@frontlinesystems/rason-mcp-server 2026.5.0

package/examples/datamining/DataSources/MSAccessDatabase.json

@@ -0,0 +1,50 @@
+{
+  "modelName": "MSAccessDatabase",
+  "modelDescription": "Transformation: Rescaling:  This RASON model example rescales the data contained within a Microsoft Access database. This example uses the database, ms-access-db.accdb, which may be downloaded by clicking the RASON Examples Download icon (download cloud icon). To solve this model, you must first POST the model to the RASON Server by clicking the POST icon (upload cloud icon on the left). Afterwards click Choose Files (on the Properties pane on the right), browse to the location of the downloaded examples, and select the ms-access-db.accdb database. Click Open. Then click the down arrow next to the Play icon and click Solve. For more information on POSTing and solving example models, click Help - Defining Your Data Science Model.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "msAccessSrc": {
+      "comment": "Binds the MS Access database, ms-access-db.accdb, to the msAccessSrc datasource. The file name is ms-access-db.accdb and is passed to the 'connection' property. The selection property selects all columns in the Hald table. This file is being imported, so 'direction' is set to 'import'. For a complete list of options and setting for a datasource, see the RASON Data Science Model Components chapter within the RASON Reference Guide, which can be downloaded from the Help tab.",
+      "type": "access",
+      "connection": "ms-access-db.accdb",
+      "selection": "SELECT * FROM Hald",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myData": {
+      "comment": "Binds the msAccessSrc datasource to the myData dataset.",
+      "binding": "msAccessSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "myRescaler": {
+      "comment": "Creates a new rescaling estimator, myRescaler, which will be called in 'actions' (below) to rescale the dataset within the Hald table in the MS Access database. Two options are set.  For a complete list of options and setting for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "transformation",
+      "algorithm": "rescaling",
+      "parameters": {
+        "technique": "UNIT_NORMALIZATION",
+        "normType": "L1"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "rescalerModel": {
+      "comment": "Calls the myRescaler estimator to fit a model to the myData dataset.",
+      "trainData": "myData",
+      "estimator": "myRescaler",
+      "action": "fit"
+    },
+    "rescaledData": {
+      "comment": "Uses the rescalerModel (created above) to rescale (transform) the myData dataset. The evaluation, transformation, returns the rescaled dataset in the results. For a complete list of rescaler evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myData",
+      "fittedModel": "rescalerModel",
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/DataSources/MSExcelTable.json

@@ -0,0 +1,51 @@
+{
+  "modelName": "MSExcelTable",
+  "modelDescription": "Transformation: Rescaling:  This RASON model example rescales the data contained within the Microsoft Excel spreadsheet, hald.xlsx, which may be downloaded by clicking the RASON Examples Download icon (download cloud icon). To solve this model, you must first POST the model to the RASON Server by clicking the POST icon (upload cloud icon on the left). Afterwards click Choose Files (on the Properties pane on the right), browse to the location of the downloaded examples, and select the hald.xlsx workbook. Click Open. Then click the down arrow next to the Play icon and click Solve. For more information on POSTing and solving example models, click Help - Defining Your Data Science Model.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "msExcelSrc": {
+      "comment": "Binds the data within the Microsoft Excel workbook, hald.xlsx, located on the Data worksheet in cells A1:E14, to the msExcelSrc datasource. The file name is passed to the 'connection' property. The selection property selects cells Data!A2:E14. Since the data contains column headings, the property 'headerExists' must be set to true.  This file is being imported, so 'direction' is set to 'import'. For a complete list of options and setting for a datasource, see the RASON Data Science Model Components chapter within the RASON Reference Guide, which can be downloaded from the Help tab.",
+      "type": "excel",
+      "connection": "hald.xlsx",
+      "selection": "Data!A2:E14",
+      "headerExists": true,
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myData": {
+      "comment": "Binds the msExcelSrc datasource to the myData dataset.",
+      "binding": "msExcelSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "myRescaler": {
+      "comment": "Creates a new rescaling estimator, myRescaler, which will be called in 'actions' (below) to rescale the dataset within the Excel worksheet. Two options are set.  For a complete list of options and setting for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "transformation",
+      "algorithm": "rescaling",
+      "parameters": {
+        "technique": "UNIT_NORMALIZATION",
+        "normType": "L1"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "rescalerModel": {
+      "comment": "Calls the myRescaler estimator to fit a model to the myData dataset.",
+      "trainData": "myData",
+      "estimator": "myRescaler",
+      "action": "fit"
+    },
+    "rescaledData": {
+      "comment": "Uses the rescalerModel (created above) to rescale (transform) the myData dataset. The evaluation, transformation, returns the rescaled dataset in the results. For a complete list of rescaler evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myData",
+      "fittedModel": "rescalerModel",
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/DataSources/MSSQLDatabase.json

