Quick and Easy Deployment of Machine Learning (ML) Models

from sklearn.compose import ColumnTransformer
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import OneHotEncoder
from sklearn2pmml import sklearn2pmml
from sklearn2pmml.pipeline import PMMLPipeline

import pandas

df = pandas.read_csv("Audit.csv")

pipeline = PMMLPipeline([
    ("transformer", ColumnTransformer([
        ("continuous", "passthrough", ["Age", "Hours", "Income"]),
        ("categorical", OneHotEncoder(), ["Employment", "Education", "Marital", "Occupation", "Gender", "Deductions"])
    ])),
    ("classifier", LogisticRegression(multi_class = "ovr"))
])
pipeline.fit(df, df["Adjusted"])
pipeline.verify(df.sample(10))

sklearn2pmml(pipeline, "LogisticRegression.pmml")

library("dplyr")
library("r2pmml")

df = read.csv("Audit.csv")
df$Adjusted = as.factor(df$Adjusted)

audit.glm = glm("Adjusted ~ .", data = df, family = "binomial")
audit.glm = verify(audit.glm, newdata = sample_n(df, 10))

r2pmml(audit.glm, "LogisticRegression.pmml")

import java.io.File
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.feature.RFormula
import org.jpmml.sparkml.PMMLBuilder
import org.jpmml.sparkml.model.HasPredictionModelOptions;

val df = spark.read.format("csv").option("header", "true").option("inferSchema", "true").load("Audit.csv")

val rFormula = new RFormula().setFormula("Adjusted ~ .")
val lr = new LogisticRegression().setLabelCol(rFormula.getLabelCol).setFeaturesCol(rFormula.getFeaturesCol)
val pipeline = new Pipeline().setStages(Array(rFormula, lr))

val pipelineModel = pipeline.fit(df)

val pmmlBuilder = new PMMLBuilder(df.schema, pipelineModel).putOption(HasPredictionModelOptions.OPTION_KEEP_PREDICTIONCOL, false).verify(df.sample(false, 0.01).limit(10))

pmmlBuilder.buildFile(new File("LogisticRegression.pmml"))

$ java -jar openscoring-server-executable-${version}.jar

$ curl -X PUT --data-binary @LogisticRegression.pmml -H "Content-type: text/xml" http://localhost:8080/openscoring/model/MyAuditModel
$ curl -X POST --data-binary @Audit.csv -H "Content-type: text/plain; charset=UTF-8" http://localhost:8080/openscoring/model/MyAuditModel/csv > Audit-results.csv
$ curl -X DELETE http://localhost:8080/openscoring/model/MyAuditModel

from openscoring import Openscoring

os = Openscoring(base_url = "http://localhost:8080/openscoring")

os.deployFile("MyAuditModel", "LogisticRegression.pmml")
os.evaluateCsvFile("MyAuditModel", "Audit.csv", "Audit-results.csv")
os.undeploy("MyAuditModel")