Question

我使用Mongo v2.2.0。

我编写了查询，但主要问题是$ arrayElemAt。使用$ unwind- $ first的标准替换对我不起作用，我认为存在更好的解决方案。我有限制将此聚合管道作为单个操作运行，而不是运行正和否定数据的查询，然后在代码中合并结果。我需要对结果查询应用$ sort，$ limit和$ skip来限制用于从其他集合中过滤记录的words计数，并在Java代码中组合来自两个集合的数据。

汇总查询：

[
  {
    $match: {
      "merchantId": ObjectId("59520e6ccc7a701fbed31f94"),
      "date": {
        "$gte": NumberLong(1389644800000),
        "$lt": NumberLong(1502409599999)
      },
      "isbn": "a123",

    }
  },
  {
    $project: {
      "word": 1,
      "sentence": 1,
      "type": 1,
      "date": 1
    }
  },
  {
    $sort: {
      "date": -1
    }
  },
  {
    $group: {
      "_id": {
        "word": "$word",
        "type": "$type"
      },
      "date": {
          $max: "$date"
      },
      "sentence": {
        $first: "$sentence"
      },
      "sentenceCount": {
        "$sum": 1
      }
    },    
  },
  {
    $group: {
            "_id": "$_id.word",
            "word": { $first: "$_id.word"},
            "positiveCount": {$sum: {$cond: [{$eq: ["$_id.type", "positive"]}, "$sentenceCount", 0]}},
            "count": {$sum: "$sentenceCount"},
            "positiveSentence": {
                "$push": {
                    "$cond": [{$eq: ["$_id.type", "positive"]}, "$sentence", "$noval"] 
                }
            },
            "negativeSentence": {
                "$push": {
                    "$cond": [{$eq: ["$_id.type", "negative"]}, "$sentence", "$noval"] 
                }
            }
    }
  },
  {
    $project: {
            "_id": 0,
            "word": 1,
            "sentimentPercentage": {$cond: [{$eq: ["$count", 0]}, 0, {$multiply: [{$divide: ["$positiveCount", "$count"]}, 100]}]},
            "positiveSentence": {$arrayElemAt: ["$positiveSentence", 0]},
            "negativeSentence": {$arrayElemAt: ["$negativeSentence", 0]},
    }
  },
  {
    $sort: {
            sentimentPercentage: -1
    }
  },
  {
    $limit: 50
  }
]

收集文件“架构”：

{ 
    "_id" : ObjectId("59887424e4b099e00724aa44"), 
    "merchantId" : ObjectId("59520e6ccc7a701fbed31f94"), 
    "isbn" : "a123", 
    "sentence" : "Great, friendly service.", 
    "word" : "service", 
    "type" : "positive", 
    "date" : NumberLong(1466809200000),    
}

预期产出：

{ 
    "word" : "expectations", 
    "sentimentPercentage" : 100.0, 
    "positiveSentence" : "The service exceeded our expectations."
},
{ 
    "word" : "representative", 
    "sentimentPercentage" : 87.5, 
    "positiveSentence" : "Excellent local representative, met the flight and gave us all the relevant information to ensure a great holiday.", 
    "negativeSentence" : "The representative at resort was poor."
},
{ 
    "word" : "seats", 
    "sentimentPercentage" : 0.0, 
    "negativeSentence" : "Long delay and pre booked seats were lost ."
}

拜托，您能否告诉我如何使用Mongo＆lt; = 2.2.0？

的功能替换$ arrayElemAt运算符，甚至更好地如何优化此查询到所需的输出？

Answer 1

这似乎给了我合理的结果。但是，如果因为$unwind阶段不支持v2.2中的preserveNullAndEmptyArrays参数而没有肯定或没有否定句子，我认为它将无法正常工作......

db.getCollection('test').aggregate([
  {
    $project: {
      "word": 1,
      "sentence": 1,
      "type": 1,
      "date": 1
    }
  },
  {
    $sort: {
      "date": -1
    }
  },
  {
    $group: {
      "_id": {
        "word": "$word",
        "type": "$type"
      },
      "date": {
          $max: "$date"
      },
      "sentence": {
        $first: "$sentence"
      },
      "sentenceCount": {
        "$sum": 1
      }
    },    
  },
  {
    $group: {
            "_id": "$_id.word",
            "word": { $first: "$_id.word"},
            "positiveCount": {$sum: {$cond: [{$eq: ["$_id.type", "positive"]}, "$sentenceCount", 0]}},
            "count": {$sum: "$sentenceCount"},
            "positiveSentence": {
                "$push": {
                    "$cond": [{$eq: ["$_id.type", "positive"]}, "$sentence", "$noval"] 
                }
            },
            "negativeSentence": {
                "$push": {
                    "$cond": [{$eq: ["$_id.type", "negative"]}, "$sentence", "$noval"] 
                }
            }
    }
  },
  { $unwind: "$positiveSentence" },
  { $group: 
      {
          "_id": "$_id",
          "word": { $first: "$word" },
          "count": { $first: "$count" },
          "positiveCount": { $first: "$positiveCount" },
          "positiveSentence": { $first: "$positiveSentence" },
          "negativeSentence": { $first: "$negativeSentence" },
      }
  },
  { $unwind: "$negativeSentence" },
  { $group: 
      {
          "_id": "$_id",
          "word": { $first: "$word" },
          "count": { $first: "$count" },
          "positiveCount": { $first: "$positiveCount" },
          "positiveSentence": { $first: "$positiveSentence" },
          "negativeSentence": { $first: "$negativeSentence" },
      }
  },
  {
    $project: {
            "_id": 0,
            "word": 1,
            "sentimentPercentage": {$cond: [{$eq: ["$count", 0]}, 0, {$multiply: [{$divide: ["$positiveCount", "$count"]}, 100]}]},
            "positiveSentence": 1,
            "negativeSentence": 1
    }
  }
])

您可以进一步简化此操作，例如摆脱第一个投影和分组阶段。如果你愿意，我可以在几个小时内调查一下。

Mongo聚合$ group条件$ eq为字符串字段

1 个答案: