使用另外两列中的信息并列放置两个PySpark df列

from pyspark.sql import SparkSession

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

# 创建两个DataFrame
df1 = spark.createDataFrame([(1, 'A'), (2, 'B'), (3, 'C')], ['id', 'col1'])
df2 = spark.createDataFrame([(4, 'D'), (5, 'E'), (6, 'F')], ['id', 'col2'])

# 使用withColumn()方法将两个DataFrame的列并列放置
df_combined = df1.withColumn('col2', df2['col2'])

# 显示结果
df_combined.show()

from pyspark.sql import SparkSession

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

# 创建两个DataFrame
df1 = spark.createDataFrame([(1, 'A'), (2, 'B'), (3, 'C')], ['id', 'col1'])
df2 = spark.createDataFrame([(1, 'D'), (2, 'E'), (3, 'F')], ['id', 'col2'])

# 使用join()方法将两个DataFrame合并
df_combined = df1.join(df2, on='id', how='inner')

# 显示结果
df_combined.show()