teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.2__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 (263) hide show
  1. teradataml/LICENSE-3RD-PARTY.pdf +0 -0
  2. teradataml/LICENSE.pdf +0 -0
  3. teradataml/README.md +183 -0
  4. teradataml/__init__.py +6 -3
  5. teradataml/_version.py +2 -2
  6. teradataml/analytics/__init__.py +3 -2
  7. teradataml/analytics/analytic_function_executor.py +275 -40
  8. teradataml/analytics/analytic_query_generator.py +92 -0
  9. teradataml/analytics/byom/__init__.py +3 -2
  10. teradataml/analytics/json_parser/metadata.py +1 -0
  11. teradataml/analytics/json_parser/utils.py +17 -21
  12. teradataml/analytics/meta_class.py +40 -1
  13. teradataml/analytics/sqle/DecisionTreePredict.py +1 -1
  14. teradataml/analytics/sqle/__init__.py +10 -2
  15. teradataml/analytics/table_operator/__init__.py +3 -2
  16. teradataml/analytics/uaf/__init__.py +21 -2
  17. teradataml/analytics/utils.py +62 -1
  18. teradataml/analytics/valib.py +1 -1
  19. teradataml/automl/__init__.py +1553 -319
  20. teradataml/automl/custom_json_utils.py +139 -61
  21. teradataml/automl/data_preparation.py +276 -319
  22. teradataml/automl/data_transformation.py +163 -81
  23. teradataml/automl/feature_engineering.py +402 -239
  24. teradataml/automl/feature_exploration.py +9 -2
  25. teradataml/automl/model_evaluation.py +48 -51
  26. teradataml/automl/model_training.py +291 -189
  27. teradataml/catalog/byom.py +8 -8
  28. teradataml/catalog/model_cataloging_utils.py +1 -1
  29. teradataml/clients/auth_client.py +133 -0
  30. teradataml/clients/pkce_client.py +1 -1
  31. teradataml/common/aed_utils.py +3 -2
  32. teradataml/common/constants.py +48 -6
  33. teradataml/common/deprecations.py +13 -7
  34. teradataml/common/garbagecollector.py +156 -120
  35. teradataml/common/messagecodes.py +6 -1
  36. teradataml/common/messages.py +3 -1
  37. teradataml/common/sqlbundle.py +1 -1
  38. teradataml/common/utils.py +103 -11
  39. teradataml/common/wrapper_utils.py +1 -1
  40. teradataml/context/context.py +121 -31
  41. teradataml/data/advertising.csv +201 -0
  42. teradataml/data/bank_marketing.csv +11163 -0
  43. teradataml/data/bike_sharing.csv +732 -0
  44. teradataml/data/boston2cols.csv +721 -0
  45. teradataml/data/breast_cancer.csv +570 -0
  46. teradataml/data/complaints_test_tokenized.csv +353 -0
  47. teradataml/data/complaints_tokens_model.csv +348 -0
  48. teradataml/data/covid_confirm_sd.csv +83 -0
  49. teradataml/data/customer_segmentation_test.csv +2628 -0
  50. teradataml/data/customer_segmentation_train.csv +8069 -0
  51. teradataml/data/dataframe_example.json +10 -0
  52. teradataml/data/docs/sqle/docs_17_10/OneHotEncodingFit.py +3 -1
  53. teradataml/data/docs/sqle/docs_17_10/OneHotEncodingTransform.py +6 -0
  54. teradataml/data/docs/sqle/docs_17_10/OutlierFilterTransform.py +5 -1
  55. teradataml/data/docs/sqle/docs_17_20/ANOVA.py +61 -1
  56. teradataml/data/docs/sqle/docs_17_20/CFilter.py +132 -0
  57. teradataml/data/docs/sqle/docs_17_20/ColumnTransformer.py +2 -0
  58. teradataml/data/docs/sqle/docs_17_20/FTest.py +105 -26
  59. teradataml/data/docs/sqle/docs_17_20/GLM.py +162 -1
  60. teradataml/data/docs/sqle/docs_17_20/GetFutileColumns.py +5 -3
  61. teradataml/data/docs/sqle/docs_17_20/KMeans.py +48 -1
  62. teradataml/data/docs/sqle/docs_17_20/NaiveBayes.py +162 -0
  63. teradataml/data/docs/sqle/docs_17_20/NonLinearCombineFit.py +3 -2
  64. teradataml/data/docs/sqle/docs_17_20/OneHotEncodingFit.py +5 -0
  65. teradataml/data/docs/sqle/docs_17_20/OneHotEncodingTransform.py +6 -0
  66. teradataml/data/docs/sqle/docs_17_20/OutlierFilterFit.py +2 -0
  67. teradataml/data/docs/sqle/docs_17_20/Pivoting.py +279 -0
  68. teradataml/data/docs/sqle/docs_17_20/ROC.py +3 -2
