from pyspark.ml import Pipeline
from pyspark.ml.regression import DecisionTreeRegressor
from pyspark.ml.feature import VectorIndexer
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.sql import SparkSession
spark= SparkSession\
.builder \
.appName("dataFrame") \
.getOrCreate()
# Load the data stored in LIBSVM format as 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.# We specify 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 DecisionTree model.
dt = DecisionTreeRegressor(featuresCol="indexedFeatures")
# Chain indexer and tree in a Pipeline
pipeline = Pipeline(stages=[featureIndexer, dt])
# 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)
treeModel = model.stages[1]
# summary only
print(treeModel)
+----------+-----+--------------------+|prediction|label| features|
+----------+-----+--------------------+
| 0.0| 0.0|(692,[125,126,127...|
| 0.0| 0.0|(692,[126,127,128...|
| 0.0| 0.0|(692,[126,127,128...|
| 0.0| 0.0|(692,[126,127,128...|
| 0.0| 0.0|(692,[127,128,129...|
+----------+-----+--------------------+
only showing top 5 rows
Root Mean Squared Error (RMSE) on test data = 0
DecisionTreeRegressionModel (uid=DecisionTreeRegressor_477f82ec820c0502851e) of depth 2 with 5 nodes
