修改ctr_task_wgt参数

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -332,10 +332,8 @@ object EsmmPredData {
 
       val native_data1 = sc.sql(
         s"""
-           |select device_id,city_id as ucity_id,
-           |explode(native_queue) as cid_id
-           |from native_data
-         """.stripMargin
+           |select device_id,city_id as ucity_id,explode(split(native_queue,',')) as cid_id from native_data
+          """.stripMargin
       ).withColumn("label",lit(0))
       native_data1.createOrReplaceTempView("native_data1")
       println("native_explode_count",native_data1.count())

tensnsorflow/pipe.sh

@@ -32,15 +32,15 @@ rm ${DATA_PATH}/nearby/nearby_*
 
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.999 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
 
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.999 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
 
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.999 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=260100 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
 
 echo "sort and 2sql"
 ${PYTHON_PATH} ${MODEL_PATH}/sort_to_sql.py

tensnsorflow/train.py

@@ -180,8 +180,7 @@ def model_fn(features, labels, mode, params):
         ctr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctr, labels=y))
         #cvr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctcvr, labels=z))
         cvr_loss = tf.reduce_mean(tf.losses.log_loss(predictions=pctcvr, labels=z))
-        # loss = ctr_task_wgt * ctr_loss + (1  -ctr_task_wgt) * cvr_loss + l2_reg * tf.nn.l2_loss(Feat_Emb)
-        loss = ctr_loss
+        loss = ctr_task_wgt * ctr_loss + (1  -ctr_task_wgt) * cvr_loss + l2_reg * tf.nn.l2_loss(Feat_Emb)
 
         tf.summary.scalar('ctr_loss', ctr_loss)
         tf.summary.scalar('cvr_loss', cvr_loss)