Hide keyboard shortcuts

Hot-keys on this page

r m x p   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

# 

# Licensed to the Apache Software Foundation (ASF) under one or more 

# contributor license agreements. See the NOTICE file distributed with 

# this work for additional information regarding copyright ownership. 

# The ASF licenses this file to You under the Apache License, Version 2.0 

# (the "License"); you may not use this file except in compliance with 

# the License. You may obtain a copy of the License at 

# 

# http://www.apache.org/licenses/LICENSE-2.0 

# 

# Unless required by applicable law or agreed to in writing, software 

# distributed under the License is distributed on an "AS IS" BASIS, 

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 

# See the License for the specific language governing permissions and 

# limitations under the License. 

# 

 

# DO NOT MODIFY THIS FILE! It was generated by _shared_params_code_gen.py. 

 

from pyspark.ml.param import * 

 

 

class HasMaxIter(Params): 

""" 

Mixin for param maxIter: max number of iterations (>= 0). 

""" 

 

maxIter = Param(Params._dummy(), "maxIter", "max number of iterations (>= 0).", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasMaxIter, self).__init__() 

 

def getMaxIter(self): 

""" 

Gets the value of maxIter or its default value. 

""" 

return self.getOrDefault(self.maxIter) 

 

 

class HasRegParam(Params): 

""" 

Mixin for param regParam: regularization parameter (>= 0). 

""" 

 

regParam = Param(Params._dummy(), "regParam", "regularization parameter (>= 0).", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasRegParam, self).__init__() 

 

def getRegParam(self): 

""" 

Gets the value of regParam or its default value. 

""" 

return self.getOrDefault(self.regParam) 

 

 

class HasFeaturesCol(Params): 

""" 

Mixin for param featuresCol: features column name. 

""" 

 

featuresCol = Param(Params._dummy(), "featuresCol", "features column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasFeaturesCol, self).__init__() 

self._setDefault(featuresCol='features') 

 

def getFeaturesCol(self): 

""" 

Gets the value of featuresCol or its default value. 

""" 

return self.getOrDefault(self.featuresCol) 

 

 

class HasLabelCol(Params): 

""" 

Mixin for param labelCol: label column name. 

""" 

 

labelCol = Param(Params._dummy(), "labelCol", "label column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasLabelCol, self).__init__() 

self._setDefault(labelCol='label') 

 

def getLabelCol(self): 

""" 

Gets the value of labelCol or its default value. 

""" 

return self.getOrDefault(self.labelCol) 

 

 

class HasPredictionCol(Params): 

""" 

Mixin for param predictionCol: prediction column name. 

""" 

 

predictionCol = Param(Params._dummy(), "predictionCol", "prediction column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasPredictionCol, self).__init__() 

self._setDefault(predictionCol='prediction') 

 

def getPredictionCol(self): 

""" 

Gets the value of predictionCol or its default value. 

""" 

return self.getOrDefault(self.predictionCol) 

 

 

class HasProbabilityCol(Params): 

""" 

Mixin for param probabilityCol: Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities. 

""" 

 

probabilityCol = Param(Params._dummy(), "probabilityCol", "Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasProbabilityCol, self).__init__() 

self._setDefault(probabilityCol='probability') 

 

def getProbabilityCol(self): 

""" 

Gets the value of probabilityCol or its default value. 

""" 

return self.getOrDefault(self.probabilityCol) 

 

 

class HasRawPredictionCol(Params): 

""" 

Mixin for param rawPredictionCol: raw prediction (a.k.a. confidence) column name. 

""" 

 

rawPredictionCol = Param(Params._dummy(), "rawPredictionCol", "raw prediction (a.k.a. confidence) column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasRawPredictionCol, self).__init__() 

self._setDefault(rawPredictionCol='rawPrediction') 

 

def getRawPredictionCol(self): 

""" 

Gets the value of rawPredictionCol or its default value. 

""" 

return self.getOrDefault(self.rawPredictionCol) 

 

 

class HasInputCol(Params): 

""" 

Mixin for param inputCol: input column name. 

""" 

 

inputCol = Param(Params._dummy(), "inputCol", "input column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasInputCol, self).__init__() 

 

def getInputCol(self): 

""" 

Gets the value of inputCol or its default value. 

""" 

return self.getOrDefault(self.inputCol) 

 

 

class HasInputCols(Params): 

""" 

Mixin for param inputCols: input column names. 

