2021.06.29 빅데이터 분석을 위한 스파크 프로그래밍 - DataFrame 함수
# sample_df1, sample_df2, ldf, rdf # sample dataFrame 1 Person = collections.namedtuple('Person', 'name age job') row1 = Person(name="hayoon", age=7, job="student") row2 = Person(name="sunwoo", age=13, job="student") row3 = Person(name="hajoo", age=5, job="kindergartener") row4 = Person(name="jinwoo", age=13, job="student") data = [row1, row2, row3, row4] sample_df = spark.createDataFrame(data) ..