workflow = Workflow(sc)
contextUrl = "https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json"
#1. Read the input
#test big file
# inputRDD = workflow.batch_read_csv(inputFilename).partitionBy(1000)
#test small file
inputRDD = workflow.batch_read_csv(inputFilename)
#2. Apply the karma Model
outputRDD = workflow.run_karma(
inputRDD,
"https://raw.githubusercontent.com/american-art/npg/master/NPGConstituents/NPGConstituents-model.ttl",
"http://dig.isi.edu/npgConstituents/",
"http://www.cidoc-crm.org/cidoc-crm/E39_Actor1",
"https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json",
data_type="csv",
additional_settings={"karma.input.delimiter": ","})
#3. Save the output
# fileUtil.save_file(outputRDD, outputFilename, "text", "json")
reducedRDD = workflow.reduce_rdds(outputRDD)
reducedRDD.persist()
types = [{
"name": "E39_Actor",
"uri": "http://www.cidoc-crm.org/cidoc-crm/E39_Actor"
}, {
"name": "E82_Actor_Appellation",
"uri": "http://www.cidoc-crm.org/cidoc-crm/E82_Actor_Appellation"
outputFilename = argv[2]
numPartitions = 1000
numFramerPartitions = max(10, numPartitions / 10)
fileUtil = FileUtil(sc)
workflow = Workflow(sc)
contextUrl = "https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json"
#1. Read the input
inputRDD = workflow.batch_read_csv(inputFilename)
#2. Apply the karma Model
outputRDD = workflow.run_karma(inputRDD,
"https://raw.githubusercontent.com/american-art/npg/master/NPGConstituents/NPGConstituents-model.ttl",
"http://americanartcollaborative.org/npg/",
"http://www.cidoc-crm.org/cidoc-crm/E39_Actor1",
"https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json",
num_partitions=numPartitions,
data_type="csv",
additional_settings={"karma.input.delimiter":","})
#3. Save the output
# fileUtil.save_file(outputRDD, outputFilename, "text", "json")
#4. Reduce rdds
reducedRDD = workflow.reduce_rdds(numFramerPartitions, outputRDD)
reducedRDD.persist()
types = [
{"name": "E39_Actor", "uri": "http://www.cidoc-crm.org/cidoc-crm/E39_Actor"},
{"name": "E82_Actor_Appellation", "uri": "http://www.cidoc-crm.org/cidoc-crm/E82_Actor_Appellation"},
{"name": "E67_Birth", "uri": "http://www.cidoc-crm.org/cidoc-crm/E67_Birth"},
root = str(params[4])
context = str(params[5])
output_folder = str(params[6])
output_zip_path = str(params[7])
#0. Download data file
dataFileName = download_file(data_file_URL)
#1. Read the input
inputRDD = workflow.batch_read_csv(dataFileName).partitionBy(num_partitions)
#2. Apply the karma Model
outputRDD = workflow.run_karma(inputRDD,
model_file_URL,
base,
root,
context,
data_type="csv",
additional_settings={"karma.input.delimiter":",", "karma.output.format": "n3"})
#3. Save the output
outputPath = outputFilename + "/" + output_folder
outputRDD.map(lambda x: x[1]).saveAsTextFile(outputPath)
print "Successfully apply karma!"
#4. Concate data files
input_sum_file = outputFilename + "/" + output_folder + "/"
output_sum_file = outputFilename + "/" + output_folder + ".n3"
concate_file(input_sum_file, output_sum_file)
print "Successfully generate whole data file!"
contextUrl = "https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json"
#1. Read the input
#test big file
inputRDD = workflow.batch_read_csv(inputFilename).partitionBy(1)
#test small file
# inputRDD = workflow.batch_read_csv(inputFilename)
#2. Apply the karma Model
outputRDD = workflow.run_karma(inputRDD,
"https://raw.githubusercontent.com/american-art/autry/master/AutryMakers/AutryMakers-model.ttl",
"http://dig.isi.edu/AutryMakers/",
"http://www.cidoc-crm.org/cidoc-crm/E22_Man-Made_Object1",
"https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json",
data_type="csv",
additional_settings={"karma.input.delimiter":","})
#3. Save the output
# fileUtil.save_file(outputRDD, outputFilename, "text", "json")
reducedRDD = workflow.reduce_rdds(outputRDD)
reducedRDD.persist()
types = [
{"name": "E82_Actor_Appellation", "uri": "http://www.cidoc-crm.org/cidoc-crm/E82_Actor_Appellation"}
]
frames = [
{"name": "AutryMakers", "url": "https://raw.githubusercontent.com/american-art/aac-alignment/master/frames/autryMakers.json-ld"}
workflow = Workflow(sc)
contextUrl = "https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json"
#1. Read the input
#test big file
inputRDD = workflow.batch_read_csv(inputFilename).partitionBy(1)
#test small file
# inputRDD = workflow.batch_read_csv(inputFilename)
#2. Apply the karma Model
outputRDD = workflow.run_karma(
inputRDD,
"https://raw.githubusercontent.com/american-art/autry/master/AutryMakers/AutryMakers-model.ttl",
"http://dig.isi.edu/AutryMakers/",
"http://www.cidoc-crm.org/cidoc-crm/E22_Man-Made_Object1",
"https://raw.githubusercontent.com/american-art/aac-alignment/master/karma-context.json",
data_type="csv",
additional_settings={"karma.input.delimiter": ","})
#3. Save the output
# fileUtil.save_file(outputRDD, outputFilename, "text", "json")
reducedRDD = workflow.reduce_rdds(outputRDD)
reducedRDD.persist()
types = [{
"name": "E82_Actor_Appellation",
"uri": "http://www.cidoc-crm.org/cidoc-crm/E82_Actor_Appellation"
}]
frames = [{
