def get_xy_random2(X, y, cols_family={}):
# X = np.random.rand(100,30)
# y = np.random.binomial(n=1, p=0.5, size=[100])
## PREPROCESSING STEPS
# change into dataframe
target = 'y'
cols = [str(i) for i in range(X.shape[1])] # define column pd dataframe, need to be string type
data = pd.DataFrame(X, columns=cols) # need to convert into df, following the step from documentation
#data['y'] = y
# define which feature columns sparse or dense type
# since our data categorize as Dense Features, we define the sparse features as empty list
#cols_sparse_features = []
#cols_dense_features = [str(i) for i in range(X.shape[1])]
cols_sparse_features = cols_family['colsparse']
cols_dense_features = cols_family['coldense']
# convert feature type into SparseFeat or DenseFeat type, adjusting from DeepCTR library
sparse_feat_l = [SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i,feat in enumerate(cols_sparse_features)]
dense_feat_l = [DenseFeat(feat, dimension=1) for feat in cols_dense_features]
feature_col = sparse_feat_l + dense_feat_l
linear_feat_col = feature_col # containing all the features used by linear part of the model
dnn_feat_col = feature_col # containing all the features used by deep part of the model
feature_names = get_feature_names(linear_feat_col + dnn_feat_col)
train_model_input = {name: data[name] for name in feature_names}
X_train, y_train = train_model_input, y.values
return X_train, y_train, linear_feat_col, dnn_feat_col
def test_long_dense_vector():
feature_columns = [
SparseFeat(
'user_id',
4,
),
SparseFeat(
'item_id',
5,
),
DenseFeat("pic_vec", 5)
]
fixlen_feature_names = get_feature_names(feature_columns)
user_id = np.array([[1], [0], [1]])
item_id = np.array([[3], [2], [1]])
pic_vec = np.array([[0.1, 0.5, 0.4, 0.3, 0.2], [0.1, 0.5, 0.4, 0.3, 0.2],
[0.1, 0.5, 0.4, 0.3, 0.2]])
label = np.array([1, 0, 1])
input_dict = {'user_id': user_id, 'item_id': item_id, 'pic_vec': pic_vec}
model_input = [input_dict[name] for name in fixlen_feature_names]
model = DeepFM(feature_columns, feature_columns[:-1])
model.compile('adagrad', 'binary_crossentropy')
model.fit(model_input, label)
def test_long_dense_vector():
#构造特征
feature_columns = [
SparseFeat(
'user_id',
4,
),
SparseFeat(
'item_id',
5,
),
DenseFeat("pic_vec", 5)
]
fixlen_feature_names = get_feature_names(feature_columns)
#构造样本
user_id = np.array([[1], [0], [1]])
item_id = np.array([[3], [2], [1]])
pic_vec = np.array([[0.1, 0.5, 0.4, 0.3, 0.2], [0.1, 0.5, 0.4, 0.3, 0.2],
[0.1, 0.5, 0.4, 0.3, 0.2]])
label = np.array([1, 0, 1])
input_dict = {'user_id': user_id, 'item_id': item_id, 'pic_vec': pic_vec}
model_input = [input_dict[name] for name in fixlen_feature_names]
#创建模型model
model = DeepFM(feature_columns, feature_columns[:-1])
# model.summary()
#tf.keras.utils.plot_model(model, "test_compu")
#训练模型
model.compile('adagrad', 'binary_crossentropy')
model.fit(model_input, label)
def get_xy_fd(hash_flag=False):
feature_columns = [SparseFeat('user', 3, embedding_dim=10), SparseFeat(
'gender', 2, embedding_dim=4), SparseFeat('item_id', 3 + 1, embedding_dim=8),
SparseFeat('cate_id', 2 + 1, embedding_dim=4), DenseFeat('pay_score', 1)]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item_id', vocabulary_size=3 + 1, embedding_dim=8, embedding_name='item_id'),
maxlen=4, length_name="seq_length"),
VarLenSparseFeat(SparseFeat('hist_cate_id', 2 + 1, embedding_dim=4, embedding_name='cate_id'), maxlen=4,
length_name="seq_length")]
