teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of teradataml might be problematic. Click here for more details.

Files changed (108) hide show
  1. teradataml/LICENSE-3RD-PARTY.pdf +0 -0
  2. teradataml/LICENSE.pdf +0 -0
  3. teradataml/README.md +71 -0
  4. teradataml/_version.py +2 -2
  5. teradataml/analytics/analytic_function_executor.py +51 -24
  6. teradataml/analytics/json_parser/utils.py +11 -17
  7. teradataml/automl/__init__.py +103 -48
  8. teradataml/automl/data_preparation.py +55 -37
  9. teradataml/automl/data_transformation.py +131 -69
  10. teradataml/automl/feature_engineering.py +117 -185
  11. teradataml/automl/feature_exploration.py +9 -2
  12. teradataml/automl/model_evaluation.py +13 -25
  13. teradataml/automl/model_training.py +214 -75
  14. teradataml/catalog/model_cataloging_utils.py +1 -1
  15. teradataml/clients/auth_client.py +133 -0
  16. teradataml/common/aed_utils.py +3 -2
  17. teradataml/common/constants.py +11 -6
  18. teradataml/common/garbagecollector.py +5 -0
  19. teradataml/common/messagecodes.py +3 -1
  20. teradataml/common/messages.py +2 -1
  21. teradataml/common/utils.py +6 -0
  22. teradataml/context/context.py +49 -29
  23. teradataml/data/advertising.csv +201 -0
  24. teradataml/data/bank_marketing.csv +11163 -0
  25. teradataml/data/bike_sharing.csv +732 -0
  26. teradataml/data/boston2cols.csv +721 -0
  27. teradataml/data/breast_cancer.csv +570 -0
  28. teradataml/data/customer_segmentation_test.csv +2628 -0
  29. teradataml/data/customer_segmentation_train.csv +8069 -0
  30. teradataml/data/docs/sqle/docs_17_10/OneHotEncodingFit.py +3 -1
  31. teradataml/data/docs/sqle/docs_17_10/OneHotEncodingTransform.py +6 -0
  32. teradataml/data/docs/sqle/docs_17_10/OutlierFilterTransform.py +5 -1
  33. teradataml/data/docs/sqle/docs_17_20/ANOVA.py +61 -1
  34. teradataml/data/docs/sqle/docs_17_20/ColumnTransformer.py +2 -0
  35. teradataml/data/docs/sqle/docs_17_20/FTest.py +105 -26
  36. teradataml/data/docs/sqle/docs_17_20/GLM.py +162 -1
  37. teradataml/data/docs/sqle/docs_17_20/GetFutileColumns.py +5 -3
  38. teradataml/data/docs/sqle/docs_17_20/KMeans.py +48 -1
  39. teradataml/data/docs/sqle/docs_17_20/NonLinearCombineFit.py +3 -2
  40. teradataml/data/docs/sqle/docs_17_20/OneHotEncodingFit.py +5 -0
  41. teradataml/data/docs/sqle/docs_17_20/OneHotEncodingTransform.py +6 -0
  42. teradataml/data/docs/sqle/docs_17_20/ROC.py +3 -2
  43. teradataml/data/docs/sqle/docs_17_20/SVMPredict.py +13 -2
  44. teradataml/data/docs/sqle/docs_17_20/ScaleFit.py +119 -1
  45. teradataml/data/docs/sqle/docs_17_20/ScaleTransform.py +93 -1
  46. teradataml/data/docs/sqle/docs_17_20/TDGLMPredict.py +163 -1
  47. teradataml/data/docs/sqle/docs_17_20/XGBoost.py +12 -4
  48. teradataml/data/docs/sqle/docs_17_20/XGBoostPredict.py +7 -1
  49. teradataml/data/docs/sqle/docs_17_20/ZTest.py +72 -7
  50. teradataml/data/glm_example.json +28 -1
  51. teradataml/data/housing_train_segment.csv +201 -0
  52. teradataml/data/insect2Cols.csv +61 -0
  53. teradataml/data/jsons/sqle/17.20/TD_ANOVA.json +99 -27
  54. teradataml/data/jsons/sqle/17.20/TD_FTest.json +166 -83
  55. teradataml/data/jsons/sqle/17.20/TD_GLM.json +90 -14