""" 

 

inputCols = Param(Params._dummy(), "inputCols", "input column names.", typeConverter=TypeConverters.toListString) 

 

def __init__(self): 

super(HasInputCols, self).__init__() 

 

def getInputCols(self): 

""" 

Gets the value of inputCols or its default value. 

""" 

return self.getOrDefault(self.inputCols) 

 

 

class HasOutputCol(Params): 

""" 

Mixin for param outputCol: output column name. 

""" 

 

outputCol = Param(Params._dummy(), "outputCol", "output column name.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasOutputCol, self).__init__() 

self._setDefault(outputCol=self.uid + '__output') 

 

def getOutputCol(self): 

""" 

Gets the value of outputCol or its default value. 

""" 

return self.getOrDefault(self.outputCol) 

 

 

class HasOutputCols(Params): 

""" 

Mixin for param outputCols: output column names. 

""" 

 

outputCols = Param(Params._dummy(), "outputCols", "output column names.", typeConverter=TypeConverters.toListString) 

 

def __init__(self): 

super(HasOutputCols, self).__init__() 

 

def getOutputCols(self): 

""" 

Gets the value of outputCols or its default value. 

""" 

return self.getOrDefault(self.outputCols) 

 

 

class HasNumFeatures(Params): 

""" 

Mixin for param numFeatures: Number of features. Should be greater than 0. 

""" 

 

numFeatures = Param(Params._dummy(), "numFeatures", "Number of features. Should be greater than 0.", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasNumFeatures, self).__init__() 

self._setDefault(numFeatures=262144) 

 

def getNumFeatures(self): 

""" 

Gets the value of numFeatures or its default value. 

""" 

return self.getOrDefault(self.numFeatures) 

 

 

class HasCheckpointInterval(Params): 

""" 

Mixin for param checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext. 

""" 

 

checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext.", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasCheckpointInterval, self).__init__() 

 

def getCheckpointInterval(self): 

""" 

Gets the value of checkpointInterval or its default value. 

""" 

return self.getOrDefault(self.checkpointInterval) 

 

 

class HasSeed(Params): 

""" 

Mixin for param seed: random seed. 

""" 

 

seed = Param(Params._dummy(), "seed", "random seed.", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasSeed, self).__init__() 

self._setDefault(seed=hash(type(self).__name__)) 

 

def getSeed(self): 

""" 

Gets the value of seed or its default value. 

""" 

return self.getOrDefault(self.seed) 

 

 

class HasTol(Params): 

""" 

Mixin for param tol: the convergence tolerance for iterative algorithms (>= 0). 

""" 

 

tol = Param(Params._dummy(), "tol", "the convergence tolerance for iterative algorithms (>= 0).", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasTol, self).__init__() 

 

def getTol(self): 

""" 

Gets the value of tol or its default value. 

""" 

return self.getOrDefault(self.tol) 

 

 

class HasRelativeError(Params): 

""" 

Mixin for param relativeError: the relative target precision for the approximate quantile algorithm. Must be in the range [0, 1] 

""" 

 

relativeError = Param(Params._dummy(), "relativeError", "the relative target precision for the approximate quantile algorithm. Must be in the range [0, 1]", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasRelativeError, self).__init__() 

self._setDefault(relativeError=0.001) 

 

def getRelativeError(self): 

""" 

Gets the value of relativeError or its default value. 

""" 

return self.getOrDefault(self.relativeError) 

 

 

class HasStepSize(Params): 

""" 

Mixin for param stepSize: Step size to be used for each iteration of optimization (>= 0). 

""" 

 

stepSize = Param(Params._dummy(), "stepSize", "Step size to be used for each iteration of optimization (>= 0).", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasStepSize, self).__init__() 

 

def getStepSize(self): 

""" 

Gets the value of stepSize or its default value. 

""" 

return self.getOrDefault(self.stepSize) 

 

 

class HasHandleInvalid(Params): 

""" 

Mixin for param handleInvalid: how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later. 

""" 

 

handleInvalid = Param(Params._dummy(), "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasHandleInvalid, self).__init__() 

 

def getHandleInvalid(self): 

""" 

Gets the value of handleInvalid or its default value. 

""" 

return self.getOrDefault(self.handleInvalid) 

 

 

class HasElasticNetParam(Params): 

""" 

Mixin for param elasticNetParam: the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty. 

""" 

 

elasticNetParam = Param(Params._dummy(), "elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasElasticNetParam, self).__init__() 

self._setDefault(elasticNetParam=0.0) 

 

def getElasticNetParam(self): 

""" 

Gets the value of elasticNetParam or its default value. 

