1. 程式人生 > >用spark分析北京積分落戶資料,按使用者分數分析

用spark分析北京積分落戶資料,按使用者分數分析

按使用者分數分析

#匯入積分落戶人員名單資料
sqlContext = SQLContext(sc)
df = sqlContext.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load('jifenluohu.csv')
#print(df)
df.createOrReplaceTempView("jflh")
#df.show()
#按分數分析
#按分數倒序
spark.sql("select score,count(*) as num from jflh group by score order by score desc").show(30)
#按分數數量倒序
spark.sql("select score,count(*) as num from jflh group by score order by num desc").show(60)

+------+---+
| score|num|
+------+---+
|122.59|  1|
|121.25|  1|
|118.96|  1|
|118.21|  1|
|117.79|  1|
|117.34|  1|
|116.17|  1|
|116.13|  1|
|115.95|  1|
|115.91|  1|
|115.45|  1|
|115.29|  1|
|115.25|  1|
|115.21|  1|
|115.13|  1|
|114.88|  1|
| 114.5|  1|
|114.42|  1|
|113.67|  2|
|113.45|  1|
|113.25|  1|
|113.09|  1|
|112.66|  1|
|112.58|  1|
|112.25|  1|
|112.17|  1|
|112.05|  1|
|111.79|  1|
|111.75|  1|
| 111.7|  1|
+------+---+
only showing top 30 rows

+-----+---+
|score|num|
+-----+---+
| 91.0| 51|
| 93.0| 49|
|90.96| 47|
| 92.0| 44|
|91.25| 41|
|91.96| 41|
| 94.0| 38|
|92.46| 38|
|91.88| 36|
|90.79| 36|
|91.67| 35|
| 91.5| 35|
|92.29| 33|
| 94.5| 33|
|91.38| 33|
|93.21| 33|
|92.17| 33|
|90.83| 33|
|92.71| 33|
|91.33| 31|
|91.17| 31|
|93.63| 31|
|91.75| 31|
|90.75| 30|
|96.21| 30|
|91.29| 30|
|93.96| 30|
|92.96| 30|
|91.21| 29|
|92.67| 29|
|91.46| 29|
|91.08| 28|
|94.46| 28|
|92.21| 28|
|91.71| 28|
|90.92| 28|
|93.46| 28|
|91.54| 28|
| 92.5| 28|
|92.54| 27|
|92.08| 27|
|94.33| 27|
|93.25| 27|
|93.33| 27|
|93.71| 27|
|92.33| 27|
|95.79| 26|
|92.92| 26|
|92.63| 26|
|92.75| 26|
|92.04| 26|
|92.25| 26|
|95.21| 26|
|91.58| 25|
|92.13| 25|
|91.79| 25|
| 95.0| 25|
|93.75| 24|
|94.96| 24|
|92.58| 24|
+-----+---+
only showing top 60 rows