特征生成fg.json和EasyRec模型config配置案例_智能推荐 AIRec(AIRec)-阿里云帮助中心

本文通过如下示例为您说明如何配置特征生成配置文件fg.json和模型配置文件config。

示例数据

以下为示例数据，字段包括了常见的数据类型，其中：

ID特征：user_id、item_id
类别特征：gender、category
数值特征：age
lookup特征：user__kv_category_click_1d
多值特征：tags
文本特征：description
行为序列特征：click_10_seq
样本的label：is_click

说明

Lookup特征是一种通过外部预计算的映射表（如KV存储、缓存或数据库表）来获取特征值的机制。它允许模型在训练或预测时快速查询已预先计算好的特征值，而无需实时计算或复杂的数据处理逻辑。这种方式在推荐系统、点击率预估等场景中常见，例如用户的历史行为统计特征（如用户对某类商品的点击次数）、物品的流行度等。

字段名称	示例数据1	示例数据2	示例数据3
request_id	101	102	103
user_id	1	2	3
item_id	4	5	10
event_unix_time	1672502400	1672502400	1672502400
is_click	0	1	1
age	25	30	22
gender	男	女	女
user__kv_category_click_1d	电子产品:10家电:1饰品:2	电子产品:1家电:5饰品:1	电子产品:1家电:2饰品:11
category	电子产品	家电	饰品
tags	科技电脑便携	家居电器冷藏	时尚眼镜防晒
description	便携高性能笔记本	大容量冷藏冰箱	时尚防晒太阳镜
click_10_seq	item__item_id:4#item__category:电子产品#user__ts:21041;item__item_id:5#item__category:家电#user__ts:168139;item__item_id:10#item__category:饰品#user__ts:168284
ds	20230101	20230101	20230101

特征生成配置文件 fg.json

以下是配置好的fg.json示例：

{
    "features": [
        {
            "feature_name": "user_id",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "user:user_id",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": false
        },
        {
            "feature_name": "item_id",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "item:item_id",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": false
        },
        {
            "feature_name": "age",
            "feature_type": "raw_feature",
            "value_type": "Double",
            "expression": "user:age",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false
        },
        {
            "feature_name": "gender",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "user:gender",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": false
        },
        {
            "feature_name": "user__kv_category_click_1d",
            "feature_type": "lookup_feature",
            "value_type": "Double",
            "map": "user:user__kv_category_click_1d",
            "key": "item:category",
            "needDiscrete": false,
            "needWeighting": false,
            "needKey": false,
            "default_value": "0",
            "combiner": "mean",
            "need_prefix": false
        },
        {
            "feature_name": "category",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "item:category",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": false
        },
        {
            "feature_name": "tags",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "item:tags",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": true
        },
        {
            "feature_name": "description",
            "feature_type": "id_feature",
            "value_type": "String",
            "expression": "item:description",
            "default_value": "-1024",
            "combiner": "mean",
            "need_prefix": false,
            "is_multi": true
        },
        {
            "sequence_name": "click_10_seq",
            "sequence_column": "click_10_seq",
            "sequence_length": 10,
            "sequence_delim": ";",
            "attribute_delim": "#",
            "sequence_table": "item",
            "sequence_pk": "user:click_10_seq",
            "features": [
                {
                    "feature_name": "item_id",
                    "feature_type": "id_feature",
                    "value_type": "String",
                    "expression": "item:item_id",
                    "default_value": "-1024",
                    "combiner": "mean",
                    "need_prefix": false,
                    "is_multi": false,
                    "group": "click_10_seq_feature"
                },
                {
                    "feature_name": "category",
                    "feature_type": "id_feature",
                    "value_type": "String",
                    "expression": "item:category",
                    "default_value": "-1024",
                    "combiner": "mean",
                    "need_prefix": false,
                    "is_multi": false,
                    "group": "click_10_seq_feature"
                },
                {
                    "feature_name": "ts",
                    "feature_type": "raw_feature",
                    "value_type": "Double",
                    "expression": "user:ts",
                    "default_value": "-1024",
                    "combiner": "mean",
                    "need_prefix": false,
                    "group": "click_10_seq_feature"
                }
            ]
        }
    ],
    "reserves": [
        "request_id",
        "user_id",
        "item_id",
        "is_click"
    ]
}

