def rfTest(sqlContext,dataset_rdd):
dataset_positive = dataset_rdd.filter(lambda e:e[1]>0.5)
dataset_negotive = dataset_rdd.filter(lambda e:e[1]<0.5)
train_positive = dataset_positive.sample(False,0.8)
test_positive = dataset_positive.subtract(train_positive)
train_negotive = dataset_negotive.sample(False,0.8)
test_negotive = dataset_negotive.subtract(train_negotive)
trainset_rdd = train_positive.union(train_negotive)
testset_rdd = test_positive.union(test_negotive)
trainset = trainset_rdd.map(lambda e:LabeledPoint(e[1],e[2:]))
trainset_nums = trainset.count()
testset = testset_rdd.map(lambda e:LabeledPoint(e[1],e[2:]))
testset_nums = testset.count()
trainset_positive = train_positive.count()
testset_positive = test_positive.count()
model = RandomForest.trainClassifier(trainset,2,{},3)
predictions = model.predict(testset.map(lambda x:x.features))
predict = testset.map(lambda lp: lp.label).zip(predictions)
hitALL =predict.filter(lambda e:e[0]==e[1]).count()
hitPositive = predict.filter(lambda e:e[0]==e[1] and (e[0]>0.5)).count()
positive = predict.filter(lambda e:e[1]>0.5).count()
recallPositive = hitPositive/float(testset_positive)
precision = hitPositive/float(positive)
accuracy = hitALL/float(testset.count())
F_Value = 2/(1/precision+1/recallPositive)
return (trainset_nums,testset_nums,trainset_positive,testset_positive,positive,hitPositive,precision,recallPositive,accuracy,F_Value,model)
def Random_Forest(filename, sc):
filename = "/Users/Jacob/SparkService/data/sample_libsvm_data.txt"
# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLibSVMFile(sc, filename)
# 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.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
print('Test Error = ' + str(testErr))
print('Learned classification forest model:')
print(model.toDebugString())
# Save and load model
#model.save(sc, "target/tmp/myRandomForestClassificationModel")
#sameModel = RandomForestModel.load(sc, "target/tmp/myRandomForestClassificationModel")
def generateRandomForest():
if os.path.exists(RF_PATH):
print("RF_PATH Already available")
return
data = sc.textFile(F_PATH).map(parseLine)
(trainingData, testData) = data.randomSplit([0.9, 0.1], seed=1L)
# Train a RandomForest model.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainClassifier(trainingData, numClasses=classes.__len__(), categoricalFeaturesInfo={},
numTrees=4, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
print('Test Error', str(testErr))
print('Learned classification forest model:')
print(model.toDebugString())
modelStatistics(labelsAndPredictions)
# Save and load model
model.save(sc, RF_PATH)
print("Saved RF Model.")
def testOnce ():
# split the data into training and testing sets
(trainingData, testData) = data.randomSplit([1-test_size, test_size])
# train the random forest
model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
numTrees=num_trees, featureSubsetStrategy = strat,
impurity='gini', maxDepth = max_depth, maxBins=32)
# test the random forest
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
Mg = float(labelsAndPredictions.filter(lambda (v, p): v == 0 and p == 1).count())
Ng = float(labelsAndPredictions.filter(lambda (v, p): v == 0 and p == 0).count())
Ms = float(labelsAndPredictions.filter(lambda (v, p): v == 1 and p == 0).count())
Ns = float(labelsAndPredictions.filter(lambda (v, p): v == 1 and p == 1).count())
probsAndScores = probTest(testData, model)
threshold_accuracy = probsAndScores[0]
probs = probsAndScores[1].map(lambda x: x/num_trees)
labelsAndPredictions = labelsAndPredictions.zip(probs)
labelsAndProbs = testData.map(lambda lp: lp.label).zip(probs)
save(labelsAndProbs, 'answers')
print ('Galaxy Purity = ' + str(Ng / (Ng+Ms)))
print ('Galaxy Completeness = ' + str(Ng / (Ng+Mg)))
print ('Star Purity = ' + str(Ns / (Ns+Mg)))
print ('Star Completeness = ' + str(Ns/(Ns+Ms)))
print ('Accuracy = ' + str(1 - testErr))
print ('Threshold method accuracy = ' + str(threshold_accuracy))
def main():
sc = SparkContext(appName="MyApp")
sc.setLogLevel('ERROR')
# Parse data
train_labels, train_data = load_data('train.csv')
dummy_labels, test_data = load_data('test.csv', use_labels=False)
# Truncate the last 2 features of the data
for dataPoint in train_data:
len = np.size(dataPoint)
dataPoint = np.delete(dataPoint, [len - 2, len - 1])