# Notice: History behavior sequence feature name must start with "hist_".
behavior_feature_list = ["item_id", "cate_id"]
uid = np.array([0, 1, 2])
ugender = np.array([0, 1, 0])
iid = np.array([1, 2, 3]) # 0 is mask value
cate_id = np.array([1, 2, 2]) # 0 is mask value
pay_score = np.array([0.1, 0.2, 0.3])
hist_iid = np.array([[1, 2, 3, 0], [3, 2, 1, 0], [1, 2, 0, 0]])
hist_cate_id = np.array([[1, 2, 2, 0], [2, 2, 1, 0], [1, 2, 0, 0]])
seq_length = np.array([3, 3, 2]) # the actual length of the behavior sequence
feature_dict = {'user': uid, 'gender': ugender, 'item_id': iid, 'cate_id': cate_id,
'hist_item_id': hist_iid, 'hist_cate_id': hist_cate_id,
'pay_score': pay_score, 'seq_length': seq_length}
x = {name: feature_dict[name] for name in get_feature_names(feature_columns)}
y = np.array([1, 0, 1])
return x, y, feature_columns, behavior_feature_list
def get_xy_random():
X = np.random.rand(100, 30)
y = np.random.binomial(n=1, p=0.5, size=[100])
## PREPROCESSING STEPS
# change into dataframe
cols = [str(i) for i in range(X.shape[1])
] # define column pd dataframe, need to be string type
data = pd.DataFrame(
X, columns=cols
) # need to convert into df, following the step from documentation
data['y'] = y
# define which feature columns sparse or dense type
# since our data categorize as Dense Features, we define the sparse features as empty list
cols_sparse_features = []
cols_dense_features = [str(i) for i in range(X.shape[1])]
# convert feature type into SparseFeat or DenseFeat type, adjusting from DeepCTR library
sparse_feat_l = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(cols_sparse_features)
]
dense_feat_l = [
DenseFeat(feat, dimension=1) for feat in cols_dense_features
]
feature_col = sparse_feat_l + dense_feat_l
linear_feat_col = feature_col # containing all the features used by linear part of the model
dnn_feat_col = feature_col # containing all the features used by deep part of the model
feature_names = get_feature_names(linear_feat_col + dnn_feat_col)
train_full, test = train_test_split(data,
random_state=2021,
stratify=data['y'])
train, val = train_test_split(train_full,
random_state=2021,
stratify=train_full['y'])
train_model_input = {name: train[name] for name in feature_names}
val_model_input = {name: val[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
target = 'y'
## END OF PREPROCESSING STEPS
X_train, y_train = train_model_input, train[target].values
X_val, y_val = val_model_input, val[target].values
X_test, y_test = test_model_input, test[target].values
return X_train, X_val, X_test, y_train, y_val, y_test, linear_feat_col, dnn_feat_col
def fit(self, X, y):
X_ = X.copy()
self.dense_features = list(X_.columns.difference(self.cat_features))
logger.debug("MinMaxScaler")
self.min_max_scaler.fit(X_[self.dense_features])
X_[self.dense_features] = self.min_max_scaler.transform(
X_[self.dense_features])
self._column_mapping(X_)
X_.columns = [self.columns_mapping[col] for col in X_.columns]
self.fixlen_feature_columns = [
SparseFeat(
self.columns_mapping[feat],
vocabulary_size=X_[self.columns_mapping[feat]].max() + 1,
embedding_dim=4,
) for i, feat in enumerate(self.cat_features)
] + [
DenseFeat(
self.columns_mapping[feat],
1,
) for feat in self.dense_features
]
self.feature_names = get_feature_names(self.fixlen_feature_columns)
logger.debug("Compile DeepFM model")
self.model = DeepFM(self.fixlen_feature_columns,
self.fixlen_feature_columns,
task="binary")
self.model.compile(
"adam",
"binary_crossentropy",
metrics=["binary_crossentropy"],
)
logger.debug("Fit DeepFM")
train_model_input = {
name: X_[name].values
for name in self.feature_names
}
self.model.fit(
train_model_input,
y,
batch_size=256,
epochs=3,
verbose=2,
validation_split=0.2,
)
def run_base_experiment(data_path, dataset_type, model_params, model_type,
opt):
if dataset_type == 'critero':
data_df, sparse_features, dense_features, target = load_citero_dataset(
data_path)
else:
data_df, sparse_features, dense_features, target = load_taboola_dataset(
data_path)
data_df = prepare_data_for_train(data_df, sparse_features, dense_features)
fixlen_feature_columns = [
SparseFeat(
