Nexosis Api

API change history

Sessions: Create model session

Queues a new model-building session to run

Model-building sessions are used to build regression and classification models for later use. To build a model, specify the data source to model and the type of model to build. Once the model is built, use the various model endpoints to interact with it and generate predictions.

Model types

The type of model to build is determined by the predictionDomain property on the request. Acceptable values are:

  • regression: Builds a regression model
  • classification: Builds a classification model
  • anomalies: Builds an anomaly detection model

Regression models

Regression models are used to predict a target (dependent) variable from one or more feature (independent) variables. Regression models always require at least one feature column, and since the output of a regression model is a continuous value, these models can only be used to predict numeric targets.

Classification models

Classification models are used to predict which of a discrete set of classes a given record represents. Like regression models, classification models predict a target (dependent) variable from one or more feature (independent) variables, and they require at least one feature column. Unlike regression models, the target column of a classification model can be any data type. (The target should contain relatively few distinct values, or classes, to predict.)
By default, the Nexosis API will balance the data source used to build a classification model. That is, if 90% of the records in the data source have class A and 10% have class B, the API will strive to generate a model that is equally proficient at identifying both class A and class B records. If the extraParameters.balance property in is set to false, the API will not seek to balance the data source, which may result in a model better at predicting class A than class B. The real-world domain of data being used to build a model should determine whether balancing the data or not is appropriate.

Anomaly detection models

Anomaly detection models are used to detect outliers in a dataset. Unlike other model types, anomaly detection models are built on unlabeled data, that is, data without known target values. (If you know which rows in your dataset are anomalies and which rows are not, build a classification model instead.) When building an anomaly detection model, you should not specify a target column. The results of the session will be returned in a new column named 'anomaly'.
Nexosis uses one of two different algorithms to build an anomaly detection model on your dataset. By default, we assume that your dataset contains some anomalies. If you are certain that your dataset does not contain anomalies (it's from a known good source, for instance), you can specify as such. Set the extraParameters.containsAnomalies property to false and Nexosis will use an algorithm optimized for this sort of dataset to build a model.

Try it

Request URL

Request headers

(optional)
string
Media type of the body sent to the API.
string
Subscription key which provides access to this API. Found in your Profile.

