@frontlinesystems/rason-mcp-server 2026.5.1 → 2026.5.2

package/examples/datamining/Simulation/pmml-risk-scoring.json

@@ -1,63 +1,63 @@
-{
-  "modelDescription": "Regression: Linear RASON model scoring from pmml and risk analysis. This example model first imports two datasources, a training partition and a file containing new data.  Then each datasource is bound to a dataset.  Afterwards a previously posted fitted model, linear-fitted, is used to score both datasets.  The fitted model must first be POSTed to the RASON Server BEFORE this model can be POSTed. Download the fitted model by clicking the download icon above RASON Examples (on the ribbon). Then click the Open File icon (far left), browse to the downloaded files, and open the file, linear-fitted.xml. POST the fitted model by clicking the POST icon, cloud icon on the left of the ribbon.",
-  "comment": "Fitted model, linear-fitted, must first be POSTed to RASON Server. (Click Download RASON Example data to download file.)",
-  "modelName": "pmmlRiskScorer",
-  "modelType": "datamining",
-  "datasources": {
-    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
-    "trainDataSource": {
-      "comment": "Binds the bh-scale-reg.txt data set to the trainDataSource datasource. This represents the training partition.",
-      "type": "csv",
-      "connection": "bh-scale-reg.txt"
-    },
-    "newDataSource": {
-      "comment": "Binds the bh-scale-reg-score.txt data set to the newDataSource datasource. This represents the new data to be scored.",
-      "type": "csv",
-      "connection": "bh-scale-reg-score.txt"
-    }
-  },
-  "datasets": {
-    "comment": "Binds each datasource to a dataset.",
-    "trainData": {
-      "comment": "Binds the data source trainDataSource (bh-scale-reg.txt) to the trainData dataset.",
-      "binding": "trainDataSource",
-      "targetCol": "MEDV"
-    },
-    "newData": {
-      "comment": "Binds the data source newDataSource (bh-scale-reg-score.txt) to the newData dataset.",
-      "binding": "newDataSource"
-    }
-  },
-  "fittedModel": {
-    "comment": "Binds an imported or POSTed fitted model to a fittedModel. This step is not optional.",
-    "mlrModel": {
-      "comment": "Binds the linear-fitted fitted model, already POSTed to the RASON Server, to mlrModel. Recall that this fitted model must first be downloaded (by clicking the Download RASON Examples icon) and then POSTed to the RASON model (by clicking the POST icon, cloud icon on the top left).",
-      "modelName": "linear-fitted",
-      "simulation": {
-        "metalogAuto": true,
-        "useMinMaxAsBounds": true,
-        "correlationType": "RANK",
-        "sampleSize": 506,
-        "randomSeed": 12345,
-        "expression": "IF(CRIM<10, MEDV, 2*MEDV)"
-      }
-    }
-  },
-  "actions": {
-    "comment": "define the actions, evaluations, and data to be used by the estimator defined above.",
-    "trainPrediction": {
-      "comment": "Scores the trainData dataset (bh-scale-reg.txt) using the fitted model, mlrModel. For a complete list of all available evaluations and parameters, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.) ",
-      "data": "trainData",
-      "fittedModel": "mlrModel",
-      "action": "predict",
-      "evaluations": [ "prediction", "simulationLog", "simulationData", "simulationPrediction", "simulationExpression", "trainingExpression", "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ]
-    },
-    "newPrediction": {
-      "comment": "Scores the myData dataset (bh-scale-reg-score.txt) using the fitted model, mlrModel. For a complete list of all available evaluations and parameters, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "data": "newData",
-      "fittedModel": "mlrModel",
-      "action": "predict",
-      "evaluations": [ "prediction", "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ]
-    }
-  }
+{