feat, vocabulary_size=data_df[feat].nunique(), embedding_dim=10)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
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_df, 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}
batch_size = 1024
# 4.Define Model,train,predict and evaluate
model = model_type(linear_feature_columns,
dnn_feature_columns,
seed=1024,
**model_params)
model.compile(
optimizer=opt,
loss="binary_crossentropy",
metrics=['binary_crossentropy', 'accuracy'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=batch_size,
epochs=10,
verbose=1,
validation_split=0.2,
)
pred_ans = model.predict(test_model_input, batch_size=batch_size)
print("test LogLoss", round(log_loss(test[target].values, pred_ans), 4))
print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))
pass
def get_xy_fd():
feature_columns = [
SparseFeat('user', 3, embedding_dim=10),
SparseFeat('gender', 2, embedding_dim=4),
SparseFeat('item_id', 3 + 1, embedding_dim=8),
SparseFeat('cate_id', 2 + 1, embedding_dim=4),
DenseFeat('pay_score', 1)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item_id',
vocabulary_size=3 + 1,
embedding_dim=8,
embedding_name='item_id'),
maxlen=4),
VarLenSparseFeat(SparseFeat('hist_cate_id',
2 + 1,
embedding_dim=4,
embedding_name='cate_id'),
maxlen=4)
]
behavior_feature_list = ["item_id", "cate_id"] # 变长特征使用的base稀疏特征
uid = np.array([0, 1, 2])
ugender = np.array([0, 1, 0])
iid = np.array([1, 2, 3]) # 0 is mask value
cate_id = np.array([1, 2, 2]) # 0 is mask value
pay_score = np.array([0.1, 0.2, 0.3])
hist_iid = np.array([[1, 2, 3, 0], [3, 2, 1, 0], [1, 2, 0, 0]])
hist_cate_id = np.array([[1, 2, 2, 0], [2, 2, 1, 0], [1, 2, 0, 0]])
# 特征名->data输入
feature_dict = {
'user': uid,
'gender': ugender,
'item_id': iid,
'cate_id': cate_id,
'hist_item_id': hist_iid,
'hist_cate_id': hist_cate_id,
'pay_score': pay_score
}
x = {
name: feature_dict[name]
for name in get_feature_names(feature_columns)
}
y = np.array([1, 0, 1])
return x, y, feature_columns, behavior_feature_list
def read_data_as_model():
data = pd.read_csv('GiveMeSomeCredit/cs-training.csv')
sparse_features = [
'NumberOfTime30-59DaysPastDueNotWorse', 'NumberOfTimes90DaysLate',
'NumberOfTime60-89DaysPastDueNotWorse', 'NumberOfDependents'
]
dense_features = [
'RevolvingUtilizationOfUnsecuredLines', 'age', 'DebtRatio',
'MonthlyIncome', 'NumberOfOpenCreditLinesAndLoans',
'NumberRealEstateLoansOrLines'
]
data[sparse_features] = data[sparse_features].fillna(-1, )
data[dense_features] = data[dense_features].fillna(-1, )
target = ['SeriousDlqin2yrs']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
data[feat] = lbe.fit_transform(data[feat])
mms = MinMaxScaler(feature_range=(0, 1))
data[dense_features] = mms.fit_transform(data[dense_features])
# 2.count #unique features for each sparse field,and record dense feature field name
fixlen_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
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, random_state=1234)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
return train, test, train_model_input, test_model_input, dnn_feature_columns, linear_feature_columns, feature_names, target
def get_xy_fd(hash_flag=False):
feature_columns = [
SparseFeat('user', 3),
SparseFeat('gender', 2),
SparseFeat('item', 3 + 1),
SparseFeat('item_gender', 2 + 1),
DenseFeat('score', 1)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item',
vocabulary_size=3 + 1,
embedding_dim=8,
embedding_name='item'),
maxlen=4),
VarLenSparseFeat(SparseFeat('hist_item_gender',
2 + 1,
embedding_dim=4,
embedding_name='item_gender'),
maxlen=4)
]
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
}
feature_names = get_feature_names(feature_columns)
x = {name: feature_dict[name] for name in feature_names}
y = [1, 0, 1]
return x, y, feature_columns, behavior_feature_list
def get_xy_fd():
feature_columns = [SparseFeat('driver_age', 7, embedding_dim=32),
SparseFeat('pax_age', 7, embedding_dim=32),
SparseFeat('des_id', 10000, embedding_dim=32),
SparseFeat('price_id', 20, embedding_dim=32)]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_price_id', vocabulary_size=5, embedding_dim=32), maxlen=3),
VarLenSparseFeat(SparseFeat('hist_des_id', vocabulary_size=5, embedding_dim=32), maxlen=3)]
