atamborrino

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

atamborrino

from tensorflow import keras
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras import Model
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras.models import load_model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.layers import Input, Conv2D, Conv2DTranspose, MaxPooling2D, concatenate, Dropout,BatchNormalization
from tensorflow.keras.layers import Conv2D, Concatenate, MaxPooling2D
from tensorflow.keras.layers import UpSampling2D, Dropout, BatchNormalization

atamborrino

# src: https://www.kaggle.com/aglotero/another-iou-metric
def iou_metric(y_true_in, y_pred_in, print_table=False):
    labels = y_true_in
    y_pred = y_pred_in
    
    true_objects = 2
    pred_objects = 2

    intersection = np.histogram2d(labels.flatten(), y_pred.flatten(), bins=(true_objects, pred_objects))[0]

atamborrino

Classic ML:

• Customer churn prediction using improved balanced random forests https://sci-hub.tw/10.1016/j.eswa.2008.06.121
• Predicting Customer Churn: Extreme Gradient Boosting with Temporal Data https://arxiv.org/pdf/1802.03396v1.pdf

Class imbalance:

• Handling class imbalance in customer churn prediction https://sci-hub.tw/10.1016/j.eswa.2008.05.027
• Learning from Imbalanced Classes https://www.svds.com/learning-imbalanced-classes/
• Scikit-learn contrib Imbalanced Learn http://contrib.scikit-learn.org/imbalanced-learn/stable/index.html

DL:

• Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline https://arxiv.org/pdf/1611.06455.pdf
• Exploiting Multi-Channels Deep Convolutional Neural Networks for Multivariate Time Series Classification http://staff.ustc.edu.cn/~cheneh/paper_pdf/2016/YiZheng-FCS2016.pdf

atamborrino

atamborrino

Keybase proof

I hereby claim:

• I am atamborrino on github.
• I am atamborrino (https://keybase.io/atamborrino) on keybase.
• I have a public key ASBtyXFwZvKC4C4JCyiktqVzas0I6gsAnKjZp2OodH54Ogo

To claim this, I am signing this object:

atamborrino

import java.time.Instant
import shapeless._
import simulacrum._
import scala.concurrent.duration.FiniteDuration
import scala.language.implicitConversions
import scala.concurrent.duration._

@typeclass
trait Timed[A] {
  def getInstant(a: A): Instant

atamborrino

import cats.derived._, eq._, legacy._
import cats.implicits._ 

case class Foo(a: String, b: Int)
case class Bar(c: Boolean)

Foo("a", 0) === Foo("b", 0) // compile
Foo("a", 0) === Bar(true) // does not compile
Foo("a", 0) == Bar(true) // compile with warning

atamborrino

import ml.combust.mleap.runtime.{LeapFrame, LocalDataset, Row}
import ml.combust.mleap.runtime.types.{DoubleType, StructField, StructType, TensorType}
import ml.combust.mleap.tensor.Tensor
import resource._
import ml.combust.mleap.runtime.MleapSupport._
import scala.collection.JavaConverters._
import com.google.common.jimfs.{Configuration, Jimfs}
import ml.combust.bundle.BundleFile
import java.nio.file.{FileSystems, Files}

atamborrino

import java.util.concurrent._
import akka.dispatch.{Dispatcher, ExecutorServiceDelegate}
import config.Config
import helpers.ScalaLogger

class ExecutionContextMonitor()(implicit metricsService: MetricsClient, config: Config) {
  private val log = ScalaLogger.get(this.getClass)

  private val scheduler = Executors.newSingleThreadScheduledExecutor()