7d0743b493
### Why is this change being proposed? This patch adds support for a new "product" aggregation function in `sql.functions` which multiplies-together all values in an aggregation group. This is likely to be useful in statistical applications which involve combining probabilities, or financial applications that involve combining cumulative interest rates, but is also a versatile mathematical operation of similar status to `sum` or `stddev`. Other users [have noted](https://stackoverflow.com/questions/52991640/cumulative-product-in-spark) the absence of such a function in current releases of Spark. This function is both much more concise than an expression of the form `exp(sum(log(...)))`, and avoids awkward edge-cases associated with some values being zero or negative, as well as being less computationally costly. ### Does this PR introduce _any_ user-facing change? No - only adds new function. ### How was this patch tested? Built-in tests have been added for the new `catalyst.expressions.aggregate.Product` class and its invocation via the (scala) `sql.functions.product` function. The latter, and the PySpark wrapper have also been manually tested in spark-shell and pyspark sessions. The SparkR wrapper is currently untested, and may need separate validation (I'm not an "R" user myself). An illustration of the new functionality, within PySpark is as follows: ``` import pyspark.sql.functions as pf, pyspark.sql.window as pw df = sqlContext.range(1, 17).toDF("x") win = pw.Window.partitionBy(pf.lit(1)).orderBy(pf.col("x")) df.withColumn("factorial", pf.product("x").over(win)).show(20, False) +---+---------------+ |x |factorial | +---+---------------+ |1 |1.0 | |2 |2.0 | |3 |6.0 | |4 |24.0 | |5 |120.0 | |6 |720.0 | |7 |5040.0 | |8 |40320.0 | |9 |362880.0 | |10 |3628800.0 | |11 |3.99168E7 | |12 |4.790016E8 | |13 |6.2270208E9 | |14 |8.71782912E10 | |15 |1.307674368E12 | |16 |2.0922789888E13| +---+---------------+ ``` Closes #30745 from rwpenney/feature/agg-product. Lead-authored-by: Richard Penney <rwp@rwpenney.uk> Co-authored-by: Richard Penney <rwpenney@users.noreply.github.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
553 lines
15 KiB
Plaintext
553 lines
15 KiB
Plaintext
#
|
|
# 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.
|
|
#
|
|
|
|
# Imports from base R
|
|
# Do not include stats:: "rpois", "runif" - causes error at runtime
|
|
importFrom("methods", "setGeneric", "setMethod", "setOldClass")
|
|
importFrom("methods", "is", "new", "signature", "show")
|
|
importFrom("stats", "gaussian", "setNames")
|
|
importFrom("utils", "download.file", "object.size", "packageVersion", "tail", "untar")
|
|
|
|
# Disable native libraries till we figure out how to package it
|
|
# See SPARKR-7839
|
|
#useDynLib(SparkR, stringHashCode)
|
|
|
|
# S3 methods exported
|
|
export("sparkR.session")
|
|
export("sparkR.init")
|
|
export("sparkR.session.stop")
|
|
export("sparkR.stop")
|
|
export("sparkR.conf")
|
|
export("sparkR.version")
|
|
export("sparkR.uiWebUrl")
|
|
export("print.jobj")
|
|
|
|
export("sparkR.newJObject")
|
|
export("sparkR.callJMethod")
|
|
export("sparkR.callJStatic")
|
|
|
|
