resultsBestDtDf.write.save('/mnt/data/resultsBestDtDf.parquet',
format='parquet',
header=True,
mode="overwrite")
# COMMAND ----------
# COMMAND ----------
from pyspark.ml.regression import RandomForestRegressor
# Create a RandomForestRegressor
rf = RandomForestRegressor()
rf.setPredictionCol("Prediction_cuisine")\
.setLabelCol("6714")\
.setFeaturesCol("features")\
.setSeed(190088121L)\
.setMaxDepth(8)\
.setNumTrees(25)
# Create a Pipeline
rfPipeline = Pipeline()
# Set the stages of the Pipeline
rfPipeline.setStages([vectorizer, rf])
# Let's first train on the entire dataset to see what we get
rfModel = rfPipeline.fit(trainingSetDF)
# COMMAND ----------
trainingSetDF = split80DF
testSetDF = split20DF
# Guardamos en cache los datos para agilizar los cáluclos
trainingSetDF.cache()
testSetDF.cache()
# Árboles de decisión
rf = RandomForestRegressor()
# Para información sobre los parametros: print(rf.explainParams())
rf.setPredictionCol('Predicted_PE')\
.setLabelCol('PE')\
.setNumTrees(20)\
.setMaxDepth(5)
# Forest Pipeline
pipeline = Pipeline(stages = [vectorizer, rf])
# Entrenamos el modelo
model = pipeline.fit(trainingSetDF)
# Podemos ver los detalles del árbol creado:
"""
print("Nodos: " + str(model.stages[-1]._java_obj.parent().getNumTrees()))
print("Profundidad: "+ str(model.stages[-1]._java_obj.parent().getMaxDepth()))
