Please note that matrix entity is of type long, long, double
Reference: https://spark.apache.org/docs/2.1.0/api/scala/index.html#org.apache.spark.mllib.linalg.distributed.MatrixEntry
Also, as user/ item columns are string, those need to be indexed before processing. Here is how you can create coordinatematrix with scala:
//Imports needed
scala> import org.apache.spark.mllib.linalg.distributed.CoordinateMatrix
import org.apache.spark.mllib.linalg.distributed.CoordinateMatrix
scala> import org.apache.spark.mllib.linalg.distributed.MatrixEntry
import org.apache.spark.mllib.linalg.distributed.MatrixEntry
scala> import org.apache.spark.ml.feature.StringIndexer
import org.apache.spark.ml.feature.StringIndexer
//Let's create a dummy dataframe
scala> val df = spark.sparkContext.parallelize(List(
| ("u1","i1" ,true),
| ("u1","i2" ,true),
| ("u2","i3" ,false),
| ("u2","i4" ,false),
| ("u3","i1" ,true),
| ("u3","i3" ,true),
| ("u4","i3" ,false),
| ("u4","i4" ,false))).toDF("user","item","bought")
df: org.apache.spark.sql.DataFrame = [user: string, item: string ... 1 more field]
scala> df.show
+----+----+------+
|user|item|bought|
+----+----+------+
| u1| i1| true|
| u1| i2| true|
| u2| i3| false|
| u2| i4| false|
| u3| i1| true|
| u3| i3| true|
| u4| i3| false|
| u4| i4| false|
+----+----+------+
//Index user/ item columns
scala> val indexer1 = new StringIndexer().setInputCol("user").setOutputCol("userIndex")
indexer1: org.apache.spark.ml.feature.StringIndexer = strIdx_2de8d35b8301
scala> val indexed1 = indexer1.fit(df).transform(df)
indexed1: org.apache.spark.sql.DataFrame = [user: string, item: string ... 2 more fields]
scala> val indexer2 = new StringIndexer().setInputCol("item").setOutputCol("itemIndex")
indexer2: org.apache.spark.ml.feature.StringIndexer = strIdx_493ce45dbec3
scala> val indexed2 = indexer2.fit(indexed1).transform(indexed1)
indexed2: org.apache.spark.sql.DataFrame = [user: string, item: string ... 3 more fields]
scala> val tempDF = indexed2.withColumn("userIndex",indexed2("userIndex").cast("long")).withColumn("itemIndex",indexed2("itemIndex").cast("long")).withColumn("bought",indexed2("bought").cast("double")).select("userIndex","itemIndex","bought")
tempDF: org.apache.spark.sql.DataFrame = [userIndex: bigint, itemIndex: bigint ... 1 more field]
scala> tempDF.show
+---------+---------+------+
|userIndex|itemIndex|bought|
+---------+---------+------+
| 0| 1| 1.0|
| 0| 3| 1.0|
| 1| 0| 0.0|
| 1| 2| 0.0|
| 2| 1| 1.0|
| 2| 0| 1.0|
| 3| 0| 0.0|
| 3| 2| 0.0|
+---------+---------+------+
//Create coordinate matrix of size 4*4
scala> val corMat = new CoordinateMatrix(tempDF.rdd.map(m => MatrixEntry(m.getLong(0),m.getLong(1),m.getDouble(2))), 4, 4)
corMat: org.apache.spark.mllib.linalg.distributed.CoordinateMatrix = org.apache.spark.mllib.linalg.distributed.CoordinateMatrix@16be6b36
//Check the content of coordinate matrix
scala> corMat.entries.collect
res2: Array[org.apache.spark.mllib.linalg.distributed.MatrixEntry] = Array(MatrixEntry(0,1,1.0), MatrixEntry(0,3,1.0), MatrixEntry(1,0,0.0), MatrixEntry(1,2,0.0), MatrixEntry(2,1,1.0), MatrixEntry(2,0,1.0), MatrixEntry(3,0,0.0), MatrixEntry(3,2,0.0))
Hope, this helps!