Skip to main content
Ctrl+K
Logo image

Site Navigation

  • Overview
  • Getting Started
  • User Guides
  • API Reference
  • Development
  • Migration Guides

Site Navigation

  • Overview
  • Getting Started
  • User Guides
  • API Reference
  • Development
  • Migration Guides

Section Navigation

  • Spark SQL
    • Core Classes
      • pyspark.sql.SparkSession
      • pyspark.sql.Catalog
      • pyspark.sql.DataFrame
      • pyspark.sql.Column
      • pyspark.sql.Observation
      • pyspark.sql.Row
      • pyspark.sql.GroupedData
      • pyspark.sql.PandasCogroupedOps
      • pyspark.sql.DataFrameNaFunctions
      • pyspark.sql.DataFrameStatFunctions
      • pyspark.sql.Window
      • pyspark.sql.DataFrameReader
      • pyspark.sql.DataFrameWriter
      • pyspark.sql.DataFrameWriterV2
      • pyspark.sql.UDFRegistration
      • pyspark.sql.UDTFRegistration
      • pyspark.sql.udf.UserDefinedFunction
      • pyspark.sql.udtf.UserDefinedTableFunction
      • pyspark.sql.datasource.DataSource
      • pyspark.sql.datasource.DataSourceReader
      • pyspark.sql.datasource.DataSourceStreamReader
      • pyspark.sql.datasource.DataSourceWriter
      • pyspark.sql.datasource.DataSourceRegistration
      • pyspark.sql.datasource.InputPartition
      • pyspark.sql.datasource.WriterCommitMessage
      • pyspark.sql.VariantVal
    • Spark Session
      • pyspark.sql.SparkSession.active
      • pyspark.sql.SparkSession.builder.appName
      • pyspark.sql.SparkSession.builder.config
      • pyspark.sql.SparkSession.builder.enableHiveSupport
      • pyspark.sql.SparkSession.builder.getOrCreate
      • pyspark.sql.SparkSession.builder.master
      • pyspark.sql.SparkSession.builder.remote
      • pyspark.sql.SparkSession.catalog
      • pyspark.sql.SparkSession.conf
      • pyspark.sql.SparkSession.createDataFrame
      • pyspark.sql.SparkSession.dataSource
      • pyspark.sql.SparkSession.getActiveSession
      • pyspark.sql.SparkSession.newSession
      • pyspark.sql.SparkSession.profile
      • pyspark.sql.SparkSession.range
      • pyspark.sql.SparkSession.read
      • pyspark.sql.SparkSession.readStream
      • pyspark.sql.SparkSession.sparkContext
      • pyspark.sql.SparkSession.sql
      • pyspark.sql.SparkSession.stop
      • pyspark.sql.SparkSession.streams
      • pyspark.sql.SparkSession.table
      • pyspark.sql.SparkSession.udf
      • pyspark.sql.SparkSession.udtf
      • pyspark.sql.SparkSession.version
      • pyspark.sql.is_remote
      • pyspark.sql.SparkSession.builder.create
      • pyspark.sql.SparkSession.addArtifact
      • pyspark.sql.SparkSession.addArtifacts
      • pyspark.sql.SparkSession.addTag
      • pyspark.sql.SparkSession.clearProgressHandlers
      • pyspark.sql.SparkSession.clearTags
      • pyspark.sql.SparkSession.client
      • pyspark.sql.SparkSession.copyFromLocalToFs
      • pyspark.sql.SparkSession.getTags
      • pyspark.sql.SparkSession.interruptAll
      • pyspark.sql.SparkSession.interruptOperation
      • pyspark.sql.SparkSession.interruptTag
      • pyspark.sql.SparkSession.registerProgressHandler
      • pyspark.sql.SparkSession.removeProgressHandler
      • pyspark.sql.SparkSession.removeTag
    • Configuration
      • pyspark.sql.conf.RuntimeConfig
    • Input/Output
      • pyspark.sql.DataFrameReader.csv
      • pyspark.sql.DataFrameReader.format
      • pyspark.sql.DataFrameReader.jdbc
      • pyspark.sql.DataFrameReader.json
      • pyspark.sql.DataFrameReader.load
      • pyspark.sql.DataFrameReader.option
      • pyspark.sql.DataFrameReader.options
      • pyspark.sql.DataFrameReader.orc
      • pyspark.sql.DataFrameReader.parquet
      • pyspark.sql.DataFrameReader.schema
      • pyspark.sql.DataFrameReader.table
      • pyspark.sql.DataFrameReader.text