  56. teradataml/data/jsons/sqle/17.20/TD_GLMPREDICT.json +48 -5
  57. teradataml/data/jsons/sqle/17.20/TD_GetFutileColumns.json +5 -3
  58. teradataml/data/jsons/sqle/17.20/TD_KMeans.json +31 -11
  59. teradataml/data/jsons/sqle/17.20/TD_NonLinearCombineFit.json +3 -2
  60. teradataml/data/jsons/sqle/17.20/TD_ROC.json +2 -1
  61. teradataml/data/jsons/sqle/17.20/TD_SVM.json +16 -16
  62. teradataml/data/jsons/sqle/17.20/TD_SVMPredict.json +19 -1
  63. teradataml/data/jsons/sqle/17.20/TD_ScaleFit.json +168 -15
  64. teradataml/data/jsons/sqle/17.20/TD_ScaleTransform.json +50 -1
  65. teradataml/data/jsons/sqle/17.20/TD_XGBoost.json +25 -7
  66. teradataml/data/jsons/sqle/17.20/TD_XGBoostPredict.json +17 -4
  67. teradataml/data/jsons/sqle/17.20/TD_ZTest.json +157 -80
  68. teradataml/data/kmeans_example.json +5 -0
  69. teradataml/data/kmeans_table.csv +10 -0
  70. teradataml/data/onehot_encoder_train.csv +4 -0
  71. teradataml/data/openml_example.json +29 -0
  72. teradataml/data/scale_attributes.csv +3 -0
  73. teradataml/data/scale_example.json +52 -1
  74. teradataml/data/scale_input_part_sparse.csv +31 -0
  75. teradataml/data/scale_input_partitioned.csv +16 -0
  76. teradataml/data/scale_input_sparse.csv +11 -0
  77. teradataml/data/scale_parameters.csv +3 -0
  78. teradataml/data/scripts/deploy_script.py +20 -1
  79. teradataml/data/scripts/sklearn/sklearn_fit.py +23 -27
  80. teradataml/data/scripts/sklearn/sklearn_fit_predict.py +20 -28
  81. teradataml/data/scripts/sklearn/sklearn_function.template +13 -18
  82. teradataml/data/scripts/sklearn/sklearn_model_selection_split.py +23 -33
  83. teradataml/data/scripts/sklearn/sklearn_neighbors.py +18 -27
  84. teradataml/data/scripts/sklearn/sklearn_score.py +20 -29
  85. teradataml/data/scripts/sklearn/sklearn_transform.py +30 -38
  86. teradataml/data/teradataml_example.json +77 -0
  87. teradataml/data/ztest_example.json +16 -0
  88. teradataml/dataframe/copy_to.py +8 -3
  89. teradataml/dataframe/data_transfer.py +120 -61
  90. teradataml/dataframe/dataframe.py +102 -17
  91. teradataml/dataframe/dataframe_utils.py +47 -9
  92. teradataml/dataframe/fastload.py +272 -89
  93. teradataml/dataframe/sql.py +84 -0
  94. teradataml/dbutils/dbutils.py +2 -2
  95. teradataml/lib/aed_0_1.dll +0 -0
  96. teradataml/opensource/sklearn/_sklearn_wrapper.py +102 -55
  97. teradataml/options/__init__.py +13 -4
  98. teradataml/options/configure.py +27 -6
  99. teradataml/scriptmgmt/UserEnv.py +19 -16
  100. teradataml/scriptmgmt/lls_utils.py +117 -14
  101. teradataml/table_operators/Script.py +2 -3
  102. teradataml/table_operators/TableOperator.py +58 -10
  103. teradataml/utils/validators.py +40 -2
  104. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/METADATA +78 -6
  105. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/RECORD +108 -90
  106. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/WHEEL +0 -0
  107. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/top_level.txt +0 -0
  108. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.1.dist-info}/zip-safe +0 -0
@@ -28,7 +28,7 @@
28
28
  "useInR": true,
29
29
  "rOrderNum": 1
30
30
  },
31
- {