Request body

{
  "dataSourceName": "HousingData",
  "targetColumn": "SalePrice",
  "predictionDomain": "Regression",
  "extraParameters": {},
  "name": "Modeling housing data sale price",
  "columns": {
    "SalePrice": {
      "dataType": "numeric",
      "role": "target"
    },
    "LotFrontage": {
      "dataType": "numeric",
      "role": "feature"
    },
    "LotArea": {
      "dataType": "numeric",
      "role": "feature"
    },
    "YearBuilt": {
      "dataType": "numeric",
      "role": "feature"
    }
  }
}
{
  "type": "object",
  "properties": {
    "dataSourceName": {
      "description": "Name of the dataset or view from which to generate a model",
      "type": "string"
    },
    "targetColumn": {
      "description": "Column in the specified data source to predict with the generated model",
      "type": "string"
    },
    "predictionDomain": {
      "description": "Type of prediction the built model is intended to make. Currently values \"regression\" and \"classification\" are supported",
      "type": "string"
    },
    "extraParameters": {
      "type": "object",
      "properties": {
        "balance": {
          "description": "For classification models, whether or not to balance classes during model building (default is true)",
          "type": "boolean"
        },
        "containsAnomalies": {
          "description": "For anomaly detection models, whether or not the source dataset contains anomalies (default is true)",
          "type": "boolean"
        }
      }
    },
    "name": {
      "description": "A name for the session, to make it easier to locate",
      "type": "string"
    },
    "callbackUrl": {
      "description": "The Webhook url that will receive updates when the Session status changes<br />\r\nIf you provide a callback url, your response will contain a header named Nexosis-Webhook-Token.  You will receive this \r\nsame header in the request message to your Webhook, which you can use to validate that the message came from Nexosis.",
      "type": "string"
    },
    "columns": {
      "description": "Metadata about each column in the data source",
      "type": "object",
      "additionalProperties": {
        "type": "object",
        "properties": {
          "dataType": {
            "enum": [
              "string",
              "numeric",
              "logical",
              "date",
              "text",
              "numericMeasure"
            ],
            "type": "string"
          },
          "role": {
            "enum": [
              "none",
              "timestamp",
              "target",
              "feature",
              "key"
            ],
            "type": "string"
          },
          "imputation": {
            "enum": [
              "zeroes",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          },
          "aggregation": {
            "enum": [
              "sum",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          }
        }
      }
    },
    "missingValues": {
      "description": "Values in the data that ought to be treated as null/missing/empty",
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "example": {
    "dataSourceName": "HousingData",
    "targetColumn": "SalePrice",
    "predictionDomain": "Regression",
    "extraParameters": {},
    "name": "Modeling housing data sale price",
    "columns": {
      "SalePrice": {
        "dataType": "numeric",
        "role": "target"
      },
      "LotFrontage": {
        "dataType": "numeric",
        "role": "feature"
      },
      "LotArea": {
        "dataType": "numeric",
        "role": "feature"
      },
      "YearBuilt": {
        "dataType": "numeric",
        "role": "feature"
      }
    }
  }
}
{
  "dataSourceName": "HousingData",
  "targetColumn": "SalePrice",
  "predictionDomain": "Regression",
  "extraParameters": {},
  "name": "Modeling housing data sale price",
  "columns": {
    "SalePrice": {
      "dataType": "numeric",
      "role": "target"
    },
    "LotFrontage": {
      "dataType": "numeric",
      "role": "feature"
    },
    "LotArea": {
      "dataType": "numeric",
      "role": "feature"
    },
    "YearBuilt": {
      "dataType": "numeric",
      "role": "feature"
    }
  }
}
{
  "type": "object",
  "properties": {
    "dataSourceName": {
      "description": "Name of the dataset or view from which to generate a model",
      "type": "string"
    },
    "targetColumn": {
      "description": "Column in the specified data source to predict with the generated model",
      "type": "string"
    },
    "predictionDomain": {
      "description": "Type of prediction the built model is intended to make. Currently values \"regression\" and \"classification\" are supported",
      "type": "string"
    },
    "extraParameters": {
      "type": "object",
      "properties": {
        "balance": {
          "description": "For classification models, whether or not to balance classes during model building (default is true)",
          "type": "boolean"
        },
        "containsAnomalies": {
          "description": "For anomaly detection models, whether or not the source dataset contains anomalies (default is true)",
          "type": "boolean"
        }
      }
    },
    "name": {
      "description": "A name for the session, to make it easier to locate",
      "type": "string"
    },
    "callbackUrl": {
      "description": "The Webhook url that will receive updates when the Session status changes<br />\r\nIf you provide a callback url, your response will contain a header named Nexosis-Webhook-Token.  You will receive this \r\nsame header in the request message to your Webhook, which you can use to validate that the message came from Nexosis.",
      "type": "string"
    },
    "columns": {
      "description": "Metadata about each column in the data source",
      "type": "object",
      "additionalProperties": {
        "type": "object",
        "properties": {
          "dataType": {
            "enum": [
              "string",
              "numeric",
              "logical",
              "date",
              "text",
              "numericMeasure"
            ],
            "type": "string"
          },
          "role": {
            "enum": [
              "none",
              "timestamp",
              "target",
              "feature",
              "key"
            ],
            "type": "string"
          },
          "imputation": {
            "enum": [
              "zeroes",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          },
          "aggregation": {
            "enum": [
              "sum",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          }
        }
      }
    },
    "missingValues": {
      "description": "Values in the data that ought to be treated as null/missing/empty",
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "example": {
    "dataSourceName": "HousingData",
    "targetColumn": "SalePrice",
    "predictionDomain": "Regression",
    "extraParameters": {},
    "name": "Modeling housing data sale price",
    "columns": {
      "SalePrice": {
        "dataType": "numeric",
        "role": "target"
      },
      "LotFrontage": {
        "dataType": "numeric",
        "role": "feature"
      },
      "LotArea": {
        "dataType": "numeric",
        "role": "feature"
      },
      "YearBuilt": {
        "dataType": "numeric",
        "role": "feature"
      }
    }
  }
}