      • pyspark.sql.DataFrameWriter.bucketBy
      • pyspark.sql.DataFrameWriter.csv
      • pyspark.sql.DataFrameWriter.format
      • pyspark.sql.DataFrameWriter.insertInto
      • pyspark.sql.DataFrameWriter.jdbc
      • pyspark.sql.DataFrameWriter.json
      • pyspark.sql.DataFrameWriter.mode
      • pyspark.sql.DataFrameWriter.option
      • pyspark.sql.DataFrameWriter.options
      • pyspark.sql.DataFrameWriter.orc
      • pyspark.sql.DataFrameWriter.parquet
      • pyspark.sql.DataFrameWriter.partitionBy
      • pyspark.sql.DataFrameWriter.save
      • pyspark.sql.DataFrameWriter.saveAsTable
      • pyspark.sql.DataFrameWriter.sortBy
      • pyspark.sql.DataFrameWriter.text
      • pyspark.sql.DataFrameWriterV2.using
      • pyspark.sql.DataFrameWriterV2.option
      • pyspark.sql.DataFrameWriterV2.options
      • pyspark.sql.DataFrameWriterV2.tableProperty
      • pyspark.sql.DataFrameWriterV2.partitionedBy
      • pyspark.sql.DataFrameWriterV2.create
      • pyspark.sql.DataFrameWriterV2.replace
      • pyspark.sql.DataFrameWriterV2.createOrReplace
      • pyspark.sql.DataFrameWriterV2.append
      • pyspark.sql.DataFrameWriterV2.overwrite
      • pyspark.sql.DataFrameWriterV2.overwritePartitions
      • pyspark.sql.MergeIntoWriter.whenMatched
      • pyspark.sql.MergeIntoWriter.whenNotMatched
      • pyspark.sql.MergeIntoWriter.whenNotMatchedBySource
      • pyspark.sql.MergeIntoWriter.withSchemaEvolution
      • pyspark.sql.MergeIntoWriter.merge
    • DataFrame
      • pyspark.sql.DataFrame.__getattr__
      • pyspark.sql.DataFrame.__getitem__
      • pyspark.sql.DataFrame.agg
      • pyspark.sql.DataFrame.alias
      • pyspark.sql.DataFrame.approxQuantile
      • pyspark.sql.DataFrame.cache
      • pyspark.sql.DataFrame.checkpoint
      • pyspark.sql.DataFrame.coalesce
      • pyspark.sql.DataFrame.colRegex
      • pyspark.sql.DataFrame.collect
      • pyspark.sql.DataFrame.columns
      • pyspark.sql.DataFrame.corr
      • pyspark.sql.DataFrame.count
      • pyspark.sql.DataFrame.cov
      • pyspark.sql.DataFrame.createGlobalTempView
      • pyspark.sql.DataFrame.createOrReplaceGlobalTempView
      • pyspark.sql.DataFrame.createOrReplaceTempView
      • pyspark.sql.DataFrame.createTempView
      • pyspark.sql.DataFrame.crossJoin
      • pyspark.sql.DataFrame.crosstab
      • pyspark.sql.DataFrame.cube
      • pyspark.sql.DataFrame.describe
      • pyspark.sql.DataFrame.distinct
      • pyspark.sql.DataFrame.drop
      • pyspark.sql.DataFrame.dropDuplicates
      • pyspark.sql.DataFrame.dropDuplicatesWithinWatermark
      • pyspark.sql.DataFrame.drop_duplicates
      • pyspark.sql.DataFrame.dropna
      • pyspark.sql.DataFrame.dtypes
      • pyspark.sql.DataFrame.exceptAll
      • pyspark.sql.DataFrame.executionInfo
      • pyspark.sql.DataFrame.explain
      • pyspark.sql.DataFrame.fillna
      • pyspark.sql.DataFrame.filter
      • pyspark.sql.DataFrame.first
      • pyspark.sql.DataFrame.foreach
      • pyspark.sql.DataFrame.foreachPartition
      • pyspark.sql.DataFrame.freqItems
      • pyspark.sql.DataFrame.groupBy
      • pyspark.sql.DataFrame.groupingSets
      • pyspark.sql.DataFrame.head
      • pyspark.sql.DataFrame.hint
      • pyspark.sql.DataFrame.inputFiles
      • pyspark.sql.DataFrame.intersect
      • pyspark.sql.DataFrame.intersectAll
      • pyspark.sql.DataFrame.isEmpty
      • pyspark.sql.DataFrame.isLocal
      • pyspark.sql.DataFrame.isStreaming
      • pyspark.sql.DataFrame.join
      • pyspark.sql.DataFrame.limit
      • pyspark.sql.DataFrame.localCheckpoint
      • pyspark.sql.DataFrame.mapInPandas
      • pyspark.sql.DataFrame.mapInArrow
      • pyspark.sql.DataFrame.melt
      • pyspark.sql.DataFrame.na
      • pyspark.sql.DataFrame.observe
