pyspark 梯度提升树回归

from pyspark.ml import Pipeline
from pyspark.ml.regression import GBTRegressor
from pyspark.ml.feature import VectorIndexer
from pyspark.ml.evaluation import RegressionEvaluator


from pyspark.sql import SparkSession

spark= SparkSession\
                .builder \
                .appName("dataFrame") \
                .getOrCreate()

# Load and parse the data file, converting it to a DataFrame.
data = spark.read.format("libsvm").load("/home/luogan/lg/softinstall/spark-2.2.0-bin-hadoop2.7/data/mllib/sample_libsvm_data.txt")

# Automatically identify categorical features, and index them.
# Set maxCategories so features with > 4 distinct values are treated as continuous.
featureIndexer =\
    VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)

# Split the data into training and test sets (30% held out for testing)
(trainingData, testData) = data.randomSplit([0.7, 0.3])

# Train a GBT model.
gbt = GBTRegressor(featuresCol="indexedFeatures", maxIter=10)

# Chain indexer and GBT in a Pipeline
pipeline = Pipeline(stages=[featureIndexer, gbt])

# Train model.  This also runs the indexer.
model = pipeline.fit(trainingData)

# Make predictions.
predictions = model.transform(testData)

# Select example rows to display.
predictions.select("prediction", "label", "features").show(5)

# Select (prediction, true label) and compute test error
evaluator = RegressionEvaluator(
    labelCol="label", predictionCol="prediction", metricName="rmse")
rmse = evaluator.evaluate(predictions)
print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)

gbtModel = model.stages[1]
print(gbtModel)  # summary only

+----------+-----+--------------------+
|prediction|label|            features|
+----------+-----+--------------------+
|       0.0|  0.0|(692,[121,122,123...|
|       0.0|  0.0|(692,[122,123,124...|
|       0.0|  0.0|(692,[123,124,125...|
|       0.0|  0.0|(692,[124,125,126...|
|       0.0|  0.0|(692,[124,125,126...|
+----------+-----+--------------------+
only showing top 5 rows

Root Mean Squared Error (RMSE) on test data = 0.196116
GBTRegressionModel (uid=GBTRegressor_4205a4065616ba74c745) with 10 trees