Response 200

success

{
  "columns": {
    "SalePrice": {
      "dataType": "numeric",
      "role": "target"
    },
    "LotFrontage": {
      "dataType": "numeric",
      "role": "feature"
    },
    "LotArea": {
      "dataType": "numeric",
      "role": "feature"
    },
    "YearBuilt": {
      "dataType": "numeric",
      "role": "feature"
    }
  },
  "approximateCompletionPercentage": 0,
  "sessionId": "b14b0535-587c-4845-93ce-96bb78fe7f3c",
  "type": "model",
  "status": "requested",
  "supportsFeatureImportance": false,
  "requestedDate": "0001-01-01T00:00:00+00:00",
  "statusHistory": [],
  "extraParameters": {},
  "messages": [],
  "name": "Modeling housing data sale price",
  "dataSourceName": "HousingData",
  "dataSetName": "HousingData",
  "targetColumn": "SalePrice",
  "callbackUrl": "",
  "isEstimate": false,
  "links": []
}
{
  "type": "object",
  "properties": {
    "columns": {
      "type": "object",
      "additionalProperties": {
        "type": "object",
        "properties": {
          "dataType": {
            "enum": [
              "string",
              "numeric",
              "logical",
              "date",
              "text",
              "numericMeasure"
            ],
            "type": "string"
          },
          "role": {
            "enum": [
              "none",
              "timestamp",
              "target",
              "feature",
              "key"
            ],
            "type": "string"
          },
          "imputation": {
            "enum": [
              "zeroes",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          },
          "aggregation": {
            "enum": [
              "sum",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          }
        }
      }
    },
    "approximateCompletionPercentage": {
      "format": "int32",
      "type": "integer"
    },
    "sessionId": {
      "format": "uuid",
      "type": "string"
    },
    "type": {
      "enum": [
        "import",
        "forecast",
        "impact",
        "model"
      ],
      "type": "string"
    },
    "status": {
      "enum": [
        "requested",
        "started",
        "completed",
        "cancelled",
        "failed",
        "estimated",
        "cancellationPending"
      ],
      "type": "string"
    },
    "eventName": {
      "type": "string"
    },
    "predictionDomain": {
      "type": "string"
    },
    "supportsFeatureImportance": {
      "type": "boolean"
    },
    "availablePredictionIntervals": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "modelId": {
      "format": "uuid",
      "type": "string"
    },
    "startDate": {
      "format": "date-time",
      "type": "string"
    },
    "endDate": {
      "format": "date-time",
      "type": "string"
    },
    "resultInterval": {
      "enum": [
        "hour",
        "day",
        "week",
        "month",
        "year"
      ],
      "type": "string"
    },
    "requestedDate": {
      "format": "date-time",
      "type": "string"
    },
    "statusHistory": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "date": {
            "format": "date-time",
            "type": "string"
          },
          "status": {
            "enum": [
              "requested",
              "started",
              "completed",
              "cancelled",
              "failed",
              "estimated",
              "cancellationPending"
            ],
            "type": "string"
          }
        }
      }
    },
    "extraParameters": {
      "type": "object",
      "properties": {
        "event": {
          "type": "string"
        },
        "balance": {
          "type": "boolean"
        },
        "containsAnomalies": {
          "type": "boolean"
        }
      }
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "severity": {
            "enum": [
              "informational",
              "warning",
              "error",
              "status",
              "debug"
            ],
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        }
      }
    },
    "name": {
      "type": "string"
    },
    "dataSourceName": {
      "type": "string"
    },
    "targetColumn": {
      "type": "string"
    },
    "algorithm": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "description": {
          "type": "string"
        },
        "key": {
          "type": "string"
        }
      }
    },
    "callbackUrl": {
      "type": "string"
    },
    "missingValues": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "links": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "rel": {
            "type": "string",
            "readOnly": true
          },
          "href": {
            "type": "string",
            "readOnly": true
          }
        }
      },
      "readOnly": true
    }
  }
}
{
  "columns": {
    "SalePrice": {
      "dataType": "numeric",
