当列未知时，按特定值过滤Spark Scala Dataframe中的列

import org.apache.spark.sql.functions._
import org.apache.spark.sql.Column

def filterColumnByValue(df: DataFrame, columnName: String, filterValue: String): DataFrame = {
    val filteredDf = df.filter(col(columnName) === filterValue)
    filteredDf
}

val filteredDf = filterColumnByValue(df, columnName, filterValue)

import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("Filter DataFrame by Column Value")
  .master("local")
  .getOrCreate()

import spark.implicits._

// 创建包含学生信息的Dataframe
val data = Seq(("Alice", 18, "女"), ("Bob", 20, "男"), ("Catherine", 19, "女"))
val df = data.toDF("姓名", "年龄", "性别")
df.show()

// 定义过滤函数
def filterColumnByValue(df: DataFrame, columnName: String, filterValue: String): DataFrame = {
    val filteredDf = df.filter(col(columnName) === filterValue)
    filteredDf
}

// 调用过滤函数来过滤Dataframe中的列
val filteredDf = filterColumnByValue(df, "性别", "女")
filteredDf.show()

+---------+---+---+
|     姓名|年龄|性别|
+---------+---+---+
|    Alice| 18| 女|
|      Bob| 20| 男|
|Catherine| 19| 女|
+---------+---+---+

+-------+---+---+
|   姓名|年龄|性别|
+-------+---+---+
|  Alice| 18| 女|
|Catherine| 19| 女|
+-------+---+---+