doppiomacchiatto

# You need to install scikit-learn:
# sudo pip install scikit-learn
#
# Dataset: Polarity dataset v2.0
# http://www.cs.cornell.edu/people/pabo/movie-review-data/
#
# Full discussion:
# https://marcobonzanini.wordpress.com/2015/01/19/sentiment-analysis-with-python-and-scikit-learn

doppiomacchiatto

Count stats for twitter stream and store in Cassandra

cd $SPARK_HOME

/bin/spark-submit --packages TargetHolding/pyspark-cassandra:0.3.5 /Users/drehman/Apps/workspace/spark_cassandra_stream_example.py

python twitter_rolling_count.py -q data -d data 2>&1 | nc -lk 10.0.0.235 9999

doppiomacchiatto

{
  "taskDefinitionArn": "arn:aws:ecs:us-west-2:<scc number>:task-definition/build-blog:3",
  "revision": 3,
  "containerDefinitions": [
    {
      "volumesFrom": [],
      "portMappings": [],
      "command": [],
      "environment": [
        {

doppiomacchiatto

#!/bin/bash

# get all running docker container names
containers=$(sudo docker ps | awk '{if(NR>1) print $NF}')
host=$(hostname)

# loop through all containers
for container in $containers
do
  echo "Container: $container"

doppiomacchiatto

import nltk
with open('sample.txt', 'r') as f:
    sample = f.read()


sentences = nltk.sent_tokenize(sample)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)

doppiomacchiatto

# Useful links:
# http://zookeeper.apache.org/doc/trunk/zookeeperStarted.html
mkdir zookeeper
cd zookeeper
curl http://mirror.olnevhost.net/pub/apache/zookeeper/zookeeper-3.4.6/zookeeper-3.4.6.tar.gz | tar xz
ln -s zookeeper-3.4.6/ latest
cat <<EOF > latest/conf/zoo.cfg
tickTime=2000
dataDir=$(pwd)/latest
clientPort=2181

doppiomacchiatto

# Copyright (c) 2012-2013 Mitch Garnaat http://garnaat.org/
# Copyright 2012-2014 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
# http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is

doppiomacchiatto

import boto3

def role_arn_to_session(**args):
    """
    Usage :
        session = role_arn_to_session(
            RoleArn='arn:aws:iam::012345678901:role/example-role',
            RoleSessionName='ExampleSessionName')
        client = session.client('sqs')
    """

doppiomacchiatto

apply plugin: 'java'
apply plugin: 'spring-boot'
apply plugin: 'eclipse'
apply plugin: 'idea'

// mainClass =  'org.liqweed.boot.ServerStarter'

ext {
	springVersion = '4.0.3.RELEASE'
	springBootVersion = '1.0.1.RELEASE'

doppiomacchiatto

#!/usr/bin/env python
import sys
import json

from boto.s3.connection import S3Connection
from boto.s3.prefix import Prefix
from boto.s3.key import Key

bucketname = sys.argv[1]
delimiter = '/'