44 lines
1.7 KiB
JSON
44 lines
1.7 KiB
JSON
[
|
|
{
|
|
"paramName": "w",
|
|
"paramLongName": "workingPath",
|
|
"paramDescription": "location of the working directory",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "v",
|
|
"paramLongName": "vocabularyPath",
|
|
"paramDescription": "location to store the vocabulary",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "vt",
|
|
"paramLongName": "vocabularyType",
|
|
"paramDescription": "type of vocabulary: it could ben 'tokens' if generated with tokens or 'file' if generated from file of words",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "md",
|
|
"paramLongName": "minDF",
|
|
"paramDescription": "specifies the minimum number of different documents a term must appear in to be included in the vocabulary. If this is an integer greater than or equal to 1, this specifies the number of documents the term must appear in; if this is a double in [0,1), then this specifies the fraction of documents",
|
|
"paramRequired": false
|
|
},
|
|
{
|
|
"paramName": "mt",
|
|
"paramLongName": "minTF",
|
|
"paramDescription": "filter to ignore rare words in a document. For each document, terms with frequency/count less than the given threshold are ignored. If this is an integer greater than or equal to 1, then this specifies a count (of times the term must appear in the document); if this is a double in [0,1), then this specifies a fraction (out of the document's token count)",
|
|
"paramRequired": false
|
|
},
|
|
{
|
|
"paramName": "s",
|
|
"paramLongName": "vocabSize",
|
|
"paramDescription": "size of the vocabulary",
|
|
"paramRequired": false
|
|
},
|
|
{
|
|
"paramName": "np",
|
|
"paramLongName": "numPartitions",
|
|
"paramDescription": "number of partitions for the similarity relations intermediate phases",
|
|
"paramRequired": false
|
|
}
|
|
] |