在PySpark中选择具有最小空字段值的记录

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

spark = SparkSession.builder.appName("MinNullFields").getOrCreate()

df = spark.read.csv("path/to/data.csv", header=True, inferSchema=True)

df_no_null = df.na.drop()

min_null_record = df_no_null.agg(*[col(c).isNull().cast("int").alias(c) for c in df_no_null.columns]).orderBy(*df_no_null.columns).limit(1)

min_null_record.show()