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
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
|
#
# 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.
#
# mllib.R: Provides methods for MLlib integration
# Integration with R's standard functions.
# Most of MLlib's argorithms are provided in two flavours:
# - a specialization of the default R methods (glm). These methods try to respect
# the inputs and the outputs of R's method to the largest extent, but some small differences
# may exist.
# - a set of methods that reflect the arguments of the other languages supported by Spark. These
# methods are prefixed with the `spark.` prefix: spark.glm, spark.kmeans, etc.
#' S4 class that represents a generalized linear model
#'
#' @param jobj a Java object reference to the backing Scala GeneralizedLinearRegressionWrapper
#' @export
#' @note GeneralizedLinearRegressionModel since 2.0.0
setClass("GeneralizedLinearRegressionModel", representation(jobj = "jobj"))
#' S4 class that represents a NaiveBayesModel
#'
#' @param jobj a Java object reference to the backing Scala NaiveBayesWrapper
#' @export
#' @note NaiveBayesModel since 2.0.0
setClass("NaiveBayesModel", representation(jobj = "jobj"))
#' S4 class that represents a AFTSurvivalRegressionModel
#'
#' @param jobj a Java object reference to the backing Scala AFTSurvivalRegressionWrapper
#' @export
#' @note AFTSurvivalRegressionModel since 2.0.0
setClass("AFTSurvivalRegressionModel", representation(jobj = "jobj"))
#' S4 class that represents a KMeansModel
#'
#' @param jobj a Java object reference to the backing Scala KMeansModel
#' @export
#' @note KMeansModel since 2.0.0
setClass("KMeansModel", representation(jobj = "jobj"))
#' S4 class that represents an IsotonicRegressionModel
#'
#' @param jobj a Java object reference to the backing Scala IsotonicRegressionModel
#' @export
#' @note IsotonicRegressionModel since 2.1.0
setClass("IsotonicRegressionModel", representation(jobj = "jobj"))
#' Saves the MLlib model to the input path
#'
#' Saves the MLlib model to the input path. For more information, see the specific
#' MLlib model below.
#' @rdname write.ml
#' @name write.ml
#' @export
#' @seealso \link{spark.glm}, \link{glm}
#' @seealso \link{spark.kmeans}, \link{spark.naiveBayes}, \link{spark.survreg}
#' @seealso \link{spark.isoreg}
#' @seealso \link{read.ml}
NULL
#' Makes predictions from a MLlib model
#'
#' Makes predictions from a MLlib model. For more information, see the specific
#' MLlib model below.
#' @rdname predict
#' @name predict
#' @export
#' @seealso \link{spark.glm}, \link{glm}
#' @seealso \link{spark.kmeans}, \link{spark.naiveBayes}, \link{spark.survreg}
#' @seealso \link{spark.isoreg}
NULL
#' Generalized Linear Models
#'
#' Fits generalized linear model against a Spark DataFrame.
#' Users can call \code{summary} to print a summary of the fitted model, \code{predict} to make
#' predictions on new data, and \code{write.ml}/\code{read.ml} to save/load fitted models.
#'
#' @param data SparkDataFrame for training.
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', '.', ':', '+', and '-'.
#' @param family A description of the error distribution and link function to be used in the model.
#' This can be a character string naming a family function, a family function or
#' the result of a call to a family function. Refer R family at
#' \url{https://stat.ethz.ch/R-manual/R-devel/library/stats/html/family.html}.
#' @param tol Positive convergence tolerance of iterations.
#' @param maxIter Integer giving the maximal number of IRLS iterations.
#' @param weightCol The weight column name. If this is not set or NULL, we treat all instance
#' weights as 1.0.