+  "modelDescription": "Regression: Linear RASON model scoring from pmml and risk analysis. This example model first imports two datasources, a training partition and a file containing new data.  Then each datasource is bound to a dataset.  Afterwards a previously posted fitted model, linear-fitted, is used to score both datasets.  The fitted model must first be POSTed to the RASON Server BEFORE this model can be POSTed. Download the fitted model by clicking the download icon above RASON Examples (on the ribbon). Then click the Open File icon (far left), browse to the downloaded files, and open the file, linear-fitted.xml. POST the fitted model by clicking the POST icon, cloud icon on the left of the ribbon.",
+  "comment": "Fitted model, linear-fitted, must first be POSTed to RASON Server. (Click Download RASON Example data to download file.)",
+  "modelName": "pmmlRiskScorer",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
+    "trainDataSource": {
+      "comment": "Binds the bh-scale-reg.txt data set to the trainDataSource datasource. This represents the training partition.",
+      "type": "csv",
+      "connection": "bh-scale-reg.txt"
+    },
+    "newDataSource": {
+      "comment": "Binds the bh-scale-reg-score.txt data set to the newDataSource datasource. This represents the new data to be scored.",
+      "type": "csv",
+      "connection": "bh-scale-reg-score.txt"
+    }
+  },
+  "datasets": {
+    "comment": "Binds each datasource to a dataset.",
+    "trainData": {
+      "comment": "Binds the data source trainDataSource (bh-scale-reg.txt) to the trainData dataset.",
+      "binding": "trainDataSource",
+      "targetCol": "MEDV"
+    },
+    "newData": {
+      "comment": "Binds the data source newDataSource (bh-scale-reg-score.txt) to the newData dataset.",
+      "binding": "newDataSource"
+    }
+  },
+  "fittedModel": {
+    "comment": "Binds an imported or POSTed fitted model to a fittedModel. This step is not optional.",
+    "mlrModel": {
+      "comment": "Binds the linear-fitted fitted model, already POSTed to the RASON Server, to mlrModel. Recall that this fitted model must first be downloaded (by clicking the Download RASON Examples icon) and then POSTed to the RASON model (by clicking the POST icon, cloud icon on the top left).",
+      "modelName": "linear-fitted",
+      "simulation": {
+        "metalogAuto": true,
+        "useMinMaxAsBounds": true,
+        "correlationType": "RANK",
+        "sampleSize": 506,
+        "randomSeed": 12345,
+        "expression": "IF(CRIM<10, MEDV, 2*MEDV)"
+      }
+    }
+  },
+  "actions": {
+    "comment": "define the actions, evaluations, and data to be used by the estimator defined above.",
+    "trainPrediction": {
+      "comment": "Scores the trainData dataset (bh-scale-reg.txt) using the fitted model, mlrModel. For a complete list of all available evaluations and parameters, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.) ",
+      "data": "trainData",
+      "fittedModel": "mlrModel",
+      "action": "predict",
+      "evaluations": [ "prediction", "simulationLog", "simulationData", "simulationPrediction", "simulationExpression", "trainingExpression", "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ]
+    },
+    "newPrediction": {
+      "comment": "Scores the myData dataset (bh-scale-reg-score.txt) using the fitted model, mlrModel. For a complete list of all available evaluations and parameters, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "data": "newData",
+      "fittedModel": "mlrModel",
+      "action": "predict",
+      "evaluations": [ "prediction", "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ]
+    }
+  }
 }

package/examples/datamining/Summarizer/Summarization.json

@@ -1,55 +1,55 @@
-{
-  "modelName": "summarization",
-  "modelDescription": "This RASON model example calls summarization to calculate statistics, percentiles and six sigma metrics for the dataset.",
-  "modelType": "datamining",
-  "datasources": {
-    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
-    "mySrc": {
-      "comment": "Binds the hald-small.txt data set to the mySrc datasource.",
-      "type": "csv",
-      "connection": "hald-small.txt"
-    }
-  },
-  "datasets": {
