John Robenalt robenalt

## pedantically_commented_playbook.yml
---
# ^^^ YAML documents must begin with the document separator "---"
#
#### Example docblock, I like to put a descriptive comment at the top of my
#### playbooks.
#
# Overview: Playbook to bootstrap a new host for configuration management.
# Applies to: production
# Description:
#   Ensures that a host is configured for management with Ansible.

## helloworld-win32-service.py
import win32serviceutil
import win32service
import win32event
import servicemanager
import socket
import time
import logging

logging.basicConfig(
    filename = 'c:\\Temp\\hello-service.log',

## read-flowfile-contents.py
from org.apache.nifi.processors.script import ExecuteScript
from org.apache.nifi.processor.io import InputStreamCallback
from java.io import BufferedReader, InputStreamReader

class ReadFirstLine(InputStreamCallback) :
    __line = None;

    def __init__(self) :
        pass

## pspark_config.py
	# Set up spark configuration
	conf = SparkConf().setMaster("yarn-client").setAppName("sparK-mer")
	#conf = SparkConf().setMaster("local[16]").setAppName("sparK-mer")
	conf.set("yarn.nodemanager.resource.cpu_vcores",args.C)
	# Saturate with executors
	conf.set("spark.executor.instances",executorInstances)
	conf.set("spark.executor.heartbeatInterval","5s")
	# cores per executor
	conf.set("spark.executor.cores",args.E)
	# set driver cores

## iterm2-solarized.md

      
              2 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                robenalt
                / iterm2-solarized.md
            
            
              Created
              July 18, 2016 12:50
                — forked from kevin-smets/iterm2-solarized.md
            
              
                iTerm2 + oh my zsh + solarized + Meslo powerline font (OS X / macOS)
              
          
## sklearn_randomforest_snip.py
%matplotlib inline

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import recall_score

## save_dataframe_pyspark.py
#from pyspark.sql import HiveContext
#sqlContext = HiveContext(sc)
query = """
select * from db.sometable where col>50
"""
results = sqlContext.sql(query)
result_writer = pyspark.sql.DataFrameWriter(results)
result_writer.saveAsTable('db.new_table_name',format='parquet', mode='overwrite',path='/path/to/new/data/files')

## scala_spark_logger.scala
// Set logging level for spark scala
Logger.getLogger("org").setLevel(Level.WARN)
Logger.getLogger("akka").setLevel(Level.WARN)

## read_avro_spark_1.3.0.py
# pyspark --packages com.databricks:spark-avro_2.10:1.0.0
# read avro files from 1.3.0 spark
df = sqlCtx.load("/path/to/my_avro", "com.databricks.spark.avro")

## run_commandline.scala
import scala.sys.process._
//"ls -la".!!
val result = "ls -la".!!
	---
	# ^^^ YAML documents must begin with the document separator "---"
	#
	#### Example docblock, I like to put a descriptive comment at the top of my
	#### playbooks.
	#
	# Overview: Playbook to bootstrap a new host for configuration management.
	# Applies to: production
	# Description:
	# Ensures that a host is configured for management with Ansible.
	import win32serviceutil
	import win32service
	import win32event
	import servicemanager
	import socket
	import time
	import logging

	logging.basicConfig(
	filename = 'c:\\Temp\\hello-service.log',
	from org.apache.nifi.processors.script import ExecuteScript
	from org.apache.nifi.processor.io import InputStreamCallback
	from java.io import BufferedReader, InputStreamReader

	class ReadFirstLine(InputStreamCallback) :
	__line = None;

	def __init__(self) :
	pass
	# Set up spark configuration
	conf = SparkConf().setMaster("yarn-client").setAppName("sparK-mer")
	#conf = SparkConf().setMaster("local[16]").setAppName("sparK-mer")
	conf.set("yarn.nodemanager.resource.cpu_vcores",args.C)
	# Saturate with executors
	conf.set("spark.executor.instances",executorInstances)
	conf.set("spark.executor.heartbeatInterval","5s")
	# cores per executor
	conf.set("spark.executor.cores",args.E)
	# set driver cores
	%matplotlib inline

	import pandas as pd
	import numpy as np
	from sklearn.ensemble import RandomForestClassifier
	from sklearn.cross_validation import train_test_split
	from sklearn.metrics import classification_report
	from sklearn.metrics import confusion_matrix
	from sklearn.metrics import accuracy_score
	from sklearn.metrics import recall_score
	#from pyspark.sql import HiveContext
	#sqlContext = HiveContext(sc)
	query = """
	select * from db.sometable where col>50
	"""
	results = sqlContext.sql(query)
	result_writer = pyspark.sql.DataFrameWriter(results)
	result_writer.saveAsTable('db.new_table_name',format='parquet', mode='overwrite',path='/path/to/new/data/files')
	// Set logging level for spark scala
	Logger.getLogger("org").setLevel(Level.WARN)
	Logger.getLogger("akka").setLevel(Level.WARN)
	# pyspark --packages com.databricks:spark-avro_2.10:1.0.0
	# read avro files from 1.3.0 spark
	df = sqlCtx.load("/path/to/my_avro", "com.databricks.spark.avro")
	import scala.sys.process._
	//"ls -la".!!
	val result = "ls -la".!!