def find_l2_reg_embedding(linear_feature_columns, dnn_feature_columns,
train_model_input, train, test_model_input, test):
cols = ['l2_reg_embedding', 'RMSE', 'MAE', 'MSE', 'AUC']
df_result = pd.DataFrame(columns=cols,
index=range(
len(config.param_rand['l2_reg_embedding'])))
for i, x in enumerate(config.param_rand['l2_reg_embedding']):
##Add dnn_hidden_units as b later
model = WDL(
linear_feature_columns,
dnn_feature_columns,
# ADD LATER
dnn_hidden_units=(2, 2),
l2_reg_linear=0.1,
l2_reg_embedding=x,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
task='binary')
model.compile("adam", "mse", metrics=['mse'])
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=config.model_epoch['epoch'],
verbose=2,
validation_split=0.2,
)
pred_ans = model.predict(test_model_input, batch_size=256)
auc = roc_auc_score(test[target].values, pred_ans)
df_result.loc[i].l2_reg_embedding = x
df_result.loc[i].RMSE = np.round(
math.sqrt(mean_squared_error(test[target].values, pred_ans)), 3)
df_result.loc[i].MAE = np.round(
mean_absolute_error(test[target].values, pred_ans), 3)
df_result.loc[i].MSE = np.round(
mean_squared_error(test[target].values, pred_ans), 3)
df_result.loc[i].AUC = np.round(auc, 3)
return df_result
def widendeep_model(linear_feature_columns, dnn_feature_columns,
train_model_input, train, test_model_input, test):
cols = ['model', 'RMSE', 'MAE', 'MSE', 'AUC', 'score']
df_result = pd.DataFrame(columns=cols, index=range(1))
model = WDL(
linear_feature_columns,
dnn_feature_columns,
dnn_hidden_units=config.widendeep_att["dnn_hidden_units"],
#l2_reg_linear=config.widendeep_att["l2_reg_linear"],
# l2_reg_embedding=config.widendeep_att["l2_reg_embedding"],
#l2_reg_dnn=config.widendeep_att["l2_reg_dnn"],
# init_std=config.widendeep_att["init_std"],
dnn_dropout=config.widendeep_att['dnn_dropout'],
dnn_activation=config.widendeep_att['dnn_activation'],
seed=config.widendeep_att["seed"],
task=config.widendeep_att["task"])
model.compile("adam", "mse", metrics=['mse'])
history = model.fit(train_model_input,
train[target].values,
batch_size=256,
epochs=config.model_epoch['epoch'],
verbose=2,
validation_split=0.2)
pred_ans = model.predict(test_model_input, batch_size=256)
save_model(model, 'saved_widendeep.h5') # save_model
auc = roc_auc_score(test[target].values, pred_ans)
df_result.loc[0].model = "Wide and Deep"
df_result.loc[0].RMSE = np.round(
math.sqrt(mean_squared_error(test[target].values, pred_ans)), 3)
df_result.loc[0].MAE = np.round(
mean_absolute_error(test[target].values, pred_ans), 3)
df_result.loc[0].MSE = np.round(
mean_squared_error(test[target].values, pred_ans), 3)
df_result.loc[0].AUC = np.round(auc, 3)
return df_result
def test_WDL():
name = "WDL"
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 = WDL(feature_dim_dict,
feature_dim_dict,
hidden_size=[32, 32],
keep_prob=0.5)
model.compile('adam',
'binary_crossentropy',
metrics=['binary_crossentropy'])
model.fit(x + 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!")
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]
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WDL进行训练
model = WDL(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=100, verbose=True, validation_split=0.2, )
plt.figure()
x = range(len(history.history['loss']))
plt.plot(x, history.history['loss'])
plt.title('loss')
# 使用WDL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
print("test RMSE", rmse)
# 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 = WDL(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,
)
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))
t1 = time.time()
# print(data.head())
# 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
print(fixlen_feature_columns)
print(type(fixlen_feature_columns))
dnn_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
# print(fixlen_feature_columns)
# print(feature_names)
# 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} # 字典
test_model_input = {name: test[name].values for name in feature_names}
# 使用WDL进行训练
model = WDL(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WDL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
print('test RMSE', rmse)
l2_reg_embedding=1e-5,
l2_reg_dnn=0.01,
init_std=0.0001,
dnn_hidden_units=(256, 128),
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
)
model.summary()
# 可以进行调优
from tensorflow.keras.optimizers import Adam
optmizer = Adam(1e-4)
model.compile(
optmizer,
"mse",
metrics=['mse'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=20,
verbose=True,
validation_split=0.2,
)
# 7.绘图展示， 观看模型训练情况
plt.figure(figsize=(8, 8))