#' @aliases spark.glm,SparkDataFrame,formula-method
#' @return \code{spark.glm} returns a fitted generalized linear model
#' @rdname spark.glm
#' @name spark.glm
#' @export
#' @examples
#' \dontrun{
#' sparkR.session()
#' data(iris)
#' df <- createDataFrame(iris)
#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family = "gaussian")
#' summary(model)
#'
#' # fitted values on training data
#' fitted <- predict(model, df)
#' head(select(fitted, "Sepal_Length", "prediction"))
#'
#' # save fitted model to input path
#' path <- "path/to/model"
#' write.ml(model, path)
#'
#' # can also read back the saved model and print
#' savedModel <- read.ml(path)
#' summary(savedModel)
#' }
#' @note spark.glm since 2.0.0
#' @seealso \link{glm}, \link{read.ml}
setMethod("spark.glm", signature(data = "SparkDataFrame", formula = "formula"),
function(data, formula, family = gaussian, tol = 1e-6, maxIter = 25, weightCol = NULL) {
if (is.character(family)) {
family <- get(family, mode = "function", envir = parent.frame())
}
if (is.function(family)) {
family <- family()
}
if (is.null(family$family)) {
print(family)
stop("'family' not recognized")
}
formula <- paste(deparse(formula), collapse = "")
if (is.null(weightCol)) {
weightCol <- ""
}
jobj <- callJStatic("org.apache.spark.ml.r.GeneralizedLinearRegressionWrapper",
"fit", formula, data@sdf, family$family, family$link,
tol, as.integer(maxIter), as.character(weightCol))
return(new("GeneralizedLinearRegressionModel", jobj = jobj))
})
#' Generalized Linear Models (R-compliant)
#'
#' Fits a generalized linear model, similarly to R's glm().
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', '.', ':', '+', and '-'.
#' @param data SparkDataFrame for training.
#' @param family A description of the error distribution and link function to be used in the model.
#' This can be a character string naming a family function, a family function or
#' the result of a call to a family function. Refer R family at
#' \url{https://stat.ethz.ch/R-manual/R-devel/library/stats/html/family.html}.
#' @param epsilon Positive convergence tolerance of iterations.
#' @param maxit Integer giving the maximal number of IRLS iterations.
#' @param weightCol The weight column name. If this is not set or NULL, we treat all instance
#' weights as 1.0.
#' @return \code{glm} returns a fitted generalized linear model.
#' @rdname glm
#' @export
#' @examples
#' \dontrun{
#' sparkR.session()
#' data(iris)
#' df <- createDataFrame(iris)
#' model <- glm(Sepal_Length ~ Sepal_Width, df, family = "gaussian")
#' summary(model)
#' }
#' @note glm since 1.5.0
#' @seealso \link{spark.glm}
setMethod("glm", signature(formula = "formula", family = "ANY", data = "SparkDataFrame"),
function(formula, family = gaussian, data, epsilon = 1e-6, maxit = 25, weightCol = NULL) {
spark.glm(data, formula, family, tol = epsilon, maxIter = maxit, weightCol = weightCol)
})
# Returns the summary of a model produced by glm() or spark.glm(), similarly to R's summary().
#' @param object A fitted generalized linear model
#' @return \code{summary} returns a summary object of the fitted model, a list of components
#' including at least the coefficients, null/residual deviance, null/residual degrees
#' of freedom, AIC and number of iterations IRLS takes.
#'
#' @rdname spark.glm
#' @export
#' @note summary(GeneralizedLinearRegressionModel) since 2.0.0
setMethod("summary", signature(object = "GeneralizedLinearRegressionModel"),
function(object, ...) {
jobj <- object@jobj
is.loaded <- callJMethod(jobj, "isLoaded")
features <- callJMethod(jobj, "rFeatures")
coefficients <- callJMethod(jobj, "rCoefficients")
dispersion <- callJMethod(jobj, "rDispersion")
null.deviance <- callJMethod(jobj, "rNullDeviance")
deviance <- callJMethod(jobj, "rDeviance")
df.null <- callJMethod(jobj, "rResidualDegreeOfFreedomNull")
df.residual <- callJMethod(jobj, "rResidualDegreeOfFreedom")
aic <- callJMethod(jobj, "rAic")
iter <- callJMethod(jobj, "rNumIterations")
family <- callJMethod(jobj, "rFamily")
deviance.resid <- if (is.loaded) {
NULL
} else {
dataFrame(callJMethod(jobj, "rDevianceResiduals"))
}
coefficients <- matrix(coefficients, ncol = 4)