  69. teradataml/data/docs/sqle/docs_17_20/SVMPredict.py +13 -2
  70. teradataml/data/docs/sqle/docs_17_20/ScaleFit.py +119 -1
  71. teradataml/data/docs/sqle/docs_17_20/ScaleTransform.py +93 -1
  72. teradataml/data/docs/sqle/docs_17_20/Shap.py +197 -0
  73. teradataml/data/docs/sqle/docs_17_20/TDGLMPredict.py +163 -1
  74. teradataml/data/docs/sqle/docs_17_20/TDNaiveBayesPredict.py +189 -0
  75. teradataml/data/docs/sqle/docs_17_20/TFIDF.py +142 -0
  76. teradataml/data/docs/sqle/docs_17_20/Unpivoting.py +216 -0
  77. teradataml/data/docs/sqle/docs_17_20/XGBoost.py +12 -4
  78. teradataml/data/docs/sqle/docs_17_20/XGBoostPredict.py +7 -1
  79. teradataml/data/docs/sqle/docs_17_20/ZTest.py +72 -7
  80. teradataml/data/docs/uaf/docs_17_20/ACF.py +1 -10
  81. teradataml/data/docs/uaf/docs_17_20/ArimaEstimate.py +1 -1
  82. teradataml/data/docs/uaf/docs_17_20/ArimaForecast.py +35 -5
  83. teradataml/data/docs/uaf/docs_17_20/ArimaValidate.py +3 -1
  84. teradataml/data/docs/uaf/docs_17_20/ArimaXEstimate.py +293 -0
  85. teradataml/data/docs/uaf/docs_17_20/AutoArima.py +354 -0
  86. teradataml/data/docs/uaf/docs_17_20/BreuschGodfrey.py +3 -2
  87. teradataml/data/docs/uaf/docs_17_20/BreuschPaganGodfrey.py +1 -1
  88. teradataml/data/docs/uaf/docs_17_20/Convolve.py +13 -10
  89. teradataml/data/docs/uaf/docs_17_20/Convolve2.py +4 -1
  90. teradataml/data/docs/uaf/docs_17_20/CumulPeriodogram.py +5 -4
  91. teradataml/data/docs/uaf/docs_17_20/DFFT2Conv.py +4 -4
  92. teradataml/data/docs/uaf/docs_17_20/DWT.py +235 -0
  93. teradataml/data/docs/uaf/docs_17_20/DWT2D.py +214 -0
  94. teradataml/data/docs/uaf/docs_17_20/DurbinWatson.py +1 -1
  95. teradataml/data/docs/uaf/docs_17_20/ExtractResults.py +1 -1
  96. teradataml/data/docs/uaf/docs_17_20/FilterFactory1d.py +160 -0
  97. teradataml/data/docs/uaf/docs_17_20/GenseriesSinusoids.py +1 -1
  98. teradataml/data/docs/uaf/docs_17_20/GoldfeldQuandt.py +9 -31
  99. teradataml/data/docs/uaf/docs_17_20/HoltWintersForecaster.py +4 -2
  100. teradataml/data/docs/uaf/docs_17_20/IDFFT2.py +1 -8
  101. teradataml/data/docs/uaf/docs_17_20/IDWT.py +236 -0
  102. teradataml/data/docs/uaf/docs_17_20/IDWT2D.py +226 -0
  103. teradataml/data/docs/uaf/docs_17_20/IQR.py +134 -0
  104. teradataml/data/docs/uaf/docs_17_20/LineSpec.py +1 -1
  105. teradataml/data/docs/uaf/docs_17_20/LinearRegr.py +2 -2
  106. teradataml/data/docs/uaf/docs_17_20/MAMean.py +3 -3
  107. teradataml/data/docs/uaf/docs_17_20/Matrix2Image.py +297 -0
  108. teradataml/data/docs/uaf/docs_17_20/MatrixMultiply.py +15 -6
  109. teradataml/data/docs/uaf/docs_17_20/PACF.py +0 -1
  110. teradataml/data/docs/uaf/docs_17_20/Portman.py +2 -2
  111. teradataml/data/docs/uaf/docs_17_20/PowerSpec.py +2 -2
  112. teradataml/data/docs/uaf/docs_17_20/Resample.py +9 -1
  113. teradataml/data/docs/uaf/docs_17_20/SAX.py +246 -0
  114. teradataml/data/docs/uaf/docs_17_20/SeasonalNormalize.py +17 -10
  115. teradataml/data/docs/uaf/docs_17_20/SignifPeriodicities.py +1 -1
  116. teradataml/data/docs/uaf/docs_17_20/WhitesGeneral.py +3 -1
  117. teradataml/data/docs/uaf/docs_17_20/WindowDFFT.py +368 -0
  118. teradataml/data/dwt2d_dataTable.csv +65 -0
  119. teradataml/data/dwt_dataTable.csv +8 -0
  120. teradataml/data/dwt_filterTable.csv +3 -0
  121. teradataml/data/finance_data4.csv +13 -0
  122. teradataml/data/glm_example.json +28 -1
  123. teradataml/data/grocery_transaction.csv +19 -0
  124. teradataml/data/housing_train_segment.csv +201 -0
  125. teradataml/data/idwt2d_dataTable.csv +5 -0
  126. teradataml/data/idwt_dataTable.csv +8 -0
  127. teradataml/data/idwt_filterTable.csv +3 -0
  128. teradataml/data/insect2Cols.csv +61 -0
  129. teradataml/data/interval_data.csv +5 -0
  130. teradataml/data/jsons/paired_functions.json +14 -0
