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
import os | |
import sys | |
import argparse | |
import json | |
from shutil import rmtree | |
import re | |
import pypff | |
sys.setrecursionlimit(10000) |
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
#!/bin/bash | |
# from https://gist.githubusercontent.com/nehalecky/9258c01fb2077f51545a/raw/789f08141dc681cf1ad5da05455c2cd01d1649e8/install-py3-dataproc.sh | |
apt-get -y install python3 | |
echo "export PYSPARK_PYTHON=python3" | tee -a /etc/profile.d/spark_config.sh /etc/*bashrc /usr/lib/spark/conf/spark-env.sh | |
echo "Adding PYTHONHASHSEED=0 to profiles and spark-defaults.conf..." | |
echo "export PYTHONHASHSEED=0" | tee -a /etc/profile.d/spark_config.sh /etc/*bashrc /usr/lib/spark/conf/spark-env.sh | |
echo "spark.executorEnv.PYTHONHASHSEED=0" >> /etc/spark/conf/spark-defaults.conf |
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
import json, datetime | |
class RoundTripEncoder(json.JSONEncoder): | |
DATE_FORMAT = "%Y-%m-%d" | |
TIME_FORMAT = "%H:%M:%S" | |
def default(self, obj): | |
if isinstance(obj, datetime.datetime): | |
return { | |
"_type": "datetime", | |
"value": obj.strftime("%s %s" % ( |