方法一:用pandas辅助
from pyspark import SparkContext
from pyspark.sql import SQLContext
import pandas as pd
sc = SparkContext()
sqlContext=SQLContext(sc)
df=pd.read_csv(r'D:\tc\security_train\security_train.csv')
sdf=sqlc.createDataFrame(df)
方法二:纯spark
from pyspark import SparkContext
from pyspark.sql import SQLContext
sc = SparkContext()
spark = SQLContext(sc)
dfcsv=spark.read.csv(r'D:\tc\security_train\security_train.csv',header=True)