add devcie_id

tensnsorflow/feature_engineering.py

@@ -45,12 +45,12 @@ def get_data():
     print("after")
     df = df.drop_duplicates()
     df = df.drop_duplicates(["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                             "channel", "top", "l1","l2", "time", "stat_date"])
+                             "channel", "top", "l1","l2", "time", "stat_date","device_id"])
     print(df.shape)
 
     unique_values = []
     features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]
+                "channel", "top", "time", "stat_date","device_id"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
@@ -75,7 +75,7 @@ def get_data():
     train = df[df["stat_date"] != validate_date+"stat_date"]
     test = df[df["stat_date"] == validate_date+"stat_date"]
     for i in ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "l1", "time", "stat_date","l2"]:
+                "channel", "top", "l1", "time", "stat_date","l2","device_id"]:
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
@@ -120,7 +120,7 @@ def get_predict(date,value_map):
     print(df.shape)
 
     features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "time", "stat_date"]
+                "channel", "top", "time", "stat_date","device_id"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
@@ -137,7 +137,7 @@ def get_predict(date,value_map):
     nearby_pre = nearby_pre.drop("label", axis=1)
 
     for i in ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "l1", "time", "stat_date","l2"]:
+                "channel", "top", "l1", "time", "stat_date","l2","device_id"]:
         native_pre[i] = native_pre[i].map(value_map)
         # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
         native_pre[i] = native_pre[i].fillna(0)

tensnsorflow/pipe.sh

@@ -33,15 +33,15 @@ rm ${DATA_PATH}/nearby/nearby_*
 
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
 
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
 
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=12 --feature_size=2000 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
 
 echo "sort and 2sql"
 ${PYTHON_PATH} ${OLD_PATH}/Model_pipline/sort_and_2sql.py

tensnsorflow/test.py

@@ -29,7 +29,7 @@ def gen_tfrecords(in_file):
 
     for i in range(df.shape[0]):
         feats = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "l1", "time", "stat_date","l2"]
+                "channel", "top", "l1", "time", "stat_date","l2","device_id"]
         id = np.array([])
         for j in feats:
             id = np.append(id,df[j][i])

tensnsorflow/train.py

@@ -53,7 +53,7 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
         features = {
             "y": tf.FixedLenFeature([], tf.float32),
             "z": tf.FixedLenFeature([], tf.float32),
-            "ids": tf.FixedLenFeature([11], tf.int64)
+            "ids": tf.FixedLenFeature([12], tf.int64)
         }
 
         parsed = tf.parse_single_example(record, features)