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
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)
SparseFeat(feature, data[feature].nunique())
for feature in sparse_features
]
linear_feature_columns = fix_len_feature_columns
dnn_feature_columns = fix_len_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_set = {name: train[name].values for name in feature_names}
test_set = {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_set,
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_set, batch_size=256)
# 输出 RMSE 或者 MSE
mse = round(mean_squared_error(test[target].values, pred_ans), 4)
rmse = mse**0.5
print(f'test rmse: {rmse}')
data = pd.read_csv("./data/sample/validation.txt")
# 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])
# 2.count #unique features for each sparse field
sparse_feature_dim = {
feat: data[feat].nunique()
for feat in sparse_features
}
# 3.generate input data for model
model_input = [data[feat].values for feat in sparse_feature_dim]
pred = model.predict(model_input, batch_size, 1)
label = data[target].values.flatten().tolist()
pred = pred.flatten().tolist()
with open('data/pctr', 'w') as fw:
for i in range(len(pred)):
if i % 10000 == 0:
print('label: %f, pred: %f' % (label[i], pred[i]))
to_write = str(i + 1) + ',' + str(label[i]) + ',' + str(
pred[i]) + '\n'
fw.write(to_write)
fw.close()
AUC = auc.auc(label, pred)
print('auc: %f' % AUC)
print("demo done")