用VectorAssembler计算平均值和最大值

from pyspark.ml.feature import VectorAssembler
from pyspark.ml.stat import Summarizer

# 假设有两个特征列：col1和col2
inputCols = ["col1", "col2"]
outputCol = "features"

# 创建VectorAssembler对象
assembler = VectorAssembler(inputCols=inputCols, outputCol=outputCol)

# 将特征列合并为向量列
data = assembler.transform(df)

# 使用Summarizer计算平均值和最大值
summary = data.select(outputCol).summary("mean", "max")

# 获取平均值和最大值
mean_values = summary.filter(summary["summary"] == "mean").first()[outputCol]
max_values = summary.filter(summary["summary"] == "max").first()[outputCol]

print("平均值：", mean_values)
print("最大值：", max_values)