@@ -0,0 +1,50 @@
+{
+  "modelName": "MSSQLDatabase",
+  "modelDescription": "Transformation: Rescaling:  This RASON model example rescales the data contained within an MS-SQL database. (This model is for illustration purposes only.) Note that RASON now allows Data Connections. In previous versions of RASON, models that accessed external databases required actual credentials to be passed, such as database URLs, port numbers, usernames and passwords, in the text of the RASON model, in a datasource declaration, as shown below. RASON now offers an alternative to tackle this security risk by substituting 'connection': 'Driver={SQL Server} ...' with three options: a file containing the contents of 'connection', a named Data Connection or a URL pointing to Microsoft Common Data Service. Click Help - Rason Subscriptions -- Data Connections for more information.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "mssqlSrc": {
+      "comment": "Binds the data within an MS-SQL database to the mssqlSrc datasource. The file name is passed to the 'connection' property. The 'selection' property selects the data to be imported.  This data is being imported, so 'direction' is set to 'import'. Note that RASON now allows Data Connections. In previous versions of RASON, models that accessed external databases required actual credentials to be passed, such as database URLs, port numbers, usernames and passwords, in the text of the RASON model, in a datasource declaration, as shown below. RASON now offers an alternative to tackle this security risk by substituting 'connection': 'Driver={SQL Server} ...' with three options: a file containing the contents of 'connection', a named Data Connection or a URL pointing to Microsoft Common Data Service. Click Help - Rason Subscriptions -- Data Connections for more information.",
+      "type": "mssql",
+      "connection": "<server_name>;<db_name>;<trusted>;<uid>;<pwd>",
+      "selection": "<selection>",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myData": {
+      "comment": "Binds the mssqlSrc datasource to the myData dataset.",
+      "binding": "mssqlSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "myRescaler": {
+      "comment": "Creates a new rescaling estimator, myRescaler, which will be called in 'actions' (below) to rescale the dataset within the MSSQL database. Two options are set. For a complete list of options and setting for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "transformation",
+      "algorithm": "rescaling",
+      "parameters": {
+        "technique": "UNIT_NORMALIZATION",
+        "normType": "L1"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "rescalerModel": {
+      "comment": "Calls the myRescaler estimator to fit a model to the myData dataset.",
+      "trainData": "myData",
+      "estimator": "myRescaler",
+      "action": "fit"
+    },
+    "rescaledData": {
+      "comment": "Uses the rescalerModel (created above) to rescale (transform) the myData dataset. The evaluation, transformation, returns the rescaled dataset in the results. For a complete list of rescaler evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myData",
+      "fittedModel": "rescalerModel",
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/DataSources/ODATATable.json

@@ -0,0 +1,50 @@
+{
+  "modelName": "ODATATable",
+  "modelDescription": "Transformation: Rescaling:  This RASON model example rescales the data contained within an OData table. (This model is for illustration purposes only.) See below for information on using a Data Connection.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "odataSrc": {
+      "comment": "Binds the data within an ODATA table to the odataSrc datasource. The file name is passed to the 'connection' property. The 'selection' property selects the data to be imported.  This data is being imported, so 'direction' is set to 'import'. Note that RASON now allows Data Connections. In previous versions of RASON, models that accessed external data required actual credentials to be passed, such as database URLs, port numbers, usernames and passwords, in the text of the RASON model, in a datasource declaration, as shown below. RASON now offers an alternative to tackle this security risk by substituting 'connection': 'Driver={SQL Server} ...' with three options: a file containing the contents of 'connection', a named Data Connection or a URL pointing to Microsoft Common Data Service. Click Help - Rason Subscriptions -- Data Connections for more information.",
+      "type": "odata",
+      "connection": "<server>",
+      "selection": "<selection>",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myData": {
+      "comment": "Binds the ODATA table to the myData dataset.",
+      "binding": "odataSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "myRescaler": {
+      "comment": "Creates a new rescaling estimator, myRescaler, which will be called in 'actions' (below) to rescale the dataset within ODATA table. Two options are set.  For a complete list of options and setting for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "transformation",
+      "algorithm": "rescaling",
+      "parameters": {
+        "technique": "UNIT_NORMALIZATION",
+        "normType": "L1"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "rescalerModel": {
+      "comment": "Calls the myRescaler estimator to fit a model to the myData dataset.",
+      "trainData": "myData",
+      "estimator": "myRescaler",
+      "action": "fit"
+    },
+    "rescaledData": {
+      "comment": "Uses the rescalerModel (created above) to rescale (transform) the myData dataset. The evaluation, transformation, returns the rescaled dataset in the results. For a complete list of rescaler evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myData",
+      "fittedModel": "rescalerModel",
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/DataSources/ODBCDatabase.json

