API从Wit.ai输出中提取置信度

Question

我是Wit.ai的新手，并且已经开始在我的代码中实现它。我正在考虑一种比硬编码更简单的方法来从给定的wit.ai应用程序接口输出中提取所有的置信度。

例如(API输出)：

{
  "_text": "I believe I am a human",
  "entities": {
    "statement": [
      {
        "confidence": 0.97691847787856,
        "value": "I",
        "type": "value"
      },
      {
        "confidence": 0.91728476663947,
        "value": "I",
        "type": "value"
      }
    ],
     "query": [
      {
        "confidence": 1,
        "value": "am",
        "type": "value"
      }
    ]
  },
  "msg_id": "0YKCUvDvHC2gyydiU"
}

提前谢谢你。

Answer 1

您可以遍历entities以获得confidence。

类似于：

data = {
"_text": "I believe I am a human",
"entities": {
    "statement": [
    {
        "confidence": 0.97691847787856,
        "value": "I",
        "type": "value"
    },
    {
        "confidence": 0.91728476663947,
        "value": "I",
        "type": "value"
    }
    ],
    "query": [
    {
        "confidence": 1,
        "value": "am",
        "type": "value"
    }
    ]
},
"msg_id": "0YKCUvDvHC2gyydiU"
}
confidence = list()
for k , v in data['entities'].iteritems():
    for item in v:
        confidence.append( (item['value'], item['confidence']))

print confidence

这就给我们提供了：

[('I', 0.97691847787856), ('I', 0.91728476663947), ('am', 1)]

希望这能有所帮助