# Notice: History behavior sequence feature name must start with "hist_".
behavior_feature_list = ["price_id", "des_id"]
driver_age = np.array([0, 1, 2])
pax_age = np.array([0, 1, 0])
pax_des = np.array([1, 2, 3]) # 0 is mask value
pax_price = np.array([1, 2, 2]) # 0 is mask value
hist_price_seq = np.array([[1, 2, 3], [3, 2, 1], [1, 2, 0]])
hist_des_seq = np.array([[1, 2, 2], [2, 2, 1], [1, 2, 0]])
feature_dict = {'driver_age': driver_age, 'pax_age': pax_age, 'des_id': pax_des, 'price_id': pax_price,
'hist_price_id': hist_price_seq, 'hist_des_id': hist_des_seq}
x = {name: feature_dict[name] for name in get_feature_names(feature_columns)}
y = np.array([1, 0, 1])
return x, y, feature_columns, behavior_feature_list
def get_xy_fd(use_neg=False, hash_flag=False):
feature_columns = [
SparseFeat('user', 3, embedding_dim=10, use_hash=hash_flag),
SparseFeat('gender', 2, embedding_dim=4, use_hash=hash_flag),
SparseFeat('item_id', 3 + 1, embedding_dim=8, use_hash=hash_flag),
SparseFeat('cate_id', 2 + 1, embedding_dim=4, use_hash=hash_flag),
DenseFeat('pay_score', 1)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item_id',
vocabulary_size=3 + 1,
embedding_dim=8,
embedding_name='item_id'),
maxlen=4,
length_name="seq_length"),
VarLenSparseFeat(SparseFeat('hist_cate_id',
2 + 1,
embedding_dim=4,
embedding_name='cate_id'),
maxlen=4,
length_name="seq_length")
]
behavior_feature_list = ["item_id", "cate_id"]
uid = np.array([0, 1, 2])
ugender = np.array([0, 1, 0])
iid = np.array([1, 2, 3]) # 0 is mask value
cate_id = np.array([1, 2, 2]) # 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_cate_id = np.array([[1, 2, 2, 0], [1, 2, 2, 0], [1, 2, 0, 0]])
behavior_length = np.array([3, 3, 2])
feature_dict = {
'user': uid,
'gender': ugender,
'item_id': iid,
'cate_id': cate_id,
'hist_item_id': hist_iid,
'hist_cate_id': hist_cate_id,
'pay_score': score,
"seq_length": behavior_length
}
if use_neg:
feature_dict['neg_hist_item_id'] = np.array([[1, 2, 3,
0], [1, 2, 3, 0],
[1, 2, 0, 0]])
feature_dict['neg_hist_cate_id'] = np.array([[1, 2, 2,
0], [1, 2, 2, 0],
[1, 2, 0, 0]])
feature_columns += [
VarLenSparseFeat(SparseFeat('neg_hist_item_id',
vocabulary_size=3 + 1,
embedding_dim=8,
embedding_name='item_id'),
maxlen=4,
length_name="seq_length"),
VarLenSparseFeat(SparseFeat('neg_hist_cate_id',
2 + 1,
embedding_dim=4,
embedding_name='cate_id'),
maxlen=4,
length_name="seq_length")
]
x = {
name: feature_dict[name]
for name in get_feature_names(feature_columns)
}
y = np.array([1, 0, 1])
return x, y, feature_columns, behavior_feature_list
def get_xy_fd(hash_flag=False):
feature_columns = [
SparseFeat('user', 3, use_hash=hash_flag),
SparseFeat('gender', 2, use_hash=hash_flag),
SparseFeat('item', 3 + 1, use_hash=hash_flag),
SparseFeat('item_gender', 2 + 1, use_hash=hash_flag),
DenseFeat('score', 1)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('sess_0_item',
3 + 1,
embedding_dim=4,
use_hash=hash_flag,
embedding_name='item'),
maxlen=4),
VarLenSparseFeat(SparseFeat('sess_0_item_gender',
2 + 1,
embedding_dim=4,
use_hash=hash_flag,
embedding_name='item_gender'),
maxlen=4)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('sess_1_item',
3 + 1,
embedding_dim=4,
use_hash=hash_flag,
embedding_name='item'),
maxlen=4),
VarLenSparseFeat(SparseFeat('sess_1_item_gender',
2 + 1,
embedding_dim=4,
use_hash=hash_flag,
embedding_name='item_gender'),
maxlen=4)
]
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])
sess1_iid = np.array([[1, 2, 3, 0], [1, 2, 3, 0], [0, 0, 0, 0]])
sess1_igender = np.array([[1, 1, 2, 0], [2, 1, 1, 0], [0, 0, 0, 0]])
sess2_iid = np.array([[1, 2, 3, 0], [0, 0, 0, 0], [0, 0, 0, 0]])
sess2_igender = np.array([[1, 1, 2, 0], [0, 0, 0, 0], [0, 0, 0, 0]])
sess_number = np.array([2, 1, 0])
feature_dict = {
'user': uid,
'gender': ugender,
'item': iid,
'item_gender': igender,
'sess_0_item': sess1_iid,
'sess_0_item_gender': sess1_igender,
'score': score,
'sess_1_item': sess2_iid,
'sess_1_item_gender': sess2_igender,
}
x = {
name: feature_dict[name]
for name in get_feature_names(feature_columns)
}
x["sess_length"] = sess_number
y = [1, 0, 1]
return x, y, feature_columns, behavior_feature_list
VarLenSparseFeat(sparsefeat=SparseFeat('hist_merchant_id', vocabulary_size=1993, embedding_dim=8,
embedding_name='merchant_id'), maxlen=M),
VarLenSparseFeat(sparsefeat=SparseFeat('hist_action_type', vocabulary_size=4, embedding_dim=4,
embedding_name='action_type'), maxlen=M)]
history_features = ['merchant_id', 'action_type']
print(len(feature_columns))
# 使用DIN模型
model = DIN(feature_columns, history_features)
# 使用Adam优化器，二分类的交叉熵
model.compile('adam', 'binary_crossentropy', metrics=['binary_crossentropy'])
# model.compile(loss=[binary_focal_loss(alpha=.25, gamma=2)], metrics=["accuracy"])
# 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
for feat in sparse_features:
lbe = LabelEncoder()
data[feat] = lbe.fit_transform(data[feat])
mms = MinMaxScaler(feature_range=(0, 1))
data[dense_features] = mms.fit_transform(data[dense_features])
# 2.count #unique features for each sparse field,and record dense feature field name
fixlen_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].max() + 1,embedding_dim=4 )
for i,feat in enumerate(sparse_features)] + [DenseFeat(feat, 1,)
for feat in dense_features]
dnn_feature_columns = fixlen_feature_columns
linear_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns) # list of string
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2, random_state=2020)
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 = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')
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, )
pred_ans = model.predict(test_model_input, batch_size=256)
print("test LogLoss", round(log_loss(test[target].values, pred_ans), 4))
print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))
print('data.columns', data.columns.tolist())
print('unique date_: ', data['date_'].unique())
train = data[data['date_'] < 14]
val = data[data['date_'] == 14] # 第14天样本作为验证集
pretrained_feed_embedding_initializer = tf.initializers.identity(feed_embedding)
# 2.count #unique features for each sparse field,and record dense feature field name
fixlen_feature_columns = [SparseFeat('feedid', vocabulary_size=data['feedid'].max() + 1, embedding_dim=512,
embeddings_initializer=pretrained_feed_embedding_initializer)] + [
SparseFeat(feat, vocabulary_size=data[feat].max() + 1, embedding_dim=embedding_dim)
for feat in sparse_features if feat is not 'feedid'] + [DenseFeat(feat, 1) for feat in
dense_features]
dnn_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(dnn_feature_columns)
# 3.generate input data for model
train_model_input = {name: train[name] for name in feature_names}
val_model_input = {name: val[name] for name in feature_names}
userid_list = val['userid'].astype(str).tolist()
test_model_input = {name: test[name] for name in feature_names}
train_labels = [train[y].values for y in target]
val_labels = [val[y].values for y in target]
# 4.Define Model,train,predict and evaluate
train_model = MMOE(dnn_feature_columns, num_tasks=4, expert_dim=8, dnn_hidden_units=(128, 128),
tasks=['binary', 'binary', 'binary', 'binary'])
train_model.compile("adagrad", loss='binary_crossentropy')
# print(train_model.summary())
def get_xy_from_txt(file_path="data/movielens_sample_din.txt"):
feature_columns = [
SparseFeat('user', 3, embedding_dim=10),
SparseFeat('gender', 2, embedding_dim=4),
SparseFeat('item_id', 3 + 1, embedding_dim=8),
SparseFeat('cate_id', 2 + 1, embedding_dim=4),
DenseFeat('pay_score', 1)
]
feature_columns += [
VarLenSparseFeat(SparseFeat('hist_item_id',
vocabulary_size=3 + 1,
embedding_dim=8,
embedding_name='item_id'),
maxlen=4),
VarLenSparseFeat(SparseFeat('hist_cate_id',
2 + 1,
embedding_dim=4,
embedding_name='cate_id'),
maxlen=4)
]
behavior_feature_list = ["item_id", "cate_id"]
# head = ['label', 'user', 'gender', 'item_id', 'cate_id', 'hist_item_id', 'hist_cate_id', 'pay_score']
data = pd.read_csv(file_path, delimiter=',')
def to_int_array(x):
ret = []
a = x.split('|')
for str in a:
ret.append(int(str))
return np.array(ret)
# return ret
data['hist_item_id'] = data['hist_item_id'].apply(to_int_array)
data['hist_cate_id'] = data['hist_cate_id'].apply(to_int_array)
uid = np.array(data['user'])
ugender = np.array(data['gender'])
iid = np.array(data['item_id']) # 0 is mask value
cate_id = np.array(data['cate_id']) # 0 is mask value
pay_score = np.array(data['pay_score'])
print("hist_cate_id: ", type(data['hist_cate_id']),
type(data['hist_cate_id'][0]), np.shape(data['hist_cate_id'][0]),
data['hist_cate_id'])
print("------------" * 10)
hist_iid = np.array(data['hist_item_id'].tolist())
hist_cate_id = np.array(data['hist_cate_id'].tolist())
print("uid: ", type(uid), uid)
print("hist_cate_id: ", type(hist_cate_id), type(hist_cate_id[0]),
np.shape(hist_cate_id[0]), hist_cate_id)
feature_dict = {
'user': uid,
'gender': ugender,
'item_id': iid,
'cate_id': cate_id,
'hist_item_id': hist_iid,
'hist_cate_id': hist_cate_id,
'pay_score': pay_score
}
x = {
name: feature_dict[name]
for name in get_feature_names(feature_columns)
}
y = np.array(data.pop('label'))
return x, y, feature_columns, behavior_feature_list
untrainable_features_columns = []
dense_features = []
else:
print('plz input dataset name')
sys.exit()
udg_features = 'userId'
target = ['rating']
behavior_feature_list = ['itemId', 'category']
fixlen_feature_columns = [SparseFeat(feat, train[feat].nunique(), embedding_dim=int(sys.argv[5])) for feat in sparse_features] + [DenseFeat(feat, 1,) for feat in dense_features]
linear_feature_columns = fixlen_feature_columns
dnn_feature_columns = fixlen_feature_columns
fixlen_feature_names = get_feature_names(fixlen_feature_columns)
train_model_input = {name: train[name] for name in fixlen_feature_names}
test_model_input = {name: test[name] for name in fixlen_feature_names}
if sys.argv[1] in ['DIEN', 'DIEN_UDG', 'DIN', 'DIN_UDG']:
test_model_input, test_label, max_len = get_input(test, 0, 'test')
train_model_input, train_label, _ = get_input(train, max_len, 'train')
fixlen_feature_columns = [SparseFeat(feat, train[feat].nunique()+1, embedding_dim=int(sys.argv[5])) for feat in sparse_features]
fixlen_feature_columns += [DenseFeat(feat, 1,) for feat in dense_features]
fixlen_feature_columns += [
VarLenSparseFeat(SparseFeat('hist_itemId', train['itemId'].nunique() + 1,
embedding_dim = int(sys.argv[5]), embedding_name='itemId'), maxlen=max_len,
length_name='seq_length'),
VarLenSparseFeat(SparseFeat('hist_category', train['category'].nunique() + 1,
embedding_dim = int(sys.argv[5]), embedding_name='category'), maxlen=max_len,
length_name='seq_length'),
def get_xy_dataset(data_sample=None):
if data_sample == "avazu":
df = pd.read_csv(
'https://raw.githubusercontent.com/shenweichen/DeepCTR/master/examples/avazu_sample.txt'
)