export("install.spark")
|
|
|
|
export("sparkRSQL.init",
|
|
"sparkRHive.init")
|
|
|
|
# MLlib integration
|
|
exportMethods("glm",
|
|
"spark.glm",
|
|
"predict",
|
|
"summary",
|
|
"spark.kmeans",
|
|
"fitted",
|
|
"spark.mlp",
|
|
"spark.naiveBayes",
|
|
"spark.survreg",
|
|
"spark.lda",
|
|
"spark.posterior",
|
|
"spark.perplexity",
|
|
"spark.isoreg",
|
|
"spark.gaussianMixture",
|
|
"spark.als",
|
|
"spark.kstest",
|
|
"spark.logit",
|
|
"spark.decisionTree",
|
|
"spark.randomForest",
|
|
"spark.gbt",
|
|
"spark.bisectingKmeans",
|
|
"spark.svmLinear",
|
|
"spark.fpGrowth",
|
|
"spark.freqItemsets",
|
|
"spark.associationRules",
|
|
"spark.findFrequentSequentialPatterns",
|
|
"spark.assignClusters",
|
|
"spark.fmClassifier",
|
|
"spark.lm",
|
|
"spark.fmRegressor")
|
|
|
|
# Job group lifecycle management methods
|
|
export("setJobGroup",
|
|
"clearJobGroup",
|
|
"cancelJobGroup",
|
|
"setJobDescription",
|
|
"setLocalProperty",
|
|
"getLocalProperty")
|
|
|
|
# Export Utility methods
|
|
export("setLogLevel")
|
|
|
|
exportClasses("SparkDataFrame")
|
|
|
|
exportMethods("arrange",
|
|
"as.data.frame",
|
|
"attach",
|
|
"broadcast",
|
|
"cache",
|
|
"checkpoint",
|
|
"coalesce",
|
|
"collect",
|
|
"colnames",
|
|
"colnames<-",
|
|
"coltypes",
|
|
"coltypes<-",
|
|
"columns",
|
|
"count",
|
|
"cov",
|
|
"corr",
|
|
"covar_samp",
|
|
"covar_pop",
|
|
"createOrReplaceTempView",
|
|
"crossJoin",
|
|
"crosstab",
|
|
"cube",
|
|
"dapply",
|
|
"dapplyCollect",
|
|
"describe",
|
|
"dim",
|
|
"distinct",
|
|
"drop",
|
|
"dropDuplicates",
|
|
"dropna",
|
|
"dtypes",
|
|
"except",
|
|
"exceptAll",
|
|
"explain",
|
|
"fillna",
|
|
"filter",
|
|
"first",
|
|
"freqItems",
|
|
"gapply",
|
|
"gapplyCollect",
|
|
"getNumPartitions",
|
|
"group_by",
|
|
"groupBy",
|
|
"head",
|
|
"hint",
|
|
"insertInto",
|
|
"intersect",
|
|
"intersectAll",
|
|
"isLocal",
|
|
"isStreaming",
|
|
"join",
|
|
"limit",
|
|
"localCheckpoint",
|
|
"merge",
|
|
"mutate",
|
|
"na.omit",
|
|
"names",
|
|
"names<-",
|
|
"ncol",
|
|
"nrow",
|
|
"orderBy",
|
|
"persist",
|
|
"printSchema",
|
|
"randomSplit",
|
|
"rbind",
|
|
"registerTempTable",
|
|
"rename",
|
|
"repartition",
|
|
"repartitionByRange",
|
|
"rollup",
|
|
"sample",
|
|
"sample_frac",
|
|
"sampleBy",
|
|
"saveAsTable",
|
|
"saveDF",
|
|
"schema",
|
|
"select",
|
|
"selectExpr",
|
|
"show",
|
|
"showDF",
|
|
"storageLevel",
|
|
"subset",
|
|
"summarize",
|
|
"summary",
|
|
"take",
|
|
"toJSON",
|
|
"transform",
|
|
"union",
|
|
"unionAll",
|
|
"unionByName",
|
|
"unique",
|
|
"unpersist",
|
|
"where",
|
|
"with",
|
|
"withColumn",
|
|
"withColumnRenamed",
|
|
"withWatermark",
|
|
"write.df",
|
|
"write.jdbc",
|
|
"write.json",
|
|
"write.orc",
|
|
"write.parquet",
|
|
"write.stream",
|
|
"write.text",
|
|
"write.ml")
|
|
|
|
exportClasses("Column")
|
|
|
|
exportMethods("%<=>%",
|
|
"%in%",
|
|
"abs",
|
|
"acos",
|
|
"acosh",
|
|
"add_months",
|
|
"alias",
|
|
"approx_count_distinct",
|
|
"approxCountDistinct",
|
|
"approxQuantile",
|
|
"array_aggregate",
|
|
"array_contains",
|
|
"array_distinct",
|
|
"array_except",
|
|
"array_exists",
|
|
"array_filter",
|
|
"array_forall",
|
|
"array_intersect",
|
|
"array_join",
|
|
"array_max",
|
|
"array_min",
|
|
"array_position",
|
|
"array_remove",
|
|
"array_repeat",
|
|
"array_sort",
|
|
"array_to_vector",
|
|
"array_transform",
|
|
"arrays_overlap",
|
|
"array_union",
|
|
"arrays_zip",
|
|
"arrays_zip_with",
|
|
"asc",
|
|
"asc_nulls_first",
|
|
"asc_nulls_last",
|
|
"ascii",
|
|
"asin",
|
|
"asinh",
|
|
"assert_true",
|
|
"atan",
|
|
"atanh",
|
|
"atan2",
|
|
"avg",
|
|
"base64",
|
|
"between",
|
|
"bin",
|
|
"bitwise_not",
|
|
"bitwiseNOT",
|
|
"bround",
|
|
"cast",
|
|
"cbrt",
|
|
"ceil",
|
|
"ceiling",
|
|
"collect_list",
|
|
"collect_set",
|
|
"column",
|
|
"concat",
|
|
"concat_ws",
|
|
"contains",
|
|
"conv",
|
|
"cos",
|
|
"cosh",
|
|
"count",
|
|
"count_distinct",
|
|
"countDistinct",
|
|
"crc32",
|
|
"create_array",
|
|
"create_map",
|
|
"current_date",
|
|
"current_timestamp",
|
|
"hash",
|
|
"cume_dist",
|
|
"date_add",
|
|
"date_format",
|
|
"date_sub",
|
|
"date_trunc",
|
|
"datediff",
|
|
"dayofmonth",
|
|
"dayofweek",
|
|
"dayofyear",
|
|
"decode",
|
|
"degrees",
|
|
"dense_rank",
|
|
"desc",
|
|
"desc_nulls_first",
|
|
"desc_nulls_last",
|
|
"dropFields",
|
|
"element_at",
|
|
"encode",
|
|
"endsWith",
|
|
"exp",
|
|
"explode",
|
|
"explode_outer",
|
|
"expm1",
|
|
"expr",
|
|
"factorial",
|
|
"first",
|
|
"flatten",
|
|
"floor",
|
|
"format_number",
|
|
"format_string",
|
|
"from_avro",
|
|
"from_csv",
|
|
"from_json",
|
|
"from_unixtime",
|
|
"from_utc_timestamp",
|
|
"getField",
|
|
"getItem",
|
|
"greatest",
|
|
"grouping_bit",
|
|
"grouping_id",
|
|
"hex",
|
|
"histogram",
|
|
"hour",
|
|
"hypot",
|
|
"ifelse",
|
|
"initcap",
|
|
"input_file_name",
|
|
"instr",
|
|
"isNaN",
|
|
"isNotNull",
|
|
"isNull",
|
|
"is.nan",
|
|
"isnan",
|
|
"kurtosis",
|
|
"lag",
|
|
"last",
|
|
"last_day",
|
|
"lead",
|
|
"least",
|
|
"length",
|
|
"levenshtein",
|
|
"like",
|
|
"lit",
|
|
"locate",
|
|
"log",
|
|
"log10",
|
|
"log1p",
|
|
"log2",
|
|
"lower",
|
|
"lpad",
|
|
"ltrim",
|
|
"map_concat",
|
|
"map_entries",
|
|
"map_filter",
|
|
"map_from_arrays",
|
|
"map_from_entries",
|
|
"map_keys",
|
|
"map_values",
|
|
"map_zip_with",
|
|
"max",
|
|
"md5",
|
|
"mean",
|
|
"min",
|
|
"minute",
|
|
"monotonically_increasing_id",
|
|
"month",
|
|
"months_between",
|
|
"n",
|
|
"n_distinct",
|
|
"nanvl",
|
|
"negate",
|
|
"next_day",
|
|
"not",
|
|
"nth_value",
|
|
"ntile",
|
|
"otherwise",
|
|
"over",
|
|
"overlay",
|
|
"percent_rank",
|
|
"percentile_approx",
|
|
"pmod",
|
|
"posexplode",
|
|
"posexplode_outer",
|
|
"product",
|
|
"quarter",
|
|
"radians",
|
|
"raise_error",
|
|
"rand",
|
|
"randn",
|
|
"rank",
|
|
"regexp_extract",
|
|
"regexp_replace",
|
|
"repeat_string",
|
|
"reverse",
|
|
"rint",
|
|
"rlike",
|
|
"round",
|
|
"row_number",
|
|
"rpad",
|
|
"rtrim",
|
|
"schema_of_csv",
|
|
"schema_of_json",
|
|
"second",
|
|
"sha1",
|
|
"sha2",
|
|
"shiftLeft",
|
|
"shiftleft",
|
|
"shiftRight",
|
|
"shiftright",
|
|
"shiftRightUnsigned",
|
|
"shiftrightunsigned",
|
|
"shuffle",
|
|
"sd",
|
|
"sign",
|
|
"signum",
|
|
"sin",
|
|
"sinh",
|
|
"size",
|
|
"skewness",
|
|
"slice",
|
|
"sort_array",
|
|
"soundex",
|
|
"spark_partition_id",
|
|
