Created
November 13, 2018 13:27
-
-
Save hangingman/1818368f9ad6fb3f51c7719c1cd858d9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
from pyspark.sql import SparkSession | |
from pyspark import SparkContext | |
from pyspark.sql import Row | |
from pprint import pprint | |
import sys | |
reload(sys) | |
sys.setdefaultencoding('utf-8') | |
path = './sample-sjis.txt' | |
with open(path) as f: | |
str_list = map(lambda l: l.decode('shift-jis'), f.readlines()) | |
sc = SparkContext() | |
spark = SparkSession(sc) | |
pprint(str_list) | |
row = Row('title') | |
rdd = sc.parallelize(str_list) | |
df = rdd.map(row).toDF() | |
df.show() | |
import shutil | |
shutil.rmtree('sample-utf8.csv') | |
# 書き出してみる | |
df.select('title') \ | |
.coalesce(1) \ | |
.write \ | |
.format('com.databricks.spark.csv') \ | |
.option("overwrite", "true") \ | |
.save('sample-utf8.csv') | |
sc.stop() |
Author
hangingman
commented
Nov 13, 2018
databricksだけで完結
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from pyspark.sql import SparkSession
from pyspark import SparkContext
from pyspark.sql import Row
from pprint import pprint
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
sc = SparkContext()
spark = SparkSession(sc)
df = spark.read \
.format('com.databricks.spark.csv') \
.option('header', 'false') \
.option('inferschema', 'false') \
.option('charset', 'shift-jis') \
.option('delimiter', '\t') \
.load('sample-sjis.txt')
df = df.withColumnRenamed('_c0', 'title')
df.show()
#import shutil
#shutil.rmtree('sample-utf8.csv')
# 書き出してみる
df.select('title') \
.coalesce(1) \
.write \
.format('com.databricks.spark.csv') \
.option("overwrite", "true") \
.save('sample-utf8.csv')
sc.stop()
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment