PySpark でベクター列を複数の列に分割するにはどうすればよいですか?

<code class="python">from pyspark.ml.functions import vector_to_array

(df
    .withColumn("xs", vector_to_array("vector")))
    .select(["word"] + [col("xs")[i] for i in range(3)]))</code>

<code class="python">from pyspark.ml.linalg import Vectors

df = sc.parallelize([
    ("assert", Vectors.dense([1, 2, 3])),
    ("require", Vectors.sparse(3, {1: 2}))
]).toDF(["word", "vector"])

def extract(row):
    return (row.word, ) + tuple(row.vector.toArray().tolist())

df.rdd.map(extract).toDF(["word"])  # Vector values will be named _2, _3, ...</code>

<code class="python">from pyspark.sql.functions import udf, col
from pyspark.sql.types import ArrayType, DoubleType

def to_array(col):
    def to_array_(v):
        return v.toArray().tolist()
    # Important: asNondeterministic requires Spark 2.3 or later
    # It can be safely removed i.e.
    # return udf(to_array_, ArrayType(DoubleType()))(col)
    # but at the cost of decreased performance
    return udf(to_array_, ArrayType(DoubleType())).asNondeterministic()(col)

(df
    .withColumn("xs", to_array(col("vector")))
    .select(["word"] + [col("xs")[i] for i in range(3)]))</code>