for dataPoint in test_data:
len = np.size(dataPoint)
dataPoint = np.delete(dataPoint, [len - 2, len - 1])
# Map each data point's label to its features
train_set = reformatData(train_data, train_labels)
test_set = reformatData(test_data, dummy_labels)
# Parallelize the data
parallelized_train_set = sc.parallelize(train_set)
parallelized_test_set = sc.parallelize(test_set)
# Split the data
trainSet, validationSet = parallelized_train_set.randomSplit([0.01, 0.99], seed=42)
# Train the models
randomForestModel = RandomForest.trainClassifier(trainSet, numClasses=4, impurity='gini', categoricalFeaturesInfo={},
numTrees=750, seed=42, maxDepth=30, maxBins=32)
# Test the model
testRandomForest(randomForestModel, parallelized_test_set)
def main():
input_train = sys.argv[1]
input_test = sys.argv[2]
conf = SparkConf().setAppName('Sentiment Analysis with Random Forest')
sc = SparkContext(conf=conf)
assert sc.version >= '1.5.1'
train = sc.textFile(input_train).cache()
test = sc.textFile(input_test).cache()
'''sbaronia - get training and testing labeled points'''
train_lp = train.map(to_labeledpoint).cache()
test_lp = test.map(to_labeledpoint).cache()
'''sbaronia - run RandomForest regression on our training data with
default options except numTrees = 5'''
rf_model = RandomForest.trainRegressor(train_lp,categoricalFeaturesInfo={},numTrees=5,featureSubsetStrategy="auto", impurity='variance', maxDepth=4, maxBins=32)
'''sbaronia - run predictions on testing data and calculate RMSE value'''
predictions = rf_model.predict(test_lp.map(lambda x: x.features))
labelsAndPredictions = test_lp.map(lambda lp: lp.label).zip(predictions)
rmse = math.sqrt(labelsAndPredictions.map(lambda (v, p): (v-p)**2).reduce(lambda x, y: x + y)/float(test_lp.count()))
print("RMSE = " + str(rmse))
def test_regression(self):
from pyspark.mllib.regression import LinearRegressionWithSGD, LassoWithSGD, \
RidgeRegressionWithSGD
from pyspark.mllib.tree import DecisionTree, RandomForest, GradientBoostedTrees
data = [
LabeledPoint(-1.0, [0, -1]),
LabeledPoint(1.0, [0, 1]),
LabeledPoint(-1.0, [0, -2]),
LabeledPoint(1.0, [0, 2])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
lr_model = LinearRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
lasso_model = LassoWithSGD.train(rdd, iterations=10)
self.assertTrue(lasso_model.predict(features[0]) <= 0)
self.assertTrue(lasso_model.predict(features[1]) > 0)
self.assertTrue(lasso_model.predict(features[2]) <= 0)
self.assertTrue(lasso_model.predict(features[3]) > 0)
rr_model = RidgeRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(rr_model.predict(features[0]) <= 0)
self.assertTrue(rr_model.predict(features[1]) > 0)
self.assertTrue(rr_model.predict(features[2]) <= 0)
self.assertTrue(rr_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 2} # feature 0 has 2 categories
dt_model = DecisionTree.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, maxBins=4)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
rf_model = RandomForest.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numTrees=10, maxBins=4, seed=1)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
gbt_model = GradientBoostedTrees.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
try:
LinearRegressionWithSGD.train(rdd, initialWeights=array([1.0, 1.0]), iterations=10)
LassoWithSGD.train(rdd, initialWeights=array([1.0, 1.0]), iterations=10)
RidgeRegressionWithSGD.train(rdd, initialWeights=array([1.0, 1.0]), iterations=10)
except ValueError:
self.fail()
def trainRandomForestModel(data):
"""
Train a random forest regression model and return it
:param data: RDD[LabeledPoint]
:return: random forest regression model
"""
from pyspark.mllib.tree import RandomForest
model = RandomForest.trainRegressor(data, categoricalFeaturesInfo={}, numTrees=2000, featureSubsetStrategy="auto", impurity="variance", maxDepth=4, maxBins=32)
return model
def train_model(cls, trianData, cateFeaInfo={}, trees=3, impurity="gini",\
depth=4):
"""
训练模型
"""
model = RandomForest.trainClassifier(trainData, numClasses=2,\
categoricalFeaturesInfo=cateFeaInfo, numTrees=trees, \
featureSubsetStrategy="auto", impurity=impurity, maxDepth=depth,\
maxBins=32)
return model
def trainModel(trainingData):
print "\nTrainning Random Forest model started!"
Utils.logTime()
model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto", impurity='gini',
maxDepth=5, maxBins=32)
print '\nTraining Random Forest model finished'
Utils.logTime()
return model
def evaluate(self, trainingData, testData=None, metric=None):
if testData !=None:
model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
numTrees=10, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testData.count())
print('Test Error = ' + str(testErr))
else: #cross validation
pass
def getRandomForestRMSE(trees_array):
valRMSE_list = []
for trees in trees_array:
model = RandomForest.trainRegressor(train_featureScoreTimeRDD, categoricalFeaturesInfo={},
numTrees=trees, featureSubsetStrategy="auto",
impurity='variance', maxDepth=4, maxBins=32)
predictions = model.predict(val_featureScoreTimeRDD.map(lambda lp: lp.features))
labelsAndPreds = val_featureScoreTimeRDD.map(lambda lp: lp.label).zip(predictions)
valMSE = labelsAndPreds.map(lambda (v, p): (v - p)*(v-p)).sum() / float(val_featureScoreTimeRDD.count())
valRMSE=valMSE**0.5
valRMSE_list.append((trees, valRMSE))
return valRMSE_list
def trainOptimalModel(trainingData, testData):
print "\nTraining optimal Random Forest model started!"
Utils.logTime()
numTreesVals = [3,5,8]
featureSubsetStrategyVals = ['auto','all','sqrt','log2','onethird']
impurityVals = ['gini', 'entropy']
maxDepthVals = [3,4,5,6,7]
maxBinsVals = [8,16,32]
optimalModel = None
optimalNumTrees = None
optimalFeatureSubsetStrategy = None
optimalMaxDepth = None
optimalImpurity = None
optimalBinsVal = None
minError = None
try:
for curNumTree in numTreesVals:
for curFeatureSubsetStrategy in featureSubsetStrategyVals:
for curImpurity in impurityVals:
for curMaxDepth in maxDepthVals:
for curMaxBins in maxBinsVals:
model = RandomForest.trainClassifier(trainingData,
numClasses=2,
categoricalFeaturesInfo={},
numTrees=curNumTree,
featureSubsetStrategy=curFeatureSubsetStrategy,
impurity=curImpurity,
maxDepth=curMaxDepth,
maxBins=curMaxBins)
testErr = Evaluation.evaluate(model, testData)
if testErr < minError or not minError:
minError = testErr
optimalNumTrees = curNumTree
optimalFeatureSubsetStrategy = curFeatureSubsetStrategy
optimalImpurity = curImpurity
optimalMaxDepth = curMaxDepth
optimalBinsVal = curMaxBins
optimalModel = model
except:
msg = "\nException during model training with below parameters:"
msg += "\tnum trees: " + str(optimalNumTrees)
msg += "\tfeature subset strategy: " + optimalFeatureSubsetStrategy
msg += "\timpurity: " + str(curImpurity)
msg += "\tmaxDepth: " + str(curMaxDepth)
msg += "\tmaxBins: " + str(curMaxBins)
Utls.logMessage(msg)
logMessage(optimalModel, optimalNumTrees, optimalFeatureSubsetStrategy, optimalMaxDepth, optimalImpurity, optimalBinsVal, minError)
return optimalModel
def test_regression(self):
from pyspark.mllib.regression import LinearRegressionWithSGD, LassoWithSGD, \
RidgeRegressionWithSGD
from pyspark.mllib.tree import DecisionTree, RandomForest, GradientBoostedTrees
data = [
LabeledPoint(-1.0, [0, -1]),
LabeledPoint(1.0, [0, 1]),
LabeledPoint(-1.0, [0, -2]),
LabeledPoint(1.0, [0, 2])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
lr_model = LinearRegressionWithSGD.train(rdd)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
lasso_model = LassoWithSGD.train(rdd)
self.assertTrue(lasso_model.predict(features[0]) <= 0)
self.assertTrue(lasso_model.predict(features[1]) > 0)
self.assertTrue(lasso_model.predict(features[2]) <= 0)
self.assertTrue(lasso_model.predict(features[3]) > 0)
rr_model = RidgeRegressionWithSGD.train(rdd)
self.assertTrue(rr_model.predict(features[0]) <= 0)
self.assertTrue(rr_model.predict(features[1]) > 0)
self.assertTrue(rr_model.predict(features[2]) <= 0)
self.assertTrue(rr_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 2} # feature 0 has 2 categories
dt_model = DecisionTree.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