  131. teradataml/data/jsons/sqle/17.20/TD_ANOVA.json +99 -27
  132. teradataml/data/jsons/sqle/17.20/TD_CFilter.json +118 -0
  133. teradataml/data/jsons/sqle/17.20/TD_FTest.json +166 -83
  134. teradataml/data/jsons/sqle/17.20/TD_GLM.json +90 -14
  135. teradataml/data/jsons/sqle/17.20/TD_GLMPREDICT.json +48 -5
  136. teradataml/data/jsons/sqle/17.20/TD_GetFutileColumns.json +5 -3
  137. teradataml/data/jsons/sqle/17.20/TD_KMeans.json +31 -11
  138. teradataml/data/jsons/sqle/17.20/TD_NaiveBayes.json +193 -0
  139. teradataml/data/jsons/sqle/17.20/TD_NaiveBayesPredict.json +212 -0
  140. teradataml/data/jsons/sqle/17.20/TD_NonLinearCombineFit.json +3 -2
  141. teradataml/data/jsons/sqle/17.20/TD_OneClassSVM.json +9 -9
  142. teradataml/data/jsons/sqle/17.20/TD_Pivoting.json +280 -0
  143. teradataml/data/jsons/sqle/17.20/TD_ROC.json +2 -1
  144. teradataml/data/jsons/sqle/17.20/TD_SVM.json +16 -16
  145. teradataml/data/jsons/sqle/17.20/TD_SVMPredict.json +19 -1
  146. teradataml/data/jsons/sqle/17.20/TD_ScaleFit.json +168 -15
  147. teradataml/data/jsons/sqle/17.20/TD_ScaleTransform.json +50 -1
  148. teradataml/data/jsons/sqle/17.20/TD_Shap.json +222 -0
  149. teradataml/data/jsons/sqle/17.20/TD_TFIDF.json +162 -0
  150. teradataml/data/jsons/sqle/17.20/TD_Unpivoting.json +235 -0
  151. teradataml/data/jsons/sqle/17.20/TD_XGBoost.json +25 -7
  152. teradataml/data/jsons/sqle/17.20/TD_XGBoostPredict.json +17 -4
  153. teradataml/data/jsons/sqle/17.20/TD_ZTest.json +157 -80
  154. teradataml/data/jsons/storedprocedure/17.20/TD_FILTERFACTORY1D.json +150 -0
  155. teradataml/data/jsons/uaf/17.20/TD_ACF.json +1 -18
  156. teradataml/data/jsons/uaf/17.20/TD_ARIMAESTIMATE.json +3 -16
  157. teradataml/data/jsons/uaf/17.20/TD_ARIMAFORECAST.json +0 -3
  158. teradataml/data/jsons/uaf/17.20/TD_ARIMAVALIDATE.json +5 -3
  159. teradataml/data/jsons/uaf/17.20/TD_ARIMAXESTIMATE.json +362 -0
  160. teradataml/data/jsons/uaf/17.20/TD_AUTOARIMA.json +469 -0
  161. teradataml/data/jsons/uaf/17.20/TD_BINARYMATRIXOP.json +0 -3
  162. teradataml/data/jsons/uaf/17.20/TD_BINARYSERIESOP.json +0 -2
  163. teradataml/data/jsons/uaf/17.20/TD_BREUSCH_GODFREY.json +2 -1
  164. teradataml/data/jsons/uaf/17.20/TD_BREUSCH_PAGAN_GODFREY.json +2 -5
  165. teradataml/data/jsons/uaf/17.20/TD_CONVOLVE.json +3 -6
  166. teradataml/data/jsons/uaf/17.20/TD_CONVOLVE2.json +1 -3
  167. teradataml/data/jsons/uaf/17.20/TD_CUMUL_PERIODOGRAM.json +0 -5
  168. teradataml/data/jsons/uaf/17.20/TD_DFFT.json +1 -4
  169. teradataml/data/jsons/uaf/17.20/TD_DFFT2.json +2 -7
  170. teradataml/data/jsons/uaf/17.20/TD_DFFT2CONV.json +1 -2
  171. teradataml/data/jsons/uaf/17.20/TD_DFFTCONV.json +0 -2
  172. teradataml/data/jsons/uaf/17.20/TD_DTW.json +3 -6
  173. teradataml/data/jsons/uaf/17.20/TD_DWT.json +173 -0
  174. teradataml/data/jsons/uaf/17.20/TD_DWT2D.json +160 -0
  175. teradataml/data/jsons/uaf/17.20/TD_FITMETRICS.json +1 -1
  176. teradataml/data/jsons/uaf/17.20/TD_GOLDFELD_QUANDT.json +16 -30
  177. teradataml/data/jsons/uaf/17.20/{TD_HOLT_WINTERS_FORECAST.json → TD_HOLT_WINTERS_FORECASTER.json} +1 -2
  178. teradataml/data/jsons/uaf/17.20/TD_IDFFT2.json +1 -15
  179. teradataml/data/jsons/uaf/17.20/TD_IDWT.json +162 -0
  180. teradataml/data/jsons/uaf/17.20/TD_IDWT2D.json +149 -0
  181. teradataml/data/jsons/uaf/17.20/TD_IQR.json +117 -0
  182. teradataml/data/jsons/uaf/17.20/TD_LINEAR_REGR.json +1 -1
  183. teradataml/data/jsons/uaf/17.20/TD_LINESPEC.json +1 -1
  184. teradataml/data/jsons/uaf/17.20/TD_MAMEAN.json +1 -3
  185. teradataml/data/jsons/uaf/17.20/TD_MATRIX2IMAGE.json +209 -0
  186. teradataml/data/jsons/uaf/17.20/TD_PACF.json +2 -2
  187. teradataml/data/jsons/uaf/17.20/TD_POWERSPEC.json +5 -5
  188. teradataml/data/jsons/uaf/17.20/TD_RESAMPLE.json +48 -28
  189. teradataml/data/jsons/uaf/17.20/TD_SAX.json +208 -0
  190. teradataml/data/jsons/uaf/17.20/TD_SEASONALNORMALIZE.json +12 -6
  191. teradataml/data/jsons/uaf/17.20/TD_SIMPLEEXP.json +0 -1
  192. teradataml/data/jsons/uaf/17.20/TD_TRACKINGOP.json +8 -8
  193. teradataml/data/jsons/uaf/17.20/TD_UNDIFF.json +1 -1
  194. teradataml/data/jsons/uaf/17.20/TD_UNNORMALIZE.json +1 -1
  195. teradataml/data/jsons/uaf/17.20/TD_WINDOWDFFT.json +400 -0
  196. teradataml/data/kmeans_example.json +5 -0
  197. teradataml/data/kmeans_table.csv +10 -0
  198. teradataml/data/load_example_data.py +8 -2
  199. teradataml/data/naivebayestextclassifier_example.json +1 -1
  200. teradataml/data/naivebayestextclassifierpredict_example.json +11 -0
  201. teradataml/data/onehot_encoder_train.csv +4 -0
  202. teradataml/data/openml_example.json +29 -0
  203. teradataml/data/peppers.png +0 -0
  204. teradataml/data/real_values.csv +14 -0
  205. teradataml/data/sax_example.json +8 -0
  206. teradataml/data/scale_attributes.csv +3 -0
  207. teradataml/data/scale_example.json +52 -1
  208. teradataml/data/scale_input_part_sparse.csv +31 -0
  209. teradataml/data/scale_input_partitioned.csv +16 -0
  210. teradataml/data/scale_input_sparse.csv +11 -0
  211. teradataml/data/scale_parameters.csv +3 -0
  212. teradataml/data/scripts/deploy_script.py +21 -2
  213. teradataml/data/scripts/sklearn/sklearn_fit.py +40 -37
  214. teradataml/data/scripts/sklearn/sklearn_fit_predict.py +22 -30
  215. teradataml/data/scripts/sklearn/sklearn_function.template +42 -24
  216. teradataml/data/scripts/sklearn/sklearn_model_selection_split.py +23 -33
  217. teradataml/data/scripts/sklearn/sklearn_neighbors.py +19 -28
  218. teradataml/data/scripts/sklearn/sklearn_score.py +32 -32
  219. teradataml/data/scripts/sklearn/sklearn_transform.py +85 -42
  220. teradataml/data/star_pivot.csv +8 -0
  221. teradataml/data/templates/open_source_ml.json +2 -1
  222. teradataml/data/teradataml_example.json +97 -1
  223. teradataml/data/timestamp_data.csv +4 -0
  224. teradataml/data/titanic_dataset_unpivoted.csv +19 -0
  225. teradataml/data/uaf_example.json +55 -1
  226. teradataml/data/unpivot_example.json +15 -0
  227. teradataml/data/url_data.csv +9 -0
  228. teradataml/data/windowdfft.csv +16 -0
  229. teradataml/data/ztest_example.json +16 -0
  230. teradataml/dataframe/copy_to.py +9 -4
  231. teradataml/dataframe/data_transfer.py +125 -64
  232. teradataml/dataframe/dataframe.py +575 -57
  233. teradataml/dataframe/dataframe_utils.py +47 -9
  234. teradataml/dataframe/fastload.py +273 -90
  235. teradataml/dataframe/functions.py +339 -0
  236. teradataml/dataframe/row.py +160 -0
  237. teradataml/dataframe/setop.py +2 -2
  238. teradataml/dataframe/sql.py +740 -18
  239. teradataml/dataframe/window.py +1 -1
  240. teradataml/dbutils/dbutils.py +324 -18
  241. teradataml/geospatial/geodataframe.py +1 -1
  242. teradataml/geospatial/geodataframecolumn.py +1 -1
  243. teradataml/hyperparameter_tuner/optimizer.py +13 -13
  244. teradataml/lib/aed_0_1.dll +0 -0
  245. teradataml/opensource/sklearn/_sklearn_wrapper.py +254 -122
  246. teradataml/options/__init__.py +16 -5
  247. teradataml/options/configure.py +39 -6
  248. teradataml/options/display.py +2 -2
  249. teradataml/plot/axis.py +4 -4
  250. teradataml/scriptmgmt/UserEnv.py +26 -19
  251. teradataml/scriptmgmt/lls_utils.py +120 -16
  252. teradataml/table_operators/Script.py +4 -5
  253. teradataml/table_operators/TableOperator.py +160 -26
  254. teradataml/table_operators/table_operator_util.py +88 -41
  255. teradataml/table_operators/templates/dataframe_udf.template +63 -0
  256. teradataml/telemetry_utils/__init__.py +0 -0
  257. teradataml/telemetry_utils/queryband.py +52 -0
  258. teradataml/utils/validators.py +41 -3
