Spark机器学习基础——监督学习
1.1线性回归（加L1 L2 正则化）
!head -3 data/mllib/sample_linear_regression_data.txt
1
from __future__ import print_function
from pyspark.ml.regression import LinearRegression
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("LinearRegressionWithElasticNet")\
.getOrCreate()
# 加载数据
training = spark.read.format("libsvm")\
.load("data/mllib/sample_linear_regression_data.txt")
lr = LinearRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
# 拟合模型
lrModel = lr.fit(training)
# 输出系数和截距 y=WX+b
print("Coefficients: %s" % str(lrModel.coefficients))
print("Intercept: %s" % str(lrModel.intercept))
# 模型信息总结输出
trainingSummary = lrModel.summary
print("numIterations: %d" % trainingSummary.totalIterations)
print("objectiveHistory: %s" % str(trainingSummary.objectiveHistory))
trainingSummary.residuals.show()
print("RMSE: %f" % trainingSummary.rootMeanSquaredError)
print("r2: %f" % trainingSummary.r2)
spark.stop()
2
1.2广义线性模型
from __future__ import print_function
from pyspark.sql import SparkSession
from pyspark.ml.regression import GeneralizedLinearRegression
spark = SparkSession\
.builder\
.appName("GeneralizedLinearRegressionExample")\
.getOrCreate()
# 加载数据
dataset = spark.read.format("libsvm")\
.load("data/mllib/sample_linear_regression_data.txt")
glr = GeneralizedLinearRegression(family="gaussian", link="identity", maxIter=10, regParam=0.3)
# 拟合模型
model = glr.fit(dataset)
# 输出系数和截距
print("Coefficients: " + str(model.coefficients))
print("Intercept: " + str(model.intercept))
# 模型信息总结与输出
summary = model.summary
print("Coefficient Standard Errors: " + str(summary.coefficientStandardErrors))
print("T Values: " + str(summary.tValues))
print("P Values: " + str(summary.pValues))
print("Dispersion: " + str(summary.dispersion))
print("Null Deviance: " + str(summary.nullDeviance))
print("Residual Degree Of Freedom Null: " + str(summary.residualDegreeOfFreedomNull))
print("Deviance: " + str(summary.deviance))
print("Residual Degree Of Freedom: " + str(summary.residualDegreeOfFreedom))
print("AIC: " + str(summary.aic))
print("Deviance Residuals: ")
summary.residuals().show()
spark.stop()
3
1.3逻辑回归
from __future__ import print_function
from pyspark.ml.classification import LogisticRegression
from pyspark.sql import SparkSession
spark = SparkSession \
.builder \
.appName("LogisticRegressionSummary") \
.getOrCreate()
# 加载数据
training = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
# 拟合模型
lrModel = lr.fit(training)
# 模型信息总结与输出
trainingSummary = lrModel.summary
# 输出每一轮的损失函数值
objectiveHistory = trainingSummary.objectiveHistory
print("objectiveHistory:")
for objective in objectiveHistory:
print(objective)
# ROC曲线
trainingSummary.roc.show()
print("areaUnderROC: " + str(trainingSummary.areaUnderROC))
# Set the model threshold to maximize F-Measure
#fMeasure = trainingSummary.fMeasureByThreshold
#maxFMeasure = fMeasure.groupBy(['threshold']).max('F-Measure').select('max(F-Measure)')
#bestThreshold = fMeasure.where(fMeasure['F-Measure'] == maxFMeasure.select('max(F-Measure)')['max(F-Measure)']).select('threshold')['threshold']
#lr.setThreshold(bestThreshold)
spark.stop()
4
from __future__ import print_function
from pyspark.ml.classification import LogisticRegression
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("LogisticRegressionWithElasticNet")\
.getOrCreate()
# 加载数据
training = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
# 拟合模型
lrModel = lr.fit(training)
# 系数与截距
print("Coefficients: " + str(lrModel.coefficients))
print("Intercept: " + str(lrModel.intercept))
# 多项式逻辑回归
mlr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8, family="multinomial")
# 拟合模型
mlrModel = mlr.fit(training)
# 输出系数
print("Multinomial coefficients: " + str(mlrModel.coefficientMatrix))
print("Multinomial intercepts: " + str(mlrModel.interceptVector))
spark.stop()
5
1.4 多分类逻辑回归
from __future__ import print_function
from pyspark.ml.classification import LogisticRegression
from pyspark.sql import SparkSession
spark = SparkSession \
.builder \
.appName("MulticlassLogisticRegressionWithElasticNet") \
.getOrCreate()
# 加载数据
training = spark \
.read \
.format("libsvm") \
.load("data/mllib/sample_multiclass_classification_data.txt")
lr = LogisticRegression(maxIter=10, regParam=0.3, elasticNetParam=0.8)
# 拟合模型
lrModel = lr.fit(training)
# 输出系数
print("Coefficients: \n" + str(lrModel.coefficientMatrix))
print("Intercept: " + str(lrModel.interceptVector))
# 预测结果
lrModel.transform(training).show()
spark.stop()
6
1.5多层感知机(MLP)
from __future__ import print_function
from pyspark.ml.classification import MultilayerPerceptronClassifier
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
from pyspark.sql import SparkSession
spark = SparkSession\
.builder.appName("multilayer_perceptron_classification_example").getOrCreate()
# 加载数据
data = spark.read.format("libsvm")\
.load("data/mllib/sample_multiclass_classification_data.txt")
# 切分训练集和测试集
splits = data.randomSplit([0.6, 0.4], 1234)
train = splits[0]
test = splits[1]
# 输入、隐层、隐层、输出个数
layers = [4, 5, 4, 3]
# 创建多层感知器
trainer = MultilayerPerceptronClassifier(maxIter=100, layers=layers, blockSize=128, seed=1234)
# 训练模型
model = trainer.fit(train)
# 预测和计算准确度
result = model.transform(test)
result.show()
predictionAndLabels = result.select("prediction", "label")
evaluator = MulticlassClassificationEvaluator(metricName="accuracy")
print("Test set accuracy = " + str(evaluator.evaluate(predictionAndLabels)))
spark.stop()
7
1.6决策树分类
!head -2 data/mllib/sample_libsvm_data.txt
8
from __future__ import print_function
from pyspark.ml import Pipeline
from pyspark.ml.classification import DecisionTreeClassifier
from pyspark.ml.feature import StringIndexer, VectorIndexer
from pyspark.ml.evaluation import MulticlassClassificationEvaluator
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("DecisionTreeClassificationExample")\
.getOrCreate()
# 加载数据
data = spark.read.format("libsvm").load("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.