      • pyspark.sql.DataFrame.offset
      • pyspark.sql.DataFrame.orderBy
      • pyspark.sql.DataFrame.persist
      • pyspark.sql.DataFrame.printSchema
      • pyspark.sql.DataFrame.randomSplit
      • pyspark.sql.DataFrame.rdd
      • pyspark.sql.DataFrame.registerTempTable
      • pyspark.sql.DataFrame.repartition
      • pyspark.sql.DataFrame.repartitionByRange
      • pyspark.sql.DataFrame.replace
      • pyspark.sql.DataFrame.rollup
      • pyspark.sql.DataFrame.sameSemantics
      • pyspark.sql.DataFrame.sample
      • pyspark.sql.DataFrame.sampleBy
      • pyspark.sql.DataFrame.schema
      • pyspark.sql.DataFrame.select
      • pyspark.sql.DataFrame.selectExpr
      • pyspark.sql.DataFrame.semanticHash
      • pyspark.sql.DataFrame.show
      • pyspark.sql.DataFrame.sort
      • pyspark.sql.DataFrame.sortWithinPartitions
      • pyspark.sql.DataFrame.sparkSession
      • pyspark.sql.DataFrame.stat
      • pyspark.sql.DataFrame.storageLevel
      • pyspark.sql.DataFrame.subtract
      • pyspark.sql.DataFrame.summary
      • pyspark.sql.DataFrame.tail
      • pyspark.sql.DataFrame.take
      • pyspark.sql.DataFrame.to
      • pyspark.sql.DataFrame.toArrow
      • pyspark.sql.DataFrame.toDF
      • pyspark.sql.DataFrame.toJSON
      • pyspark.sql.DataFrame.toLocalIterator
      • pyspark.sql.DataFrame.toPandas
      • pyspark.sql.DataFrame.transform
      • pyspark.sql.DataFrame.union
      • pyspark.sql.DataFrame.unionAll
      • pyspark.sql.DataFrame.unionByName
      • pyspark.sql.DataFrame.unpersist
      • pyspark.sql.DataFrame.unpivot
      • pyspark.sql.DataFrame.where
      • pyspark.sql.DataFrame.withColumn
      • pyspark.sql.DataFrame.withColumns
      • pyspark.sql.DataFrame.withColumnRenamed
      • pyspark.sql.DataFrame.withColumnsRenamed
      • pyspark.sql.DataFrame.withMetadata
      • pyspark.sql.DataFrame.withWatermark
      • pyspark.sql.DataFrame.write
      • pyspark.sql.DataFrame.writeStream
      • pyspark.sql.DataFrame.writeTo
      • pyspark.sql.DataFrame.mergeInto
      • pyspark.sql.DataFrame.pandas_api
      • pyspark.sql.DataFrameNaFunctions.drop
      • pyspark.sql.DataFrameNaFunctions.fill
      • pyspark.sql.DataFrameNaFunctions.replace
      • pyspark.sql.DataFrameStatFunctions.approxQuantile
      • pyspark.sql.DataFrameStatFunctions.corr
      • pyspark.sql.DataFrameStatFunctions.cov
      • pyspark.sql.DataFrameStatFunctions.crosstab
      • pyspark.sql.DataFrameStatFunctions.freqItems
      • pyspark.sql.DataFrameStatFunctions.sampleBy
    • Column
      • pyspark.sql.Column.__getattr__
      • pyspark.sql.Column.__getitem__
      • pyspark.sql.Column.alias
      • pyspark.sql.Column.asc
      • pyspark.sql.Column.asc_nulls_first
      • pyspark.sql.Column.asc_nulls_last
      • pyspark.sql.Column.astype
      • pyspark.sql.Column.between
      • pyspark.sql.Column.bitwiseAND
      • pyspark.sql.Column.bitwiseOR
      • pyspark.sql.Column.bitwiseXOR
      • pyspark.sql.Column.cast
      • pyspark.sql.Column.contains
      • pyspark.sql.Column.desc
      • pyspark.sql.Column.desc_nulls_first
      • pyspark.sql.Column.desc_nulls_last
      • pyspark.sql.Column.dropFields
      • pyspark.sql.Column.endswith
      • pyspark.sql.Column.eqNullSafe
      • pyspark.sql.Column.getField
      • pyspark.sql.Column.getItem
      • pyspark.sql.Column.ilike
      • pyspark.sql.Column.isNaN
      • pyspark.sql.Column.isNotNull
      • pyspark.sql.Column.isNull
      • pyspark.sql.Column.isin
      • pyspark.sql.Column.like
      • pyspark.sql.Column.name
      • pyspark.sql.Column.otherwise
      • pyspark.sql.Column.over
      • pyspark.sql.Column.rlike
      • pyspark.sql.Column.startswith
      • pyspark.sql.Column.substr
      • pyspark.sql.Column.try_cast
