def linearRegression(df, conf):
"""
input : df [spark.dataframe], conf [configuration params]
output : linear_regression model [model]
"""
#memanggil parameter (nilai default)
featuresCol= conf["params"].get("featuresCol", "features")
labelCol= conf["params"].get("labelCol", "label")
predictionCol = conf["params"].get("predictionCol", "prediction")
max_iter = conf["params"].get("maxIter", 100)
reg_param = conf["params"].get("regParam", 0.0)
elasticnet_param = conf["params"].get("elasticNetParam", 0.0)
tol = conf["params"].get("tol", 1e-6)
fitIntercept = conf["params"].get("fitIntercept", True)
standardization = conf["params"].get("standardization", True)
solver = conf["params"].get("solver", "auto")
weightCol = conf["params"].get("weightCol", None)
aggregationDepth = conf["params"].get("aggregationDepth", 2)
loss = conf["params"].get("loss", "squaredError")
epsilon = conf["params"].get("epsilon", 1.35)
lr = LinearRegression(maxIter=max_iter, regParam=reg_param,
elasticNetParam=elasticnet_param)
print ("maxIter : " , lr.getMaxIter())
print ("regParam : " , lr.getRegParam())
print ("aggrDepth : " , lr.getAggregationDepth())
#jika menggunakan ml-tuning
if conf["tuning"]:
#jika menggunakan ml-tuning cross validation
if conf["tuning"].get("method").lower() == "crossval":
paramGrids = conf["tuning"].get("paramGrids")
pg = ParamGridBuilder()
for key in paramGrids:
pg.addGrid(key, paramGrids[key])
grid = pg.build()
folds = conf["tuning"].get("methodParam")
evaluator = RegressionEvaluator()
cv = CrossValidator(estimator=lr, estimatorParamMaps=grid,
evaluator=evaluator, numFolds= folds)
model = cv.fit(df)
#jika menggunakan ml-tuning train validation split
elif conf["tuning"].get("method").lower() == "trainvalsplit":
paramGrids = conf["tuning"].get("paramGrids")
pg = ParamGridBuilder()
for key in paramGrids:
pg.addGrid(key, paramGrids[key])
grid = pg.build()
tr = conf["tuning"].get("methodParam")
evaluator = RegressionEvaluator()
tvs = TrainValidationSplit(estimator=lr, estimatorParamMaps=grid,
evaluator=evaluator, trainRatio=tr )
model = tvs.fit(df)
#jika tidak menggunakan ml-tuning
elif conf["tuning"] == None:
print ("test")
model = lr.fit(df)
return model
