ledell

### Kaggle Days SF: Hackathon submission (8th place) 

# I used the latest version of H2O (3.24.0.1)
# Latest stable always here: http://h2o-release.s3.amazonaws.com/h2o/latest_stable.html
# H2O 3.24.0.1: http://h2o-release.s3.amazonaws.com/h2o/rel-yates/1/index.html
# If you are a Python user, you can use the demo Python code available on the H2O AutoML User Guide 
# instead: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html

# Unfortunately it was a private competition, so the data is not publicly available! 

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

# Count the number of covid meetups for R-Ladies and WiMLDS

library(meetupr)
library(tidyverse)

# Look up all R-Ladies & WiMLDS groups by "topic id" & count the events.  
# You can find topic ids for associated tags by querying 
# [here](https://secure.meetup.com/meetup_api/console/?path=/find/topics).  
# The `topic_id` for topic, "R-Ladies", is 1513883.
# The `topic_id` for topic, "WiMLDS", is 1517030.

ledell

# Meetups since quarantine started (feel free to adjust the date to your local lockdown date)

library(meetupr)
library(tidyverse)

meetup_urlname <- "Bay-Area-Women-in-Machine-Learning-and-Data-Science"  #insert your meetup urlnamne here
events <- get_events(urlname = meetup_urlname, 
                     event_status = "past")

events %>%

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

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

# This example is outdated because we have the H2O Stacked Ensemble function now (so it's better to use that):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

install.packages("h2o", repos="http://h2o-release.s3.amazonaws.com/h2o/latest_stable_R", method="curl")

ledell

# My version of the code at this blog post:
# https://towardsdatascience.com/automl-a-tool-to-improve-your-workflow-1a132248371f

import h2o
from h2o.automl import H2OAutoML

h2o.init()

train = h2o.import_file("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data")
y = "C1" #e = edible, p = poisonous

ledell

library(R.utils)
# Note: For saving H2O AutoML objects, if path is NULL (default), 
# then save in pwd with project_name as folder name
# This function (or something similar to it) will be part of H2O soon...
# Written by: https://github.com/tomasfryda

.dump_aml_frames <- function(aml, path) {
  frames <- c(attr(aml@leaderboard, "id"), attr(aml@event_log, "id"))
  frames <- c(frames,
              unlist(sapply(aml@leaderboard$model_id, function(model_id)