說(shuō)明

NLC服務(wù)使用機(jī)器學(xué)習(xí)算法返回短文本輸入的匹配預(yù)定義類(lèi)不见。創(chuàng)建和訓(xùn)練一個(gè)分類(lèi)器，將預(yù)定義分類(lèi)與示例文本連接起來(lái)蚀腿，以便服務(wù)可以將這些分類(lèi)器可以對(duì)新的輸入進(jìn)行分類(lèi)

認(rèn)證方式

使用HTTP Basic Authentication方式認(rèn)證慢味。 即用戶(hù)名/密碼方式

創(chuàng)建一個(gè)分類(lèi)器

CURL命令

curl -u "USERNAME":"PASSWORD"  ^
-F training_data=@weather_data_train.csv  ^
-F training_metadata="{\"language\":\"en\",\"name\":\"atp-weather\"}"  ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers"

返回值

{
  "classifier_id" : "359f3fx202-nlc-223328",
  "name" : "atp-weather",
  "language" : "en",
  "created" : "2017-07-25T03:20:16.451Z",
  "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
  "status" : "Training",
  "status_description" : "The classifier instance is in its training phase, not yet ready to accept classify requests"
}

** 注意此時(shí)分類(lèi)器的狀態(tài)為訓(xùn)練中 暫時(shí)還不能使用澈蚌。我們可以通過(guò)命令查看分類(lèi)器狀態(tài)**

查看分類(lèi)器列表

CURL命令

curl -u "USERNAME":"PASSWORD" ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers"

返回值

{
  "classifiers" : [ {
    "classifier_id" : "359f3fx202-nlc-223328",
    "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
    "name" : "atp-weather",
    "language" : "en",
    "created" : "2017-07-25T03:20:16.451Z"
  } ]
}

查看分類(lèi)器信息

CURL命令

curl -u "USERNAME":"PASSWORD"  ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328"

返回值

{
  "classifier_id" : "359f3fx202-nlc-223328",
  "name" : "atp-weather",
  "language" : "en",
  "created" : "2017-07-25T03:20:16.451Z",
  "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
  "status" : "Available",
  "status_description" : "The classifier instance is now available and is ready to take classifier requests."
}

分類(lèi)器有如下五種狀態(tài)

• 1 Non Existent : 不存在
• 2 Training : 訓(xùn)練中
• 3 Failed：失敗
• 4 Available：有效
• 5 Unavailable：無(wú)效

使用分類(lèi)器進(jìn)行分類(lèi)

CURL命令

• Get方法分類(lèi) How how will it be today?

curl -G -u "USERNAME":"PASSWORD" ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328/classify?text=How%20hot%20will%20it%20be%20today%3F"

• Post方法分類(lèi) How how will it be today?

curl -X POST -u "USERNAME":"PASSWORD" ^
-H "Content-Type:application/json" ^
-d "{\"text\":\"How hot will it be today?\"}" ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328/classify"

返回值

{
  "classifier_id" : "359f3fx202-nlc-223328",
  "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
  "text" : "How hot will it be today?",
  "top_class" : "temperature",
  "classes" : [ {
    "class_name" : "temperature",
    "confidence" : 0.9929586035651006
  }, {
    "class_name" : "conditions",
    "confidence" : 0.007041396434899482
  } ]
}

使用分類(lèi)器訓(xùn)練數(shù)據(jù)中未包含的詞匯（sleet 為雨夾雪）
特意使用了temperature分類(lèi)中包含的句式 how xxx it is today?
分類(lèi)器還是準(zhǔn)確將其分到condition類(lèi)中了亦镶。

curl -X POST -u "username":"password" ^
-H "Content-Type:application/json" ^
-d "{\"text\":\"How sleet will it be today?\"}" ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328/classify"

返回值

{
  "classifier_id" : "359f3fx202-nlc-223328",
  "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
  "text" : "How sleet will it be today?",
  "top_class" : "conditions",
  "classes" : [ {
    "class_name" : "conditions",
    "confidence" : 0.89688785244637
  }, {
    "class_name" : "temperature",
    "confidence" : 0.10311214755363002
  } ]
}

使用分類(lèi)器完全無(wú)關(guān)的詞匯 it is atp's notebook?
分類(lèi)結(jié)果非常不理想 temperature類(lèi)的置信度竟然高達(dá)82%

curl -X POST -u "74e23665-dfea-4bd6-ad80-3e9b4a7f7604":"RxFKejjwlUcA" ^
-H "Content-Type:application/json" ^
-d "{\"text\":\"it is atp's notebook?\"}" ^
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328/classify"

返回值

{
  "classifier_id" : "359f3fx202-nlc-223328",
  "url" : "https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/359f3fx202-nlc-223328",
  "text" : "it is atp's notebook?",
  "top_class" : "temperature",
  "classes" : [ {
    "class_name" : "temperature",
    "confidence" : 0.8255246180698945
  }, {
    "class_name" : "conditions",
    "confidence" : 0.1744753819301055
  } ]
}

刪除一個(gè)分類(lèi)器

CURL命令

curl -X DELETE -u "{username}":"{password}" 
"https://gateway.watsonplatform.net/natural-language-classifier/api/v1/classifiers/10D41B-nlc-1"

要點(diǎn)

• 置信度值表示為百分比日月，值越大表示置信度越高。響應(yīng)最多包含 10 個(gè)類(lèi)染乌。
• 如果培訓(xùn)數(shù)據(jù)中的類(lèi)少于10個(gè)山孔，那么所有置信度值的和為 100%懂讯。例如只定義了兩個(gè)類(lèi)荷憋，就只能返回兩個(gè)類(lèi)。
• 其中一個(gè)樣本問(wèn)題包含未對(duì)分類(lèi)器進(jìn)行培訓(xùn)的詞語(yǔ)（“foggy”）褐望。您無(wú)須執(zhí)行額外工作來(lái)識(shí)別這些“缺少”的詞語(yǔ)勒庄，分類(lèi)器對(duì)于這些詞語(yǔ)就能獲得不錯(cuò)的分?jǐn)?shù)。請(qǐng)嘗試使用包含培訓(xùn)數(shù)據(jù)中沒(méi)有的詞（例如瘫里，“sleet”或“storm”）的其他問(wèn)題实蔽。

課題

• 1 支持語(yǔ)言 en之外還包含？
• 2 訓(xùn)練數(shù)據(jù)文本的格式 csv固定谨读？ csv的format也是固定局装？
• 3 分類(lèi)器建成以后是否可以追加training數(shù)據(jù)