@@ -0,0 +1,50 @@
+{
+  "modelName": "ODBCDatabase",
+  "modelDescription": "Transformation: Rescaling:  This RASON model example rescales the data contained within an ODBC database. (This example is for illustration purposes only.) Note that RASON now allows Data Connections. In previous versions of RASON, models that accessed external databases required actual credentials to be passed, such as database URLs, port numbers, usernames and passwords, in the text of the RASON model, in a datasource declaration, as shown below. RASON now offers an alternative to tackle this security risk by substituting 'connection': 'Driver={SQL Server} ...' with three options: a file containing the contents of 'connection', a named Data Connection or a URL pointing to Microsoft Common Data Service. Click Help - Rason Subscriptions -- Data Connections for more information.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "odbcSrc": {
+      "comment": "Binds the data within an ODBC database to the odbcSrc datasource. The file name is passed to the 'connection' property. The 'selection' property selects the data to be imported.  This data is being imported, so 'direction' is set to 'import'. Note that RASON now allows Data Connections. In previous versions of RASON, models that accessed external databases required actual credentials to be passed, such as database URLs, port numbers, usernames and passwords, in the text of the RASON model, in a datasource declaration, as shown below. RASON now offers an alternative to tackle this security risk by substituting 'connection': '<connection_string>' with three options: a file containing the contents of 'connection', a named Data Connection or a URL pointing to Microsoft Common Data Service. Click Help - Rason Subscriptions -- Data Connections for more information.",
+      "type": "odbc",
+      "connection": "<connection_string>",
+      "selection": "<selection>",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myData": {
+      "comment": "Binds the odbcSrc datasource to the myData dataset.",
+      "binding": "odbcSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "myRescaler": {
+      "comment": "Creates a new rescaling estimator, myRescaler, which will be called in 'actions' (below) to rescale the dataset within the ODBC database. Two options are set.  For a complete list of options and setting for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "transformation",
+      "algorithm": "rescaling",
+      "parameters": {
+        "technique": "UNIT_NORMALIZATION",
+        "normType": "L1"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "rescalerModel": {
+      "comment": "Calls the myRescaler estimator to fit a model to the myData dataset.",
+      "trainData": "myData",
+      "estimator": "myRescaler",
+      "action": "fit"
+    },
+    "rescaledData": {
+      "comment": "Uses the rescalerModel (created above) to rescale (transform) the myData dataset. The evaluation, transformation, returns the rescaled dataset in the results. For a complete list of rescaler evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myData",
+      "fittedModel": "rescalerModel",
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/FeatureSelection/LinearWrapping.json

@@ -0,0 +1,54 @@
+{
+  "modelName": "LinearWrapping",
+  "modelDescription": "Feature Selection Linear Wrapping: This RASON model example illustrates how to import data from an outside datasource, fit a model to the Feature Selection estimator, then use the fitted model to transform the dataset using feature selection linear wrapping.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Binds the data within hald-small.txt to the myTrainSrc datasource. This data is being imported, so 'direction' is set to 'import'.",
+      "type": "csv",
+      "connection": "hald-small.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the 'datasets' section to bind to an entry in the 'datasources' section",
+    "myTrainData": {
+      "comment": "Binds the myTrainSrc datasource to the myTrainData dataset.",
+      "binding": "myTrainSrc",
+      "targetCol": "Y"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "linearFSEstimator": {
+      "comment": "Creates a new rescaling estimator, linearFSEstimator, which will be called in 'actions' (below) to transform the dataset using Feature Selection Linear Wrapping. Exhaustive Search where searches of all combinations of variables are performed to observe which combination has the best fit. For a complete list of options and settings for the rescaling feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "featureSelection",
+      "algorithm": "linearWrapping",
+      "parameters": {
+        "fitIntercept": true,
+        "method": "EXHAUSTIVE_SEARCH"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "linearFSModel": {
+      "comment": "Calls the linearFSEstimator estimator to fit a model to the myTrainData dataset. Two evaluations are requested in the results: bestSubsets, which returns the best subsets as determined by various error values and the probability, and bestSubsetsDetails, which returns the number of predictors, the residual sum of squares (RSS), Mallows CP, and the Probability for each subset. See the RASON Data Science Model Components chapter within the RASON Reference Guide for a list of all options related to the linear wrapping feature.",
+      "estimator": "linearFSEstimator",
+      "data": "myTrainData",
+      "action": "fit",
+      "evaluations": [ "bestSubsets", "bestSubsetsDetails" ]
+    },
+    "reducedTrainData": {
+      "comment": "Uses the linearFSModel (created above) to transform the myTrainData dataset. The evaluation, transformation, returns the transformed dataset in the results. For a complete list of linear wrapping evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myTrainData",
+      "fittedModel": "linearFSModel",
+      "parameters": {
+        "numTopFeatures": 2
+      },
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/FeatureSelection/LogisticWrapping.json

@@ -0,0 +1,57 @@
+{
+  "modelName": "LogisticWrapping",
+  "modelDescription": "Feature Selection Logistic Wrapping: This RASON model example illustrates how to import data from an outside datasource, fit a model to the Feature Selection estimator, then use the fitted model to transform the dataset using feature selection logistic wrapping.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Binds the data within hald-small-binary.txt to the myTrainSrc datasource. This data is being imported, so 'direction' is set to 'import'.",
+      "type": "csv",
+      "connection": "hald-small-binary.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the 'datasets' section to bind to an entry in the 'datasources' section",
+    "myTrainData": {
+      "comment": "Binds the myTrainSrc datasource to the myTrainData dataset. The variable Y is selected as the output variable using 'targetCol': 'Y'.",
+      "binding": "myTrainSrc",
+      "targetCol": "Y"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "logisticFSEstimator": {
+      "comment": "Creates a new feature selection estimator, logisticFSEstimator, which will be called in 'actions' (below) to transform the dataset using Feature Selection Logistic Wrapping.  Three options are set:  fitIntercept, maxIterations and method.  The exhaustive Search method searches of all combinations of variables are performed to observe which combination has the best fit. For a complete list of options and settings for the this feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "featureSelection",
+      "algorithm": "logisticWrapping",
+      "parameters": {
+        "fitIntercept": true,
+        "maxIterations": 10,
+        "method": "EXHAUSTIVE_SEARCH"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "logisticFSModel": {
+      "comment": "Calls the logisticFSEstimator estimator to fit a model to the myTrainData dataset. Two evaluations are requested in the results: bestSubsets, which returns the best subsets as determined by various error values and the probability, and bestSubsetsDetails, which returns the number of predictors, the residual sum of squares (RSS), Mallows CP, and the Probability for each subset. See the RASON Data Science Model Components chapter within the RASON Reference Guide for a list of all options related to the logistic wrapping feature.",
+      "data": "myTrainData",
+      "estimator": "logisticFSEstimator",
+      "action": "fit",
+      "evaluations": [ "bestSubsets", "bestSubsetsDetails" ]
+    },
+    "reducedTrainData": {
+      "comment": "Uses the logisticFSModel (created above) to transform the myTrainData dataset. The evaluation, transformation, returns the transformed dataset in the results. For a complete list of logistic wrapping parameters and evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myTrainData",
+      "fittedModel": "logisticFSModel",
+      "parameters": {
+        "numTopFeatures": 2,
+        "successClass": "1",
+        "successProbability": 0.6
+      },
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
+}

