修改zhao分支上的esmm生产项目

eda/esmm/Model_pipline/submit.sh

@@ -32,15 +32,15 @@ rm ${DATA_PATH}/nearby/nearby_*
 
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=8 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=15 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
 
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=8 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/native_infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=15 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/native_infer.log
 
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=8 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/nearby_infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=15 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/nearby_infer.log
 
 echo "sort and 2sql"
 ${PYTHON_PATH} ${MODEL_PATH}/to_database.py > ${DATA_PATH}/insert_database.log

eda/esmm/Model_pipline/to_tfrecord.py

@@ -21,6 +21,7 @@ tf.app.flags.DEFINE_string("input_dir", "./", "input dir")
 tf.app.flags.DEFINE_string("output_dir", "./", "output dir")
 tf.app.flags.DEFINE_integer("threads", 16, "threads num")
 
+
 def gen_tfrecords(in_file):
     basename = os.path.basename(in_file) + ".tfrecord"
     out_file = os.path.join(FLAGS.output_dir, basename)
@@ -29,18 +30,21 @@ def gen_tfrecords(in_file):
 
     for i in range(df.shape[0]):
         feats = ["ucity_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]
+                 "channel", "top", "time", "stat_date", "hospital_id",
+                 "method", "min", "max", "treatment_time", "maintain_time", "recover_time"]
         id = np.array([])
         for j in feats:
             id = np.append(id,df[j][i])
         app_list = np.array(str(df["app_list"][i]).split(","))
         level2_list = np.array(str(df["clevel2_id"][i]).split(","))
+        level3_list = np.array(str(df["level3_ids"][i]).split(","))
         features = tf.train.Features(feature={
             "y": tf.train.Feature(float_list=tf.train.FloatList(value=[df["y"][i]])),
             "z": tf.train.Feature(float_list=tf.train.FloatList(value=[df["z"][i]])),
             "ids": tf.train.Feature(int64_list=tf.train.Int64List(value=id.astype(np.int))),
-            "app_list":tf.train.Feature(int64_list=tf.train.Int64List(value=app_list.astype(np.int))),
-            "level2_list": tf.train.Feature(int64_list=tf.train.Int64List(value=level2_list.astype(np.int)))
+            "app_list": tf.train.Feature(int64_list=tf.train.Int64List(value=app_list.astype(np.int))),
+            "level2_list": tf.train.Feature(int64_list=tf.train.Int64List(value=level2_list.astype(np.int))),
+            "level3_list": tf.train.Feature(int64_list=tf.train.Int64List(value=level3_list.astype(np.int)))
         })
 
         example = tf.train.Example(features = features)

eda/esmm/Model_pipline/train.py

@@ -55,7 +55,8 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
             "z": tf.FixedLenFeature([], tf.float32),
             "ids": tf.FixedLenFeature([FLAGS.field_size], tf.int64),
             "app_list": tf.VarLenFeature(tf.int64),
-            "level2_list": tf.VarLenFeature(tf.int64)
+            "level2_list": tf.VarLenFeature(tf.int64),
+            "level3_list": tf.VarLenFeature(tf.int64)
         }
 
         parsed = tf.parse_single_example(record, features)
@@ -103,6 +104,7 @@ def model_fn(features, labels, mode, params):
     feat_ids = features['ids']
     app_list = features['app_list']
     level2_list = features['level2_list']
+    level3_list = features['level3_list']
 
     if FLAGS.task_type != "infer":
         y = labels['y']
@@ -113,10 +115,11 @@ def model_fn(features, labels, mode, params):
         embedding_id = tf.nn.embedding_lookup(Feat_Emb,feat_ids)
         app_id = tf.nn.embedding_lookup_sparse(Feat_Emb, sp_ids=app_list, sp_weights=None, combiner="sum")
         level2 = tf.nn.embedding_lookup_sparse(Feat_Emb, sp_ids=level2_list, sp_weights=None, combiner="sum")
+        level3 = tf.nn.embedding_lookup_sparse(Feat_Emb, sp_ids=level3_list, sp_weights=None, combiner="sum")
 
 
         # x_concat = tf.reshape(embedding_id,shape=[-1, common_dims])  # None * (F * K)
-        x_concat = tf.concat([tf.reshape(embedding_id,shape=[-1,common_dims]),app_id,level2], axis=1)
+        x_concat = tf.concat([tf.reshape(embedding_id,shape=[-1,common_dims]),app_id,level2,level3], axis=1)
 
     with tf.name_scope("CVR_Task"):
         if mode == tf.estimator.ModeKeys.TRAIN: