pyspark 随机森林

from pyspark.ml import Pipeline
from pyspark.ml.classification import RandomForestClassifier
from pyspark.ml.feature import IndexToString, StringIndexer, VectorIndexer
from pyspark.ml.evaluation import MulticlassClassificationEvaluator

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")

# Index labels, adding metadata to the label column.
# Fit on whole dataset to include all labels in index.
labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)

# 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 RandomForest model.
rf = RandomForestClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures", numTrees=10)

# Convert indexed labels back to original labels.
labelConverter = IndexToString(inputCol="prediction", outputCol="predictedLabel",
                               labels=labelIndexer.labels)

# Chain indexers and forest in a Pipeline
pipeline = Pipeline(stages=[labelIndexer, featureIndexer, rf, labelConverter])

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

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

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

# Select (prediction, true label) and compute test error
evaluator = MulticlassClassificationEvaluator(
    labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
accuracy = evaluator.evaluate(predictions)
print("Test Error = %g" % (1.0 - accuracy))

rfModel = model.stages[2]
print(rfModel)  # summary only

+--------------+-----+--------------------+
|predictedLabel|label|            features|
+--------------+-----+--------------------+
|           0.0|  0.0|(692,[95,96,97,12...|
|           0.0|  0.0|(692,[123,124,125...|
|           0.0|  0.0|(692,[124,125,126...|
|           0.0|  0.0|(692,[124,125,126...|
|           0.0|  0.0|(692,[125,126,127...|
+--------------+-----+--------------------+
only showing top 5 rows

Test Error = 0
RandomForestClassificationModel (uid=RandomForestClassifier_430fb4cd634d0e87412d) with 10 trees