-    "comment": "Binds each datasource to a dataset.",
-    "myData": {
-      "comment": "Binds the data source mySrc (hald-small.txt) to the myData dataset.",
-      "binding": "mySrc"
-    }
-  },
-  "transformer": {
-    "comment": "Defines a transformer, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
-    "summarizer": {
-      "comment": "Defines the summarizer as a summarization transformer. For a complete list of all supported options for summarization, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "type": "transformation",
-      "algorithm": "summarization",
-      "parameters": {
-        "numBins": [
-          [ "X2", 4 ],
-          [ "X4", 5 ]
-        ]
-      }
-    }
-  },
-  "actions": {
-    "comment": "Define actions, evaluations, and data to be used by the estimator created above.",
-    "mySummaries": {
-      "comment": "Summarizes the myData dataset (hald-small.txt) using the summarization transformer. Various evaluations are requested such as summary information, six sigma metrics, percentiles, etc. For a complete list of all available parameters and evaluations for summarization, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "data": "myData",
-      "action": "transform",
-      "evaluations": [ "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ],
-      "parameters": {
-        "semiVariancePower": 2,
-        "semiDeviationPower": 2,
-        "varPercentile": 0.95,
-        "cvarPercentile": 0.95,
-        "meanConfidencePercentile": 0.95,
-        "sixSigmaPercentileLB": 0.05,
-        "sixSigmaPercentileUB": 0.95,
-        "sixSigmaShift": 0.0,
-        "sixSigmaNumStdDev": 6.0,
-        "sixSigmaTarget": 0.0
-      }
-    }
-  }
+{
+  "modelName": "summarization",
+  "modelDescription": "This RASON model example calls summarization to calculate statistics, percentiles and six sigma metrics for the dataset.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
+    "mySrc": {
+      "comment": "Binds the hald-small.txt data set to the mySrc datasource.",
+      "type": "csv",
+      "connection": "hald-small.txt"
+    }
+  },
+  "datasets": {
+    "comment": "Binds each datasource to a dataset.",
+    "myData": {
+      "comment": "Binds the data source mySrc (hald-small.txt) to the myData dataset.",
+      "binding": "mySrc"
+    }
+  },
+  "transformer": {
+    "comment": "Defines a transformer, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "summarizer": {
+      "comment": "Defines the summarizer as a summarization transformer. For a complete list of all supported options for summarization, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "transformation",
+      "algorithm": "summarization",
+      "parameters": {
+        "numBins": [
+          [ "X2", 4 ],
+          [ "X4", 5 ]
+        ]
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define actions, evaluations, and data to be used by the estimator created above.",
+    "mySummaries": {
+      "comment": "Summarizes the myData dataset (hald-small.txt) using the summarization transformer. Various evaluations are requested such as summary information, six sigma metrics, percentiles, etc. For a complete list of all available parameters and evaluations for summarization, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "data": "myData",
+      "action": "transform",
+      "evaluations": [ "summary", "advancedSummary", "sixSigma", "percentiles", "histogram" ],
+      "parameters": {
+        "semiVariancePower": 2,
+        "semiDeviationPower": 2,
+        "varPercentile": 0.95,
+        "cvarPercentile": 0.95,
+        "meanConfidencePercentile": 0.95,
+        "sixSigmaPercentileLB": 0.05,
+        "sixSigmaPercentileUB": 0.95,
+        "sixSigmaShift": 0.0,
+        "sixSigmaNumStdDev": 6.0,
+        "sixSigmaTarget": 0.0
+      }
+    }
+  }
 }

package/examples/datamining/TextMining/LatentSemanticAnalysis.json

@@ -1,52 +1,52 @@
-{
-  "modelName": "LatentSemanticAnalysis",
