pyspark提升树（GBT）

没什么好说的，就是一种调用方式学习

分类

from pyspark.ml import Pipeline
from pyspark.ml.classification import GBTClassifier
from pyspark.ml.feature import StringIndexer, VectorIndexer
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
from pyspark.sql import SparkSession

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

data = spark.read.format("libsvm").load("sample_libsvm_data.txt")
labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
featureIndexer =VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)# 小于5种取值的特征转为类别向量
(trainingData, testData) = data.randomSplit([0.7, 0.3])
gbt = GBTClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures", maxIter=10)
pipeline = Pipeline(stages=[labelIndexer, featureIndexer, gbt])
model = pipeline.fit(trainingData)
predictions = model.transform(testData)
predictions.select("prediction", "indexedLabel", "features").show(5)
evaluator = MulticlassClassificationEvaluator(
    labelCol="indexedLabel", predictionCol="prediction", metricName="accuracy")
accuracy = evaluator.evaluate(predictions)
print("Test Error = %g" % (1.0 - accuracy))
gbtModel = model.stages[2]
print(gbtModel) # 打印第3阶段的模型

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("GradientBoostedTreeRegressorExample")\
    .getOrCreate()

data = spark.read.format("libsvm").load("sample_libsvm_data.txt")
featureIndexer =\
    VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
(trainingData, testData) = data.randomSplit([0.7, 0.3])
gbt = GBTRegressor(featuresCol="indexedFeatures", maxIter=10)
pipeline = Pipeline(stages=[featureIndexer, gbt])
model = pipeline.fit(trainingData)
predictions = model.transform(testData)
predictions.select("prediction", "label", "features").show(5)
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)