esmm测试项目

tensnsorflow/es/submit.sh

@@ -32,7 +32,7 @@ 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} ${MODEL_PATH}/train.py --ctr_task_wgt=0.5 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=9 --feature_size=300000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
 
 
 echo "infer native..."

tensnsorflow/es/to_tfrecord.py

@@ -29,18 +29,20 @@ 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"]
         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)))
+            "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)

tensnsorflow/es/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)