31
+ {
32
32
  "requiredInputKind": [
33
33
  "Dimension"
34
34
  ],
@@ -85,7 +85,7 @@
85
85
  "useInR": true,
86
86
  "rOrderNum": 4
87
87
  },
88
- {
88
+ {
89
89
  "targetTable": [
90
90
  "InputTable"
91
91
  ],
@@ -107,7 +107,7 @@
107
107
  "useInR": true,
108
108
  "rOrderNum": 5
109
109
  },
110
- {
110
+ {
111
111
  "lowerBound": 1,
112
112
  "upperBound": 2147483647,
113
113
  "lowerBoundType": "EXCLUSIVE",
@@ -124,7 +124,7 @@
124
124
  "useInR": true,
125
125
  "rOrderNum": 6
126
126
  },
127
- {
127
+ {
128
128
  "lowerBound": 0,
129
129
  "upperBound": 2147483647,
130
130
  "lowerBoundType": "INCLUSIVE",
@@ -141,8 +141,8 @@
141
141
  "useInR": true,
142
142
  "rOrderNum": 7
143
143
  },
144
- {
145
- "defaultValue": 0.0395,
144
+ {
145
+ "defaultValue": 0.0395,
146
146
  "lowerBound": 0,
147
147
  "upperBound": 1.797e+308,
148
148
  "lowerBoundType": "INCLUSIVE",
@@ -159,8 +159,8 @@
159
159
  "useInR": true,
160
160
  "rOrderNum": 8
161
161
  },
162
- {
163
- "defaultValue": 10,
162
+ {
163
+ "defaultValue": 10,
164
164
  "lowerBound": 1,
165
165
  "upperBound": 2147483647,
166
166
  "lowerBoundType": "INCLUSIVE",
@@ -177,8 +177,8 @@
177
177
  "useInR": true,
178
178
  "rOrderNum": 9
179
179
  },
180
- {
181
- "defaultValue": 1,
180
+ {
181
+ "defaultValue": 1,
182
182
  "lowerBound": 1,
183
183
  "upperBound": 2147483647,
184
184
  "lowerBoundType": "INCLUSIVE",
@@ -195,7 +195,7 @@
195
195
  "useInR": true,
196
196
  "rOrderNum": 10
197
197
  },
198
- {
198
+ {
199
199
  "defaultValue": false,
200
200
  "name": "OutputClusterAssignment",
201
201
  "alternateNames": [],
@@ -207,6 +207,26 @@
207
207
  "rName": "output.cluster.assignment",
208
208
  "useInR": true,
209
209
  "rOrderNum": 11
210
+ },
211
+ {
212
+ "permittedValues": [
213
+ "RANDOM",
214
+ "KMEANS++"
215
+ ],
216
+ "defaultValue": "RANDOM",
217
+ "isOutputColumn": false,
218
+ "matchLengthOfArgument": "",
219
+ "allowPadding": false,
220
+ "name": "InitialCentroidsMethod",
221
+ "alternateNames": [],
222
+ "isRequired": false,
223
+ "rDescription": "Specifies the initialization method to be used for selecting initial set of centroids.",
224
+ "description": "Specifies the initialization method to be used for selecting initial set of centroids.",
225
+ "datatype": "STRING",
226
+ "allowsLists": false,
227
+ "rName": "initialcentroids.method",
228
+ "useInR": true,
229
+ "rOrderNum": 12
210
230
  }
211
231
  ]
212
232
  }
@@ -83,12 +83,13 @@
83
83
  },
84
84
  {
85
85
  "permittedValues": [],
86
+ "defaultValue": "TD_CombinedValue",
86
87
  "isOutputColumn": true,
87
88
  "matchLengthOfArgument": "",
88
89
  "allowPadding": false,
89
90
  "name": "ResultColumn",
90
91
  "alternateNames": [],
91
- "isRequired": true,
92
+ "isRequired": false,
92
93
  "rDescription": "Specifies the name of the new feature column.",
93
94
  "description": "Specifies the name of the new feature column.",
94
95
  "datatype": "STRING",
@@ -98,4 +99,4 @@
98
99
  "rOrderNum": 5
99
100
  }
100
101
  ]
101
- }
102
+ }
@@ -118,10 +118,11 @@
118
118
  },
119
119
  {
120
120
  "permittedValues": [],
121
+ "defaultValue": "1",
121
122
  "isOutputColumn": false,
122
123
  "name": "PositiveLabel",
