将pyspark中的null替换为"“

from pyspark.sql import SparkSession

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("Alice", 25, None), ("Bob", None, 30), ("Charlie", 35, 40)]
df = spark.createDataFrame(data, ["name", "age", "score"])

# 将null值替换为"unknown"
df_filled = df.na.fill("unknown")

# 显示替换后的数据
df_filled.show()

+-------+---+-----+
|   name|age|score|
+-------+---+-----+
|  Alice| 25|unknown|
|    Bob|unknown|   30|
|Charlie| 35|   40|
+-------+---+-----+

# 删除包含null值的行
df_dropped = df.na.drop()

# 显示删除后的数据
df_dropped.show()

+-------+---+-----+
|   name|age|score|
+-------+---+-----+
|Charlie| 35|   40|
+-------+---+-----+