rdd 方法:
routes = sc.parallelize([("A", 1, 2),("B", 1, 3), ("C", 2, 1) ])
cities = sc.parallelize([(1, "London"),(2, "Paris"), (3, "Tokyo")])
print routes.map(lambda x: (x[1], (x[0], x[2]))).join(cities) \
.map(lambda x: (x[1][0][1], (x[1][0][0], x[1][1]))).join(cities). \
map(lambda x: (x[1][0][0], x[1][0][1], x[1][1])).collect()
どちらが印刷されますか:
[('C', 'Paris', 'London'), ('A', 'London', 'Paris'), ('B', 'London', 'Tokyo')]
そしてSQLContextの方法:
from pyspark.sql import HiveContext
from pyspark.sql import SQLContext
df_routes = sqlContext.createDataFrame(\
routes, ["Route", "SourceCityID", "DestinationCityID"])
df_cities = sqlContext.createDataFrame(\
cities, ["CityID", "CityName"])
temp = df_routes.join(df_cities, df_routes.SourceCityID == df_cities.CityID) \
.select("Route", "DestinationCityID", "CityName")
.withColumnRenamed("CityName", "SourceCity")
print temp.join(df_cities, temp.DestinationCityID == df_cities.CityID) \
.select("Route", "SourceCity", "CityName")
.withColumnRenamed("CityName", "DestinationCity").collect()
どちらが印刷されますか:
[Row(Route=u'C', SourceCity=u'Paris', DestinationCity=u'London'),
Row(Route=u'A', SourceCity=u'London', DestinationCity=u'Paris'),
Row(Route=u'B', SourceCity=u'London', DestinationCity=u'Tokyo')]