如何获取Pyspark dataframe的列是否包含NaN值？

from pyspark.sql.functions import isnan, sum as spark_sum

nan_check = df.select([spark_sum(isnan(col)).alias(col) for col in df.columns])

nan_count = nan_check.collect()[0].asDict()

nan_columns = [col for col, count in nan_count.items() if count > 0]

from pyspark.sql import SparkSession
from pyspark.sql.functions import isnan, sum as spark_sum

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

# 创建示例DataFrame
data = [("Alice", 25, 5.6),
        ("Bob", 30, None),
        ("Charlie", None, 6.1)]
df = spark.createDataFrame(data, ["name", "age", "height"])

# 获取包含NaN值的列
nan_check = df.select([spark_sum(isnan(col)).alias(col) for col in df.columns])
nan_count = nan_check.collect()[0].asDict()
nan_columns = [col for col, count in nan_count.items() if count > 0]

print("Columns with NaN values:", nan_columns)

Columns with NaN values: ['age', 'height']