123
124
  "alternateNames": [],
124
- "isRequired": true,
125
+ "isRequired": false,
125
126
  "rDescription": "Specifies the label of the positive class.",
126
127
  "description": "Specify the label of the positive class.",
127
128
  "datatype": "STRING",
@@ -144,7 +144,7 @@
144
144
  "allowsLists": false,
145
145
  "rName": "epsilon",
146
146
  "useInR": true,
147
- "rOrderNum": 6
147
+ "rOrderNum": 5
148
148
  },
149
149
  {
150
150
  "defaultValue": 10,
@@ -162,7 +162,7 @@
162
162
  "allowsLists": false,
163
163
  "rName": "batch.size",
164
164
  "useInR": true,
165
- "rOrderNum": 5
165
+ "rOrderNum": 6
166
166
  },
167
167
  {
168
168
  "defaultValue": 0.02,
@@ -180,7 +180,7 @@
180
180
  "allowsLists": false,
181
181
  "rName": "lambda1",
182
182
  "useInR": true,
183
- "rOrderNum": 6
183
+ "rOrderNum": 7
184
184
  },
185
185
  {
186
186
  "defaultValue": 0.15,
@@ -198,7 +198,7 @@
198
198
  "allowsLists": false,
199
199
  "rName": "alpha",
200
200
  "useInR": true,
201
- "rOrderNum": 7
201
+ "rOrderNum": 8
202
202
  },
203
203
  {
204
204
  "defaultValue": 50,
@@ -216,7 +216,7 @@
216
216
  "allowsLists": false,
217
217
  "rName": "iter.num.no.change",
218
218
  "useInR": true,
219
- "rOrderNum": 8
219
+ "rOrderNum": 9
220
220
  },
221
221
  {
222
222
  "defaultValue": 0.001,
@@ -234,7 +234,7 @@
234
234
  "allowsLists": false,
235
235
  "rName": "tolerance",
236
236
  "useInR": true,
237
- "rOrderNum": 9
237
+ "rOrderNum": 10
238
238
  },
239
239
  {
240
240
  "defaultValue": true,
@@ -247,7 +247,7 @@
247
247
  "allowsLists": false,
248
248
  "rName": "intercept",
249
249
  "useInR": true,
250
- "rOrderNum": 10
250
+ "rOrderNum": 11
251
251
  },
252
252
  {
253
253
  "defaultValue": "0:1.0, 1:1.0",
@@ -261,7 +261,7 @@
261
261
  "allowsLists": false,
262
262
  "rName": "class.weights",
263
263
  "useInR": true,
264
- "rOrderNum": 11
264
+ "rOrderNum": 12
265
265
  },
266
266
  {
267
267
  "permittedValues": [
@@ -280,7 +280,7 @@
280
280
  "allowsLists": false,
281
281
  "rName": "learning.rate",
282
282
  "useInR": true,
283
- "rOrderNum": 12
283
+ "rOrderNum": 13
284
284
  },
285
285
  {
286
286
  "defaultValue": 0.05,
@@ -298,7 +298,7 @@
298
298
  "allowsLists": false,
299
299
  "rName": "initial.eta",
300
300
  "useInR": true,
301
- "rOrderNum": 13
301
+ "rOrderNum": 14
302
302
  },
303
303
  {
304
304
  "defaultValue": 0.25,
@@ -316,7 +316,7 @@
316
316
  "allowsLists": false,
317
317
  "rName": "decay.rate",
318
318
  "useInR": true,
319
- "rOrderNum": 14
319
+ "rOrderNum": 15
320
320
  },
321
321
  {
322
322
  "defaultValue": 5,
@@ -334,7 +334,7 @@
334
334
  "allowsLists": false,
335
335
  "rName": "decay.steps",
336
336
  "useInR": true,
337
- "rOrderNum": 15
337
+ "rOrderNum": 16
338
338
  },
339
339
  {
340
340
  "defaultValue": 0.0,
@@ -352,7 +352,7 @@
352
352
  "allowsLists": false,
353
353
  "rName": "momentum",
354
354
  "useInR": true,
355
- "rOrderNum": 16
355
+ "rOrderNum": 17
356
356
  },
357
357
  {
358
358
  "defaultValue": false,
@@ -365,7 +365,7 @@
365
365
  "allowsLists": false,
366
366
  "rName": "nesterov",
367
367
  "useInR": true,
368
- "rOrderNum": 17
368
+ "rOrderNum": 18
369
369
  },
370
