美购精排模型

mlp/train.py

@@ -72,40 +72,45 @@ def getDataSet(df,shuffleSize = 10000,batchSize=128):
 def getTrainColumns(train_columns,data_vocab):
     columns = []
     dataColumns = []
+    inputs = {}
     # 离散特征
     for feature in train_columns:
-        if data_vocab.get(feature):
-            cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature,vocabulary_list=data_vocab[feature])
+        # if data_vocab.get(feature):
+        #     cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature,vocabulary_list=data_vocab[feature])
+        #     col = tf.feature_column.embedding_column(cat_col, 10)
+        #     columns.append(col)
+        #     dataColumns.append(feature)
+        #     inputs[feature] = tf.keras.layers.Input(name=feature, shape=(), dtype='string')
+        if feature.startswith("userRatedHistory") or feature.count("__") > 0 or feature in embedding_columns:
+            cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature, vocabulary_list=data_vocab[feature])
             col = tf.feature_column.embedding_column(cat_col, 10)
             columns.append(col)
             dataColumns.append(feature)
-            # if feature.startswith("userRatedHistory") or feature.count("__") > 0 or feature in embedding_columns:
-            #     cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature, vocabulary_list=data_vocab[feature])
-            #     col = tf.feature_column.embedding_column(cat_col, 10)
-            #     columns.append(col)
-            #     dataColumns.append(feature)
-            #
-            # elif feature in one_hot_columns or feature.count("Bucket") > 0:
-            #     cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature, vocabulary_list=data_vocab[feature])
-            #     col = tf.feature_column.indicator_column(cat_col)
-            #     columns.append(col)
-            #     dataColumns.append(feature)
+            inputs[feature] = tf.keras.layers.Input(name=feature, shape=(), dtype='string')
+
+        elif feature in one_hot_columns or feature.count("Bucket") > 0:
+            cat_col = tf.feature_column.categorical_column_with_vocabulary_list(key=feature, vocabulary_list=data_vocab[feature])
+            col = tf.feature_column.indicator_column(cat_col)
+            columns.append(col)
+            dataColumns.append(feature)
+            inputs[feature] = tf.keras.layers.Input(name=feature, shape=(), dtype='string')
 
         elif feature in ITEM_NUMBER_COLUMNS:
             col = tf.feature_column.numeric_column(feature)
             columns.append(col)
             dataColumns.append(feature)
+            inputs[feature] = tf.keras.layers.Input(name=feature, shape=(), dtype='float32')
 
-    return columns,dataColumns
 
+    return columns,dataColumns,inputs
 
-def train(columns,train_dataset):
-    model = tf.keras.Sequential([
-        tf.keras.layers.DenseFeatures(columns),
-        tf.keras.layers.Dense(128, activation='relu'),
-        tf.keras.layers.Dense(128, activation='relu'),
-        tf.keras.layers.Dense(1, activation='sigmoid'),
-    ])
+
+def train(columns,inputs,train_dataset):
+    deep = tf.keras.layers.DenseFeatures(columns)(inputs)
+    deep = tf.keras.layers.Dense(64, activation='relu')(deep)
+    deep = tf.keras.layers.Dense(64, activation='relu')(deep)
+    output_layer = tf.keras.layers.Dense(1, activation='sigmoid')(deep)
+    model = tf.keras.Model(inputs, output_layer)
 
     # compile the model, set loss function, optimizer and evaluation metrics
     model.compile(
@@ -121,6 +126,7 @@ def train(columns,train_dataset):
 
     model.save(model_file, include_optimizer=False, save_format='tf')
 
+
 def evaluate(model,test_dataset):
     # evaluate the model
     timestmp1 = int(round(time.time()))
@@ -161,7 +167,7 @@ if __name__ == '__main__':
 
     # 获取训练列
     columns = df_train.columns.tolist()
-    trainColumns, datasColumns = getTrainColumns(columns, data_vocab)
+    trainColumns, datasColumns,inputs = getTrainColumns(columns, data_vocab)
 
     df_train = df_train[datasColumns + ["label"]]
     df_test = df_test[datasColumns + ["label"]]
@@ -180,7 +186,7 @@ if __name__ == '__main__':
 
 
     timestmp3 = int(round(time.time()))
-    model = train(trainColumns,train_data)
+    model = train(trainColumns,inputs,train_data)
     timestmp4 = int(round(time.time()))
     print("读取数据耗时h:{}".format((timestmp4 - timestmp3)/60/60))