用pyspark df中的新元素填充空值

from pyspark.sql import SparkSession

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

# 创建示例DataFrame
data = [("Alice", 25, "F"),
        ("Bob", None, "M"),
        ("Charlie", 30, None)]

df = spark.createDataFrame(data, ["name", "age", "gender"])

# 填充空值
fill_values = {"age": 0, "gender": "Unknown"}
df_filled = df.fillna(fill_values)

# 显示填充后的DataFrame
df_filled.show()

+-------+---+------+
|   name|age|gender|
+-------+---+------+
|  Alice| 25|     F|
|    Bob|  0|     M|
|Charlie| 30|Unknown|
+-------+---+------+