在pyspark中填充各种缺失的分类数据

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

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

# 创建示例数据集
data = [("Alice", "Female", 25),
        ("Bob", None, 30),
        ("Charlie", "Male", None)]

df = spark.createDataFrame(data, ["Name", "Gender", "Age"])

# 填充缺失的分类数据
filled_df = df.fillna({"Gender": "Unknown"})

# 显示填充后的数据
filled_df.show()