  259. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.2.dist-info}/METADATA +191 -6
  260. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.2.dist-info}/RECORD +263 -185
  261. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.2.dist-info}/WHEEL +0 -0
  262. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.2.dist-info}/top_level.txt +0 -0
  263. {teradataml-20.0.0.0.dist-info → teradataml-20.0.0.2.dist-info}/zip-safe +0 -0
@@ -0,0 +1,162 @@
1
+ {
2
+ "json_schema_major_version": "1",
3
+ "json_schema_minor_version": "1",
4
+ "json_content_version": "1",
5
+ "function_name": "TD_TFIDF",
6
+ "function_version": "1.0",
7
+ "function_type": "fastpath",
8
+ "function_category": "Feature Engineering Transform",
9
+ "function_alias_name": "TD_TFIDF",
10
+ "function_r_name": "td.tfidf",
11
+ "short_description": "This function is used to take any document set and compute the Term Frequency (TF), Inverse Document Frequency (IDF), and Term Frequency * Inverse Document Frequency (TF-IDF) scores for each term.",
12
+ "long_description": "This function is used to take any document set and compute the Term Frequency (TF), Inverse Document Frequency (IDF), and Term Frequency * Inverse Document Frequency (TF-IDF) scores for each term.",
13
+ "input_tables": [
14
+ {
15
+ "requiredInputKind": [
16
+ "PartitionByAny"
17
+ ],
18
+ "isOrdered": false,
19
+ "partitionByOne": false,
20
+ "name": "InputTable",
21
+ "alternateNames": [],
22
+ "isRequired": true,
23
+ "rDescription": "The table that contains the document id and the term.",
24
+ "description": "The table that contains the document id and the term.",
25
+ "datatype": "TABLE_ALIAS",
26
+ "allowsLists": false,
27
+ "rName": "data",
28
+ "useInR": true,
29
+ "rOrderNum": 1
30
+ }
31
+ ],
32
+ "argument_clauses": [
33
+ {
34
+ "targetTable": [
35
+ "InputTable"
36
+ ],
37
+ "checkDuplicate": true,
38
+ "allowedTypes": [],
39
+ "allowedTypeGroups": [
40
+ "INTEGER"
41
+ ],
42
+ "requiredLength": 1,
43
+ "matchLengthOfArgument": "",
44
+ "allowPadding": true,
45
+ "name": "DocIdColumn",
46
+ "alternateNames": [],
47
+ "isRequired": true,
48
+ "rDescription": "Specifies the name of the input table column that contains the document identifier.",
49
+ "description": "Specifies the name of the input table column that contains the document identifier.",
50
+ "datatype": "COLUMN_NAMES",
51
+ "allowsLists": false,
52
+ "rName": "doc.id.column",
53
+ "useInR": true,
54
+ "rOrderNum": 2
55
+ },
56
+ {
57
+ "targetTable": [
58
+ "InputTable"
59
+ ],
60
+ "checkDuplicate": true,
61
+ "allowedTypes": [],
62
+ "allowedTypeGroups": [
63
+ "STRING"
64
+ ],
65
+ "requiredLength": 1,
66
+ "matchLengthOfArgument": "",
67
+ "allowPadding": true,
68
+ "name": "TokenColumn",
69
+ "alternateNames": [],
70
+ "isRequired": true,
71
+ "rDescription": "Specifies the name of the input table column that contains the tokens.",
72
+ "description": "Specifies the name of the input table column that contains the tokens.",
73
+ "datatype": "COLUMN_NAMES",
74
+ "allowsLists": false,
75
+ "rName": "token.column",
76
+ "useInR": true,
77
+ "rOrderNum": 3
78
+ },
79
+ {
80
+ "permittedValues": [
81
+ "BOOL",
82
+ "COUNT",
83
+ "NORMAL",
84
+ "LOG",
85
+ "AUGMENT"
86
+ ],
87
+ "defaultValue": "NORMAL",
88
+ "isOutputColumn": false,
89
+ "name": "TFNormalization",
90
+ "alternateNames": [],
91
+ "isRequired": false,
92
+ "rDescription": "Specifies the normalization method for calculating the term frequency (TF). Default: 'NORMAL'.",
93
+ "description": "Specifies the normalization method for calculating the term frequency (TF). Default: 'NORMAL'.",
94
+ "datatype": "STRING",
95
+ "allowsLists": false,
96
+ "rName": "tf.normalization",
97
+ "useInR": true,
98
+ "rOrderNum": 4
99
+ },
100
+ {
101