370
  {
371
371
  "defaultValue": 0,
@@ -383,7 +383,7 @@
383
383
  "allowsLists": false,
384
384
  "rName": "local.sgd.iterations",
385
385
  "useInR": true,
386
- "rOrderNum": 18
386
+ "rOrderNum": 19
387
387
  }
388
388
  ]
389
- }
389
+ }
@@ -119,6 +119,24 @@
119
119
  "rName": "output.responses",
120
120
  "useInR": true,
121
121
  "rOrderNum": 6
122
+ },
123
+ {
124
+ "permittedValues": [
125
+ "Regression",
126
+ "Classification"
127
+ ],
128
+ "defaultValue": "Classification",
129
+ "isOutputColumn": false,
130
+ "name": "ModelType",
131
+ "alternateNames": [],
132
+ "isRequired": false,
133
+ "rDescription": "Specify the type of the analysis. Acceptable values are Regression, Classification.",
134
+ "description": "Specify the type of the analysis. Acceptable values are Regression, Classification.",
135
+ "datatype": "STRING",
136
+ "allowsLists": false,
137
+ "rName": "model.type",
138
+ "useInR": true,
139
+ "rOrderNum": 7
122
140
  }
123
141
  ]
124
- }
142
+ }
@@ -12,6 +12,10 @@
12
12
  "long_description": "fastpath function to generate required statistics and scaling parameters to be used by TD_ScaleTransform for scaling the input data.",
13
13
  "input_tables": [
14
14
  {
15
+ "requiredInputKind": [
16
+ "PartitionByAny",
17
+ "PartitionByKey"
18
+ ],
15
19
  "isOrdered": false,
16
20
  "partitionByOne": false,
17
21
  "name": "InputTable",
@@ -24,6 +28,40 @@
24
28
  "rName": "data",
25
29
  "useInR": true,
26
30
  "rOrderNum": 1
31
+ },
32
+ {
33
+ "requiredInputKind": [
34
+ "PartitionByKey"
35
+ ],
36
+ "isOrdered": false,
37
+ "partitionByOne": false,
38
+ "name": "ParameterTable",
39
+ "alternateNames": [],
40
+ "isRequired": false,
41
+ "rDescription": "The relation that contains parameters.",
42
+ "description": "The relation that contains parameters.",
43
+ "datatype": "TABLE_ALIAS",
44
+ "allowsLists": false,
45
+ "rName": "parameter.table",
46
+ "useInR": true,
47
+ "rOrderNum": 2
48
+ },
49
+ {
50
+ "requiredInputKind": [
51
+ "PartitionByKey"
52
+ ],
53
+ "isOrdered": false,
54
+ "partitionByOne": false,
55
+ "name": "AttributeTable",
56
+ "alternateNames": [],
57
+ "isRequired": false,
58
+ "rDescription": "The relation that contains input data.",
59
+ "description": "The relation that contains input data.",
60
+ "datatype": "TABLE_ALIAS",
61
+ "allowsLists": false,
62
+ "rName": "attribute.table",
63
+ "useInR": true,
64
+ "rOrderNum": 3
27
65
  }
28
66
  ],
29
67
  "output_tables": [
@@ -39,7 +77,7 @@
39
77
  "allowsLists": false,
40
78
  "rName": "output.table",
41
79
  "useInR": true,
42
- "rOrderNum": 2
80
+ "rOrderNum": 4
43
81
  }
44
82
  ],
45
83
  "argument_clauses": [
@@ -56,16 +94,16 @@
56
94
  "allowPadding": false,
57
95
  "name": "TargetColumns",
58
96
  "alternateNames": [],
59
- "isRequired": true,
60
- "rDescription": "Specifies the input table columns for which scaling parameters and statistics will be generated.",
61
- "description": "Specifies the input table columns for which scaling parameters and statistics will be generated.",
97
+ "isRequired": false,
98
+ "rDescription": "Specifies the input table columns (for dense input) for which scaling parameters and statistics will be generated.",