      "role": "target"
    },
    "LotFrontage": {
      "dataType": "numeric",
      "role": "feature"
    },
    "LotArea": {
      "dataType": "numeric",
      "role": "feature"
    },
    "YearBuilt": {
      "dataType": "numeric",
      "role": "feature"
    }
  },
  "approximateCompletionPercentage": 0,
  "sessionId": "b14b0535-587c-4845-93ce-96bb78fe7f3c",
  "type": "model",
  "status": "requested",
  "supportsFeatureImportance": false,
  "requestedDate": "0001-01-01T00:00:00+00:00",
  "statusHistory": [],
  "extraParameters": {},
  "messages": [],
  "name": "Modeling housing data sale price",
  "dataSourceName": "HousingData",
  "dataSetName": "HousingData",
  "targetColumn": "SalePrice",
  "callbackUrl": "",
  "isEstimate": false,
  "links": []
}
{
  "type": "object",
  "properties": {
    "columns": {
      "type": "object",
      "additionalProperties": {
        "type": "object",
        "properties": {
          "dataType": {
            "enum": [
              "string",
              "numeric",
              "logical",
              "date",
              "text",
              "numericMeasure"
            ],
            "type": "string"
          },
          "role": {
            "enum": [
              "none",
              "timestamp",
              "target",
              "feature",
              "key"
            ],
            "type": "string"
          },
          "imputation": {
            "enum": [
              "zeroes",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          },
          "aggregation": {
            "enum": [
              "sum",
              "mean",
              "median",
              "mode",
              "min",
              "max"
            ],
            "type": "string"
          }
        }
      }
    },
    "approximateCompletionPercentage": {
      "format": "int32",
      "type": "integer"
    },
    "sessionId": {
      "format": "uuid",
      "type": "string"
    },
    "type": {
      "enum": [
        "import",
        "forecast",
        "impact",
        "model"
      ],
      "type": "string"
    },
    "status": {
      "enum": [
        "requested",
        "started",
        "completed",
        "cancelled",
        "failed",
        "estimated",
        "cancellationPending"
      ],
      "type": "string"
    },
    "eventName": {
      "type": "string"
    },
    "predictionDomain": {
      "type": "string"
    },
    "supportsFeatureImportance": {
      "type": "boolean"
    },
    "availablePredictionIntervals": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "modelId": {
      "format": "uuid",
      "type": "string"
    },
    "startDate": {
      "format": "date-time",
      "type": "string"
    },
    "endDate": {
      "format": "date-time",
      "type": "string"
    },
    "resultInterval": {
      "enum": [
        "hour",
        "day",
        "week",
        "month",
        "year"
      ],
      "type": "string"
    },
    "requestedDate": {
      "format": "date-time",
      "type": "string"
    },
    "statusHistory": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "date": {
            "format": "date-time",
            "type": "string"
          },
          "status": {
            "enum": [
              "requested",
              "started",
              "completed",
              "cancelled",
              "failed",
              "estimated",
              "cancellationPending"
            ],
            "type": "string"
          }
        }
      }
    },
    "extraParameters": {
      "type": "object",
      "properties": {
        "event": {
          "type": "string"
        },
        "balance": {
          "type": "boolean"
        },
        "containsAnomalies": {
          "type": "boolean"
        }
      }
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "severity": {
            "enum": [
              "informational",
              "warning",
              "error",
              "status",
              "debug"
            ],
            "type": "string"
          },
          "message": {
            "type": "string"
          }
        }
      }
    },
    "name": {
      "type": "string"
    },
    "dataSourceName": {
      "type": "string"
    },
    "targetColumn": {
      "type": "string"
    },
    "algorithm": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "description": {
          "type": "string"
        },
        "key": {
          "type": "string"
        }
      }
    },
    "callbackUrl": {
      "type": "string"
    },
    "missingValues": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "links": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "rel": {
            "type": "string",
            "readOnly": true
          },
          "href": {
            "type": "string",
            "readOnly": true
          }
        }
      },
      "readOnly": true
    }
  }
}

