Merge branch 'master' of http://git.wanmeizhensuo.com/ML/ffm-baseline

eda/esmm/Model_pipline/submit.sh

@@ -16,14 +16,17 @@ rm -r ${LOCAL_PATH}/model_ckpt/DeepCvrMTL/20*
 b=`date +%Y%m%d`
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH} --hdfs_dir=${HDFS_PATH}/native --task_type=train > "/home/gmuser/esmm/log/$b_train.log"
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH} --hdfs_dir=${HDFS_PATH}/native --task_type=train > "/home/gmuser/esmm/log/train_$b.log"
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=8000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/native --hdfs_dir=${HDFS_PATH}/native --task_type=infer > "/home/gmuser/esmm/log/$b_native.log"
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/native --hdfs_dir=${HDFS_PATH}/native --task_type=infer > "/home/gmuser/esmm/log/native_$b.log"
 
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=8000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/nearby --hdfs_dir=${HDFS_PATH}/nearby --task_type=infer > "/home/gmuser/esmm/log/$b_nearby.log"
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=10000 --field_size=15 --feature_size=600000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${LOCAL_PATH}/model_ckpt/DeepCvrMTL/ --local_dir=${LOCAL_PATH}/nearby --hdfs_dir=${HDFS_PATH}/nearby --task_type=infer > "/home/gmuser/esmm/log/nearby_$b.log"
 
 echo "sort and 2sql"
-${PYTHON_PATH} ${MODEL_PATH}/to_database.py > "/home/gmuser/esmm/log/$b_insert.log"
+${PYTHON_PATH} ${MODEL_PATH}/to_database.py > "/home/gmuser/esmm/log/insert_$b.log"
+
+echo "delete files"
+

eda/esmm/Model_pipline/to_database.py

@@ -26,11 +26,8 @@ def nearby_set_join(lst):
 
 def native_set_join(lst):
     l = lst.unique().tolist()
-    d = int(len(l)/2)
-    if d == 0:
-        d = 1
     r = [str(i) for i in l]
-    r =r[:d]
+    r =r[:500]
     return ','.join(r)