colnames(coefficients) <- c("Estimate", "Std. Error", "t value", "Pr(>|t|)")
rownames(coefficients) <- unlist(features)
ans <- list(deviance.resid = deviance.resid, coefficients = coefficients,
dispersion = dispersion, null.deviance = null.deviance,
deviance = deviance, df.null = df.null, df.residual = df.residual,
aic = aic, iter = iter, family = family, is.loaded = is.loaded)
class(ans) <- "summary.GeneralizedLinearRegressionModel"
return(ans)
})
# Prints the summary of GeneralizedLinearRegressionModel
#' @rdname spark.glm
#' @param x Summary object of fitted generalized linear model returned by \code{summary} function
#' @export
#' @note print.summary.GeneralizedLinearRegressionModel since 2.0.0
print.summary.GeneralizedLinearRegressionModel <- function(x, ...) {
if (x$is.loaded) {
cat("\nSaved-loaded model does not support output 'Deviance Residuals'.\n")
} else {
x$deviance.resid <- setNames(unlist(approxQuantile(x$deviance.resid, "devianceResiduals",
c(0.0, 0.25, 0.5, 0.75, 1.0), 0.01)), c("Min", "1Q", "Median", "3Q", "Max"))
x$deviance.resid <- zapsmall(x$deviance.resid, 5L)
cat("\nDeviance Residuals: \n")
cat("(Note: These are approximate quantiles with relative error <= 0.01)\n")
print.default(x$deviance.resid, digits = 5L, na.print = "", print.gap = 2L)
}
cat("\nCoefficients:\n")
print.default(x$coefficients, digits = 5L, na.print = "", print.gap = 2L)
cat("\n(Dispersion parameter for ", x$family, " family taken to be ", format(x$dispersion),
")\n\n", apply(cbind(paste(format(c("Null", "Residual"), justify = "right"), "deviance:"),
format(unlist(x[c("null.deviance", "deviance")]), digits = 5L),
" on", format(unlist(x[c("df.null", "df.residual")])), " degrees of freedom\n"),
1L, paste, collapse = " "), sep = "")
cat("AIC: ", format(x$aic, digits = 4L), "\n\n",
"Number of Fisher Scoring iterations: ", x$iter, "\n", sep = "")
cat("\n")
invisible(x)
}
# Makes predictions from a generalized linear model produced by glm() or spark.glm(),
# similarly to R's predict().
#' @param newData SparkDataFrame for testing
#' @return \code{predict} returns a SparkDataFrame containing predicted labels in a column named
#' "prediction"
#' @rdname spark.glm
#' @export
#' @note predict(GeneralizedLinearRegressionModel) since 1.5.0
setMethod("predict", signature(object = "GeneralizedLinearRegressionModel"),
function(object, newData) {
return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
})
# Makes predictions from a naive Bayes model or a model produced by spark.naiveBayes(),
# similarly to R package e1071's predict.
#' @param newData A SparkDataFrame for testing
#' @return \code{predict} returns a SparkDataFrame containing predicted labeled in a column named
#' "prediction"
#' @rdname spark.naiveBayes
#' @export
#' @note predict(NaiveBayesModel) since 2.0.0
setMethod("predict", signature(object = "NaiveBayesModel"),
function(object, newData) {
return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
})
# Returns the summary of a naive Bayes model produced by \code{spark.naiveBayes}
#' @param object A naive Bayes model fitted by \code{spark.naiveBayes}
#' @return \code{summary} returns a list containing \code{apriori}, the label distribution, and
#' \code{tables}, conditional probabilities given the target label
#' @rdname spark.naiveBayes
#' @export
#' @note summary(NaiveBayesModel) since 2.0.0
setMethod("summary", signature(object = "NaiveBayesModel"),
function(object, ...) {
jobj <- object@jobj
features <- callJMethod(jobj, "features")
labels <- callJMethod(jobj, "labels")
apriori <- callJMethod(jobj, "apriori")
apriori <- t(as.matrix(unlist(apriori)))
colnames(apriori) <- unlist(labels)
tables <- callJMethod(jobj, "tables")
tables <- matrix(tables, nrow = length(labels))
rownames(tables) <- unlist(labels)
colnames(tables) <- unlist(features)
return(list(apriori = apriori, tables = tables))
})
#' Isotonic Regression Model
#'
#' Fits an Isotonic Regression model against a Spark DataFrame, similarly to R's isoreg().
#' Users can print, make predictions on the produced model and save the model to the input path.
#'
#' @param data SparkDataFrame for training
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', '.', ':', '+', and '-'.