# 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 = DecisionTreeClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures")
# Chain indexers and tree in a Pipeline
pipeline = Pipeline(stages=[labelIndexer, featureIndexer, dt])
# Train model. This also runs the indexers.
model = pipeline.fit(trainingData)
# Make predictions.
predictions = model.transform(testData)
# Select example rows to display.
predictions.select("prediction", "indexedLabel", "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))
treeModel = model.stages[2]
# summary only
print(treeModel)
spark.stop()
9
1.7决策树回归
from __future__ import print_function
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("DecisionTreeRegressionExample")\
.getOrCreate()
# 加载数据
data = spark.read.format("libsvm").load("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)
spark.stop()
10
1.8随机森林分类
from __future__ import print_function
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("RandomForestClassifierExample")\
.getOrCreate()
# 加载数据
data = spark.read.format("libsvm").load("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
spark.stop()
11
1.9随机森林回归
from __future__ import print_function
from pyspark.ml import Pipeline
from pyspark.ml.regression import RandomForestRegressor
from pyspark.ml.feature import VectorIndexer
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("RandomForestRegressorExample")\
.getOrCreate()
# 加载数据
data = spark.read.format("libsvm").load("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 RandomForest model.
rf = RandomForestRegressor(featuresCol="indexedFeatures")
# Chain indexer and forest in a Pipeline
pipeline = Pipeline(stages=[featureIndexer, rf])
# 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)
rfModel = model.stages[1]
print(rfModel) # summary only
spark.stop()
12
1.10 梯度增强树分类
from __future__ import print_function
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()
# 加载数据
data = spark.read.format("libsvm").load("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 GBT model.
gbt = GBTClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures", maxIter=10)
# Chain indexers and GBT in a Pipeline
pipeline = Pipeline(stages=[labelIndexer, featureIndexer, gbt])
# Train model. This also runs the indexers.
model = pipeline.fit(trainingData)
# Make predictions.
predictions = model.transform(testData)
# Select example rows to display.
predictions.select("prediction", "indexedLabel", "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))
gbtModel = model.stages[2]
print(gbtModel) # summary only
spark.stop()
13
1.11 梯度增强树回归
from __future__ import print_function
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()
# 加载数据
data = spark.read.format("libsvm").load("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
spark.stop()
14
1.12 机器学习模板与交叉验证
from __future__ import print_function
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.evaluation import BinaryClassificationEvaluator
from pyspark.ml.feature import HashingTF, Tokenizer
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("CrossValidatorExample")\
.getOrCreate()
# $example on$
# Prepare training documents, which are labeled.
training = spark.createDataFrame([
(0, "a b c d e spark", 1.0),
(1, "b d", 0.0),
(2, "spark f g h", 1.0),
(3, "hadoop mapreduce", 0.0),
(4, "b spark who", 1.0),
(5, "g d a y", 0.0),
(6, "spark fly", 1.0),
(7, "was mapreduce", 0.0),
(8, "e spark program", 1.0),
(9, "a e c l", 0.0),
(10, "spark compile", 1.0),
(11, "hadoop software", 0.0)
], ["id", "text", "label"])
# Configure an ML pipeline, which consists of tree stages: tokenizer, hashingTF, and lr.
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])
# We now treat the Pipeline as an Estimator, wrapping it in a CrossValidator instance.
# This will allow us to jointly choose parameters for all Pipeline stages.
# A CrossValidator requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
# We use a ParamGridBuilder to construct a grid of parameters to search over.
# With 3 values for hashingTF.numFeatures and 2 values for lr.regParam,
# this grid will have 3 x 2 = 6 parameter settings for CrossValidator to choose from.
paramGrid = ParamGridBuilder() \
.addGrid(hashingTF.numFeatures, [10, 100, 1000]) \
.addGrid(lr.regParam, [0.1, 0.01]) \
.build()
crossval = CrossValidator(estimator=pipeline,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator(),
numFolds=2) # use 3+ folds in practice
# Run cross-validation, and choose the best set of parameters.
cvModel = crossval.fit(training)
# Prepare test documents, which are unlabeled.
test = spark.createDataFrame([
(4, "spark i j k"),
(5, "l m n"),
(6, "mapreduce spark"),
(7, "apache hadoop")
], ["id", "text"])
# Make predictions on test documents. cvModel uses the best model found (lrModel).
prediction = cvModel.transform(test)
selected = prediction.select("id", "text", "probability", "prediction")
for row in selected.collect():
print(row)
spark.stop()
15