PySpark之机器学习库ML(分类、聚类、回归)

PySpark之机器学习库ML(分类、聚类、回归)

import findspark
findspark.init()

from pyspark.sql.session import SparkSession
spark = SparkSession.builder.appName('LIXU').getOrCreate()

案例 1 使用逻辑回归预测婴幼儿存活

1、加载数据

数据的下载地址：http://www.tomdrabas.com/data/LearningPySpark/births_transformed.csv.gz

import pyspark.sql.types as typ

labels = [
            ('INFANT_ALIVE_AT_REPORT', typ.IntegerType()),
            ('BIRTH_PLACE', typ.StringType()),
            ('MOTHER_AGE_YEARS', typ.IntegerType()),
            ('FATHER_COMBINED_AGE', typ.IntegerType()),
            ('CIG_BEFORE', typ.IntegerType()),
            ('CIG_1_TRI', typ.IntegerType()),
            ('CIG_2_TRI', typ.IntegerType()),
            ('CIG_3_TRI', typ.IntegerType()),
            ('MOTHER_HEIGHT_IN', typ.IntegerType()),
            ('MOTHER_PRE_WEIGHT', typ.IntegerType()),
            ('MOTHER_DELIVERY_WEIGHT', typ.IntegerType()),
            ('MOTHER_WEIGHT_GAIN', typ.IntegerType()),
            ('DIABETES_PRE', typ.IntegerType()),
            ('DIABETES_GEST', typ.IntegerType()),
            ('HYP_TENS_PRE', typ.IntegerType()),
            ('HYP_TENS_GEST', typ.IntegerType()),
            ('PREV_BIRTH_PRETERM', typ.IntegerType())
        ]

schema = typ.StructType([typ.StructField(e[0], e[1], False) for e in labels])

births = spark.read.csv('./births_transformed.csv.gz', header=True, schema=schema)

births.head(1)

[Row(INFANT_ALIVE_AT_REPORT=0, BIRTH_PLACE='1', MOTHER_AGE_YEARS=29, FATHER_COMBINED_AGE=99, CIG_BEFORE=0, CIG_1_TRI=0, CIG_2_TRI=0, CIG_3_TRI=0, MOTHER_HEIGHT_IN=99, MOTHER_PRE_WEIGHT=999, MOTHER_DELIVERY_WEIGHT=999, MOTHER_WEIGHT_GAIN=99, DIABETES_PRE=0, DIABETES_GEST=0, HYP_TENS_PRE=0, HYP_TENS_GEST=0, PREV_BIRTH_PRETERM=0)]

2、创建transformers

import pyspark.ml.feature as ft

births = births.withColumn('BIRTH_PLACE_INT', births['BIRTH_PLACE'].cast(typ.IntegerType())) # 将字符“1”转换成数字1
encoder = ft.OneHotEncoder(inputCol = 'BIRTH_PLACE_INT', outputCol = 'BIRTH_PLACE_VEC') # onehot处理
featuresCreator = ft.VectorAssembler(inputCols = [col[0] for col in labels[2:]] + [encoder.getOutputCol()], outputCol = 'features') # 将特征合并成features

3、创建逻辑回归模型

import pyspark.ml.classification as cl

logistic = cl.LogisticRegression(maxIter = 10, regParam = 0.01, labelCol = 'INFANT_ALIVE_AT_REPORT')

4、创建pipeline

from pyspark.ml import Pipeline

pipeline = Pipeline(stages = [encoder, featuresCreator, logistic])

5、训练模型

births_train, births_test = births.randomSplit([0.7, 0.3], seed = 666)
model = pipeline.fit(births_train)
test_model = model.transform(births_test)
test_model.take(1)

[Row(INFANT_ALIVE_AT_REPORT=0, BIRTH_PLACE='1', MOTHER_AGE_YEARS=13, FATHER_COMBINED_AGE=99, CIG_BEFORE=0, CIG_1_TRI=0, CIG_2_TRI=0, CIG_3_TRI=0, MOTHER_HEIGHT_IN=66, MOTHER_PRE_WEIGHT=133, MOTHER_DELIVERY_WEIGHT=135, MOTHER_WEIGHT_GAIN=2, DIABETES_PRE=0, DIABETES_GEST=0, HYP_TENS_PRE=0, HYP_TENS_GEST=0, PREV_BIRTH_PRETERM=0, BIRTH_PLACE_INT=1, BIRTH_PLACE_VEC=SparseVector(9, {1: 1.0}), features=SparseVector(24, {0: 13.0, 1: 99.0, 6: 66.0, 7: 133.0, 8: 135.0, 9: 2.0, 16: 1.0}), rawPrediction=DenseVector([1.0573, -1.0573]), probability=DenseVector([0.7422, 0.2578]), prediction=0.0)]