#' @param isotonic Whether the output sequence should be isotonic/increasing (TRUE) or
#' antitonic/decreasing (FALSE)
#' @param featureIndex The index of the feature if \code{featuresCol} is a vector column (default: `0`),
#' no effect otherwise
#' @param weightCol The weight column name.
#' @return \code{spark.isoreg} returns a fitted Isotonic Regression model
#' @rdname spark.isoreg
#' @aliases spark.isoreg,SparkDataFrame,formula-method
#' @name spark.isoreg
#' @export
#' @examples
#' \dontrun{
#' sparkR.session()
#' data <- list(list(7.0, 0.0), list(5.0, 1.0), list(3.0, 2.0),
#' list(5.0, 3.0), list(1.0, 4.0))
#' df <- createDataFrame(data, c("label", "feature"))
#' model <- spark.isoreg(df, label ~ feature, isotonic = FALSE)
#' # return model boundaries and prediction as lists
#' result <- summary(model, df)
#' # prediction based on fitted model
#' predict_data <- list(list(-2.0), list(-1.0), list(0.5),
#' list(0.75), list(1.0), list(2.0), list(9.0))
#' predict_df <- createDataFrame(predict_data, c("feature"))
#' # get prediction column
#' predict_result <- collect(select(predict(model, predict_df), "prediction"))
#'
#' # save fitted model to input path
#' path <- "path/to/model"
#' write.ml(model, path)
#'
#' # can also read back the saved model and print
#' savedModel <- read.ml(path)
#' summary(savedModel)
#' }
#' @note spark.isoreg since 2.1.0
setMethod("spark.isoreg", signature(data = "SparkDataFrame", formula = "formula"),
function(data, formula, isotonic = TRUE, featureIndex = 0, weightCol = NULL) {
formula <- paste0(deparse(formula), collapse = "")
if (is.null(weightCol)) {
weightCol <- ""
}
jobj <- callJStatic("org.apache.spark.ml.r.IsotonicRegressionWrapper", "fit",
data@sdf, formula, as.logical(isotonic), as.integer(featureIndex),
as.character(weightCol))
return(new("IsotonicRegressionModel", jobj = jobj))
})
# Predicted values based on an isotonicRegression model
#' @param object a fitted IsotonicRegressionModel
#' @param newData SparkDataFrame for testing
#' @return \code{predict} returns a SparkDataFrame containing predicted values
#' @rdname spark.isoreg
#' @aliases predict,IsotonicRegressionModel,SparkDataFrame-method
#' @export
#' @note predict(IsotonicRegressionModel) since 2.1.0
setMethod("predict", signature(object = "IsotonicRegressionModel"),
function(object, newData) {
return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
})
# Get the summary of an IsotonicRegressionModel model
#' @param object a fitted IsotonicRegressionModel
#' @param ... Other optional arguments to summary of an IsotonicRegressionModel
#' @return \code{summary} returns the model's boundaries and prediction as lists
#' @rdname spark.isoreg
#' @aliases summary,IsotonicRegressionModel-method
#' @export
#' @note summary(IsotonicRegressionModel) since 2.1.0
setMethod("summary", signature(object = "IsotonicRegressionModel"),
function(object, ...) {
jobj <- object@jobj
boundaries <- callJMethod(jobj, "boundaries")
predictions <- callJMethod(jobj, "predictions")
return(list(boundaries = boundaries, predictions = predictions))
})
#' K-Means Clustering Model
#'
#' Fits a k-means clustering model against a Spark DataFrame, similarly to R's kmeans().
#' Users can call \code{summary} to print a summary of the fitted model, \code{predict} to make
#' predictions on new data, and \code{write.ml}/\code{read.ml} to save/load fitted models.
#'
#' @param data SparkDataFrame for training
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', '.', ':', '+', and '-'.
#' Note that the response variable of formula is empty in spark.kmeans.