Response 400

One or more parameter values are invalid

{
  "statusCode": 400,
  "message": "Request is invalid",
  "errorType": "RequestValidation",
  "errorDetails": {
    "predictionDomain": [
      "A prediction domain is required to build a model. Acceptable values are: 'regression'"
    ]
  }
}
{
  "type": "object",
  "properties": {
    "statusCode": {
      "format": "int32",
      "type": "integer"
    },
    "message": {
      "type": "string"
    },
    "errorType": {
      "type": "string"
    },
    "errorDetails": {
      "type": "object",
      "additionalProperties": {
        "type": "object"
      }
    }
  }
}
{
  "statusCode": 400,
  "message": "Request is invalid",
  "errorType": "RequestValidation",
  "errorDetails": {
    "predictionDomain": [
      "A prediction domain is required to build a model. Acceptable values are: 'regression'"
    ]
  }
}
{
  "type": "object",
  "properties": {
    "statusCode": {
      "format": "int32",
      "type": "integer"
    },
    "message": {
      "type": "string"
    },
    "errorType": {
      "type": "string"
    },
    "errorDetails": {
      "type": "object",
      "additionalProperties": {
        "type": "object"
      }
    }
  }
}

Code samples

@ECHO OFF

curl -v -X POST "https://ml.nexosis.com/v1/sessions/model"
-H "Content-Type: application/json"
-H "api-key: {subscription key}"

--data-ascii "{body}" 
using System;
using System.Net.Http.Headers;
using System.Text;
using System.Net.Http;
using System.Web;

namespace CSHttpClientSample
{
    static class Program
    {
        static void Main()
        {
            MakeRequest();
            Console.WriteLine("Hit ENTER to exit...");
            Console.ReadLine();
        }
        
        static async void MakeRequest()
        {
            var client = new HttpClient();
            var queryString = HttpUtility.ParseQueryString(string.Empty);

            // Request headers
            client.DefaultRequestHeaders.Add("api-key", "{subscription key}");

            var uri = "https://ml.nexosis.com/v1/sessions/model?" + queryString;

            HttpResponseMessage response;

            // Request body
            byte[] byteData = Encoding.UTF8.GetBytes("{body}");

            using (var content = new ByteArrayContent(byteData))
            {
               content.Headers.ContentType = new MediaTypeHeaderValue("< your content type, i.e. application/json >");
               response = await client.PostAsync(uri, content);
            }

        }
    }
}	
// // This sample uses the Apache HTTP client from HTTP Components (http://hc.apache.org/httpcomponents-client-ga/)
import java.net.URI;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.utils.URIBuilder;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

public class JavaSample 
{
    public static void main(String[] args) 
    {
        HttpClient httpclient = HttpClients.createDefault();

        try
        {
            URIBuilder builder = new URIBuilder("https://ml.nexosis.com/v1/sessions/model");


            URI uri = builder.build();
            HttpPost request = new HttpPost(uri);
            request.setHeader("Content-Type", "application/json");
            request.setHeader("api-key", "{subscription key}");


            // Request body
            StringEntity reqEntity = new StringEntity("{body}");
            request.setEntity(reqEntity);

            HttpResponse response = httpclient.execute(request);
            HttpEntity entity = response.getEntity();

            if (entity != null) 
            {
                System.out.println(EntityUtils.toString(entity));
            }
        }
        catch (Exception e)
        {
            System.out.println(e.getMessage());
        }
    }
}

<!DOCTYPE html>
<html>
<head>
    <title>JSSample</title>
    <script src="http://ajax.googleapis.com/ajax/libs/jquery/1.9.0/jquery.min.js"></script>
</head>
<body>

<script type="text/javascript">
    $(function() {
        var params = {
            // Request parameters
        };
      
        $.ajax({
            url: "https://ml.nexosis.com/v1/sessions/model?" + $.param(params),
            beforeSend: function(xhrObj){
                // Request headers
                xhrObj.setRequestHeader("Content-Type","application/json");
                xhrObj.setRequestHeader("api-key","{subscription key}");
            },
            type: "POST",
            // Request body
            data: "{body}",
        })
        .done(function(data) {
            alert("success");
        })
        .fail(function() {
            alert("error");
        });
    });
</script>
</body>
</html>
#import <Foundation/Foundation.h>

int main(int argc, const char * argv[])
{
    NSAutoreleasePool * pool = [[NSAutoreleasePool alloc] init];
    
