h2o.ps1

# Published for http://powertoe.wordpress.com
# https://powertoe.wordpress.com/2017/10/23/h2o-machine-learning-with-powershell/

function ConvertTo-FormData {
	param(
		  [Parameter(ValueFromPipeline=$true)] [PSObject] $InputObject
		 )
	Begin {
		$output = ""
	}
	Process {
		foreach ($prop in $InputObject.psobject.properties |select -expandproperty name) {
			if ($InputObject.($prop).gettype().name -eq "Boolean") {
				if ($InputObject.($prop)) {
					$output += "$prop=true&"
				} else {
					$output += "$prop=false&"
				}
			} if ($InputObject.($prop).gettype().isarray) {
				# hacky for h2o collections
				if ($InputObject.($prop).name) {
					$output += "$prop=[{0}]&" -f ($InputObject.($prop).name -join ",")
				} else {
					$output += "$prop=[{0}]&" -f ($InputObject.($prop) -join ",")
				}
			}
			else {
				$output += "$prop=" + $InputObject.($prop) + "&"
			}
		}
	}
	End {
		$output.Remove($output.Length-1,1)
	}
}

function Wait-H2oJob {
	param(
		  [Parameter(Mandatory=$true, Position=0)]
		  [String] $JobPath
	)
	$notdone = $true
	while ($notdone) {
		$status = invoke-restmethod ("http://localhost:54321" + $JobPath) |select -ExpandProperty jobs |select -ExpandProperty status
		$status
		if ($status -eq "DONE") {
			$notdone = $false
		} else {
			sleep -Milliseconds 500
		}
	}
}

$url = "http://localhost:54321/3/{0}"
$iris_url = 'https://raw.githubusercontent.com/DarrenCook/h2o/bk/datasets/iris_wheader.csv'

"Import the IRIS data"
$importfiles_url = $url -f "ImportFiles"
$importfiles_body = "path=$iris_url"
$ret = Invoke-RestMethod $importfiles_url -Method POST -Body $importfiles_body

"Run parse setup to find out how H2o thinks it should parse the data"
$parsesetup_url = $url -f "ParseSetup"
$parsesetup_body = 'source_frames=[{0}]' -f $iris_url
$ret = Invoke-RestMethod $parsesetup_url -Method Post -Body $parsesetup_body

"Parse the data into a real H2o dataframe"
$parse_url = $url -f "Parse"
$parse_body = $ret | select source_frames,parse_type,separator,number_columns,single_quotes,column_names,column_types,check_header,chunk_size |ConvertTo-FormData
$parse_body += "&destination_frame=iris&delete_on_done=true"
$ret = Invoke-RestMethod $parse_url -Method Post -Body $parse_body
Wait-H2oJob $ret.job.key.URL

"Split the data into an 90% training set and a 10% testing set"
$splitframe_url = $url -f "SplitFrame"
$splitframe_body = "dataset=iris&ratios=[.90,.1]&destination_frames=[train,test]"
$ret = invoke-restmethod $splitframe_url -Method Post -Body $splitframe_body
wait-H2oJob $ret.key.URL

"Train a deep learning model using defaults"
$deeplearning_url = $url -f "ModelBuilders/deeplearning"
$deeplearning_body = 'training_frame=train&response_column=class&model_id=neural'
$ret = invoke-restmethod $deeplearning_url -Method Post -Body $deeplearning_body
wait-H2oJob $ret.job.key.URL

"Predict against the test data and view MSE to see how well it's doing"
$predict_url = $url -f "Predictions/models/neural/frames/test"
$ret = invoke-restmethod $predict_url -method POST -Body "predictions_frame=predicted_test_data"
$ret.model_metrics |select -expandproperty MSE

"Load something you want to predict"
@"
sepal_len, sepal_wid, petal_len, petal_wid
5.1,3.5,1.4,0.15
"@ |out-file -encoding ASCII c:\h2o\predict.csv
$importfiles_url = $url -f "ImportFiles"
$importfiles_body = "path=c:\h2o\predict.csv"
$ret = Invoke-RestMethod $importfiles_url -Method POST -Body $importfiles_body

"Run parse setup to find out how H2o thinks it should parse the data"
$parsesetup_url = $url -f "ParseSetup"
$parsesetup_body = 'source_frames=[{0}]' -f $ret.destination_frames[0]
$ret = Invoke-RestMethod $parsesetup_url -Method Post -Body $parsesetup_body

"Parse the data into a real H2o dataframe"
$parse_url = $url -f "Parse"
$parse_body = $ret | select source_frames,parse_type,separator,number_columns,single_quotes,column_names,column_types,check_header,chunk_size |ConvertTo-FormData
$parse_body += "&destination_frame=predictme&delete_on_done=true"
$ret = Invoke-RestMethod $parse_url -Method Post -Body $parse_body
Wait-H2oJob $ret.job.key.URL

"Let's leverage the data model we built earlier to predict against this new data frame"
$predict_url = $url -f "Predictions/models/neural/frames/predictme"
$ret = invoke-restmethod $predict_url -method POST -Body "predictions_frame=predictme_results"

"Finally, let's look at the data returned by the prediction"
$results_url = $url -f "Frames/predictme_results"
$ret = invoke-restmethod $results_url
$ret.frames.columns |select label, data

<#
Copyright (c) 2015 Tome Tanasovski

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
#>