 3])
user_gender = np.array([0, 1, 0])
item_id = np.array([0, 1, 2])
item_gender = np.array([0, 1, 0])
# multi-value feature input
hist_item_id = np.array([[0, 1, 2, 3], [0, 1, 2, 3], [0, 1, 2, 0]])
hist_item_gender = np.array([[0, 1, 0, 1], [0, 1, 1, 1], [0, 0, 1, 0]])
# valid length of behavior sequence of every sample
hist_length = np.array([4, 4, 3])
feature_dict = {'user_age': user_age, 'user_gender': user_gender, 'item_id': item_id, 'item_gender': item_gender,
'hist_item_id': hist_item_id, 'hist_item_gender': hist_item_gender, }
x = [feature_dict[feat] for feat in feature_dim_dict["sparse"]] + \
[feature_dict['hist_'+feat]
for feat in behavior_feature_list] + [hist_length]
# Notice the concatenation order: single feature + multi-value feature + length
# Since the length of the historical sequences of different features in DIN are the same(they are all extended from item_id),only one length vector is enough.
y = [1, 0, 1]
return x, y, feature_dim_dict, behavior_feature_list
if __name__ == "__main__":
x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
model = DIN(feature_dim_dict, behavior_feature_list, hist_len_max=4,)
model.compile('adam', 'binary_crossentropy',
metrics=['binary_crossentropy'])
history = model.fit(x, y, verbose=1, validation_split=0.5)
att_activation='dice',
att_weight_normalization=False,
hist_len_max=sess_len_max,
dnn_hidden_units=(200, 80),
att_hidden_size=(
64,
16,
),
l2_reg_embedding=REG,
seed=2019)
model.compile('adagrad',
'binary_crossentropy',
metrics=[
'binary_crossentropy',
])
hist_ = model.fit(
train_input[:],
train_label,
batch_size=BATCH_SIZE,
epochs=1,
initial_epoch=0,
verbose=1,
)
pred_ans = model.predict(test_input, TEST_BATCH_SIZE)
print()
print("test LogLoss", round(log_loss(test_label, pred_ans), 4), "test AUC",
round(roc_auc_score(test_label, pred_ans), 4))
class Trainer:
def __init__(self):
self.data = None
self.encoder = None
self.model = None
# number of positive samples
self.num_pos = None
self.recipeDomain = None
def loadData(self, url: str):
self.data = pd.read_csv(url)
self.recipeDomain = pd.read_csv(url)
self.num_pos = self.data.shape[0]
self.encoder = ModelEncoder()
self.encoder.train()
def preProcessData(self):
self.data = self.encoder.encode(self.data)
self.data['result'] = [1] * self.num_pos
self.recipeDomain = self.encoder.encode(self.recipeDomain)
self.build_negative_data()
def buildModel(self):
feature_columns = self.encoder.getFeatureColumns()
self.model = DIN(feature_columns, self.encoder.behavior_list)
self.model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
def train(self):
model_input = {}
for feat, _ in self.encoder.fixed_sparse_dict + self.encoder.var_sparse_dict:
model_input[feat] = self.data[feat]
history = self.model.fit(model_input,
self.data['gt'].values,
batch_size=256,
epochs=10,
verbose=2,
validation_split=0.2,
shuffle=True)
def dump_model(self, path: str):
save_model(self.model, path)
def dump_encoder(self, path: str):
pickle.dump(self.encoder, self, protocol=4)
def update(self):
url = ''
self.recipeDomain = pd.read_csv(url)
self.encoder.encode(self.recipeDomain)
def build_negative_data(self):
for i in range(self.num_pos):
record = self.data.iloc[i]
clicked_set = record['hist_recipe'] + record['recipe'][i]
for j in self.recipeDomain.shape[0]:
if self.recipeDomain.iloc[j]['recipe'] not in clicked_set:
# valid unclicked combination
for feat in record.columns:
if feat in self.recipeDomain.columns:
record[feat] = self.recipeDomain.iloc[j][feat]
record['result'] = 0
self.data.append(record)