99
+ "description": "Specifies the input table columns (for dense input) for which scaling parameters and statistics will be generated.",
62
100
  "datatype": "COLUMNS",
63
101
  "allowsLists": true,
64
102
  "rName": "target.columns",
65
103
  "useInR": true,
66
- "rOrderNum": 3
104
+ "rOrderNum": 5
67
105
  },
68
- {
106
+ {
69
107
  "permittedValues": [],
70
108
  "isOutputColumn": false,
71
109
  "matchLengthOfArgument": "",
@@ -79,9 +117,9 @@
79
117
  "allowsLists": true,
80
118
  "rName": "scale.method",
81
119
  "useInR": true,
82
- "rOrderNum": 4
120
+ "rOrderNum": 6
83
121
  },
84
- {
122
+ {
85
123
  "permittedValues": [
86
124
  "KEEP",
87
125
  "ZERO",
@@ -100,9 +138,9 @@
100
138
  "allowsLists": false,
101
139
  "rName": "miss.value",
102
140
  "useInR": true,
103
- "rOrderNum": 5
141
+ "rOrderNum": 7
104
142
  },
105
- {
143
+ {
106
144
  "defaultValue": false,
107
145
  "name": "GlobalScale",
108
146
  "alternateNames": [],
@@ -113,9 +151,9 @@
113
151
  "allowsLists": false,
114
152
  "rName": "global.scale",
115
153
  "useInR": true,
116
- "rOrderNum": 6
154
+ "rOrderNum": 8
117
155
  },
118
- {
156
+ {
119
157
  "permittedValues": [],
120
158
  "defaultValue": [
121
159
  "1"
@@ -132,9 +170,9 @@
132
170
  "allowsLists": true,
133
171
  "rName": "multiplier",
134
172
  "useInR": true,
135
- "rOrderNum": 7
173
+ "rOrderNum": 9
136
174
  },
137
- {
175
+ {
138
176
  "permittedValues": [],
139
177
  "defaultValue": [
140
178
  "0"
@@ -151,7 +189,122 @@
151
189
  "allowsLists": true,
152
190
  "rName": "intercept",
153
191
  "useInR": true,
154
- "rOrderNum": 8
192
+ "rOrderNum": 10
193
+ },
194
+ {
195
+ "targetTable": [
196
+ "InputTable"
197
+ ],
198
+ "checkDuplicate": true,
199
+ "allowedTypes": [],
200
+ "allowedTypeGroups": [
201
+ "ALL"
202
+ ],
203
+ "matchLengthOfArgument": "",
204
+ "allowPadding": false,
205
+ "name": "PartitionColumns",
206
+ "alternateNames": [],
207
+ "isRequired": false,
208
+ "rDescription": "Specify the name of the input table columns on which to partition the input.",
209
+ "description": "Specify the name of the input table columns on which to partition the input.",
210
+ "datatype": "COLUMNS",
211
+ "allowsLists": true,
212
+ "rName": "partition.columns",
213
+ "useInR": true,
214
+ "rOrderNum": 11
215
+ },
216
+ {
217
+ "defaultValue": false,
218
+ "name": "IgnoreInvalidLocationScale",
219
+ "alternateNames": [],
220
+ "isRequired": false,
221
+ "rDescription": "Specify whether to ignore invalid values of location and scale parameters.",
222
+ "description": "Specify whether to ignore invalid values of location and scale parameters.",
223
+ "datatype": "BOOLEAN",
224
+ "allowsLists": false,
225
+ "rName": "ignoreinvalid.locationscale",
226
+ "useInR": true,
227
+ "rOrderNum": 12
228
+ },
229
+ {
230
+ "permittedValues": [
231
+ "UNSCALED",
232
+ "NULLIFY"
233
+ ],
234
+ "defaultValue": "UNSCALED",
235
+ "isOutputColumn": false,
236
+ "matchLengthOfArgument": "",
237
+ "allowPadding": false,
238
+ "name": "UnusedAttributes",
239
+ "alternateNames": [],
240
+ "isRequired": false,
241
+ "rDescription": "Specify whether to emit out unused attributes of different partitions as unscaled values or NULLs (for dense input).",
