标签：schema column font expr 3.1 highlight ref sql www
data数据源，请参考我的博客http://www.cnblogs.com/wwxbi/p/6063613.html
import org.apache.Spark.sql.DataFrameStatFunctions
import org.apache.spark.sql.functions._
相关系数
val df = Range(0,10,step=1).toDF("id").withColumn("rand1", rand(seed=10)).withColumn("rand2", rand(seed=27))
df: org.apache.spark.sql.DataFrame = [id: int, rand1: double ... 1 more field]
df.show
+---+-------------------+-------------------+
| id| rand1| rand2|
+---+-------------------+-------------------+
| 0|0.41371264720975787| 0.714105256846827|
| 1| 0.7311719281896606| 0.8143487574232506|
| 2| 0.9031701155118229| 0.5282207324381174|
| 3|0.09430205113458567| 0.4420100497826609|
| 4|0.38340505276222947| 0.9387162206758006|
| 5| 0.5569246135523511| 0.6398126862647711|
| 6| 0.4977441406613893| 0.9895498513115722|
| 7| 0.2076666106201438| 0.3398720242725498|
| 8| 0.9571919406508957|0.15042237695815963|
| 9| 0.7429395461204413| 0.7302723457066639|
+---+-------------------+-------------------+
df.stat.corr("rand1", "rand2", "pearson")
res24: Double = -0.10993962467082698
查看数据的统计分布情况
val colArray = Array("age", "yearsmarried", "religiousness", "education", "occupation", "rating")
// 查看数据的统计分布情况
val descrDF = data.describe("age", "yearsmarried", "religiousness", "education", "occupation", "rating")
descrDF: org.apache.spark.sql.DataFrame = [summary: string, age: string ... 5 more fields]
descrDF.selectExpr("summary",
"round(age,2) as age",
"round(yearsmarried,2) as yearsmarried",
"round(religiousness,2) as religiousness",
"round(education,2) as education",
"round(occupation,2) as occupation",
"round(rating,2) as rating").show(10, truncate = false)
+-------+-----+------------+-------------+---------+----------+------+
|summary|age |yearsmarried|religiousness|education|occupation|rating|
+-------+-----+------------+-------------+---------+----------+------+
|count |601.0|601.0 |601.0 |601.0 |601.0 |601.0 |
|mean |32.49|8.18 |3.12 |16.17 |4.19 |3.93 |
|stddev |9.29 |5.57 |1.17 |2.4 |1.82 |1.1 |
|min |17.5 |0.13 |1.0 |9.0 |1.0 |1.0 |
|max |57.0 |15.0 |5.0 |20.0 |7.0 |5.0 |
+-------+-----+------------+-------------+---------+----------+------+
统计字段中元素的个数
// 统计字段中元素的个数
val fi = data.stat.freqItems(colArray)
fi: org.apache.spark.sql.DataFrame = [age_freqItems: array<double>, yearsmarried_freqItems: array<double> ... 4 more fields]
fi.printSchema()
root
|-- age_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
|-- yearsmarried_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
|-- religiousness_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
|-- education_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
|-- occupation_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
|-- rating_freqItems: array (nullable = true)
| |-- element: double (containsNull = false)
val f = fi.selectExpr(
| "size(age_freqItems)",
| "size(yearsmarried_freqItems)",
| "size(religiousness_freqItems)",
| "size(education_freqItems)",
| "size(occupation_freqItems)",
| "size(rating_freqItems)")
f: org.apache.spark.sql.DataFrame = [size(age_freqItems): int, size(yearsmarried_freqItems): int ... 4 more fields]
f.show(10, truncate = false)
+-------------------+----------------------------+-----------------------------+-------------------------+--------------------------+----------------------+
|size(age_freqItems)|size(yearsmarried_freqItems)|size(religiousness_freqItems)|size(education_freqItems)|size(occupation_freqItems)|size(rating_freqItems)|
+-------------------+----------------------------+-----------------------------+-------------------------+--------------------------+----------------------+
|9 |8 |5 |7 |7 |5 |
+-------------------+----------------------------+-----------------------------+-------------------------+--------------------------+----------------------+
集合字段的元素
// 集合字段的元素
val f1 = data.stat.freqItems(Array("age", "yearsmarried", "religiousness"))
f1: org.apache.spark.sql.DataFrame = [age_freqItems: array<double>, yearsmarried_freqItems: array<double> ... 1 more field]
f1.show(10, truncate = false)
+------------------------------------------------------+-----------------------------------------------+-------------------------+
|age_freqItems |yearsmarried_freqItems |religiousness_freqItems |
+------------------------------------------------------+-----------------------------------------------+-------------------------+
|[32.0, 47.0, 22.0, 52.0, 37.0, 17.5, 27.0, 57.0, 42.0]|[0.75, 0.125, 1.5, 0.417, 4.0, 7.0, 10.0, 15.0]|[2.0, 5.0, 4.0, 1.0, 3.0]|
+------------------------------------------------------+-----------------------------------------------+-------------------------+
// 对数组的元素排序
f1.selectExpr("sort_array(age_freqItems)", "sort_array(yearsmarried_freqItems)", "sort_array(religiousness_freqItems)").show(10, truncate = false)
+------------------------------------------------------+-----------------------------------------------+-----------------------------------------+
|sort_array(age_freqItems, true) |sort_array(yearsmarried_freqItems, true) |sort_array(religiousness_freqItems, true)|
+------------------------------------------------------+-----------------------------------------------+-----------------------------------------+
|[17.5, 22.0, 27.0, 32.0, 37.0, 42.0, 47.0, 52.0, 57.0]|[0.125, 0.417, 0.75, 1.5, 4.0, 7.0, 10.0, 15.0]|[1.0, 2.0, 3.0, 4.0, 5.0] |
+------------------------------------------------------+-----------------------------------------------+-----------------------------------------+
// 集合字段的元素
val f2 = data.stat.freqItems(Array("education", "occupation", "rating"))
f2: org.apache.spark.sql.DataFrame = [education_freqItems: array<double>, occupation_freqItems: array<double> ... 1 more field]
f2.show(10, truncate = false)
+-----------------------------------------+-----------------------------------+-------------------------+
|education_freqItems |occupation_freqItems |rating_freqItems |
+-----------------------------------------+-----------------------------------+-------------------------+
|[17.0, 20.0, 14.0, 16.0, 9.0, 18.0, 12.0]|[2.0, 5.0, 4.0, 7.0, 1.0, 3.0, 6.0]|[2.0, 5.0, 4.0, 1.0, 3.0]|
+-----------------------------------------+-----------------------------------+-------------------------+
// 对数组的元素排序
f2.selectExpr("sort_array(education_freqItems)", "sort_array(occupation_freqItems)", "sort_array(rating_freqItems)").show(10, truncate = false)
+-----------------------------------------+--------------------------------------+----------------------------------+
|sort_array(education_freqItems, true) |sort_array(occupation_freqItems, true)|sort_array(rating_freqItems, true)|
+-----------------------------------------+--------------------------------------+----------------------------------+
|[9.0, 12.0, 14.0, 16.0, 17.0, 18.0, 20.0]|[1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0] |[1.0, 2.0, 3.0, 4.0, 5.0] |
+-----------------------------------------+--------------------------------------+----------------------------------+
Spark2 DataFrameStatFunctions探索性数据统计分析
标签：schema column font expr 3.1 highlight ref sql www
原文地址：http://www.cnblogs.com/wwxbi/p/6125363.html