package/examples/datamining/FeatureSelection/Univariate.json

@@ -0,0 +1,79 @@
+{
+  "modelName": "Univariate",
+  "modelDescription": "Feature Selection Univariate: This RASON model example illustrates how to import data from an outside datasource, fit a model to the Feature Selection estimator, then use the fitted model to transform the dataset using feature selection univariate.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Binds the data within hald-small-binary-train.txt to the myTrainSrc datasource. This data is being imported, so 'direction' is set to 'import'. This dataset represents the training partition",
+      "type": "csv",
+      "connection": "hald-small-binary-train.txt",
+      "direction": "import"
+    },
+    "myValidSrc": {
+      "comment": "Binds the data within hald-small-binary-valid.txt to the myValidSrc datasource. This data is being imported, so 'direction' is set to 'import'. This dataset represents the validation partition",
+      "type": "csv",
+      "connection": "hald-small-binary-valid.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the 'datasets' section to bind to an entry in the 'datasources' section",
+    "myTrainData": {
+      "comment": "Binds the myTrainSrc datasource to the myTrainData dataset. The variable Y is selected as the output variable using 'targetCol': 'Y'.",
+      "binding": "myTrainSrc",
+      "targetCol": "Y"
+    },
+    "myValidData": {
+      "comment": "Binds the myValidSrc datasource to the myValidData dataset. The variable Y is selected as the output variable using 'targetCol': 'Y'.",
+      "binding": "myValidSrc",
+      "targetCol": "Y"
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "univariateFSEstimator": {
+      "comment": "Creates a new feature selection estimator, UnivariateFSEstimator, which will be called in 'actions' (below) to transform the dataset using Feature Selection Univariate. Four options are set:  metric:CHI2 (computes the CHI^2 statistic), categoricalTarget (denotes that the output variable is categorical), binningTypeFeatures (transforms continuous input variables into categorical variables) and numBinsFeatures (sets the maximum number of bins for the input variables)s. For a complete list of options and settings for the this feature, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "type": "featureSelection",
+      "algorithm": "univariate",
+      "parameters": {
+        "metric": "CHI2",
+        "categoricalTarget": true,
+        "binningTypeFeatures": "EQUAL_INTERVAL",
+        "numBinsFeatures": 5
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "ufsModel": {
+      "comment": "Calls the univariateFSEstimator estimator to fit a model to the myTrainData dataset. One evaluation is requested in the results, statistics. See the RASON Data Science Model Components chapter within the RASON Reference Guide for a list of all options related to the univariate feature.",
+      "data": "myTrainData",
+      "estimator": "univariateFSEstimator",
+      "action": "fit",
+      "evaluations": [ "statistics" ]
+    },
+    "reducedTrainData": {
+      "comment": "Uses the ufsModel (created above) to transform the myTrainData dataset, the training partition. Two parameters are set: numTopFeatures (used to determine the variables included in the Top Features Table and Feature Importance Plot) and usePvalueForSelection (if 'True' then variables will be ranked from smallest to largest using the P-value of the measure of the selected statistic (in this case the ChiSquared statistic)). Two evaluations are set: transformation (which returns the transformed model) and topFeaturesInfo (which returns a table containing the top number of features). For a complete list of univariate parameters and evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myTrainData",
+      "fittedModel": "ufsModel",
+      "parameters": {
+        "numTopFeatures": 2,
+        "usePvalueForSelection": true
+      },
+      "action": "transform",
+      "evaluations": [ "transformation", "topFeaturesInfo" ]
+    },
+    "reducedValidData": {
+      "comment": "Uses the ufsModel (created above) to transform the myValidData dataset, the validation partition. Two parameters are set: numTopFeatures and usePvalueForSelection, see above for explanations. Two evaluations are set: transformation and topFeaturesInfo, see above for explanations. For a complete list of univariate parameters and evaluations, see the RASON Data Science Model Components chapter within the RASON Reference Guide (downloadable from the Help tab).",
+      "data": "myValidData",
+      "fittedModel": "ufsModel",
+      "parameters": {
+        "numTopFeatures": 2,
+        "usePvalueForSelection": false
+      },
+      "action": "transform",
+      "evaluations": [ "transformation", "topFeaturesInfo" ]
+    }
+  }
+}