"split_string",
|
|
"stddev",
|
|
"stddev_pop",
|
|
"stddev_samp",
|
|
"struct",
|
|
"sqrt",
|
|
"startsWith",
|
|
"substr",
|
|
"substring_index",
|
|
"sum",
|
|
"sum_distinct",
|
|
"sumDistinct",
|
|
"tan",
|
|
"tanh",
|
|
"timestamp_seconds",
|
|
"toDegrees",
|
|
"toRadians",
|
|
"to_avro",
|
|
"to_csv",
|
|
"to_date",
|
|
"to_json",
|
|
"to_timestamp",
|
|
"to_utc_timestamp",
|
|
"translate",
|
|
"transform_keys",
|
|
"transform_values",
|
|
"trim",
|
|
"trunc",
|
|
"unbase64",
|
|
"unhex",
|
|
"unix_timestamp",
|
|
"upper",
|
|
"var",
|
|
"variance",
|
|
"var_pop",
|
|
"var_samp",
|
|
"vector_to_array",
|
|
"weekofyear",
|
|
"when",
|
|
"window",
|
|
"withField",
|
|
"xxhash64",
|
|
"year")
|
|
|
|
exportClasses("GroupedData")
|
|
exportMethods("agg")
|
|
exportMethods("pivot")
|
|
|
|
export("as.DataFrame",
|
|
"cacheTable",
|
|
"clearCache",
|
|
"createDataFrame",
|
|
"createExternalTable",
|
|
"createTable",
|
|
"currentDatabase",
|
|
"dropTempTable",
|
|
"dropTempView",
|
|
"listColumns",
|
|
"listDatabases",
|
|
"listFunctions",
|
|
"listTables",
|
|
"loadDF",
|
|
"read.df",
|
|
"read.jdbc",
|
|
"read.json",
|
|
"read.orc",
|
|
"read.parquet",
|
|
"read.stream",
|
|
"read.text",
|
|
"recoverPartitions",
|
|
"refreshByPath",
|
|
"refreshTable",
|
|
"setCheckpointDir",
|
|
"setCurrentDatabase",
|
|
"spark.lapply",
|
|
"spark.addFile",
|
|
"spark.getSparkFilesRootDirectory",
|
|
"spark.getSparkFiles",
|
|
"sql",
|
|
"str",
|
|
"tableToDF",
|
|
"tableNames",
|
|
"tables",
|
|
"uncacheTable",
|
|
"print.summary.GeneralizedLinearRegressionModel",
|
|
"read.ml",
|
|
"print.summary.KSTest",
|
|
"print.summary.DecisionTreeRegressionModel",
|
|
"print.summary.DecisionTreeClassificationModel",
|
|
"print.summary.RandomForestRegressionModel",
|
|
"print.summary.RandomForestClassificationModel",
|
|
"print.summary.GBTRegressionModel",
|
|
"print.summary.GBTClassificationModel")
|
|
|
|
export("structField",
|
|
"structField.jobj",
|
|
"structField.character",
|
|
"print.structField",
|
|
"structType",
|
|
"structType.character",
|
|
"structType.jobj",
|
|
"structType.structField",
|
|
"print.structType")
|
|
|
|
exportClasses("WindowSpec")
|
|
|
|
export("partitionBy",
|
|
"rowsBetween",
|
|
"rangeBetween")
|
|
|
|
export("windowPartitionBy",
|
|
"windowOrderBy")
|
|
|
|
exportClasses("StreamingQuery")
|
|
|
|
export("awaitTermination",
|
|
"isActive",
|
|
"lastProgress",
|
|
"queryName",
|
|
"status",
|
|
"stopQuery")
|
|
|
|
|
|
S3method(print, jobj)
|
|
S3method(print, structField)
|
|
S3method(print, structType)
|
|
S3method(print, summary.GeneralizedLinearRegressionModel)
|
|
S3method(print, summary.KSTest)
|
|
S3method(print, summary.DecisionTreeRegressionModel)
|
|
S3method(print, summary.DecisionTreeClassificationModel)
|
|
S3method(print, summary.RandomForestRegressionModel)
|
|
S3method(print, summary.RandomForestClassificationModel)
|
|
S3method(print, summary.GBTRegressionModel)
|
|
S3method(print, summary.GBTClassificationModel)
|
|
S3method(structField, character)
|
|
S3method(structField, jobj)
|
|
S3method(structType, character)
|
|
S3method(structType, jobj)
|
|
S3method(structType, structField)
|