+ "permittedValues": [
102
+ "UNARY",
103
+ "LOG",
104
+ "LOGNORM",
105
+ "SMOOTH"
106
+ ],
107
+ "defaultValue": "LOG",
108
+ "isOutputColumn": false,
109
+ "name": "IDFNormalization",
110
+ "alternateNames": [],
111
+ "isRequired": false,
112
+ "rDescription": "Specifies the normalization method for calculating the inverse document frequency (IDF). Default: 'LOG'.",
113
+ "description": "Specifies the normalization method for calculating the inverse document frequency (IDF). Default: 'LOG'.",
114
+ "datatype": "STRING",
115
+ "allowsLists": false,
116
+ "rName": "idf.normalization",
117
+ "useInR": true,
118
+ "rOrderNum": 5
119
+ },
120
+ {
121
+ "permittedValues": [
122
+ "L2",
123
+ "L1",
124
+ "NONE"
125
+ ],
126
+ "defaultValue": "NONE",
127
+ "isOutputColumn": false,
128
+ "name": "Regularization",
129
+ "alternateNames": [],
130
+ "isRequired": false,
131
+ "rDescription": "Specifies the regularization method for calculating the TF-IDF score. Default: 'NONE'.",
132
+ "description": "Specifies the regularization method for calculating the TF-IDF score. Default: 'NONE'.",
133
+ "datatype": "STRING",
134
+ "allowsLists": false,
135
+ "rName": "regularization",
136
+ "useInR": true,
137
+ "rOrderNum": 6
138
+ },
139
+ {
140
+ "targetTable": [
141
+ "InputTable"
142
+ ],
143
+ "checkDuplicate": true,
144
+ "allowedTypes": [],
145
+ "allowedTypeGroups": [
146
+ "ALL"
147
+ ],
148
+ "matchLengthOfArgument": "",
149
+ "allowPadding": true,
150
+ "name": "Accumulate",
151
+ "alternateNames": [],
152
+ "isRequired": false,
153
+ "rDescription": "Specifies the names of the input table columns to copy to the output table.",
154
+ "description": "Specifies the names of the input table columns to copy to the output table.",
155
+ "datatype": "COLUMNS",
156
+ "allowsLists": true,
157
+ "rName": "accumulate",
158
+ "useInR": true,
159
+ "rOrderNum": 7
160
+ }
161
+ ]
162
+ }
@@ -0,0 +1,235 @@
1
+ {
2
+ "json_schema_major_version": "1",
3
+ "json_schema_minor_version": "1",
4
+ "json_content_version": "1",
5
+ "function_name": "TD_Unpivoting",
6
+ "function_version": "1.0",
7
+ "function_alias_name": "TD_Unpivoting",
8
+ "function_type": "fastpath",
9
+ "function_category": "Feature Engineering Transform",
10
+ "function_r_name": "aa.td.unpivoting",
11
+ "short_description": "This function is used to unpivot the data i.e. change the data from dense format to sparse format.",
12
+ "long_description": "This function is used to unpivot the data i.e. change the data from dense format to sparse format.",
13
+ "input_tables": [
14
+ {
15
+ "requiredInputKind": [
16
+ "PartitionByAny"
17
+ ],
18
+ "isOrdered": false,
19
+ "partitionByOne": false,
20
+ "name": "InputTable",
21
+ "alternateNames": [],
22
+ "isRequired": true,
23
+ "rDescription": "Specifies the table containing the input data to be unpivoted.",
24
+ "description": "Specifies the table containing the input data to be unpivoted.",
25
+ "datatype": "TABLE_ALIAS",
26
+ "allowsLists": false,
27
+ "rName": "data",
28
+ "useInR": true,
29
+ "rOrderNum": 1
30
+ }
31
+ ],
32
+ "argument_clauses": [
33
+ {
34
+ "targetTable": [
35
+ "InputTable"
36
+ ],
37
+ "checkDuplicate": true,
38
+ "allowedTypes": [],
39
+ "allowedTypeGroups": [
40
+ "ALL"
41
+ ],
42
+ "matchLengthOfArgument": "",
43
+ "allowPadding": false,
44
+ "name": "IDColumn",
45
+ "alternateNames": [],
46
+ "isRequired": true,
47
+ "rDescription": "Specify the column which contains the input data identifier.",
48
+ "description": "Specify the column which contains the input data identifier.",
49
+ "datatype": "COLUMNS",
50
+ "allowsLists": false,
51
+ "rName": "id.column",
52
+ "useInR": true,
53
+ "rOrderNum": 2
54
+ },
55
+ {
56
+ "targetTable": [
57
+ "InputTable"
58
+ ],
59
+ "checkDuplicate": true,
60
+ "allowedTypes": [],
