In [1]:

    

from pyspark import SparkConf, SparkContext
## set up spark context
from pyspark.sql import SQLContext
sc = SparkContext()
sqlContext = SQLContext(sc)
## set up  SparkSession
from pyspark.sql import SparkSession

spark = SparkSession \
    .builder \
    .appName("Python Spark SQL basic example") \
    .config("spark.some.config.option", "some-value") \
    .getOrCreate()


    

In [2]:

    

from pyspark.ml.linalg import Vectors
densevector = Vectors.dense([1,3,4,2.5])


    

In [3]:

    

densevector


    

    
Out[3]:





DenseVector([1.0, 3.0, 4.0, 2.5])

In [4]:

    

densevector.toArray()


    

    
Out[4]:





array([ 1. ,  3. ,  4. ,  2.5])

In [5]:

    

sparseVector = Vectors.sparse(10, [1, 3], [3.0, 4.5])


    

In [6]:

    

sparseVector.toArray()


    

    
Out[6]:





array([ 0. ,  3. ,  0. ,  4.5,  0. ,  0. ,  0. ,  0. ,  0. ,  0. ])