#' @param k Number of centers
#' @param maxIter Maximum iteration number
#' @param initMode The initialization algorithm choosen to fit the model
#' @return \code{spark.kmeans} returns a fitted k-means model
#' @rdname spark.kmeans
#' @aliases spark.kmeans,SparkDataFrame,formula-method
#' @name spark.kmeans
#' @export
#' @examples
#' \dontrun{
#' sparkR.session()
#' data(iris)
#' df <- createDataFrame(iris)
#' model <- spark.kmeans(df, Sepal_Length ~ Sepal_Width, k = 4, initMode = "random")
#' summary(model)
#'
#' # fitted values on training data
#' fitted <- predict(model, df)
#' head(select(fitted, "Sepal_Length", "prediction"))
#'
#' # save fitted model to input path
#' path <- "path/to/model"
#' write.ml(model, path)
#'
#' # can also read back the saved model and print
#' savedModel <- read.ml(path)
#' summary(savedModel)
#' }
#' @note spark.kmeans since 2.0.0
#' @seealso \link{predict}, \link{read.ml}, \link{write.ml}
setMethod("spark.kmeans", signature(data = "SparkDataFrame", formula = "formula"),
function(data, formula, k = 2, maxIter = 20, initMode = c("k-means||", "random")) {
formula <- paste(deparse(formula), collapse = "")
initMode <- match.arg(initMode)
jobj <- callJStatic("org.apache.spark.ml.r.KMeansWrapper", "fit", data@sdf, formula,
as.integer(k), as.integer(maxIter), initMode)
return(new("KMeansModel", jobj = jobj))
})
#' Get fitted result from a k-means model
#'
#' Get fitted result from a k-means model, similarly to R's fitted().
#' Note: A saved-loaded model does not support this method.
#'
#' @param object A fitted k-means model
#' @return \code{fitted} returns a SparkDataFrame containing fitted values
#' @rdname fitted
#' @export
#' @examples
#' \dontrun{
#' model <- spark.kmeans(trainingData, ~ ., 2)
#' fitted.model <- fitted(model)
#' showDF(fitted.model)
#'}
#' @note fitted since 2.0.0
setMethod("fitted", signature(object = "KMeansModel"),
function(object, method = c("centers", "classes"), ...) {
method <- match.arg(method)
jobj <- object@jobj
is.loaded <- callJMethod(jobj, "isLoaded")
if (is.loaded) {
stop(paste("Saved-loaded k-means model does not support 'fitted' method"))
} else {
return(dataFrame(callJMethod(jobj, "fitted", method)))
}
})
# Get the summary of a k-means model
#' @param object A fitted k-means model
#' @return \code{summary} returns the model's coefficients, size and cluster
#' @rdname spark.kmeans
#' @export
#' @note summary(KMeansModel) since 2.0.0
setMethod("summary", signature(object = "KMeansModel"),
function(object, ...) {
jobj <- object@jobj
is.loaded <- callJMethod(jobj, "isLoaded")
features <- callJMethod(jobj, "features")
coefficients <- callJMethod(jobj, "coefficients")
k <- callJMethod(jobj, "k")
size <- callJMethod(jobj, "size")
coefficients <- t(matrix(coefficients, ncol = k))
colnames(coefficients) <- unlist(features)
rownames(coefficients) <- 1:k
cluster <- if (is.loaded) {
NULL
} else {
dataFrame(callJMethod(jobj, "cluster"))
}
return(list(coefficients = coefficients, size = size,
cluster = cluster, is.loaded = is.loaded))
})
# Predicted values based on a k-means model
#' @return \code{predict} returns the predicted values based on a k-means model
#' @rdname spark.kmeans
#' @export
#' @note predict(KMeansModel) since 2.0.0
setMethod("predict", signature(object = "KMeansModel"),
function(object, newData) {
return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
})
#' Naive Bayes Models
#'
#' \code{spark.naiveBayes} fits a Bernoulli naive Bayes model against a SparkDataFrame.
#' Users can call \code{summary} to print a summary of the fitted model, \code{predict} to make
#' predictions on new data, and \code{write.ml}/\code{read.ml} to save/load fitted models.
#' Only categorical data is supported.
#'
#' @param data A \code{SparkDataFrame} of observations and labels for model fitting
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', '.', ':', '+', and '-'.
