17 lines
398 B
Python
17 lines
398 B
Python
import pyspark
|
|
from pyspark.sql import SQLContext
|
|
from pyspark.sql.functions import hour, when, col, date_format, to_timestamp
|
|
from pyspark.sql.functions import *
|
|
|
|
# sc = pyspark.SparkContext(appName="HW3-Q1")
|
|
# sqlContext = SQLContext(sc)
|
|
|
|
# def load_data():
|
|
# df = sqlContext.read.option("header",True).csv("./temp.csv")
|
|
# return df
|
|
|
|
# df = load_data()
|
|
# #df.printSchema()
|
|
|
|
print('done')
|