242
+ "description": "Specify whether to emit out unused attributes of different partitions as unscaled values or NULLs (for dense input).",
243
+ "datatype": "STRING",
244
+ "allowsLists": false,
245
+ "rName": "unused.attributes",
246
+ "useInR": true,
247
+ "rOrderNum": 13
248
+ },
249
+ {
250
+ "targetTable": [
251
+ "InputTable"
252
+ ],
253
+ "checkDuplicate": true,
254
+ "allowedTypes": [],
255
+ "allowedTypeGroups": [
256
+ "CHAR", "VARCHAR"
257
+ ],
258
+ "matchLengthOfArgument": "",
259
+ "allowPadding": false,
260
+ "name": "AttributeNameColumn",
261
+ "alternateNames": [],
262
+ "isRequired": false,
263
+ "rDescription": "Specifies the input table column which contains attribute names (required for sparse input).",
264
+ "description": "Specifies the input table column which contains attribute names (required for sparse input).",
265
+ "datatype": "COLUMNS",
266
+ "allowsLists": false,
267
+ "rName": "attribute.name.column",
268
+ "useInR": true,
269
+ "rOrderNum": 14
270
+ },
271
+ {
272
+ "targetTable": [
273
+ "InputTable"
274
+ ],
275
+ "checkDuplicate": true,
276
+ "allowedTypes": [],
277
+ "allowedTypeGroups": [
278
+ "NUMERIC"
279
+ ],
280
+ "matchLengthOfArgument": "",
281
+ "allowPadding": false,
282
+ "name": "AttributeValueColumn",
283
+ "alternateNames": [],
284
+ "isRequired": false,
285
+ "rDescription": "Specifies the input table column which contains attribute values (required for sparse input).",
286
+ "description": "Specifies the input table column which contains attribute values (required for sparse input).",
287
+ "datatype": "COLUMNS",
288
+ "allowsLists": false,
289
+ "rName": "attribute.value.column",
290
+ "useInR": true,
291
+ "rOrderNum": 15
292
+ },
293
+ {
294
+ "permittedValues": [],
295
+ "isOutputColumn": false,
296
+ "matchLengthOfArgument": "",
297
+ "allowPadding": false,
298
+ "name": "TargetAttributes",
299
+ "alternateNames": [],
300
+ "isRequired": false,
301
+ "rDescription": "A list of attributes for which scaling should be performed (for sparse input).",
302
+ "description": "A list of attributes for which scaling should be performed (for sparse input).",
303
+ "datatype": "STRING",
304
+ "allowsLists": true,
305
+ "rName": "target.attributes",
306
+ "useInR": true,
307
+ "rOrderNum": 16
155
308
  }
156
309
  ]
157
310
  }
@@ -13,6 +13,10 @@
13
13
  "long_description": "fastpath function to scale/standardize numeric columns.",
14
14
  "input_tables": [
15
15
  {
16
+ "requiredInputKind": [
17
+ "PartitionByAny",
18
+ "PartitionByKey"
19
+ ],
16
20
  "isOrdered": false,
17
21
  "partitionByOne": false,
18
22
  "name": "InputTable",
@@ -28,7 +32,8 @@
28
32
  },
29
33
  {
30
34
  "requiredInputKind": [
31
- "Dimension"
35
+ "Dimension",
36
+ "PartitionByKey"
32
37
  ],
33
38
  "isOrdered": false,
34
39
  "partitionByOne": false,
@@ -66,6 +71,50 @@
66
71
  "rName": "accumulate",
67
72
  "useInR": true,
68
73
  "rOrderNum": 3
74
+ },
75
+ {
76
+ "targetTable": [
77
+ "InputTable"
78
+ ],
79
+ "checkDuplicate": true,
80
+ "allowedTypes": [],
81
+ "allowedTypeGroups": [
82
+ "CHAR", "VARCHAR"
83
+ ],
84
+ "matchLengthOfArgument": "",
85
+ "allowPadding": false,
86
+ "name": "AttributeNameColumn",
87
+ "alternateNames": [],
88
+ "isRequired": false,
89
+ "rDescription": "Specifies the input table column which contains attribute names (required for sparse input).",
90
+ "description": "Specifies the input table column which contains attribute names (required for sparse input).",
91
+ "datatype": "COLUMNS",
92
+ "allowsLists": false,
93
+ "rName": "attribute.name.column",
94
+ "useInR": true,
95
+ "rOrderNum": 4
96
+ },
97
+ {
98
+ "targetTable": [
99
+ "InputTable"
100
+ ],
101
+ "checkDuplicate": true,
102
+ "allowedTypes": [],
103
+ "allowedTypeGroups": [
104
+ "NUMERIC"
105
+ ],
106
+ "matchLengthOfArgument": "",
107
+ "allowPadding": false,
108
+ "name": "AttributeValueColumn",
109
+ "alternateNames": [],
110
+ "isRequired": false,
111
+ "rDescription": "Specifies the input table column which contains attribute values (required for sparse input).",
112
+ "description": "Specifies the input table column which contains attribute values (required for sparse input).",
113
+ "datatype": "COLUMNS",
114
+ "allowsLists": false,
115
+ "rName": "attribute.value.column",
116
+ "useInR": true,
117
+ "rOrderNum": 5
69
118
  }
70
119
  ]
71
120
  }
@@ -1,9 +1,9 @@
1
1
  {
2
2
  "json_schema_major_version": "1",
3
- "json_schema_minor_version": "3",
3
+ "json_schema_minor_version": "4",
4
4
  "json_content_version": "1",
5
5
  "function_name": "TD_XGBoost",
6
- "function_version": "1.3",
6
+ "function_version": "1.4",
7
7
  "function_type": "fastpath",
8
8
  "function_category": "Model Training",
9
9
  "function_alias_name": "TD_XGBoost",
@@ -145,7 +145,7 @@
145
145
  "rName": "min.node.size",
146
146
  "useInR": true,
147
147
  "rOrderNum": 5
148
- },
148
+ },
149
149
  {
150
150
  "defaultValue": 1,
151
151
  "lowerBound": -2147483648,
@@ -166,7 +166,7 @@
166
166
  },
167
167
  {
168
168
  "permittedValues": [
169
- "REGRESSION",
169
+ "REGRESSION",
170
170
  "CLASSIFICATION"
171
171
  ],
172
172
  "defaultValue": "REGRESSION",
@@ -219,7 +219,7 @@
219
219
  "rOrderNum": 9
220
220
  },
221
221
  {
222
- "defaultValue": 100000,
222
+ "defaultValue": 1,
223
223
  "lowerBound": 0,
224
224
  "upperBound": 100000,
225
225
  "lowerBoundType": "INCLUSIVE",
@@ -237,7 +237,7 @@
237
237
  "rOrderNum": 10
238
238
  },
239
239
  {
240
- "defaultValue": 0.1,
240
+ "defaultValue": 0.5,
241
241
  "lowerBound": 1e-10,
242
242
  "upperBound": 1,
243
243
  "lowerBoundType": "INCLUSIVE",
@@ -307,6 +307,24 @@
307
307
  "rName": "tree.size",
308
308
  "useInR": true,
309
309
  "rOrderNum": 14
310
+ },
311
+ {
312
+ "defaultValue": 0,
313
+ "lowerBound": -1e50,
314
+ "upperBound": 1e50,
315
+ "lowerBoundType": "INCLUSIVE",
316
+ "upperBoundType": "INCLUSIVE",
317
+ "allowNaN": false,
318
+ "name": "BaseScore",
319
+ "alternateNames": [],
320
+ "isRequired": false,
321
+ "rDescription": "Specify the initial prediction value for all data points.",
322
+ "description": "Specify the initial prediction value for all data points.",
323
+ "datatype": "DOUBLE",
324
+ "allowsLists": false,
325
+ "rName": "base.score",
326
+ "useInR": true,
327
+ "rOrderNum": 15
310
328
  }
311
329
  ]
312
- }
330
+ }