package/examples/datamining/Regression/DecisionTree.json

@@ -0,0 +1,82 @@
+{
+  "modelName": "DecisionTreeRegression",
+  "modelDescription": "Regression Decision Trees: This RASON model example generates a fitted model and POSTs the model to the RASON server. This example uses two outside data sources, hald-small-train.txt and hald-small-valid.txt. Both may be downloaded by clicking the RASON Examples Download icon (download cloud icon). To solve this model, you must first POST the model to the RASON Server by clicking the POST icon (upload cloud icon on the left). Afterwards click Choose Files (on the Properties pane on the right), browse to the location of the downloaded examples, and select both hald-small-train.txt and hald-small-valid.txt.  Then click the down arrow next to the Play icon and click Solve. For more information on POSTing and solving example models, click Help - Defining Your Data Science Model.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Binds the dataset contained within hald-small-train.txt to the myTrainSrc datasource. This dataset represents the training partition.",
+      "type": "csv",
+      "connection": "hald-small-train.txt",
+      "direction": "import"
+    },
+    "myValidSrc": {
+      "comment": "Binds the dataset contained within hald-small-valid.txt to the myValidSrc datasource. This dataset represents the validation partition.",
+      "type": "csv",
+      "connection": "hald-small-valid.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Datasets are bound to an entry in the 'datasources' section",
+    "myTrainData": {
+      "comment": "Binds the myTrainSrc datasource to the myTrainData dataset. Note that the target variable is set to the Y variable using the 'targetCol' property.",
+      "binding": "myTrainSrc",
+      "targetCol": "Y"
+    },
+    "myValidData": {
+      "comment": "Binds the myValidSrc datasource to the myValidData dataset. Note that the target variable is set to the Y variable using the 'targetCol' property.",
+      "binding": "myValidSrc",
+      "targetCol": "Y"
+    }
+  },
+  "preProcessor": {
+    "comment": "This (optional) section may be used for preliminarily data preparation or to compute values of some properties, which are passed later, at parse-time, to the RASON Data Science engine.",
+    "numLeafRecords": {
+      "comment": "Computes the value for numLeafRecords as the Maximum of 1 and 1.3 (13 rows/10); used in the estimator below as the setting for minNumRecordsInLeaves.",
+      "formula": "INT(MAX(1, ROWS(myTrainData) / 10))"
+    }
+  },
+  "estimator": {
+    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
+    "treeEstimator": {
+      "comment": "Defines the treeEstimator as a regression decision tree estimator; various options are set. For a complete list of all algorithm options, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "regression",
+      "algorithm": "decisionTree",
+      "parameters": {
+        "minNumRecordsInLeaves": "numLeafRecords",
+        "maxNumNodes": 5,
+        "maxNumLevels": 3,
+        "maxNumSplits": 10,
+        "categoricalFeaturesNames": [ "X1" ],
+        "prunedTreeType": "BEST_PRUNED"
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define actions, evaluations, and data to be used by the estimator created above.",
+    "treeModel": {
+      "comment": "Fits treeEstimator to myTrainData and myValidData, then POSTS the fitted model in PMML format to the RASON server using export:pmml, which may be used later for scoring new data. Then scores both datasets using the fitted model. For a complete list of all available evaluations, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.",
+      "trainData": "myTrainData",
+      "validData": "myValidData",
+      "estimator": "treeEstimator",
+      "export": "pmml",
+      "action": "fit",
+      "evaluations": [ "trainingLog", "pruningLog", "featureImportance", "treeRules" ]
+    },
+    "trainScore": {
+      "comment": "Uses the fitted model treeModel to score the training dataset, myTrainData (the training partition) using the 'action':'predict' parameter. Various evaluations are requested in the results including the predicted values, using the evaluations: metrics. For a complete list of all available evaluations, see the Evaluations: Regression - Common Parameters table in the RASON Reference Guide. (Click the Help tab to download.) ",
+      "data": "myTrainData",
+      "fittedModel": "treeModel",
+      "action": "predict",
+      "evaluations": [ "prediction", "residuals", "newIntervals", "sse", "ss", "sst", "mse", "rmse", "mad", "r2", "aoc" ]
+    },
+    "validScore": {
+      "comment": "Uses the fitted model treeModel to score the validation dataset, myValidData, (the validation partition) using the 'action':'predict' parameter. Various evaluations are requested in the results including the predicted values (using 'prediction') and multiple statistics (using 'metrics'). Note that 'metrics' evaluation returns sse, ss, sst, mse, rmse, mad, r2 and aoc. For a complete list of all available evaluations, see the Evaluations: Regression - Common Parameters table in the RASON Reference Guide. (Click the Help tab to download.) ",
+      "data": "myValidData",
+      "fittedModel": "treeModel",
+      "action": "predict",
+      "evaluations": [ "prediction", "metrics" ]
+    }
+  }
+}

