如何在PySpark中从向量结构中获取项目

from pyspark.ml.feature import VectorAssembler

assembler = VectorAssembler(
    inputCols=["col1", "col2", "col3"],
    outputCol="features"
)

output = assembler.transform(dataset)

from pyspark.ml.feature import VectorAssembler

# 创建一个示例数据集
data = [(1, 2, 3), (4, 5, 6), (7, 8, 9)]
dataset = spark.createDataFrame(data, ["col1", "col2", "col3"])

# 创建VectorAssembler对象
assembler = VectorAssembler(
    inputCols=["col1", "col2", "col3"],
    outputCol="features"
)

# 转换数据集
output = assembler.transform(dataset)

# 显示结果
output.show()

+----+----+----+-------------+
|col1|col2|col3|     features|
+----+----+----+-------------+
|   1|   2|   3| [1.0,2.0,3.0]|
|   4|   5|   6| [4.0,5.0,6.0]|
|   7|   8|   9| [7.0,8.0,9.0]|
+----+----+----+-------------+