afraenkel

public class IntLinkedList {

    public class IntNode {
        public int item;
        private IntNode next;
    
        public IntNode(int i, IntNode n) {
            item = i;
            next = n;
        }

afraenkel

afraenkel

import pandas as pd
import numpy as np

# download data for example

from sklearn.datasets.california_housing import fetch_california_housing

d = fetch_california_housing()

df = pd.DataFrame(d['data'], columns=d['feature_names'])

afraenkel

import pyspark
from pyspark import SparkContext
from pyspark.sql import SQLContext
from pyspark.sql import functions as F
from pyspark.sql import types as T
from pyspark.sql import Window

sc = SparkContext()
sqlc = SQLContext(sc)

afraenkel

import os
from pathlib import Path
from subprocess import Popen
import boto3
import zipfile

# This script downloads all files from `download_bucket` to the ec2 instance (specified temp dir),
# unzips them on the instance
# creates the output bucket,
# uploads the unzipped file to the new bucket

afraenkel

afraenkel

afraenkel

#!/bin/bash

# need aws commandline interface installed (do "pip install awscli")
# need aws credentials set-up

# usage: start-tunnel.sh <INSTANCE-NAME>

instance_name=$1

key_name=$(aws ec2 \