      • pyspark.sql.Column.when
      • pyspark.sql.Column.withField
    • Data Types
      • ArrayType
      • BinaryType
      • BooleanType
      • ByteType
      • DataType
      • DateType
      • DecimalType
      • DoubleType
      • FloatType
      • IntegerType
      • LongType
      • MapType
      • NullType
      • ShortType
      • StringType
      • CharType
      • VarcharType
      • StructField
      • StructType
      • VariantType
      • TimestampType
      • TimestampNTZType
      • DayTimeIntervalType
      • YearMonthIntervalType
      • CalendarIntervalType
    • Row
      • pyspark.sql.Row.asDict
    • Functions
      • pyspark.sql.functions.broadcast
      • pyspark.sql.functions.call_function
      • pyspark.sql.functions.col
      • pyspark.sql.functions.column
      • pyspark.sql.functions.lit
      • pyspark.sql.functions.expr
      • pyspark.sql.functions.coalesce
      • pyspark.sql.functions.ifnull
      • pyspark.sql.functions.nanvl
      • pyspark.sql.functions.nullif
      • pyspark.sql.functions.nullifzero
      • pyspark.sql.functions.nvl
      • pyspark.sql.functions.nvl2
      • pyspark.sql.functions.when
      • pyspark.sql.functions.zeroifnull
      • pyspark.sql.functions.equal_null
      • pyspark.sql.functions.ilike
      • pyspark.sql.functions.isnan
      • pyspark.sql.functions.isnotnull
      • pyspark.sql.functions.isnull
      • pyspark.sql.functions.like
      • pyspark.sql.functions.regexp
      • pyspark.sql.functions.regexp_like
      • pyspark.sql.functions.rlike
      • pyspark.sql.functions.asc
      • pyspark.sql.functions.asc_nulls_first
      • pyspark.sql.functions.asc_nulls_last
      • pyspark.sql.functions.desc
      • pyspark.sql.functions.desc_nulls_first
      • pyspark.sql.functions.desc_nulls_last
      • pyspark.sql.functions.abs
      • pyspark.sql.functions.acos
      • pyspark.sql.functions.acosh
      • pyspark.sql.functions.asin
      • pyspark.sql.functions.asinh
      • pyspark.sql.functions.atan
      • pyspark.sql.functions.atan2
      • pyspark.sql.functions.atanh
      • pyspark.sql.functions.bin
      • pyspark.sql.functions.bround
      • pyspark.sql.functions.cbrt
      • pyspark.sql.functions.ceil
      • pyspark.sql.functions.ceiling
      • pyspark.sql.functions.conv
      • pyspark.sql.functions.cos
      • pyspark.sql.functions.cosh
      • pyspark.sql.functions.cot
      • pyspark.sql.functions.csc
      • pyspark.sql.functions.degrees
      • pyspark.sql.functions.e
      • pyspark.sql.functions.exp
      • pyspark.sql.functions.expm1
      • pyspark.sql.functions.factorial
      • pyspark.sql.functions.floor
      • pyspark.sql.functions.greatest
      • pyspark.sql.functions.hex
      • pyspark.sql.functions.hypot
      • pyspark.sql.functions.least
      • pyspark.sql.functions.ln
      • pyspark.sql.functions.log
      • pyspark.sql.functions.log10
      • pyspark.sql.functions.log1p
      • pyspark.sql.functions.log2
      • pyspark.sql.functions.negate
      • pyspark.sql.functions.negative
      • pyspark.sql.functions.pi
      • pyspark.sql.functions.pmod
      • pyspark.sql.functions.positive
      • pyspark.sql.functions.pow
      • pyspark.sql.functions.power
      • pyspark.sql.functions.radians
      • pyspark.sql.functions.rand
      • pyspark.sql.functions.randn
      • pyspark.sql.functions.rint
      • pyspark.sql.functions.round
      • pyspark.sql.functions.sec
      • pyspark.sql.functions.sign
      • pyspark.sql.functions.signum
      • pyspark.sql.functions.sin
      • pyspark.sql.functions.sinh
      • pyspark.sql.functions.sqrt
      • pyspark.sql.functions.tan
      • pyspark.sql.functions.tanh
      • pyspark.sql.functions.try_add
      • pyspark.sql.functions.try_divide
      • pyspark.sql.functions.try_mod