61
+ "allowedTypeGroups": [
62
+ "ALL"
63
+ ],
64
+ "matchLengthOfArgument": "",
65
+ "allowPadding": false,
66
+ "name": "TargetColumns",
67
+ "alternateNames": [],
68
+ "isRequired": true,
69
+ "rDescription": "Specify the columns from the input table which contains the data for unpivoting.",
70
+ "description": "Specify the columns from the input table which contains the data for unpivoting.",
71
+ "datatype": "COLUMNS",
72
+ "allowsLists": true,
73
+ "rName": "target.columns",
74
+ "useInR": true,
75
+ "rOrderNum": 3
76
+ },
77
+ {
78
+ "permittedValues": [],
79
+ "isOutputColumn": false,
80
+ "matchLengthOfArgument": "",
81
+ "allowPadding": false,
82
+ "name": "AttributeAliasList",
83
+ "alternateNames": [],
84
+ "isRequired": false,
85
+ "rDescription": "Specify alternate names for the values in the AttributeName output column.",
86
+ "description": "Specify alternate names for the values in the AttributeName output column.",
87
+ "datatype": "STRING",
88
+ "allowsLists": true,
89
+ "rName": "alias.names",
90
+ "useInR": true,
91
+ "rOrderNum": 4
92
+ },
93
+ {
94
+ "permittedValues": [],
95
+ "isOutputColumn": true,
96
+ "matchLengthOfArgument": "",
97
+ "allowPadding": false,
98
+ "defaultValue": "AttributeName",
99
+ "name": "AttributeColName",
100
+ "alternateNames": [],
101
+ "isRequired": false,
102
+ "rDescription": "Specify output column name for AttributeName column.",
103
+ "description": "Specify output column name for AttributeName column.",
104
+ "datatype": "STRING",
105
+ "allowsLists": false,
106
+ "rName": "attribute.column",
107
+ "useInR": true,
108
+ "rOrderNum": 5
109
+ },
110
+ {
111
+ "permittedValues": [],
112
+ "isOutputColumn": true,
113
+ "matchLengthOfArgument": "",
114
+ "allowPadding": false,
115
+ "defaultValue": "AttributeValue",
116
+ "name": "ValueColName",
117
+ "alternateNames": [],
118
+ "isRequired": false,
119
+ "rDescription": "Specify output column name for AttributeValue column.",
120
+ "description": "Specify output column name for AttributeValue column.",
121
+ "datatype": "STRING",
122
+ "allowsLists": false,
123
+ "rName": "value.column",
124
+ "useInR": true,
125
+ "rOrderNum": 6
126
+ },
127
+ {
128
+ "targetTable": [
129
+ "InputTable"
130
+ ],
131
+ "checkDuplicate": true,
132
+ "allowedTypes": [],
133
+ "allowedTypeGroups": [
134
+ "ALL"
135
+ ],
136
+ "matchLengthOfArgument": "",
137
+ "allowPadding": false,
138
+ "name": "Accumulate",
139
+ "alternateNames": [],
140
+ "isRequired": false,
141
+ "rDescription": "Specifies the input table columns to copy to the output table. By default, the function copies no input table columns to the output table.",
142
+ "description": "Specifies the input table columns to copy to the output table. By default, the function copies no input table columns to the output table.",
143
+ "datatype": "COLUMNS",
144
+ "allowsLists": true,
145
+ "rName": "accumulate",
146
+ "useInR": true,
147
+ "rOrderNum": 7
148
+ },
149
+ {
150
+ "permittedValues": [],
151
+ "isOutputColumn": false,
152
+ "matchLengthOfArgument": "",
153
+ "allowPadding": false,
154
+ "defaultValue": false,
155
+ "name": "IncludeNulls",
156
+ "alternateNames": [],
157
+ "isRequired": false,
158
+ "rDescription": "Specify whether or not to include nulls in the transformation.",
159
+ "description": "Specify whether or not to include nulls in the transformation.",
160
+ "datatype": "BOOLEAN",
161
+ "allowsLists": false,
162
+ "rName": "include.nulls",
163
+ "useInR": true,
164
+ "rOrderNum": 8
165
+ },
166
+ {
167
+ "permittedValues": [],
168
+ "isOutputColumn": false,
169
+ "matchLengthOfArgument": "",
170
+ "allowPadding": false,
171
+ "defaultValue": false,
172
+ "name": "InputTypes",
173
+ "alternateNames": [],
174
+ "isRequired": false,
175