""" 

return self.getOrDefault(self.elasticNetParam) 

 

 

class HasFitIntercept(Params): 

""" 

Mixin for param fitIntercept: whether to fit an intercept term. 

""" 

 

fitIntercept = Param(Params._dummy(), "fitIntercept", "whether to fit an intercept term.", typeConverter=TypeConverters.toBoolean) 

 

def __init__(self): 

super(HasFitIntercept, self).__init__() 

self._setDefault(fitIntercept=True) 

 

def getFitIntercept(self): 

""" 

Gets the value of fitIntercept or its default value. 

""" 

return self.getOrDefault(self.fitIntercept) 

 

 

class HasStandardization(Params): 

""" 

Mixin for param standardization: whether to standardize the training features before fitting the model. 

""" 

 

standardization = Param(Params._dummy(), "standardization", "whether to standardize the training features before fitting the model.", typeConverter=TypeConverters.toBoolean) 

 

def __init__(self): 

super(HasStandardization, self).__init__() 

self._setDefault(standardization=True) 

 

def getStandardization(self): 

""" 

Gets the value of standardization or its default value. 

""" 

return self.getOrDefault(self.standardization) 

 

 

class HasThresholds(Params): 

""" 

Mixin for param thresholds: Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0, excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold. 

""" 

 

thresholds = Param(Params._dummy(), "thresholds", "Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0, excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.", typeConverter=TypeConverters.toListFloat) 

 

def __init__(self): 

super(HasThresholds, self).__init__() 

 

def getThresholds(self): 

""" 

Gets the value of thresholds or its default value. 

""" 

return self.getOrDefault(self.thresholds) 

 

 

class HasThreshold(Params): 

""" 

Mixin for param threshold: threshold in binary classification prediction, in range [0, 1] 

""" 

 

threshold = Param(Params._dummy(), "threshold", "threshold in binary classification prediction, in range [0, 1]", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasThreshold, self).__init__() 

self._setDefault(threshold=0.5) 

 

def getThreshold(self): 

""" 

Gets the value of threshold or its default value. 

""" 

return self.getOrDefault(self.threshold) 

 

 

class HasWeightCol(Params): 

""" 

Mixin for param weightCol: weight column name. If this is not set or empty, we treat all instance weights as 1.0. 

""" 

 

weightCol = Param(Params._dummy(), "weightCol", "weight column name. If this is not set or empty, we treat all instance weights as 1.0.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasWeightCol, self).__init__() 

 

def getWeightCol(self): 

""" 

Gets the value of weightCol or its default value. 

""" 

return self.getOrDefault(self.weightCol) 

 

 

class HasSolver(Params): 

""" 

Mixin for param solver: the solver algorithm for optimization. If this is not set or empty, default value is 'auto'. 

""" 

 

solver = Param(Params._dummy(), "solver", "the solver algorithm for optimization. If this is not set or empty, default value is 'auto'.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasSolver, self).__init__() 

self._setDefault(solver='auto') 

 

def getSolver(self): 

""" 

Gets the value of solver or its default value. 

""" 

return self.getOrDefault(self.solver) 

 

 

class HasVarianceCol(Params): 

""" 

Mixin for param varianceCol: column name for the biased sample variance of prediction. 

""" 

 

varianceCol = Param(Params._dummy(), "varianceCol", "column name for the biased sample variance of prediction.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasVarianceCol, self).__init__() 

 

def getVarianceCol(self): 

""" 

Gets the value of varianceCol or its default value. 

""" 

return self.getOrDefault(self.varianceCol) 

 

 

class HasAggregationDepth(Params): 

""" 

Mixin for param aggregationDepth: suggested depth for treeAggregate (>= 2). 

""" 

 

aggregationDepth = Param(Params._dummy(), "aggregationDepth", "suggested depth for treeAggregate (>= 2).", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasAggregationDepth, self).__init__() 

self._setDefault(aggregationDepth=2) 

 

def getAggregationDepth(self): 

""" 

Gets the value of aggregationDepth or its default value. 

""" 

return self.getOrDefault(self.aggregationDepth) 

 

 

class HasParallelism(Params): 

""" 

Mixin for param parallelism: the number of threads to use when running parallel algorithms (>= 1). 

""" 

 

parallelism = Param(Params._dummy(), "parallelism", "the number of threads to use when running parallel algorithms (>= 1).", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasParallelism, self).__init__() 

self._setDefault(parallelism=1) 

 

def getParallelism(self): 

""" 

Gets the value of parallelism or its default value. 

""" 

return self.getOrDefault(self.parallelism) 

 

 

class HasCollectSubModels(Params): 

""" 

Mixin for param collectSubModels: Param for whether to collect a list of sub-models trained during tuning. If set to false, then only the single best sub-model will be available after fitting. If set to true, then all sub-models will be available. Warning: For large models, collecting all sub-models can cause OOMs on the Spark driver. 

""" 

 

collectSubModels = Param(Params._dummy(), "collectSubModels", "Param for whether to collect a list of sub-models trained during tuning. If set to false, then only the single best sub-model will be available after fitting. If set to true, then all sub-models will be available. Warning: For large models, collecting all sub-models can cause OOMs on the Spark driver.", typeConverter=TypeConverters.toBoolean) 

 

def __init__(self): 

super(HasCollectSubModels, self).__init__() 

self._setDefault(collectSubModels=False) 

 

def getCollectSubModels(self): 

""" 

Gets the value of collectSubModels or its default value. 

""" 

return self.getOrDefault(self.collectSubModels) 

 

 

class HasLoss(Params): 

""" 

Mixin for param loss: the loss function to be optimized. 

""" 

 

loss = Param(Params._dummy(), "loss", "the loss function to be optimized.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasLoss, self).__init__() 

 

def getLoss(self): 

""" 

Gets the value of loss or its default value. 

""" 

return self.getOrDefault(self.loss) 

 

 

class HasDistanceMeasure(Params): 

""" 

Mixin for param distanceMeasure: the distance measure. Supported options: 'euclidean' and 'cosine'. 

""" 

 

distanceMeasure = Param(Params._dummy(), "distanceMeasure", "the distance measure. Supported options: 'euclidean' and 'cosine'.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasDistanceMeasure, self).__init__() 

self._setDefault(distanceMeasure='euclidean') 

 

def getDistanceMeasure(self): 

""" 

Gets the value of distanceMeasure or its default value. 

""" 

return self.getOrDefault(self.distanceMeasure) 

 

 

class HasValidationIndicatorCol(Params): 

""" 

Mixin for param validationIndicatorCol: name of the column that indicates whether each row is for training or for validation. False indicates training; true indicates validation. 

""" 

 

validationIndicatorCol = Param(Params._dummy(), "validationIndicatorCol", "name of the column that indicates whether each row is for training or for validation. False indicates training; true indicates validation.", typeConverter=TypeConverters.toString) 

 

def __init__(self): 

super(HasValidationIndicatorCol, self).__init__() 

 

def getValidationIndicatorCol(self): 

""" 

Gets the value of validationIndicatorCol or its default value. 

""" 

return self.getOrDefault(self.validationIndicatorCol) 

 

 

class HasBlockSize(Params): 

""" 

Mixin for param blockSize: block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data. 

""" 

 

blockSize = Param(Params._dummy(), "blockSize", "block size for stacking input data in matrices. Data is stacked within partitions. If block size is more than remaining data in a partition then it is adjusted to the size of this data.", typeConverter=TypeConverters.toInt) 

 

def __init__(self): 

super(HasBlockSize, self).__init__() 

 

def getBlockSize(self): 

""" 

Gets the value of blockSize or its default value. 

""" 

return self.getOrDefault(self.blockSize) 

 

 

class HasMaxBlockSizeInMB(Params): 

""" 

Mixin for param maxBlockSizeInMB: maximum memory in MB for stacking input data into blocks. Data is stacked within partitions. If more than remaining data size in a partition then it is adjusted to the data size. Default 0.0 represents choosing optimal value, depends on specific algorithm. Must be >= 0. 

""" 

 

maxBlockSizeInMB = Param(Params._dummy(), "maxBlockSizeInMB", "maximum memory in MB for stacking input data into blocks. Data is stacked within partitions. If more than remaining data size in a partition then it is adjusted to the data size. Default 0.0 represents choosing optimal value, depends on specific algorithm. Must be >= 0.", typeConverter=TypeConverters.toFloat) 

 

def __init__(self): 

super(HasMaxBlockSizeInMB, self).__init__() 

self._setDefault(maxBlockSizeInMB=0.0) 

 

def getMaxBlockSizeInMB(self): 

""" 

Gets the value of maxBlockSizeInMB or its default value. 

""" 

return self.getOrDefault(self.maxBlockSizeInMB)