根据其他2列中的值向数据框中添加新列(需要Pyspark)

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

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

# 创建示例数据框
data = [("Alice", 25, 160),
        ("Bob", 30, 175),
        ("Charlie", 35, 180)]

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

# 添加新列
df_with_new_column = df.withColumn("Age_plus_Height", col("Age") + col("Height"))

# 显示结果
df_with_new_column.show()

+-------+---+------+----------------+
|   Name|Age|Height|Age_plus_Height |
+-------+---+------+----------------+
|  Alice| 25|   160|             185|
|    Bob| 30|   175|             205|
|Charlie| 35|   180|             215|
+-------+---+------+----------------+