df['day'] = df['hour'].apply(lambda x: str(x)[4:6])
df['hour'] = df['hour'].apply(lambda x: str(x)[6:])
sparse_features = [
'hour',
'C1',
'banner_pos',
'site_id',
'site_domain',
'site_category',
'app_id',
'app_domain',
'app_category',
'device_id',
'device_model',
'device_type',
'device_conn_type', # 'device_ip',
'C14',
'C15',
'C16',
'C17',
'C18',
'C19',
'C20',
'C21',
]
df[sparse_features] = df[sparse_features].fillna('-1', )
target = ['click']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
df[feat] = lbe.fit_transform(df[feat])
# 2.count #unique features for each sparse field,and record dense feature field name
field_info = dict(C14='user',
C15='user',
C16='user',
C17='user',
C18='user',
C19='user',
C20='user',
C21='user',
C1='user',
banner_pos='context',
site_id='context',
site_domain='context',
site_category='context',
app_id='item',
app_domain='item',
app_category='item',
device_model='user',
device_type='user',
device_conn_type='context',
hour='context',
device_id='user')
fixlen_feat_col = [
SparseFeat(name,
vocabulary_size=df[name].nunique(),
embedding_dim=16,
use_hash=False,
dtype='int32',
group_name=field_info[name]) for name in sparse_features
]
dnn_feat_col = fixlen_feat_col
linear_feat_col = fixlen_feat_col
feature_names = get_feature_names(linear_feat_col + dnn_feat_col)
elif data_sample == "criteo":
df = pd.read_csv(
'https://raw.githubusercontent.com/shenweichen/DeepCTR/master/examples/criteo_sample.txt'
)
sparse_features = ['C' + str(i) for i in range(1, 27)]
dense_features = ['I' + str(i) for i in range(1, 14)]
df[sparse_features] = df[sparse_features].fillna('-1', )
df[dense_features] = df[dense_features].fillna(0, )
target = ['label']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
df[feat] = lbe.fit_transform(df[feat])
mms = MinMaxScaler(feature_range=(0, 1))
df[dense_features] = mms.fit_transform(df[dense_features])
# 2.count #unique features for each sparse field,and record dense feature field name
fixlen_feat_col = [
SparseFeat(
feat, vocabulary_size=df[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
dnn_feat_col = fixlen_feat_col
linear_feat_col = fixlen_feat_col
feature_names = get_feature_names(linear_feat_col + dnn_feat_col)
elif data_sample == "movielens":
df = pd.read_csv(
"https://raw.githubusercontent.com/shenweichen/DeepCTR/master/examples/movielens_sample.txt"
)
sparse_features = [
"movie_id", "user_id", "gender", "age", "occupation", "zip"
]
target = ['rating']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
df[feat] = lbe.fit_transform(df[feat])
# 2.count #unique features for each sparse field
fixlen_feat_col = [
SparseFeat(feat, df[feat].nunique(), embedding_dim=4)
for feat in sparse_features
]
linear_feat_col = fixlen_feat_col
dnn_feat_col = fixlen_feat_col
feature_names = get_feature_names(linear_feat_col + dnn_feat_col)
# 3.generate input data for model
train_full, test = train_test_split(df,
random_state=2021,
stratify=df[target])
train, val = train_test_split(train_full,
random_state=2021,
stratify=train_full[target])
train_model_input = {name: train[name] for name in feature_names}
val_model_input = {name: val[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
X_train, y_train = train_model_input, train[target].values
X_val, y_val = val_model_input, val[target].values
X_test, y_test = test_model_input, test[target].values
return X_train, X_val, X_test, y_train, y_val, y_test, linear_feat_col, dnn_feat_col
#数据加载
data = pd.read_csv("deepfm_movielens_full.csv")
sparse_features = ["MovieID", "UserID", "Genres", "Age", "OccupationID", "Zip-code"]
target = ['Rating']
