PySpark:计算行最小值，忽略零和空值

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

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

# 创建示例数据集
data = [(1, 2, 3, 0),
        (4, 5, 6, 7),
        (8, 9, None, 10),
        (11, 0, 13, 14),
        (15, 16, 17, None)]

df = spark.createDataFrame(data, ["col1", "col2", "col3", "col4"])

# 计算行的最小值，忽略零和空值
min_values = df.select(
    col("col1"),
    col("col2"),
    col("col3"),
    col("col4"),
    when(col("col1") != 0, col("col1")).otherwise(float("inf")).alias("min_col1"),
    when(col("col2") != 0, col("col2")).otherwise(float("inf")).alias("min_col2"),
    when(col("col3").isNotNull() & (col("col3") != 0), col("col3")).otherwise(float("inf")).alias("min_col3"),
    when(col("col4").isNotNull() & (col("col4") != 0), col("col4")).otherwise(float("inf")).alias("min_col4")
)

min_values.show()