-  "modelDescription": "RASON Example using Text Miner - Latent Semantic Anlaysis is a technique in natural language processing between a set of documents and their contained terms by generating a set of concepts related to the documents and terms.",
-  "modelType": "datamining",
-  "datasources": {
-    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
-    "myTrainSrc": {
-      "comment": "Imports tdmRomeo.txt data source. This file contains a term-document matrix. This matrix is an evaluation, or output, from the Text Miner feature. See the two TFIDF (Text Miner) examples for help on generating this output. ",
-      "type": "csv",
-      "connection": "tdmRomeo.txt",
-      "direction": "import"
-    }
-  },
-  "datasets": {
-    "comment": "Binds each datasource to a dataset.",
-    "trainTermDocMatrix": {
-      "comment": "Binds the myTrainSrc data source (tdmRomeo.txt) to trainTermDocMatrix data set",
-      "binding": "myTrainSrc"
-    }
-  },
-  "estimator": {
-    "comment": "Defines a transformer, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
-    "lsaEstimator": {
-      "comment": "Defines the lsaEstimator as a text mining, latent semantic analysis (LSA) regression estimator. For a complete list of all supported algorithm options for LSA, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "type": "textMining",
-      "algorithm": "latentSemanticAnalysis",
-      "parameters": {
-        "maxNumConcepts": 4,
-        "computeTermImportance": true,
-        "computeConceptImportance": true
-      }
-    }
-  },
-  "actions": {
-    "comment": "Define actions, evaluations, and data to be used by the estimator created above.",
-    "lsaModel": {
-      "comment": "Fits lsaEstimator to trainTermDocMatrix (tdmRomeo.txt). The fitted model, given the same name as this example, LatentSemanticAnalysis, is automatically posted to the RASON Server. This fitted model may be called The export property exports the fitted model to a JSON file.  Three evaluations are requested: vocabulary, termImportance and conceptImportance. Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. Termimportance returns the most frequently appearing terms along with their Importance factor. ConceptImportance returns the Concept Importance table which lists each concept, its singular value, the cumulative singular value and the % singular value explained. For more information on the evaluations supported by LSA, click the Help tab to download te RASON Reference guide.",
-      "trainData": "trainTermDocMatrix",
-      "estimator": "lsaEstimator",
-      "export": "json",
-      "action": "fit",
-      "evaluations": [ "vocabulary", "termImportance", "conceptImportance" ]
-    },
-    "tfRomeo": {
-      "comment": "Uses the fitted model lsaModel to score trainTermDocMatrix (tdmRomeo.txt). Two evaluations are requested in the results:  transformation, which returns the transformed dataset, and termConceptMatrix, which lists the most important concepts vs most frequently appearing terms.",
-      "data": "trainTermDocMatrix",
-      "fittedModel": "lsaModel",
-      "action": "transform",
-      "evaluations": [ "transformation", "termConceptMatrix" ]
-    }
-  }
+{
+  "modelName": "LatentSemanticAnalysis",
+  "modelDescription": "RASON Example using Text Miner - Latent Semantic Anlaysis is a technique in natural language processing between a set of documents and their contained terms by generating a set of concepts related to the documents and terms.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Imports tdmRomeo.txt data source. This file contains a term-document matrix. This matrix is an evaluation, or output, from the Text Miner feature. See the two TFIDF (Text Miner) examples for help on generating this output. ",
+      "type": "csv",
+      "connection": "tdmRomeo.txt",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Binds each datasource to a dataset.",
+    "trainTermDocMatrix": {
+      "comment": "Binds the myTrainSrc data source (tdmRomeo.txt) to trainTermDocMatrix data set",
+      "binding": "myTrainSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Defines a transformer, including the type, algorithm and parameters. Only 1 estimator/transformer may appear in a RASON model.",