+ "rDescription": "Specify true, if instead of one column for all attribute values, need multiple columns corresponding to data type groups.",
176
+ "description": "Specify true, if instead of one column for all attribute values, need multiple columns corresponding to data type groups.",
177
+ "datatype": "BOOLEAN",
178
+ "allowsLists": false,
179
+ "rName": "input.types",
180
+ "useInR": true,
181
+ "rOrderNum": 9
182
+ },
183
+ {
184
+ "permittedValues": [],
185
+ "isOutputColumn": false,
186
+ "matchLengthOfArgument": "",
187
+ "allowPadding": false,
188
+ "defaultValue": false,
189
+ "name": "OutputVarchar",
190
+ "alternateNames": [],
191
+ "isRequired": false,
192
+ "rDescription": "Specify true if there is a need to output the AttributeValue column in varchar format irrespective of it's data type.",
193
+ "description": "Specify true if there is a need to output the AttributeValue column in varchar format irrespective of it's data type.",
194
+ "datatype": "BOOLEAN",
195
+ "allowsLists": false,
196
+ "rName": "output.varchar",
197
+ "useInR": true,
198
+ "rOrderNum": 10
199
+ },
200
+ {
201
+ "permittedValues": [],
202
+ "isOutputColumn": false,
203
+ "matchLengthOfArgument": "",
204
+ "allowPadding": false,
205
+ "defaultValue": false,
206
+ "name": "IndexedAttribute",
207
+ "alternateNames": [],
208
+ "isRequired": false,
209
+ "rDescription": "Specify true if there is a need to output the column indexes instead of column names in AttributeName column",
210
+ "description": "Specify true if there is a need to output the column indexes instead of column names in AttributeName column",
211
+ "datatype": "BOOLEAN",
212
+ "allowsLists": false,
213
+ "rName": "indexed.attribute",
214
+ "useInR": true,
215
+ "rOrderNum": 11
216
+ },
217
+ {
218
+ "permittedValues": [],
219
+ "isOutputColumn": false,
220
+ "matchLengthOfArgument": "",
221
+ "allowPadding": false,
222
+ "defaultValue": false,
223
+ "name": "IncludeDataTypes",
224
+ "alternateNames": [],
225
+ "isRequired": false,
226
+ "rDescription": "Specify true to output the original data type name.",
227
+ "description": "Specify true to output the original data type name.",
228
+ "datatype": "BOOLEAN",
229
+ "allowsLists": false,
230
+ "rName": "include.datatypes",
231
+ "useInR": true,
232
+ "rOrderNum": 12
233
+ }
234
+ ]
235
+ }
@@ -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
+ }
@@ -79,7 +79,7 @@
79
79
  "lowerBoundType": "EXCLUSIVE",
80
80
  "upperBoundType": "INCLUSIVE",
81
81
  "allowNaN": false,
82
- "name": "NumBoostedTrees",
82
+ "name": "NumParallelTrees",
83
83
  "alternateNames": [],
84
84
  "isRequired": false,
85
85
  "defaultValue": 1000,
@@ -97,10 +97,10 @@
97
97
  "lowerBoundType": "EXCLUSIVE",
98
98
  "upperBoundType": "INCLUSIVE",
99
99
  "allowNaN": false,
100
- "name": "IterNum",
100
+ "name": "NumBoostRounds",
101
101
  "alternateNames": [],
102
102
  "isRequired": false,
103
- "defaultValue": 3,
103
+ "defaultValue": 10,
104
104
  "rDescription": "Specify number of iterations within a boosted trees to be loaded from model table",
105
105
  "description": "Specify number of iterations within a boosted trees to be loaded from model table",
106
106
  "datatype": "NUMERIC",
@@ -177,6 +177,19 @@
177
177
  "rName": "output.responses",
178
178
  "useInR": true,
179
179
  "rOrderNum": 9
180
+ },
181
+ {
182
+ "defaultValue": false,
183
+ "name": "Detailed",
184
+ "alternateNames": [],
185
+ "isRequired": false,
186
+ "rDescription": "Specifies whether to output detailed information of each prediction.",
187
+ "description": "Specifies whether to output detailed information of each prediction.",
188
+ "datatype": "BOOLEAN",
189
+ "allowsLists": false,
190
+ "rName": "detailed",
191
+ "useInR": true,
192
+ "rOrderNum": 10
180
193
  }
181
194
  ]
182
- }
195
+ }