package/examples/datamining/Regression/Ensembles/Bagging.json

@@ -0,0 +1,63 @@
+{
+  "modelName": "BaggingRegression",
+  "modelDescription": "Bagging Regression Example: This RASON model example generates a fitted model and POSTs the model to the RASON server. Then uses the fitted model to score the training partition. This example uses one outside data source, hald-small.txt,  which may be downloaded by clicking the RASON Examples Download icon (download cloud icon). To solve this model, you must first POST the model to the RASON Server by clicking the POST icon (upload cloud icon on the left). Afterwards click Choose Files (on the Properties pane on the right), browse to the location of the downloaded examples, and select hald-small.txt. Then click the down arrow next to the Play icon and click Solve. For more information on POSTing and solving example models, click Help - Defining Your Data Science Model.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Define datasources to use with this model, in the datasources section. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Binds the dataset contained within hald-small.txt to the myTrainSrc datasource.",
+      "type": "csv",
+      "connection": "hald-small.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Use the datasets section to bind to an entry in the 'datasources' section",
+    "myTrainData": {
+      "comment": "Binds the myTrainSrc datasource to the myTrainData dataset. Note that the target variable is set to the Y variable using the 'targetCol' property.",
+      "binding": "myTrainSrc",
+      "targetCol": "Y"
+    }
+  },
+  "weakLearner": {
+    "comment": "This section is only required when a bagging or boosting estimator is specified in 'estimator', and is used to define the weak learner used in the ensemble method.",
+    "treeWeakLearner": {
+      "comment": "Creates the weaklearner, treeWeakLearner, which selects decision trees as the weak learner and sets one parameter, minNumRecordsInLeaves. This weak learner will be used in the bagging estimator below. See the Rason Data Science Model Components chapter in the RASON Reference Guide, downloadable from the Help tab.",
+      "type": "regression",
+      "algorithm": "decisionTree",
+      "parameters": {
+        "minNumRecordsInLeaves": 2
+      }
+    }
+  },
+  "estimator": {
+    "comment": "Define an estimator, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "baggingEstimator": {
+      "comment": "Defines the baggingEstimator as a bagging ensemble method estimator which uses the weakLearner above, treeWeakLearner; various options are set. For a complete list of all algorithm options, see the RASON Data Science Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "regression",
+      "algorithm": "bagging",
+      "parameters": {
+        "numWeakLearners": 2,
+        "bootstrapSeed": 10
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define the actions, evaluations, and data to be used by the estimator defined above.",
+    "baggingModel": {
+      "comment": "This action fits a model using the myTrainData dataset using the regression bagging ensemble method estimator created above, baggingEstimator. The fitted model is exported to a JSON file for later use.  Two evaluations are requested in the result, weakLearnerModels (which returns the model for all weak learners) and numWeakLearners (which returns the number of weak learners). For a list of all available evaluations for Regression - Common Parameters, see the RASON Reference Guide downloadable from the Help tab.",
+      "data": "myTrainData",
+      "estimator": "baggingEstimator",
+      "export": "json",
+      "action": "fit",
+      "evaluations": [ "weakLearnerModels", "numWeakLearners" ]
+    },
+    "trainScore": {
+      "comment": "This action uses the fitted model, baggingModel, to score the myTrainData dataset (the training partition) using the 'action':'predict' parameter. Various evaluations are requested in the results such as the predicted values and multiple statistics using the 'metrics'' evaluation (which returns sse, ss, sst, mse, rmse, mad, aoc and r2). See Evaluations: Regression - Common Parameters for a list of all evaluations supported. ",
+      "data": "myTrainData",
+      "fittedModel": "baggingModel",
+      "action": "predict",
+      "evaluations": [ "prediction", "metrics" ]
+    }
+  }
+}