rf_model = RandomForest.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numTrees=100)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
gbt_model = GradientBoostedTrees.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
def test_classification(self):
from pyspark.mllib.classification import LogisticRegressionWithSGD, SVMWithSGD, NaiveBayes
from pyspark.mllib.tree import DecisionTree, RandomForest, GradientBoostedTrees
data = [
LabeledPoint(0.0, [1, 0, 0]),
LabeledPoint(1.0, [0, 1, 1]),
LabeledPoint(0.0, [2, 0, 0]),
LabeledPoint(1.0, [0, 2, 1])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
lr_model = LogisticRegressionWithSGD.train(rdd)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
svm_model = SVMWithSGD.train(rdd)
self.assertTrue(svm_model.predict(features[0]) <= 0)
self.assertTrue(svm_model.predict(features[1]) > 0)
self.assertTrue(svm_model.predict(features[2]) <= 0)
self.assertTrue(svm_model.predict(features[3]) > 0)
nb_model = NaiveBayes.train(rdd)
self.assertTrue(nb_model.predict(features[0]) <= 0)
self.assertTrue(nb_model.predict(features[1]) > 0)
self.assertTrue(nb_model.predict(features[2]) <= 0)
self.assertTrue(nb_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 3} # feature 0 has 3 categories
dt_model = DecisionTree.trainClassifier(
rdd, numClasses=2, categoricalFeaturesInfo=categoricalFeaturesInfo)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
rf_model = RandomForest.trainClassifier(
rdd, numClasses=2, categoricalFeaturesInfo=categoricalFeaturesInfo, numTrees=100)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
gbt_model = GradientBoostedTrees.trainClassifier(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
def testRegression(trainingData, testData):
# Train a RandomForest model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto",
impurity='variance', maxDepth=4, maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testMSE = labelsAndPredictions.map(lambda v_p1: (v_p1[0] - v_p1[1]) * (v_p1[0] - v_p1[1]))\
.sum() / float(testData.count())
print('Test Mean Squared Error = ' + str(testMSE))
print('Learned regression forest model:')
print(model.toDebugString())
def testClassification(trainingData, testData):
# Train a RandomForest model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainClassifier(trainingData, numClasses=2,
categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda v_p: v_p[0] != v_p[1]).count()\
/ float(testData.count())
print('Test Error = ' + str(testErr))
print('Learned classification forest model:')
print(model.toDebugString())
def train_trend_model(self, model, data, i):
self.logger.info('Start to train the direction model')
rdd_data = self.sc.parallelize(data)
if self.trend_prediction_method == self.RANDOM_FOREST:
model = RandomForest.trainClassifier(rdd_data, numClasses=2, categoricalFeaturesInfo={}, numTrees=40,
featureSubsetStrategy="auto", impurity='gini', maxDepth=20,
maxBins=32)
elif self.trend_prediction_method == self.NAIVE_BAYES:
model = NaiveBayes.train(rdd_data)
elif self.trend_prediction_method == self.LOGISTIC_REGRESSION:
model = LogisticRegressionWithSGD.train(rdd_data, iterations=10000, step=0.001,
initialWeights=None if model is None else model.weights)
elif self.trend_prediction_method == self.SVM:
model = SVMWithSGD.train(rdd_data, iterations=10000, step=0.001,
initialWeights=None if model is None else model.weights)
return model
def create_model(name, training):
if name == 'logistic':
print_box()
print "Logistic Regression Model"
print_box()
model = LogisticRegressionWithLBFGS.train(training)
elif name == 'tree':
print_box()
print "Decision Tree Model"
print_box()
model = DecisionTree.trainClassifier(training, numClasses=2, categoricalFeaturesInfo={},
impurity='gini', maxDepth=5, maxBins=32)
elif name == 'rf':
print_box()
print "Random Forest Model"
print_box()
model = RandomForest.trainClassifier(training, numClasses=2, categoricalFeaturesInfo={},
numTrees=15, featureSubsetStrategy="auto", impurity='gini', maxDepth=5, maxBins=50)
return model
def kfolds ():
#folds = kFold(data, k) this would work in java
acc = 0
spurity = 0
scomp = 0
gpurity = 0
gcomp = 0
foldsize = data.count()/k
tested = sc.parallelize([])
for i in range(k):
test = sc.parallelize(data.subtract(tested).takeSample(False, foldsize))
tested = tested.union(test)
train = data.subtract(test)
# train the random forest
model = RandomForest.trainClassifier(train, numClasses=2, categoricalFeaturesInfo={},
numTrees=num_trees, featureSubsetStrategy="auto",
impurity='gini', maxDepth = max_depth, maxBins=32)
predictions = model.predict(test.map(lambda x: x.features))
labelsAndPredictions = test.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(test.count())
Mg = float(labelsAndPredictions.filter(lambda (v, p): v == 0 and p == 1).count())
Ng = float(labelsAndPredictions.filter(lambda (v, p): v == 0 and p == 0).count())
Ms = float(labelsAndPredictions.filter(lambda (v, p): v == 1 and p == 0).count())
Ns = float(labelsAndPredictions.filter(lambda (v, p): v == 1 and p == 1).count())
gpurity += (Ng / (Ng+Ms))
gcomp += (Ng / (Ng+Mg))
spurity += (Ns / (Ns+Mg))
scomp += (Ns/(Ns+Ms))
acc += (1 - testErr)
print 'with '+ str(k) + ' folds:'
print ('Average Galaxy Purity = ' + str(gpurity / k))
print ('Average Galaxy Completeness = ' + str(gcomp / k))
print ('Average Star Purity = ' + str(spurity / k))
print ('Average Star Completeness = ' + str(scomp / k))
print ('Average Accuracy = ' + str(acc / k))
def train_amount_model(self, model, data, i):
rdd_data = self.sc.parallelize(data)
self.logger.info('Start to train the amount model')
if self.amount_prediction_method == self.ARTIFICIAL_NEURAL_NETWORK:
input_num = self.feature_num
layers = [input_num, input_num / 3 * 2, input_num / 3, 1]
neural_network = NeuralNetworkSpark(layers=layers, bias=0)
model = neural_network.train(rdd_data, method=neural_network.BP, seed=1234, learn_rate=0.0001,
iteration=15, model=model)
elif self.amount_prediction_method == self.RANDOM_FOREST:
model = RandomForest.trainRegressor(rdd_data, categoricalFeaturesInfo={}, numTrees=40,
featureSubsetStrategy="auto", impurity='variance', maxDepth=20,
maxBins=32)
elif self.amount_prediction_method == self.LINEAR_REGRESSION:
model = LinearRegressionWithSGD.train(rdd_data, iterations=10000, step=0.001,
initialWeights=model.weights if model is not None else None)
else:
self.logger.error("Unknown training method {}".format(self.amount_prediction_method))
raise ValueError("Unknown training method {}".format(self.amount_prediction_method))
return model
data = sc.textFile("team_result.txt")
data = data.map(lambda line: line.split(","))
data = data.map(lambda x: LabeledPoint(float(x[5]), [x[0], x[1], x[2], x[3], x[4]]))
# Split the dataset into training set (70%) and test set (30%)
trainingData, testData = data.randomSplit([0.7, 0.3], seed=1071)
# Create and train the naive Bayes model
naiveBayesModel = NaiveBayes.train(trainingData, 1.0)
# Apply the model to the test set
predictionAndLabelNaiveBayes = testData.map(lambda x: (naiveBayesModel.predict(x.features), x.label))
# Calculate the accuracy of the model
errorNaiveBayes = 1.0 * predictionAndLabelNaiveBayes.filter(lambda (x, y): x != y).count() / testData.count()
print "Naive Bayes model classification error: {0:f}".format(errorNaiveBayes)
# Create and train the random forest model
randomForestModel = RandomForest.trainClassifier(trainingData, numClasses=2,
categoricalFeaturesInfo={0: 9, 1: 9, 2: 9, 3: 9, 4: 9}, numTrees=3,
impurity="gini", maxDepth=4, maxBins=32, seed=1071)
'''
Note taken from the official API documentation:
In Python, predict cannot currently be used within an RDD
transformation or action. Call predict directly on the RDD instead.
'''
predictionsRandomForest = randomForestModel.predict(testData.map(lambda x: x.features))
labelsAndPredictionsRF = testData.map(lambda x: x.label).zip(predictionsRandomForest)
errorRandomForest = labelsAndPredictionsRF.filter(lambda (x, y): x != y).count() / float(testData.count())
print "Random forest classification error: {0:f}".format(errorRandomForest)
def train_randomforest_model(dataset):
model = RandomForest.trainClassifier(dataset, 2, {}, 3, seed=42)
return model
val_data = truetestData.map(lambda line: LabeledPoint(line[7], line[0:7]))
# debug
print(data.take(1))
print(val_data.take(1))
# for holdout validation
(trData, tData) = data.randomSplit([0.7, 0.3])
# random forest training model
mod = RandomForest.trainRegressor(trData,
categoricalFeaturesInfo={
0: 13,
1: 1499,
2: 2
},
numTrees=4,
featureSubsetStrategy="auto",
impurity='variance',
maxDepth=8,
maxBins=1500)
# prediction and evaluation
predictions = mod.predict(tData.map(lambda x: x.features))
pred = mod.predict(val_data.map(lambda x: x.features))
labelsAndPredictions = tData.map(lambda lp: lp.label).zip(predictions)
truePred = val_data.map(lambda lp: lp.label).zip(pred)
metrics = RegressionMetrics(labelsAndPredictions)
met2 = RegressionMetrics(truePred)
# Squared Error
print("Validation MSE = %s" % metrics.meanSquaredError)
(model1.predict(p.features), p.label))
#model 2
from pyspark.mllib.classification import SVMWithSGD
model2 = SVMWithSGD.train(training, iterations=100)
predictionAndLabel_SVM = test.map(lambda p:
(model2.predict(p.features), p.label))
#model 3
from pyspark.mllib.tree import RandomForest
model = RandomForest.trainClassifier(training,
numClasses=6,
numTrees=2,
categoricalFeaturesInfo={},
featureSubsetStrategy="auto",
maxDepth=6,
maxBins=32)
predictions = model.predict(test.map(lambda x: x.features))
predictionAndLabel_RF = test.map(lambda lp: lp.label).zip(predictions)
# -------------- La phase prediction ------------#
def accuracy(predictionAndLabel):
return 1.0 * predictionAndLabel.filter(
lambda pl: pl[0] == pl[1]).count() / test.count()
print('model accuracy {}'.format(accuracy(predictionAndLabel_NB)))
print('model accuracy {}'.format(accuracy(predictionAndLabel_SVM)))
# Evaluate model on test instances and compute test error
predictions = GBTmodel.predict(test_dense.rdd.map(lambda x: x.features.values))
labelsAndPredictions = test_dense.rdd.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(
lambda lp: lp[0] != lp[1]).count() / float(test_dense.rdd.count())
print('Test Error = ' + str(testErr))
from pyspark.mllib.tree import RandomForest, RandomForestModel
print('Learned classification RF model:')
train_start = time.time()
RFmodel = RandomForest.trainClassifier(labelPoint_train,
numClasses=2,
categoricalFeaturesInfo={},
numTrees=30,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=4,
maxBins=32)
train_end = time.time()
print(f'Time elapsed training model: {train_end - train_start} seconds')
predictions = RFmodel.predict(test_dense.rdd.map(lambda x: x.features.values))
labelsAndPredictions = test_dense.rdd.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(
lambda lp: lp[0] != lp[1]).count() / float(test_dense.rdd.count())
print('Test Error = ' + str(testErr))
spark.stop()
def takeAndPrint(time, rdd, num=1000):
sqlContext = SQLContext(sc)
result = []
taken = rdd.take(num + 1)
print("-------------------------------------------")
print("Time: %s" % time)
print("-------------------------------------------")
for record in taken[:num]:
vals = tuple(record.split(",")) #[tuple(['Alice', '1'])]
result.append(vals)
print(type(result))
print(result)
df = sqlContext.createDataFrame(result).collect()
df.show()
# Dataframe for MLLIB's
# panda dataframe
sample_data = df.sample(False, 0.5, 83).toPandas()
sample_data.head()
# find category and numerical variables
numeric_cols = [
"account_length", "number_vmail_messages", "total_day_minutes",
"total_day_calls", "total_day_charge", "total_eve_minutes",
"total_eve_calls", "total_eve_charge", "total_night_minutes",
"total_night_calls", "total_intl_minutes", "total_intl_calls",
"total_intl_charge"
]
categorical_cols = [
"state", "international_plan", "voice_mail_plan", "area_code"
]
#some plots
ax = sb.boxplot(x="churned",
y="number_customer_service_calls",
data=sample_data,
palette="Set3")
ax.set(xlabel="Churned",
ylabel="Number of calls made to the customer service")
plt.show()
example_numeric_data = sample_data[[
"total_day_minutes", "total_day_calls", "total_day_charge", "churned"
]]
sb.pairplot(example_numeric_data, hue="churned", palette="husl")
plt.show()
# correlation and heatmap
corr = sample_data[[
"account_length", "number_vmail_messages", "total_day_minutes",
"total_day_calls", "total_day_charge", "total_eve_minutes",
"total_eve_calls", "total_eve_charge", "total_night_minutes",
"total_night_calls", "total_intl_minutes", "total_intl_calls",
"total_intl_charge"
]].corr()
sb.heatmap(corr)
reduced_numeric_cols = [
"account_length", "number_vmail_messages", "total_day_calls",
"total_day_charge", "total_eve_calls", "total_eve_charge",
"total_night_calls", "total_intl_calls", "total_intl_charge"
]
label_indexer = StringIndexer(inputCol='churned', outputCol='label')
plan_indexer = StringIndexer(inputCol='intl_plan',
outputCol='intl_plan_indexed')
assembler = VectorAssembler(inputCols=['intl_plan_indexed'] +
reduced_numeric_cols,
outputCol='features')
classifier = DecisionTreeClassifier(labelCol='label',
featuresCol='features')
pipeline = Pipeline(
stages=[plan_indexer, label_indexer, assembler, classifier])
(train, test) = df.randomSplit([0.7, 0.3])
model = pipeline.fit(train)
# Random forest
from pyspark.mllib.tree import RandomForest
model2 = RandomForest.trainClassifier(train,
numClasses=2,
numTrees=3,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=4,
maxBins=32)
# SVM needs some tweaking- not working as expected
# ROC chart
from pyspark.ml.evaluation import BinaryClassificationEvaluator
predictions = model.transform(test)
evaluator = BinaryClassificationEvaluator()
auroc = evaluator.evaluate(predictions,
{evaluator.metricName: "areaUnderROC"})
def main():
sc = SparkContext(conf=SparkConf().setAppName("Random Forest"))
sqlContext = SQLContext(sc)
bytePath = "s3n://eds-uga-csci8360/data/project2/binaries"
namePath = "s3n://eds-uga-csci8360/data/project2/labels/X_train_small.txt"
nameTestPath = "s3n://eds-uga-csci8360/data/project2/labels/X_test_small.txt"
classPath = "s3n://eds-uga-csci8360/data/project2/labels/y_train_small.txt"
#bytePath = "/Users/priyanka/Desktop/project2files/all"
#namePath = "/Users/priyanka/Desktop/X_train_small.txt"
#nameTestPath="/Users/priyanka/Desktop/X_test_small.txt"
#classPath = "/Users/priyanka/Desktop/y_train_small.txt"
#docData Output: ('file:/Users/priyanka/Desktop/project2files/train/04mcPSei852tgIKUwTJr.bytes', '00401000 20 FF 58 C0 20 FE 5C 01 F8 00 0F 8B 50 FC 06 01\r\n00401010 8C 01 FF")
docData = sc.wholeTextFiles(
bytePath,
25).map(lambda (x, y): (x.encode("utf-8"), y.encode("utf-8")))
print("docData frankie")
docData.take(1)
#clean docData here - remove 1st word from line and remove /r/n
cleanDocData = docData.map(lambda (x, y): (x, clean(y.split())))
#try calculating tf here (filename,tf)
x = 16**2 + 1
hashingTF = HashingTF(x)
