pyspark中两个DataFrames列之间的差异

from pyspark.sql import SparkSession

# 创建SparkSession
spark = SparkSession.builder.appName("DataFrame Difference").getOrCreate()

# 创建第一个DataFrame
data1 = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
df1 = spark.createDataFrame(data1, ["Name", "Age"])

# 创建第二个DataFrame
data2 = [("Alice", 25), ("David", 40)]
df2 = spark.createDataFrame(data2, ["Name", "Age"])

# 计算两个DataFrame列之间的差异
diff_df = df1.subtract(df2)

# 显示差异结果
diff_df.show()

+-------+---+
|   Name|Age|
+-------+---+
|    Bob| 30|
|Charlie| 35|
+-------+---+