Quy Nguyen trungquy

Categoical data - a fixed list of values, eg: gender, country/market/language, age group
Ordinal data - order is important. Exmaple: ranking, datetime
Numeric data

	import cv2
	import time
	import math
	import numpy as np
	import tensorflow as tf

	class SsdAnchorsCalculatorOptions:
	def __init__(self, input_size_width, input_size_height, min_scale, max_scale
	, num_layers, feature_map_width, feature_map_height
	, strides, aspect_ratios, anchor_offset_x=0.5, anchor_offset_y=0.5

	# source: https://stackoverflow.com/questions/37471346/automatically-and-elegantly-flatten-dataframe-in-spark-sql
	from pyspark.sql.types import StructType, ArrayType

	def flatten(schema, prefix=None):
	fields = []
	for field in schema.fields:
	name = prefix + '.' + field.name if prefix else field.name
	dtype = field.dataType
	if isinstance(dtype, ArrayType):
	dtype = dtype.elementType

	But here some highlights that might be of interest:
	- discussion of approximation error, estimation error, and optimization error, rather than the more vague “bias / variance” trade off;
	- full treatment of gradient boosting, one of the most successful ML algorithms in use today (along with neural network models);
	- more emphasis on conditional probability modeling than is typical (you give me an input, I give you a probability distribution over outcomes — useful for anomaly detection and prediction intervals, among other things),
	- geometric explanation for what happens with ridge, lasso, and elastic net in the [very common in practice] case of correlated features;
	- guided derivation of when the penalty forms and constraint forms of regularization are equivalent, using Lagrangian duality (in homework), proof of the representer theorem with simple linear algebra,
	- independent of kernels, but then applied to kernelize linear methods;
	- a general treatment of backpropagation

	{
	"files.exclude": {
	"**/.git": true,
	"**/.svn": true,
	"**/.hg": true,
	"**/CVS": true,
	"**/.DS_Store": true,
	"*/.pyc": true
	},
	"telemetry.enableTelemetry": false,

	#!/bin/bash
	set -e

	# Usage:
	# rsync_parallel.sh [--parallel=N] [rsync args...]
	#
	# Options:
	# --parallel=N Use N parallel processes for transfer. Defaults to 10.
	#
	# Notes:

	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import cPickle as pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward

	# create a new bridge network with your subnet and gateway for your ip block
	$ docker network create --subnet 203.0.113.0/24 --gateway 203.0.113.254 iptastic

	# run a nginx container with a specific ip in that block
	$ docker run --rm -it --net iptastic --ip 203.0.113.2 nginx

	# curl the ip from any other place (assuming this is a public ip block duh)
	$ curl 203.0.113.2

	# BOOM golden