    NSString* path = @"https://ml.nexosis.com/v1/sessions/model";
    NSArray* array = @[
                         // Request parameters
                         @"entities=true",
                      ];
    
    NSString* string = [array componentsJoinedByString:@"&"];
    path = [path stringByAppendingFormat:@"?%@", string];

    NSLog(@"%@", path);

    NSMutableURLRequest* _request = [NSMutableURLRequest requestWithURL:[NSURL URLWithString:path]];
    [_request setHTTPMethod:@"POST"];
    // Request headers
    [_request setValue:@"application/json" forHTTPHeaderField:@"Content-Type"];
    [_request setValue:@"{subscription key}" forHTTPHeaderField:@"api-key"];
    // Request body
    [_request setHTTPBody:[@"{body}" dataUsingEncoding:NSUTF8StringEncoding]];
    
    NSURLResponse *response = nil;
    NSError *error = nil;
    NSData* _connectionData = [NSURLConnection sendSynchronousRequest:_request returningResponse:&response error:&error];

    if (nil != error)
    {
        NSLog(@"Error: %@", error);
    }
    else
    {
        NSError* error = nil;
        NSMutableDictionary* json = nil;
        NSString* dataString = [[NSString alloc] initWithData:_connectionData encoding:NSUTF8StringEncoding];
        NSLog(@"%@", dataString);
        
        if (nil != _connectionData)
        {
            json = [NSJSONSerialization JSONObjectWithData:_connectionData options:NSJSONReadingMutableContainers error:&error];
        }
        
        if (error || !json)
        {
            NSLog(@"Could not parse loaded json with error:%@", error);
        }
        
        NSLog(@"%@", json);
        _connectionData = nil;
    }
    
    [pool drain];

    return 0;
}
<?php
// This sample uses the Apache HTTP client from HTTP Components (http://hc.apache.org/httpcomponents-client-ga/)
require_once 'HTTP/Request2.php';

$request = new Http_Request2('https://ml.nexosis.com/v1/sessions/model');
$url = $request->getUrl();

$headers = array(
    // Request headers
    'Content-Type' => 'application/json',
    'api-key' => '{subscription key}',
);

$request->setHeader($headers);

$parameters = array(
    // Request parameters
);

$url->setQueryVariables($parameters);

$request->setMethod(HTTP_Request2::METHOD_POST);

// Request body
$request->setBody("{body}");

try
{
    $response = $request->send();
    echo $response->getBody();
}
catch (HttpException $ex)
{
    echo $ex;
}

?>
########### Python 2.7 #############
import httplib, urllib, base64

headers = {
    # Request headers
    'Content-Type': 'application/json',
    'api-key': '{subscription key}',
}

params = urllib.urlencode({
})

try:
    conn = httplib.HTTPSConnection('ml.nexosis.com')
    conn.request("POST", "/v1/sessions/model?%s" % params, "{body}", headers)
    response = conn.getresponse()
    data = response.read()
    print(data)
    conn.close()
except Exception as e:
    print("[Errno {0}] {1}".format(e.errno, e.strerror))

####################################

########### Python 3.2 #############
import http.client, urllib.request, urllib.parse, urllib.error, base64

headers = {
    # Request headers
    'Content-Type': 'application/json',
    'api-key': '{subscription key}',
}

params = urllib.parse.urlencode({
})

try:
    conn = http.client.HTTPSConnection('ml.nexosis.com')
    conn.request("POST", "/v1/sessions/model?%s" % params, "{body}", headers)
    response = conn.getresponse()
    data = response.read()
    print(data)
    conn.close()
except Exception as e:
    print("[Errno {0}] {1}".format(e.errno, e.strerror))

####################################
require 'net/http'

uri = URI('https://ml.nexosis.com/v1/sessions/model')


request = Net::HTTP::Post.new(uri.request_uri)
# Request headers
request['Content-Type'] = 'application/json'
# Request headers
request['api-key'] = '{subscription key}'
# Request body
request.body = "{body}"

response = Net::HTTP.start(uri.host, uri.port, :use_ssl => uri.scheme == 'https') do |http|
    http.request(request)
end

puts response.body