6、对模型进行评估

import pyspark.ml.evaluation as ev

evaluator = ev.BinaryClassificationEvaluator(rawPredictionCol = 'probability', labelCol = 'INFANT_ALIVE_AT_REPORT')
print(evaluator.evaluate(test_model, {evaluator.metricName: 'areaUnderROC'}))
print(evaluator.evaluate(test_model, {evaluator.metricName: 'areaUnderPR'}))

0.7401301847095617
0.7139354342365674

7、保存和加载模型

pipelinePath = ‘./infant_oneHotEncoder_Logistic_Pipeline’

pipeline.write().overwrite().save(pipelinePath)

loadedPipeline = Pipeline.load(pipelinePath)

loadedPipeline.fit(births_train).transform(births_test).take(1)

from pyspark.ml import PipelineModel

modelPath = ‘./infant_oneHotEncoder_Logistic_PipelineModel’

model.write().overwrite().save(modelPath)

loadedPipelineModel = PipelineModel.load(modelPath)

test_loadedModel = loadedPipelineModel.transform(births_test)

案例 2 参数调整

1、Grid search

import pyspark.ml.tuning as tune

logistic = cl.LogisticRegression(labelCol="INFANT_ALIVE_AT_REPORT")
grid = tune.ParamGridBuilder().addGrid(logistic.maxIter, [2, 10, 30]).addGrid(logistic.regParam, [0.01, 0.05, 0.3]).build()

evaluator = ev.BinaryClassificationEvaluator(rawPredictionCol = 'probability', labelCol = 'INFANT_ALIVE_AT_REPORT')
cv = tune.CrossValidator(estimator = logistic, estimatorParamMaps = grid, evaluator = evaluator)

pipeline = Pipeline(stages = [encoder, featuresCreator])
data_transformer = pipeline.fit(births_train)
cvModel = cv.fit(data_transformer.transform(births_train))

data_test = data_transformer.transform(births_test)
results = cvModel.transform(data_test)

print(evaluator.evaluate(results, {evaluator.metricName: 'areaUnderROC'}))
print(evaluator.evaluate(results, {evaluator.metricName: 'areaUnderPR'}))

results = [
    (
        [
            {key.name: paramValue} 
            for key, paramValue 
            in zip(
                params.keys(), 
                params.values())
        ], metric
    ) 
    for params, metric 
    in zip(
        cvModel.getEstimatorParamMaps(), 
        cvModel.avgMetrics
    )
]

print(sorted(results,key=lambda el: el[1],reverse=True)[0])

0.7404799467361349
0.7158426790526992
([{'regParam': 0.01}, {'maxIter': 30}], 0.7384569581670912)

2、Train_validation splitt

0.7294296314442145
0.703775950281647

案例 3 使用随机森林预测婴幼儿存活

import pyspark.sql.functions as func
births = births.withColumn("INFANT_ALIVE_AT_REPORT", func.col("INFANT_ALIVE_AT_REPORT").cast(typ.DoubleType()))
births_train, births_test = births.randomSplit([0.7, 0.3], seed = 666)

classifier = cl.RandomForestClassifier(numTrees=5, maxDepth=5, labelCol='INFANT_ALIVE_AT_REPORT')
pipeline = Pipeline(stages = [encoder, featuresCreator, classifier])
model = pipeline.fit(births_train)
test = model.transform(births_test)

evaluator = ev.BinaryClassificationEvaluator(labelCol='INFANT_ALIVE_AT_REPORT')
print(evaluator.evaluate(test, {evaluator.metricName: "areaUnderROC"}))
print(evaluator.evaluate(test, {evaluator.metricName: "areaUnderPR"}))