#' @param smoothing Smoothing parameter
#' @return \code{spark.naiveBayes} returns a fitted naive Bayes model
#' @rdname spark.naiveBayes
#' @aliases spark.naiveBayes,SparkDataFrame,formula-method
#' @name spark.naiveBayes
#' @seealso e1071: \url{https://cran.r-project.org/web/packages/e1071/}
#' @export
#' @examples
#' \dontrun{
#' df <- createDataFrame(infert)
#'
#' # fit a Bernoulli naive Bayes model
#' model <- spark.naiveBayes(df, education ~ ., smoothing = 0)
#'
#' # get the summary of the model
#' summary(model)
#'
#' # make predictions
#' predictions <- predict(model, df)
#'
#' # save and load the model
#' path <- "path/to/model"
#' write.ml(model, path)
#' savedModel <- read.ml(path)
#' summary(savedModel)
#' }
#' @note spark.naiveBayes since 2.0.0
setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "formula"),
function(data, formula, smoothing = 1.0, ...) {
formula <- paste(deparse(formula), collapse = "")
jobj <- callJStatic("org.apache.spark.ml.r.NaiveBayesWrapper", "fit",
formula, data@sdf, smoothing)
return(new("NaiveBayesModel", jobj = jobj))
})
# Saves the Bernoulli naive Bayes model to the input path.
#' @param path The directory where the model is saved
#' @param overwrite Overwrites or not if the output path already exists. Default is FALSE
#' which means throw exception if the output path exists.
#'
#' @rdname spark.naiveBayes
#' @export
#' @seealso \link{read.ml}
#' @note write.ml(NaiveBayesModel, character) since 2.0.0
setMethod("write.ml", signature(object = "NaiveBayesModel", path = "character"),
function(object, path, overwrite = FALSE) {
writer <- callJMethod(object@jobj, "write")
if (overwrite) {
writer <- callJMethod(writer, "overwrite")
}
invisible(callJMethod(writer, "save", path))
})
# Saves the AFT survival regression model to the input path.
#' @param path The directory where the model is saved
#' @param overwrite Overwrites or not if the output path already exists. Default is FALSE
#' which means throw exception if the output path exists.
#'
#' @rdname spark.survreg
#' @export
#' @note write.ml(AFTSurvivalRegressionModel, character) since 2.0.0
#' @seealso \link{read.ml}
setMethod("write.ml", signature(object = "AFTSurvivalRegressionModel", path = "character"),
function(object, path, overwrite = FALSE) {
writer <- callJMethod(object@jobj, "write")
if (overwrite) {
writer <- callJMethod(writer, "overwrite")
}
invisible(callJMethod(writer, "save", path))
})
# Saves the generalized linear model to the input path.
#' @param path The directory where the model is saved
#' @param overwrite Overwrites or not if the output path already exists. Default is FALSE
#' which means throw exception if the output path exists.
#'
#' @rdname spark.glm
#' @export
#' @note write.ml(GeneralizedLinearRegressionModel, character) since 2.0.0
setMethod("write.ml", signature(object = "GeneralizedLinearRegressionModel", path = "character"),
function(object, path, overwrite = FALSE) {
writer <- callJMethod(object@jobj, "write")
if (overwrite) {
writer <- callJMethod(writer, "overwrite")
}
invisible(callJMethod(writer, "save", path))
})
# Save fitted MLlib model to the input path
#' @param path The directory where the model is saved
#' @param overwrite Overwrites or not if the output path already exists. Default is FALSE
#' which means throw exception if the output path exists.
#'
#' @rdname spark.kmeans
#' @export
#' @note write.ml(KMeansModel, character) since 2.0.0
setMethod("write.ml", signature(object = "KMeansModel", path = "character"),
function(object, path, overwrite = FALSE) {
writer <- callJMethod(object@jobj, "write")
if (overwrite) {
writer <- callJMethod(writer, "overwrite")
}
invisible(callJMethod(writer, "save", path))
})
# Save fitted IsotonicRegressionModel to the input path
#' @param path The directory where the model is saved
#' @param overwrite Overwrites or not if the output path already exists. Default is FALSE
#' which means throw exception if the output path exists.
#'
#' @rdname spark.isoreg
#' @aliases write.ml,IsotonicRegressionModel,character-method
#' @export
#' @note write.ml(IsotonicRegression, character) since 2.1.0
setMethod("write.ml", signature(object = "IsotonicRegressionModel", path = "character"),
function(object, path, overwrite = FALSE) {
writer <- callJMethod(object@jobj, "write")
if (overwrite) {
writer <- callJMethod(writer, "overwrite")
}
invisible(callJMethod(writer, "save", path))
})
#' Load a fitted MLlib model from the input path.
#'
#' @param path Path of the model to read.