模型配置文件 config

以下是配置好的模型配置文件config示例。包括了组合特征和表达式特征，详情请参见easy_rec。

train_config {
  optimizer_config {
    use_moving_average: false
    adam_optimizer {
      learning_rate {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.001
          decay_steps: 1
          decay_factor: 0.5
          min_learning_rate: 1e-06
        }
      }
    }
  }
  num_steps: 1
  sync_replicas: true
  save_summary_steps: 100
  log_step_count_steps: 100
}
eval_config {
  metrics_set {
    auc {
    }
  }
}
data_config {
  batch_size: 1024
  label_fields: "is_click"
  shuffle: false
  num_epochs: 10000
  input_type: OdpsRTPInput
  separator: ""
  selected_cols: "is_click,features"
  input_fields {
    input_name: "is_click"
    input_type: INT32
    default_val: "0"
  }
  input_fields {
    input_name: "user_id"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "item_id"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "age"
    input_type: DOUBLE
    default_val: "-1024"
  }
  input_fields {
    input_name: "gender"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "user__kv_category_click_1d"
    input_type: DOUBLE
    default_val: "0"
  }
  input_fields {
    input_name: "category"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "tags"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "description"
    input_type: STRING
    default_val: "-1024"
  }
  input_fields {
    input_name: "click_10_seq__item_id"
    input_type: STRING
  }
  input_fields {
    input_name: "click_10_seq__category"
    input_type: STRING
  }
  input_fields {
    input_name: "click_10_seq__ts"
    input_type: STRING
  }
  pai_worker_queue: true
}
feature_configs {
  input_names: "user_id"
  feature_type: IdFeature
  embedding_dim: 8
  hash_bucket_size: 48000
  separator: ""
  combiner: "mean"
}
feature_configs {
  input_names: "item_id"
  feature_type: IdFeature
  embedding_dim: 8
  hash_bucket_size: 27000
  separator: ""
  combiner: "mean"
}
feature_configs {
  input_names: "age"
  feature_type: RawFeature
  embedding_dim: 4
  separator: ""
  boundaries: 1e-08
  boundaries: 10
  boundaries: 20
  boundaries: 30
  boundaries: 40
  boundaries: 50
  boundaries: 60
}
feature_configs {
  input_names: "gender"
  feature_type: IdFeature
  embedding_dim: 4
  hash_bucket_size: 10
  separator: ""
  combiner: "mean"
}
feature_configs {
  input_names: "user__kv_category_click_1d"
  feature_type: RawFeature
  embedding_dim: 4
  separator: ""
  boundaries: 1e-08
  boundaries: 1.0
  boundaries: 2.0
  boundaries: 3.0
  boundaries: 4.0
  boundaries: 5.0
  boundaries: 6.0
}
feature_configs {
  input_names: "category"
  feature_type: IdFeature
  embedding_dim: 4
  hash_bucket_size: 100
  separator: ""
  combiner: "mean"
}
feature_configs {
  input_names: "tags"
  feature_type: TagFeature
  embedding_dim: 4
  hash_bucket_size: 1000
  separator: ""
  combiner: "mean"
}
feature_configs {
  input_names: "description"
  feature_type: SequenceFeature
  embedding_dim: 4
  hash_bucket_size: 10
  separator: ""
  sequence_combiner {
    text_cnn {
      filter_sizes: 2
      filter_sizes: 3
      filter_sizes: 4
      num_filters: 16
      num_filters: 8
      num_filters: 8
    }
  }
}
feature_configs {
  input_names: "click_10_seq__item_id"
  feature_type: SequenceFeature
  embedding_dim: 8
  hash_bucket_size: 27000
  separator: ";"
  combiner: "mean"
  sub_feature_type: IdFeature
}
feature_configs {
  input_names: "click_10_seq__category"
  feature_type: SequenceFeature
  embedding_dim: 4
  hash_bucket_size: 10000
  separator: ";"
  combiner: "mean"
  sub_feature_type: IdFeature
}
feature_configs {
  input_names: "click_10_seq__ts"
  feature_type: SequenceFeature
  embedding_dim: 4
  separator: ";"
  sub_feature_type: RawFeature
}
feature_configs {
  input_names: "click_10_seq__ts"
  feature_type: SequenceFeature
  embedding_dim: 4
  separator: ";"
  sub_feature_type: RawFeature
}
feature_configs {
  input_names: ["age", "gender"]
  feature_name: "combo_age_gender"
  feature_type: ComboFeature
  embedding_dim: 16
  hash_bucket_size: 1000
}
feature_configs {
  input_names: "age"
  feature_name: "age_satisfy1"
  feature_type: ExprFeature
  expression: "age>=18"
}
model_config {
  model_class: "MultiTower"
  feature_groups {
    group_name: "all"
    feature_names: "user_id"
    feature_names: "item_id"
    feature_names: "age"
    feature_names: "gender"
    feature_names: "user__kv_category_click_1d"
    feature_names: "category"
    feature_names: "tags"
    feature_names: "description"
    feature_names: "combo_age_gender"
    feature_names: "age_satisfy1"
    wide_deep: DEEP
    sequence_features {
      group_name: "click_10_seq"
      seq_att_map {
        key: "item_id"
        key: "category"
        hist_seq: "click_10_seq__item_id"
        hist_seq: "click_10_seq__category"
        hist_seq: "click_10_seq__ts"
      }
      tf_summary: false
      allow_key_search: false
      allow_key_transform: true
    }
  }
  embedding_regularization: 5e-06
  multi_tower {
    towers {
      input: "all"
      dnn {
        hidden_units: 256
        hidden_units: 128
      }
    }
    final_dnn {
      hidden_units: 64
      hidden_units: 32
    }
    l2_regularization: 1e-06
  }
}
export_config {
  multi_placeholder: true
}