从csv文件向现有apache spark数据帧添加数据

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

spark = SparkSession.builder.appName("AddDataToDataFrame").getOrCreate()

schema = StructType([
    StructField("col1", StringType(), True),
    StructField("col2", IntegerType(), True),
    # 添加其他列的定义
])

df_csv = spark.read.csv("path/to/csv/file.csv", header=True, schema=schema)

data = [("value1", 1), ("value2", 2), ...]  # 新数据的列表
df_new = spark.createDataFrame(data, schema)

df_combined = df_csv.union(df_new)

df_combined.show()