pablete

## Java
sudo apt-get update
sudo apt-get install default-jdk

## Scala
sudo apt-get remove scala-library scala
sudo wget http://scala-lang.org/files/archive/scala-2.12.1.deb
sudo dpkg -i scala-2.12.1.deb
sudo apt-get update
sudo apt-get install scala

pablete

c.NotebookApp.allow_root = True
c.NotebookApp.ip = '0.0.0.0'
c.NotebookApp.token = ''

pablete

ruby '2.7.1'

gem 'rails', github: 'rails/rails'
gem 'tzinfo-data', '>= 1.2016.7'  # Don't rely on OSX/Linux timezone data

# Action Text
gem 'actiontext', github: 'basecamp/actiontext', ref: 'okra'
gem 'okra', github: 'basecamp/okra'

# Drivers

pablete

from sklearn.datasets import load_boston
import pandas as pd

import xgboost as xgb
from tensorboard_logger import configure, log_value
from sklearn.cross_validation import train_test_split


def logspy(env):
    log_value("train", env.evaluation_result_list[0][1], step=env.iteration)

pablete

Last updated: 2017-03-18

Searching for Files

Find images in a directory that don't have a DateTimeOriginal

exiftool -filename -filemodifydate -createdate -r -if '(not $datetimeoriginal) and $filetype eq "JPEG"' .

###Output photos that don't have datetimeoriginal to a CSV### Note this can take a long time if you have a lot of jpgs

pablete

        val uri = "http://www.yahoo.com"
        val reqEntity = Array[Byte]()

        val respEntity = for {
          request <- Marshal(reqEntity).to[RequestEntity]
          response <- Http().singleRequest(HttpRequest(method = HttpMethods.POST, uri = uri, entity = request))
          entity <- Unmarshal(response.entity).to[ByteString]
        } yield entity

        val payload = respEntity.andThen {

pablete

:spark-submit-options [ 
                       "--conf" "spark.driver.maxResultSize=10G"
                       "--conf" "spark.cores.max=150"
                       "--conf" "spark.driver.cores=2"
                       "--conf" "spark.driver.memory=24G"
                       "--conf" "spark.executor.cores=2"
                       "--conf" "spark.executor.memory=24G"
                       "--conf" "spark.scheduler.minRegisteredResourcesRatio=1.0"
                       "--conf" "spark.scheduler.maxRegisteredResourcesWaitingTime=1200"
                       "--conf" "spark.mesos.role=pvr"

pablete

      BDASSpark("com.netflix.simulation.terasort.TeraGen",
        None,
        List("$sortSize", "20", "/terasort/IN"),
        Some("2.0"),
        List(
          ("--conf", "spark.driver.cores=2"),
          ("--conf", "spark.driver.memory=24G"),
          ("--conf", "spark.executor.cores=2"),
          ("--conf", "spark.executor.memory=24G"),
          ("--conf", "spark.cores.max=40"),

pablete

Execute

shell> python mnist_tsne.py

Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting ./data/train-images-idx3-ubyte.gz
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting ./data/train-labels-idx1-ubyte.gz
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.

Extracting ./data/t10k-images-idx3-ubyte.gz

pablete

def time[R](block: => R): R = {
    val t0 = System.currentTimeMillis
    val result = block    // call-by-name
    val t1 = System.currentTimeMillis
    println("Elapsed time: " + (t1 - t0) + "ms")
    result
}