#' @return a fitted MLlib model
#' @rdname read.ml
#' @name read.ml
#' @export
#' @seealso \link{write.ml}
#' @examples
#' \dontrun{
#' path <- "path/to/model"
#' model <- read.ml(path)
#' }
#' @note read.ml since 2.0.0
read.ml <- function(path) {
path <- suppressWarnings(normalizePath(path))
jobj <- callJStatic("org.apache.spark.ml.r.RWrappers", "load", path)
if (isInstanceOf(jobj, "org.apache.spark.ml.r.NaiveBayesWrapper")) {
return(new("NaiveBayesModel", jobj = jobj))
} else if (isInstanceOf(jobj, "org.apache.spark.ml.r.AFTSurvivalRegressionWrapper")) {
return(new("AFTSurvivalRegressionModel", jobj = jobj))
} else if (isInstanceOf(jobj, "org.apache.spark.ml.r.GeneralizedLinearRegressionWrapper")) {
return(new("GeneralizedLinearRegressionModel", jobj = jobj))
} else if (isInstanceOf(jobj, "org.apache.spark.ml.r.KMeansWrapper")) {
return(new("KMeansModel", jobj = jobj))
} else if (isInstanceOf(jobj, "org.apache.spark.ml.r.IsotonicRegressionWrapper")) {
return(new("IsotonicRegressionModel", jobj = jobj))
} else {
stop(paste("Unsupported model: ", jobj))
}
}
#' Accelerated Failure Time (AFT) Survival Regression Model
#'
#' \code{spark.survreg} fits an accelerated failure time (AFT) survival regression model on
#' a SparkDataFrame. Users can call \code{summary} to get a summary of the fitted AFT model,
#' \code{predict} to make predictions on new data, and \code{write.ml}/\code{read.ml} to
#' save/load fitted models.
#'
#' @param data A SparkDataFrame for training
#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
#' operators are supported, including '~', ':', '+', and '-'.
#' Note that operator '.' is not supported currently
#' @return \code{spark.survreg} returns a fitted AFT survival regression model
#' @rdname spark.survreg
#' @seealso survival: \url{https://cran.r-project.org/web/packages/survival/}
#' @export
#' @examples
#' \dontrun{
#' df <- createDataFrame(ovarian)
#' model <- spark.survreg(df, Surv(futime, fustat) ~ ecog_ps + rx)
#'
#' # get a summary of the model
#' summary(model)
#'
#' # make predictions
#' predicted <- predict(model, df)
#' showDF(predicted)
#'
#' # save and load the model
#' path <- "path/to/model"
#' write.ml(model, path)
#' savedModel <- read.ml(path)
#' summary(savedModel)
#' }
#' @note spark.survreg since 2.0.0
setMethod("spark.survreg", signature(data = "SparkDataFrame", formula = "formula"),
function(data, formula, ...) {
formula <- paste(deparse(formula), collapse = "")
jobj <- callJStatic("org.apache.spark.ml.r.AFTSurvivalRegressionWrapper",
"fit", formula, data@sdf)
return(new("AFTSurvivalRegressionModel", jobj = jobj))
})
# Returns a summary of the AFT survival regression model produced by spark.survreg,
# similarly to R's summary().
#' @param object A fitted AFT survival regression model
#' @return \code{summary} returns a list containing the model's coefficients,
#' intercept and log(scale)
#' @rdname spark.survreg
#' @export
#' @note summary(AFTSurvivalRegressionModel) since 2.0.0
setMethod("summary", signature(object = "AFTSurvivalRegressionModel"),
function(object, ...) {
jobj <- object@jobj
features <- callJMethod(jobj, "rFeatures")
coefficients <- callJMethod(jobj, "rCoefficients")
coefficients <- as.matrix(unlist(coefficients))
colnames(coefficients) <- c("Value")
rownames(coefficients) <- unlist(features)
return(list(coefficients = coefficients))
})
# Makes predictions from an AFT survival regression model or a model produced by
# spark.survreg, similarly to R package survival's predict.
#' @param newData A SparkDataFrame for testing
#' @return \code{predict} returns a SparkDataFrame containing predicted values
#' on the original scale of the data (mean predicted value at scale = 1.0)
#' @rdname spark.survreg
#' @export
#' @note predict(AFTSurvivalRegressionModel) since 2.0.0
setMethod("predict", signature(object = "AFTSurvivalRegressionModel"),
function(object, newData) {
return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
})
|