pyspark 读取csv文件创建DataFrame

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'game-clicks.csv') 
sdf=sqlc.createDataFrame(df) 

方法二：纯spark

from pyspark import SparkContext 
from pyspark.sql import SQLContext
sc = SparkContext()
sqlContext = SQLContext(sc)
sqlContext.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load('game-clicks.csv')