ledell

# library(devtools)
# devtools::install_github("rladies/meetupr")
library(meetupr)

# Log in to meetup.com, your key is here: https://secure.meetup.com/meetup_api/key/
api_key <- "YOUR_API_KEY_HERE"

# `urlname` is a human-readable unique id for a meetup, e.g. https://www.meetup.com/R-Ladies-Budapest/
urlname <- "R-Ladies-Budapest"  

ledell

Keybase proof

I hereby claim:

• I am ledell on github.
• I am ledell (https://keybase.io/ledell) on keybase.
• I have a public key ASCjbi8x4k_o5EN-N0Vu1Ns_UnyXr3hwC2W4Lr7xrR4djQo

To claim this, I am signing this object:

ledell

# https://ropensci.org/tutorials/arxiv_tutorial.html
install.packages("aRxiv")

library(aRxiv)
library(stringr)
library(ggplot2)

# Query arxiv: 6892 results including "Deep"; 49 DeepThings (Sept 21, 2017)
df <- arxiv_search('ti:"Deep"', batchsize = 1000, limit = 100000)
titles <- grep(pattern = "Deep[[:upper:]][[:lower:]]+", 

ledell

# H2O's K-Means algo can estimate the optimal number of clusters (method by Leland Wilkinson)
# http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/k-means.html#estimating-k-in-k-means
#
# This demo is an extension of Kasia's blog post here: 
# https://kkulma.github.io/2017-04-24-determining-optimal-number-of-clusters-in-your-data/

library(rattle)  # wine data

# Remove the factor col & convert to an H2O Frame
# Note: You can skip the scale() here since H2O K-Means standardizes automatically

ledell

library(h2o)
h2o.init()


# Load the HIGGS dataset
train <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_train_10k.csv")
test <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_test_5k.csv")
y <- "response"
x <- setdiff(names(train), y)
family <- "binomial"

ledell

# Set API Key
Sys.setenv(SIGOPT_API_TOKEN="HERE")

# Start a local H2O cluster for training models
library(h2o)
h2o.init(nthreads = -1)

# Load a dataset
data(iris)
y <- "Species"

ledell

library(h2o)
h2o.init(nthreads = -1)

# Import a sample binary outcome train/test set into H2O
train <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_train_10k.csv")
test <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_test_5k.csv")

# Identify predictors and response
y <- "response"
x <- setdiff(names(train), y)

ledell

import h2o
from h2o.estimators.random_forest import H2ORandomForestEstimator
from h2o.estimators.gbm import H2OGradientBoostingEstimator
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
from h2o.grid.grid_search import H2OGridSearch
from __future__ import print_function


h2o.init(nthreads=-1)

ledell

# This example is outdated because we have the H2O Stacked Ensemble function now (so it's better to use that):
# http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html

import h2o
from h2o.estimators.gbm import H2OGradientBoostingEstimator
from h2o.estimators.deeplearning import H2ODeepLearningEstimator
from h2o.estimators.glm import H2OGeneralizedLinearEstimator
from h2o.estimators.random_forest import H2ORandomForestEstimator
from sklearn import metrics  #will be replaced with ensemble_performance later

ledell

import h2o
from h2o.estimators.glm import H2OGeneralizedLinearEstimator



def make_Z(models):
	'''
	Takes a list of models and creates level-one data
	'''