from pyspark.sql.types import StructType,StructField, StringType, IntegerType

CreatingDataFrame = [("James","Sales","NY",90000,34,10000),
    ("Michael","Sales","NY",86000,56,20000),
    ("Robert","Sales","CA",81000,30,23000),
    ("Maria","Finance","CA",90000,24,23000),
    ("Raman","Finance","CA",99000,40,24000),
    ("Scott","Finance","NY",83000,36,19000),
    ("Jen","Finance","NY",79000,53,15000),
    ("Jeff","Marketing","CA",80000,25,18000),
    ("Kumar","Marketing","NY",91000,50,21000)
  ]

schema = StructType([ \
    StructField("employee_name",StringType(),True), \
    StructField("department",StringType(),True), \
    StructField("state",StringType(),True), \
    StructField("salary", IntegerType(), True), \
    StructField("age", StringType(), True), \
    StructField("bonus", IntegerType(), True) \
  ])

 
OurData = spark.createDataFrame(data=CreatingDataFrame,schema=schema)

OurData.show()

# COMMAND ----------

GrouppedBonusData=OurData.groupBy("department").sum("bonus")


# COMMAND ----------

GrouppedBonusData.show()


# COMMAND ----------

GrouppedBonusData.printSchema()

# COMMAND ----------

from pyspark.sql.functions import col

BonusColumnRenamed = GrouppedBonusData.select(col("department").alias("department"), col("sum(bonus)").alias("Total_Bonus"))
BonusColumnRenamed.show()

# COMMAND ----------

GrouppedBonusData.groupBy("department").count().show()

# COMMAND ----------

GrouppedSalaryData=OurData.groupBy("department").sum("salary")

# COMMAND ----------

GrouppedSalaryData.show()

# COMMAND ----------

from pyspark.sql.functions import col

SalaryColumnRenamed = GrouppedSalaryData.select(col("department").alias("Department"), col("sum(salary)").alias("Total_Salary"))
SalaryColumnRenamed.show()

df。withColumnRenamed(“年龄”、“age2”)

这是一个用循环重命名多个列的简单方法:

cols_to_rename = ["col1","col2","col3"]

for col in cols_to_rename:
  df = df.withColumnRenamed(col,"new_{}".format(col))

最简单的解决方案是使用withcolumnrename:

renamed_df = df.withColumnRenamed(‘name_1’, ‘New_name_1’).withColumnRenamed(‘name_2’, ‘New_name_2’)
renamed_df.show()

如果你想这样做，就像我们对Pandas做的那样，你可以使用toDF:

创建一个新列的顺序列表并将其传递给toDF

df_list = ["newName_1", “newName_2", “newName_3", “newName_4"]
renamed_df = df.toDF(*df_list)
renamed_df.show()

另一种重命名一个列的方法(使用import pyspark.sql.functions as F):

df = df.select( '*', F.col('count').alias('new_count') ).drop('count')

如果你想对所有列名应用一个简单的转换，这段代码可以做到:(我用下划线替换所有空格)

new_column_name_list= list(map(lambda x: x.replace(" ", "_"), df.columns))

df = df.toDF(*new_column_name_list)

感谢@user8117731的toDf技巧。