# 对特征标签进行编码
for feature in sparse_features:
lbe = LabelEncoder()
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]
print(fixlen_feature_columns)
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DeepFM进行训练
model = DeepFM(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DeepFM进行预测
pred_ans = model.predict(test_model_input, batch_size=256)
# 输出RMSE或MSE
mse = round(mean_squared_error(test[target].values, pred_ans), 4)
rmse = mse ** 0.5
def main(model_dir, data_dir, train_steps, model_name):
data = pd.read_csv(os.path.join(data_dir, 'criteo_sample.txt'))
sparse_features = ['C' + str(i) for i in range(1, 27)]
dense_features = ['I' + str(i) for i in range(1, 14)]
data[sparse_features] = data[sparse_features].fillna('-1', )
data[dense_features] = data[dense_features].fillna(0, )
target = ['label']
# 1.Label Encoding for sparse features,and do simple Transformation for dense features
for feat in sparse_features:
lbe = LabelEncoder()
data[feat] = lbe.fit_transform(data[feat])
mms = MinMaxScaler(feature_range=(0, 1))
data[dense_features] = mms.fit_transform(data[dense_features])
# 2.count #unique features for each sparse field,and record dense feature field name
fixlen_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
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, random_state=2020)
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
if model_name == 'DeepFM':
model = DeepFM(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'FNN':
model = FNN(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'WDL':
model = WDL(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'MLR':
model = MLR(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'NFM':
model = NFM(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'DIN':
model = DIN(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'CCPM':
model = CCPM(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'PNN':
model = PNN(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'AFM':
model = AFM(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'DCN':
model = DCN(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'DIEN':
model = DIEN(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'DSIN':
model = DSIN(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'xDeepFM':
model = xDeepFM(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'AutoInt':
model = AutoInt(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'ONN':
model = ONN(linear_feature_columns, dnn_feature_columns, task='binary')
elif model_name == 'FGCNN':
model = FGCNN(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'FiBiNET':
model = FiBiNET(linear_feature_columns,
dnn_feature_columns,
task='binary')
elif model_name == 'FLEN':
model = FLEN(linear_feature_columns,
dnn_feature_columns,
task='binary')
else:
print(model_name + ' is not supported now.')
return
gpus = int(os.getenv('SM_NUM_GPUS', '0'))
print('gpus:', gpus)
if gpus > 1:
from tensorflow.keras.utils import multi_gpu_model
model = multi_gpu_model(model, gpus=gpus)
model.compile(
"adam",
"binary_crossentropy",
metrics=['binary_crossentropy'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=train_steps,
verbose=2,
validation_split=0.2,
)
pred_ans = model.predict(test_model_input, batch_size=256)
try:
print("test LogLoss", round(log_loss(test[target].values, pred_ans),
4))
except Exception as e:
print(e)
try:
print("test AUC", round(roc_auc_score(test[target].values, pred_ans),
4))
except Exception as e:
print(e)
model.save_weights(os.path.join(model_dir, 'DeepFM_w.h5'))
def get_feature_names(self):
return get_feature_names(self.features_linear + self.features_dnn)