增加日记是否是视频特征

eda/esmm/Model_pipline/submit.sh

@@ -19,11 +19,11 @@ echo "rm model file"
 b=`date +%Y%m%d`
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH} --hdfs_dir=${HDFS_PATH}/native --task_type=train
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=16 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH} --hdfs_dir=${HDFS_PATH}/native --task_type=train
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/native --hdfs_dir=${HDFS_PATH}/native --task_type=infer
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=16 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/native --hdfs_dir=${HDFS_PATH}/native --task_type=infer
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/nearby --hdfs_dir=${HDFS_PATH}/nearby --task_type=infer
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=16 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${HDFS_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/nearby --hdfs_dir=${HDFS_PATH}/nearby --task_type=infer
 

eda/esmm/Model_pipline/train.py

@@ -400,7 +400,7 @@ def update_or_insert(df2,queue_name):
     cur = con.cursor()
     try:
         for i in range(0, device_count):
-            query = """INSERT INTO esmm_device_diary_queue_tmp (device_id, city_id, time,%s) VALUES('%s', '%s', '%s', '%s') \
+            query = """INSERT INTO esmm_device_diary_queue (device_id, city_id, time,%s) VALUES('%s', '%s', '%s', '%s') \
             ON DUPLICATE KEY UPDATE device_id='%s', city_id='%s', time='%s', %s='%s'""" % (queue_name, df2.device_id[i],df2.city_id[i], df2.time[i], df2[queue_name][i], df2.device_id[i], df2.city_id[i], df2.time[i], queue_name, df2[queue_name][i])
             cur.execute(query)
             con.commit()