0.7671165748668931
0.7367360611074735

import pyspark.ml.tuning as tune

clf = cl.RandomForestClassifier(labelCol="INFANT_ALIVE_AT_REPORT")
grid = tune.ParamGridBuilder().addGrid(clf.numTrees, [2, 5, 8]).addGrid(clf.maxDepth, [3, 5, 7]).build()

evaluator = ev.BinaryClassificationEvaluator(rawPredictionCol = 'probability', labelCol = 'INFANT_ALIVE_AT_REPORT')
cv = tune.CrossValidator(estimator = clf, estimatorParamMaps = grid, evaluator = evaluator)

pipeline = Pipeline(stages = [encoder, featuresCreator])
data_transformer = pipeline.fit(births_train)
cvModel = cv.fit(data_transformer.transform(births_train))

data_test = data_transformer.transform(births_test)
results = cvModel.transform(data_test)

print(evaluator.evaluate(results, {evaluator.metricName: 'areaUnderROC'}))
print(evaluator.evaluate(results, {evaluator.metricName: 'areaUnderPR'}))

results = [
    (
        [
            {key.name: paramValue} 
            for key, paramValue 
            in zip(
                params.keys(), 
                params.values())
        ], metric
    ) 
    for params, metric 
    in zip(
        cvModel.getEstimatorParamMaps(), 
        cvModel.avgMetrics
    )
]

print(sorted(results,key=lambda el: el[1],reverse=True)[0])

0.7780783438870142
0.758032350342556
([{'maxDepth': 7}, {'numTrees': 8}], 0.7751605479831878)

案例 4 KMeans

import pyspark.ml.clustering as clus
kmeans = clus.KMeans(k = 5, featuresCol = 'features')
pipeline = Pipeline(stages = [encoder, featuresCreator, kmeans])
model = pipeline.fit(births_train)
test = model.transform(births_test)
test.groupBy('prediction').agg({'*' : 'count', 'MOTHER_HEIGHT_IN' : 'avg'}).collect()

[Row(prediction=1, avg(MOTHER_HEIGHT_IN)=67.69473684210526, count(1)=475),
 Row(prediction=3, avg(MOTHER_HEIGHT_IN)=66.64658634538152, count(1)=249),
 Row(prediction=4, avg(MOTHER_HEIGHT_IN)=64.43472584856397, count(1)=2298),
 Row(prediction=2, avg(MOTHER_HEIGHT_IN)=83.91154791154791, count(1)=407),
 Row(prediction=0, avg(MOTHER_HEIGHT_IN)=64.31597357170618, count(1)=10292)]

案例 5 LDA模型

text_data = spark.createDataFrame([
    ['''To make a computer do anything, you have to write a 
    computer program. To write a computer program, you have 
    to tell the computer, step by step, exactly what you want 
    it to do. The computer then "executes" the program, 
    following each step mechanically, to accomplish the end 
    goal. When you are telling the computer what to do, you 
    also get to choose how it's going to do it. That's where 
    computer algorithms come in. The algorithm is the basic 
    technique used to get the job done. Let's follow an 
    example to help get an understanding of the algorithm 
    concept.'''],
    ['''Laptop computers use batteries to run while not 
    connected to mains. When we overcharge or overheat 
    lithium ion batteries, the materials inside start to 
    break down and produce bubbles of oxygen, carbon dioxide, 
    and other gases. Pressure builds up, and the hot battery 
    swells from a rectangle into a pillow shape. Sometimes 
    the phone involved will operate afterwards. Other times 
    it will die. And occasionally—kapow! To see what's 
    happening inside the battery when it swells, the CLS team 
    used an x-ray technology called computed tomography.'''],
    ['''This technology describes a technique where touch 
    sensors can be placed around any side of a device 
    allowing for new input sources. The patent also notes 
    that physical buttons (such as the volume controls) could 
    be replaced by these embedded touch sensors. In essence 
    Apple could drop the current buttons and move towards 
    touch-enabled areas on the device for the existing UI. It 
    could also open up areas for new UI paradigms, such as 
    using the back of the smartphone for quick scrolling or 
    page turning.'''],
    ['''The National Park Service is a proud protector of 
    America’s lands. Preserving our land not only safeguards 
    the natural environment, but it also protects the 
    stories, cultures, and histories of our ancestors. As we 
    face the increasingly dire consequences of climate 
    change, it is imperative that we continue to expand 
    America’s protected lands under the oversight of the 
    National Park Service. Doing so combats climate change 
    and allows all American’s to visit, explore, and learn 
    from these treasured places for generations to come. It 
    is critical that President Obama acts swiftly to preserve 
    land that is at risk of external threats before the end 
    of his term as it has become blatantly clear that the 
    next administration will not hold the same value for our 
    environment over the next four years.'''],
    ['''The National Park Foundation, the official charitable 
    partner of the National Park Service, enriches America’s 
    national parks and programs through the support of 
    private citizens, park lovers, stewards of nature, 
    history enthusiasts, and wilderness adventurers. 
    Chartered by Congress in 1967, the Foundation grew out of 
    a legacy of park protection that began over a century 
    ago, when ordinary citizens took action to establish and 
    protect our national parks. Today, the National Park 
    Foundation carries on the tradition of early park 
    advocates, big thinkers, doers and dreamers—from John 
    Muir and Ansel Adams to President Theodore Roosevelt.'''],
    ['''Australia has over 500 national parks. Over 28 
    million hectares of land is designated as national 
    parkland, accounting for almost four per cent of 
    Australia's land areas. In addition, a further six per 
    cent of Australia is protected and includes state 
    forests, nature parks and conservation reserves.National 
    parks are usually large areas of land that are protected 
    because they have unspoilt landscapes and a diverse 
    number of native plants and animals. This means that 
    commercial activities such as farming are prohibited and 
    human activity is strictly monitored.''']
], ['documents'])

tokenizer = ft.RegexTokenizer(inputCol='documents', outputCol='input_arr', pattern='\s+|[,.\"]')
stopwords = ft.StopWordsRemover(inputCol=tokenizer.getOutputCol(), outputCol='input_stop')
stringIndexer = ft.CountVectorizer(inputCol=stopwords.getOutputCol(), outputCol='input_indexed')
tokenized = stopwords.transform(tokenizer.transform(text_data))
stringIndexer.fit(tokenized).transform(tokenized).select('input_indexed').take(2)

clustering = clus.LDA(k=2, optimizer='online', featuresCol=stringIndexer.getOutputCol())
pipeline = Pipeline(stages = [tokenizer, stopwords, stringIndexer, clustering])
topics = pipeline.fit(text_data).transform(text_data)
topics.select('topicDistribution').collect()

[Row(topicDistribution=DenseVector([0.7338, 0.2662])),
 Row(topicDistribution=DenseVector([0.0127, 0.9873])),
 Row(topicDistribution=DenseVector([0.0191, 0.9809])),
 Row(topicDistribution=DenseVector([0.9886, 0.0114])),
 Row(topicDistribution=DenseVector([0.9896, 0.0104])),
 Row(topicDistribution=DenseVector([0.9794, 0.0206]))]

案例 6 GBDT拟合MOTHER_WEIGHT_GAIN

features = ['MOTHER_AGE_YEARS','MOTHER_HEIGHT_IN',
            'MOTHER_PRE_WEIGHT','DIABETES_PRE',
            'DIABETES_GEST','HYP_TENS_PRE', 
            'HYP_TENS_GEST', 'PREV_BIRTH_PRETERM',
            'CIG_BEFORE','CIG_1_TRI', 'CIG_2_TRI', 
            'CIG_3_TRI'
           ]

featuresCreator = ft.VectorAssembler(inputCols=[col for col in features[1:]], outputCol='features')
selector = ft.ChiSqSelector(numTopFeatures=6, outputCol='selectedFeatures', labelCol='MOTHER_WEIGHT_GAIN')

import pyspark.ml.regression as reg
regressor = reg.GBTRegressor(maxIter=15, maxDepth=3, labelCol='MOTHER_WEIGHT_GAIN')

pipeline = Pipeline(stages = [featuresCreator, selector, regressor])

weightGain = pipeline.fit(births_train)
evaluator = ev.RegressionEvaluator(predictionCol="prediction", labelCol="MOTHER_WEIGHT_GAIN")
print(evaluator.evaluate(weightGain.transform(births_test),{evaluator.metricName: 'r2'}))

0.4886585890292995