NAV Navbar
Logo
curl

Introduction

ML Analyzer is a swiss army knife of NLP and classifications API’s hosted on the mashape platform. Some of the tools include Article Summarization, Sentiment Analysis, Stock symbol extraction, Person Names Extractor, Language Detection, Locations Extractor and Adult content Analyzer. ML Analyzer has been featured in several academic studies including the Zurich University of Applied Sciences

Authentication

To authorize, sign up for a mashape account. Then use the authorization key in your requests to the api. Ex : X-Mashape-Key: meowmeowmeow 

curl --get --include 'https://nehac-ml-analyzer.p.mashape.com/adult?text=encoded+text' \
  -H 'X-Mashape-Key: meowmeowmeow' \
  -H 'Accept: application/json'

Make sure to replace meowmeowmeow with your API key.

ML Analyzer uses API keys to allow access to the API. You can register a new API key at Mashape’s developer portal.

ML Analyzer expects for the API key to be included in all API requests to the server in a header that looks like the following:

X-Mashape-Key: meowmeowmeow

ML Analyzer Toolkit

Adult Content Analyzer

curl --get --include 'https://nehac-ml-analyzer.p.mashape.com/adult?text=encoded+text' \
  -H 'X-Mashape-Key: NdJHeGk8vMmshhO5wcqdPcASbtFfp1S5w5HjsnrhsCg8aNisSn' \
  -H 'Accept: application/json'

The above command returns JSON structured like this:

{
  "value": "Non-Adult"
}

Analyze a block of text for adult content (English only)

HTTP Request

GET https://nehac-ml-analyzer.p.mashape.com/adult

Query Parameters

Parameter Type Description
callback String A callback to use for PJSON calls
text Encoded String The block of text to analyze

Article Summarizer

curl -X POST --include 'https://nehac-ml-analyzer.p.mashape.com/article/p' \
  -H 'X-Mashape-Key: NdJHeGk8vMmshhO5wcqdPcASbtFfp1S5w5HjsnrhsCg8aNisSn' \
  -H 'Content-Type: application/x-www-form-urlencoded' \
  -H 'Accept: text/plain' \
  -d 'size=3' \
  -d 'text=Hello world this is cool'

The above command returns JSON structured like this:

[
  "The gameplay is very similar to that of its predecessors, with a focus on combo-based combat.",
  "The game features quick time events that require the player to complete game controller actions in a timed sequence to defeat stronger enemies and bosses.",
  "Considered one of the best games on the platform, it has won several awards and had sold 3.2 million copies worldwide by June 2012."
]

This algorithm uses a combination of word entity detection, semantic analysis of entities and sentence detection to summarize a given block of text into it core subject lines.

HTTP Request

POST https://nehac-ml-analyzer.p.mashape.com/article/p

Query Parameters

Parameter Type Description
size Number The number of sentences to summarize the text into.
text Encoded String The body of text to summarize

Sentiment Analyzer

curl --get --include 'https://nehac-ml-analyzer.p.mashape.com/sentiment?text=hey+this+is+good' \
  -H 'X-Mashape-Key: NdJHeGk8vMmshhO5wcqdPcASbtFfp1S5w5HjsnrhsCg8aNisSn' \
  -H 'Accept: application/json'

The above command returns JSON structured like this:

{
  "value": "Positive"
}

Analyze a text block for sentiment (English only)

There are 3 levels of analysis

Document cleansing using a curated set of stop words, stemming etc Sentiment classification using trained ML models. ( Algorithm : variant of SVM ) 2.1. We use short documents ( tweets, comments etc ) for training on sentiment of phrases and short sentences 2.3 . We use larger documents ( web pages, articles etc ) for training on sentiment of multi paragraph contexts. Use heuristics to convert contexts to features. An example is is ‘not so good’ is translated into a negative feature v/s capturing good as a positive feature.

HTTP Request

GET https://nehac-ml-analyzer.p.mashape.com/sentiment

Query Parameters

Parameter Type Description
callback String A callback to use for PJSON calls
text Encoded String The block of text to analyze sentiment

Errors

The ML Analyzer API uses the following error codes:

Error Code Meaning
400 Bad Request – Your request sucks
401 Unauthorized – Your API key is wrong
403 Forbidden – The kitten requested is hidden for administrators only
404 Not Found – The specified kitten could not be found
405 Method Not Allowed – You tried to access a kitten with an invalid method
406 Not Acceptable – You requested a format that isn’t json
410 Gone – The kitten requested has been removed from our servers
418 I’m a teapot
429 Too Many Requests – You’re requesting too many kittens! Slow down!
500 Internal Server Error – We had a problem with our server. Try again later.
503 Service Unavailable – We’re temporarily offline for maintenance. Please try again later.
curl