+    "lsaEstimator": {
+      "comment": "Defines the lsaEstimator as a text mining, latent semantic analysis (LSA) regression estimator. For a complete list of all supported algorithm options for LSA, see the RASON Data Science Model Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "textMining",
+      "algorithm": "latentSemanticAnalysis",
+      "parameters": {
+        "maxNumConcepts": 4,
+        "computeTermImportance": true,
+        "computeConceptImportance": true
+      }
+    }
+  },
+  "actions": {
+    "comment": "Define actions, evaluations, and data to be used by the estimator created above.",
+    "lsaModel": {
+      "comment": "Fits lsaEstimator to trainTermDocMatrix (tdmRomeo.txt). The fitted model, given the same name as this example, LatentSemanticAnalysis, is automatically posted to the RASON Server. This fitted model may be called The export property exports the fitted model to a JSON file.  Three evaluations are requested: vocabulary, termImportance and conceptImportance. Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. Termimportance returns the most frequently appearing terms along with their Importance factor. ConceptImportance returns the Concept Importance table which lists each concept, its singular value, the cumulative singular value and the % singular value explained. For more information on the evaluations supported by LSA, click the Help tab to download te RASON Reference guide.",
+      "trainData": "trainTermDocMatrix",
+      "estimator": "lsaEstimator",
+      "export": "json",
+      "action": "fit",
+      "evaluations": [ "vocabulary", "termImportance", "conceptImportance" ]
+    },
+    "tfRomeo": {
+      "comment": "Uses the fitted model lsaModel to score trainTermDocMatrix (tdmRomeo.txt). Two evaluations are requested in the results:  transformation, which returns the transformed dataset, and termConceptMatrix, which lists the most important concepts vs most frequently appearing terms.",
+      "data": "trainTermDocMatrix",
+      "fittedModel": "lsaModel",
+      "action": "transform",
+      "evaluations": [ "transformation", "termConceptMatrix" ]
+    }
+  }
 }

package/examples/datamining/TextMining/TfIdf-FileData.json

@@ -1,66 +1,66 @@
-{
-  "modelName": "Tfldf-FileData",
-  "modelDescription": "Text Mining RASON example - TF-IDF: TF-IDF stands for Term Frequency Inverse Document Frequency of records. It can be defined as the calculation of how relevant a word in a series or corpus is to a text.",
-  "modelType": "datamining",
-  "datasources": {
-    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
-    "myTrainSrc": {
-      "comment": "Imports tm.txt as the myTrainSrc datasource.  This file contains the sample text that will be mined. Note that content is set to corpus. This property setting is used to indicate to Text Miner that a text corpus is being imported.",
-      "type": "csv",
-      "connection": "tm.txt",
-      "content": "corpus",
-      "direction": "import"
-    }
-  },
-  "datasets": {
-    "comment": "Binds myTrainSrc datasource (tm.txt) to trainCorpus dataset.",
-    "trainCorpus": {
-      "comment": "Binds myTrainSrc datasource (tm.txt) to trainCorpus dataset.",
-      "binding": "myTrainSrc"
-    }
-  },
-  "estimator": {
-    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
-    "tfidfEstimator": {
-      "comment": "Defines the tfidfEstimator as a tfIdf estimator; various options are set. For a complete list of all algorithm options, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "type": "textMining",
-      "algorithm": "tfIdf",
-      "parameters": {
-        "maxVocabulary": 5,
-        "maxTermLength": 10,
-        "minDocumentFrequency": 5,
-        "maxDocumentFrequency": 95,
-        "preprocessing": [ "REMOVE_STOPWORDS", "NORMALIZE_CASE", "STEM", "NORMALIZE_URL", "NORMALIZE_EMAIL", "NORMALIZE_NUMBER", "NORMALIZE_MONEY", "REMOVE_HTML_TAGS" ],
-        "synonyms": [
-          [ "rootTerm1", "synonym1", "synonym2" ]
-        ],
