assembler = VectorAssembler().setInputCols(bands) \
.setOutputCol("features")
assembled_df_train = assembler.transform(exploded_tiles_filtered_train)
assembled_df_test = assembler.transform(exploded_tiles_filtered_test)
classifier = RandomForestClassifier().setLabelCol('label') \
.setFeaturesCol(assembler.getOutputCol())
model = classifier.fit(assembled_df_train.cache())
prediction_df = model.transform(assembled_df_test).drop(assembler.getOutputCol()).cache()
evaluator = MulticlassClassificationEvaluator(
predictionCol=classifier.getPredictionCol(),
labelCol=classifier.getLabelCol(),
metricName='accuracy'
)
accuracy = evaluator.evaluate(prediction_df)
print("\nAccuracy:", accuracy)
cnf_mtrx = prediction_df.groupBy(classifier.getPredictionCol()) \
.pivot(classifier.getLabelCol()) \
.count() \
.sort(classifier.getPredictionCol())
cnf_mtrx
print("Tempo do calculo da cnf_matrix: "+str(datetime.datetime.now() - begin_time))
begin_time = datetime.datetime.now()