      • pyspark.sql.functions.try_multiply
      • pyspark.sql.functions.try_subtract
      • pyspark.sql.functions.unhex
      • pyspark.sql.functions.width_bucket
      • pyspark.sql.functions.ascii
      • pyspark.sql.functions.base64
      • pyspark.sql.functions.bit_length
      • pyspark.sql.functions.btrim
      • pyspark.sql.functions.char
      • pyspark.sql.functions.char_length
      • pyspark.sql.functions.character_length
      • pyspark.sql.functions.collate
      • pyspark.sql.functions.collation
      • pyspark.sql.functions.concat_ws
      • pyspark.sql.functions.contains
      • pyspark.sql.functions.decode
      • pyspark.sql.functions.elt
      • pyspark.sql.functions.encode
      • pyspark.sql.functions.endswith
      • pyspark.sql.functions.find_in_set
      • pyspark.sql.functions.format_number
      • pyspark.sql.functions.format_string
      • pyspark.sql.functions.initcap
      • pyspark.sql.functions.instr
      • pyspark.sql.functions.lcase
      • pyspark.sql.functions.left
      • pyspark.sql.functions.length
      • pyspark.sql.functions.levenshtein
      • pyspark.sql.functions.locate
      • pyspark.sql.functions.lower
      • pyspark.sql.functions.lpad
      • pyspark.sql.functions.ltrim
      • pyspark.sql.functions.mask
      • pyspark.sql.functions.octet_length
      • pyspark.sql.functions.overlay
      • pyspark.sql.functions.position
      • pyspark.sql.functions.printf
      • pyspark.sql.functions.regexp_count
      • pyspark.sql.functions.regexp_extract
      • pyspark.sql.functions.regexp_extract_all
      • pyspark.sql.functions.regexp_instr
      • pyspark.sql.functions.regexp_replace
      • pyspark.sql.functions.regexp_substr
      • pyspark.sql.functions.repeat
      • pyspark.sql.functions.replace
      • pyspark.sql.functions.right
      • pyspark.sql.functions.rpad
      • pyspark.sql.functions.rtrim
      • pyspark.sql.functions.sentences
      • pyspark.sql.functions.soundex
      • pyspark.sql.functions.split
      • pyspark.sql.functions.split_part
      • pyspark.sql.functions.startswith
      • pyspark.sql.functions.substr
      • pyspark.sql.functions.substring
      • pyspark.sql.functions.substring_index
      • pyspark.sql.functions.to_binary
      • pyspark.sql.functions.to_char
      • pyspark.sql.functions.to_number
      • pyspark.sql.functions.to_varchar
      • pyspark.sql.functions.translate
      • pyspark.sql.functions.trim
      • pyspark.sql.functions.try_to_binary
      • pyspark.sql.functions.try_to_number
      • pyspark.sql.functions.ucase
      • pyspark.sql.functions.unbase64
      • pyspark.sql.functions.upper
      • pyspark.sql.functions.bit_count
      • pyspark.sql.functions.bit_get
      • pyspark.sql.functions.bitwise_not
      • pyspark.sql.functions.getbit
      • pyspark.sql.functions.shiftleft
      • pyspark.sql.functions.shiftright
      • pyspark.sql.functions.shiftrightunsigned
      • pyspark.sql.functions.add_months
      • pyspark.sql.functions.convert_timezone
      • pyspark.sql.functions.curdate
      • pyspark.sql.functions.current_date
      • pyspark.sql.functions.current_timestamp
      • pyspark.sql.functions.current_timezone
      • pyspark.sql.functions.date_add
      • pyspark.sql.functions.date_diff
      • pyspark.sql.functions.date_format
      • pyspark.sql.functions.date_from_unix_date
      • pyspark.sql.functions.date_part
      • pyspark.sql.functions.date_sub
      • pyspark.sql.functions.date_trunc
      • pyspark.sql.functions.dateadd
      • pyspark.sql.functions.datediff
      • pyspark.sql.functions.datepart
      • pyspark.sql.functions.day
      • pyspark.sql.functions.dayname
      • pyspark.sql.functions.dayofmonth
      • pyspark.sql.functions.dayofweek</