-        "phraseReplacement": [
-          [ "phrase1", "phraseReplacement" ]
-        ]
-      }
-    }
-  },
-  "actions": {
-    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
-    "tfidfModel": {
-      "comment": "Fits the tfidfEstimator to trainCorpus, POSTs the fitted model to the RASON Server and also exports the fitted model to a JSON file using the export property.  Various evaluations are requested.  Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. DetailedVocabulary returns the number of times the terms, included in the Final List of Terms, appears in the document collection and the number of documents that include each term. TermCountInfo Returns the number of total terms, the % Reduction in Terms, the Final number of terms after preprocessing or reduction, and the setting for 'maxVocabulary'. DocInfo returns the # Characters and the # Terms per document.",
-      "trainData": "trainCorpus",
-      "estimator": "tfidfEstimator",
-      "export": "json",
-      "action": "fit",
-      "evaluations": [ "vocabulary", "detailedVocabulary", "termCountInfo", "docInfo" ]
-    },
-    "termDocMatrix": {
-      "comment": "Uses the fitted model tfidfModel to generate the term document matrix, which lists the 200 most frequently appearing terms. For information on all evaluations supported by Text Miner, click the Help tab to download the RASON Reference Guide.",
-      "data": "trainCorpus",
-      "fittedModel": "tfidfModel",
-      "parameters": {
-        "weightingSchemeTerm": "LOGARITHMIC",
-        "weightingSchemeDocument": "INVERSE",
-        "weightingSchemeNormalization": "NONE"
-      },
-      "action": "transform",
-      "evaluations": [ "transformation" ]
-    }
-  }
+{
+  "modelName": "Tfldf-FileData",
+  "modelDescription": "Text Mining RASON example - TF-IDF: TF-IDF stands for Term Frequency Inverse Document Frequency of records. It can be defined as the calculation of how relevant a word in a series or corpus is to a text.",
+  "modelType": "datamining",
+  "datasources": {
+    "comment": "Datasources to use with this model. Typically these bind to external data sources due to data volume.",
+    "myTrainSrc": {
+      "comment": "Imports tm.txt as the myTrainSrc datasource.  This file contains the sample text that will be mined. Note that content is set to corpus. This property setting is used to indicate to Text Miner that a text corpus is being imported.",
+      "type": "csv",
+      "connection": "tm.txt",
+      "content": "corpus",
+      "direction": "import"
+    }
+  },
+  "datasets": {
+    "comment": "Binds myTrainSrc datasource (tm.txt) to trainCorpus dataset.",
+    "trainCorpus": {
+      "comment": "Binds myTrainSrc datasource (tm.txt) to trainCorpus dataset.",
+      "binding": "myTrainSrc"
+    }
+  },
+  "estimator": {
+    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
+    "tfidfEstimator": {
+      "comment": "Defines the tfidfEstimator as a tfIdf estimator; various options are set. For a complete list of all algorithm options, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "textMining",
+      "algorithm": "tfIdf",
+      "parameters": {
+        "maxVocabulary": 5,
+        "maxTermLength": 10,
+        "minDocumentFrequency": 5,
+        "maxDocumentFrequency": 95,
+        "preprocessing": [ "REMOVE_STOPWORDS", "NORMALIZE_CASE", "STEM", "NORMALIZE_URL", "NORMALIZE_EMAIL", "NORMALIZE_NUMBER", "NORMALIZE_MONEY", "REMOVE_HTML_TAGS" ],
+        "synonyms": [
+          [ "rootTerm1", "synonym1", "synonym2" ]
+        ],
+        "phraseReplacement": [
+          [ "phrase1", "phraseReplacement" ]
+        ]
+      }
+    }
+  },
+  "actions": {
+    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
+    "tfidfModel": {
+      "comment": "Fits the tfidfEstimator to trainCorpus, POSTs the fitted model to the RASON Server and also exports the fitted model to a JSON file using the export property.  Various evaluations are requested.  Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. DetailedVocabulary returns the number of times the terms, included in the Final List of Terms, appears in the document collection and the number of documents that include each term. TermCountInfo Returns the number of total terms, the % Reduction in Terms, the Final number of terms after preprocessing or reduction, and the setting for 'maxVocabulary'. DocInfo returns the # Characters and the # Terms per document.",
+      "trainData": "trainCorpus",
+      "estimator": "tfidfEstimator",
+      "export": "json",
+      "action": "fit",
+      "evaluations": [ "vocabulary", "detailedVocabulary", "termCountInfo", "docInfo" ]
+    },
+    "termDocMatrix": {
+      "comment": "Uses the fitted model tfidfModel to generate the term document matrix, which lists the 200 most frequently appearing terms. For information on all evaluations supported by Text Miner, click the Help tab to download the RASON Reference Guide.",
+      "data": "trainCorpus",
+      "fittedModel": "tfidfModel",
+      "parameters": {
+        "weightingSchemeTerm": "LOGARITHMIC",
+        "weightingSchemeDocument": "INVERSE",
+        "weightingSchemeNormalization": "NONE"
+      },
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
 }

package/examples/datamining/TextMining/TfIdf-InlineData.json

@@ -1,56 +1,56 @@
-{
-  "modelName": "Tfldf-InlineData",
-  "modelDescription": "RASON Text Mining - TF-IDF example: TF-IDF stands for Term Frequency Inverse Document Frequency of records. It can be defined as the calculation of how relevant a word in a series or corpus is to a text. See the TFIDF-FileData example (Examples - Data Mining - Text Mining) to see an example where the text sample is imported from an outside data source.",
-  "modelType": "datamining",
-  "datasets": {
-    "comment": "Binds the text samples to the trainCorpus dataset.",
-    "trainCorpus": {
-      "value": [ "Romeo and Juliet.", "Juliet: O happy dagger!", "'Romeo died by dagger.'", "'Live free or die', that's the New-Hampshire's motto.", "'Did you know, New - Hampshire is in New - England.'" ]
-    }
-  },
-  "estimator": {
-    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
-    "tfidfEstimator": {
-      "comment": "Defines the tfidfEstimator as a tfIdf estimator; various options are set. For a complete list of all algorithm options, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
-      "type": "textMining",
-      "algorithm": "tfIdf",
-      "parameters": {
-        "maxVocabulary": 5,
-        "maxTermLength": 10,
-        "minDocumentFrequency": 5,
-        "maxDocumentFrequency": 95,
-        "preprocessing": [ "REMOVE_STOPWORDS", "NORMALIZE_CASE", "STEM", "NORMALIZE_URL", "NORMALIZE_EMAIL", "NORMALIZE_NUMBER", "NORMALIZE_MONEY", "REMOVE_HTML_TAGS" ],
-        "synonyms": [
-          [ "rootTerm1", "synonym1", "synonym2" ],
-          [ "rootTerm2", "synonym1", "synonym2" ]
-        ],
-        "phraseReplacement": [
-          [ "phrase1", "phraseReplacement" ],
-          [ "phrase2", "phraseReplacement" ]
-        ]
-      }
-    }
-  },
-  "actions": {
-    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
-    "tfidfModel": {
-      "comment": "Fits the tfidfEstimator to trainCorpus, POSTs the fitted model to the RASON Server and also exports the fitted model to a JSON file using the export property.  Various evaluations are requested.  Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. DetailedVocabulary returns the number of times the terms, included in the Final List of Terms, appears in the document collection and the number of documents that include each term. TermCountInfo Returns the number of total terms, the % Reduction in Terms, the Final number of terms after preprocessing or reduction, and the setting for 'maxVocabulary'. DocInfo returns the # Characters and the # Terms per document.",
-      "trainData": "trainCorpus",
-      "estimator": "tfidfEstimator",
-      "action": "fit",
-      "evaluations": [ "vocabulary", "detailedVocabulary", "termCountInfo", "docInfo" ]
-    },
-    "termDocMatrix": {
-      "comment": "Uses the fitted model tfidfModel to generate the term document matrix, which lists the 200 most frequently appearing terms. For information on all evaluations supported by Text Miner, click the Help tab to download the RASON Reference Guide.",
-      "data": "trainCorpus",
-      "fittedModel": "tfidfModel",
-      "parameters": {
-        "weightingSchemeTerm": "LOGARITHMIC",
-        "weightingSchemeDocument": "INVERSE",
-        "weightingSchemeNormalization": "NONE"
-      },
-      "action": "transform",
-      "evaluations": [ "transformation" ]
-    }
-  }
+{
+  "modelName": "Tfldf-InlineData",
+  "modelDescription": "RASON Text Mining - TF-IDF example: TF-IDF stands for Term Frequency Inverse Document Frequency of records. It can be defined as the calculation of how relevant a word in a series or corpus is to a text. See the TFIDF-FileData example (Examples - Data Mining - Text Mining) to see an example where the text sample is imported from an outside data source.",
+  "modelType": "datamining",
+  "datasets": {
+    "comment": "Binds the text samples to the trainCorpus dataset.",
+    "trainCorpus": {
+      "value": [ "Romeo and Juliet.", "Juliet: O happy dagger!", "'Romeo died by dagger.'", "'Live free or die', that's the New-Hampshire's motto.", "'Did you know, New - Hampshire is in New - England.'" ]
+    }
+  },
+  "estimator": {
+    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
+    "tfidfEstimator": {
+      "comment": "Defines the tfidfEstimator as a tfIdf estimator; various options are set. For a complete list of all algorithm options, see the RASON Data Mining Components chapter in the RASON Reference Guide. (Click the Help tab to download.)",
+      "type": "textMining",
+      "algorithm": "tfIdf",
+      "parameters": {
+        "maxVocabulary": 5,
+        "maxTermLength": 10,
+        "minDocumentFrequency": 5,
+        "maxDocumentFrequency": 95,
+        "preprocessing": [ "REMOVE_STOPWORDS", "NORMALIZE_CASE", "STEM", "NORMALIZE_URL", "NORMALIZE_EMAIL", "NORMALIZE_NUMBER", "NORMALIZE_MONEY", "REMOVE_HTML_TAGS" ],
+        "synonyms": [
+          [ "rootTerm1", "synonym1", "synonym2" ],
+          [ "rootTerm2", "synonym1", "synonym2" ]
+        ],
+        "phraseReplacement": [
+          [ "phrase1", "phraseReplacement" ],
+          [ "phrase2", "phraseReplacement" ]
+        ]
+      }
+    }
+  },
+  "actions": {
+    "comment": "Defines an estimator, including the type, algorithm and parameters. Only 1 estimator may appear in a RASON model.",
+    "tfidfModel": {
+      "comment": "Fits the tfidfEstimator to trainCorpus, POSTs the fitted model to the RASON Server and also exports the fitted model to a JSON file using the export property.  Various evaluations are requested.  Vocabulary returns the final list of terms.  The number of terms included in this list is determined by the 'maxVocabulary' estimator parameter setting. DetailedVocabulary returns the number of times the terms, included in the Final List of Terms, appears in the document collection and the number of documents that include each term. TermCountInfo Returns the number of total terms, the % Reduction in Terms, the Final number of terms after preprocessing or reduction, and the setting for 'maxVocabulary'. DocInfo returns the # Characters and the # Terms per document.",
+      "trainData": "trainCorpus",
+      "estimator": "tfidfEstimator",
+      "action": "fit",
+      "evaluations": [ "vocabulary", "detailedVocabulary", "termCountInfo", "docInfo" ]
+    },
+    "termDocMatrix": {
+      "comment": "Uses the fitted model tfidfModel to generate the term document matrix, which lists the 200 most frequently appearing terms. For information on all evaluations supported by Text Miner, click the Help tab to download the RASON Reference Guide.",
+      "data": "trainCorpus",
+      "fittedModel": "tfidfModel",
+      "parameters": {
+        "weightingSchemeTerm": "LOGARITHMIC",
+        "weightingSchemeDocument": "INVERSE",
+        "weightingSchemeNormalization": "NONE"
+      },
+      "action": "transform",
+      "evaluations": [ "transformation" ]
+    }
+  }
 }