tfDocData = cleanDocData.map(lambda (x, y): (x, hashingTF.transform(y)))
tfDocData.take(1)
#Output format : (index,filename)
nameData = sc.textFile(
namePath, 25).map(lambda x: "file:" + bytePath + "/" + x + ".bytes"
).zipWithIndex().map(lambda (x, y): (y, x))
#nameData.take(5)
#Output format: (index,label)
labelData = sc.textFile(
classPath, 25).zipWithIndex().map(lambda (x, y): (y, str(int(x) - 1)))
#Output format: (filename,label)
joinNameLabel = nameData.join(labelData).map(lambda (x, y): y)
#joinNameLabel.take(5)
#Output: (label,tfidf)
joinCleanDocLabel = joinNameLabel.join(tfDocData).map(lambda (x, y): y)
#Output: (label,tfidf)
hashData = joinCleanDocLabel.map(lambda
(label, text): LabeledPoint(label, text))
print "hashing TF done"
print("generating model fliss")
model1 = RandomForest.trainClassifier(hashData,
numClasses=9,
categoricalFeaturesInfo={},
numTrees=50,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=8,
maxBins=32)
#==============================================================================
# Testing starts here
#==============================================================================
#Output: (filename,index)
nameTestData = sc.textFile(nameTestPath, 25).map(
lambda x: "file:" + bytePath + "/" + x + ".bytes").zipWithIndex()
#Output: (index,tfidf)
joinTestDocLabel = nameTestData.join(tfDocData).map(lambda (x, y): y)
print("hashing test kenny")
hashTestData = joinTestDocLabel.map(
lambda (label, text): LabeledPoint(label, text))
hashTestData.persist()
#Random forest prediction and labels and accuracy
print "prediction part lyndz"
prediction1 = model1.predict(hashTestData.map(lambda x: x.features))
prediction1.saveAsTextFile("/Users/priyanka/Desktop/pred.txt")
# Evaluate model on test instances and compute test error
predictions = modelDT.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testAccuracy = labelsAndPredictions.filter(
lambda (v, p): v == p).count() / float(testData.count())
print('Decision Tree Test Accuracy =' + str(testAccuracy))
# Print the predictions
print("Acutual vs Predicted values - Decision Tree")
print(labelsAndPredictions.collect())
# Train a RandomForest model
modelRF = RandomForest.trainClassifier(trainingData,
numClasses=3,
categoricalFeaturesInfo={},
numTrees=3,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=4,
maxBins=32)
# Evaluate model on test instances and compute test error
predictions = modelRF.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testAccuracy = labelsAndPredictions.filter(
lambda (v, p): v == p).count() / float(testData.count())
print('Random Forest Test Accuracy =' + str(testAccuracy))
# Print the predictions
print("Acutual vs Predicted values - Random Forest")
print(labelsAndPredictions.collect())
results = []
for train_index, test_index in ss:
X_training, Y_training, X_test, Y_test = [], [], [], []
for i in train_index:
X_training.append(X[i])
Y_training.append(Y[i])
for i in test_index:
X_test.append(X[i])
Y_test.append(Y[i])
parsedData = []
for i in range(0, len(X_training)):
parsedData.append(LabeledPoint(Y_training[i], X_training[i]))
model = RandomForest.trainClassifier(sc.parallelize(parsedData),
2, {},
3,
seed=42)
testErr = 0
for i in range(0, len(X_test)):
a = Y_test[i]
b = model.predict(X_test[i])
#b = 1
if a != b:
testErr += 1
Err += float(testErr) / float(len(X_test))
print("AVG test error: %.6f" % (Err / iter_number))
# categorical = range(0,30) + range(35,39) + range(41,46) + range(48,57)
# data.cache()
# mappings = [get_mapping(data, i) for i in categorical]
labelpoints = data.map(lambda x: LabeledPoint(x[-1], x[:-1]))
return labelpoints
data = label_points(data_raw)
training, testing = data.randomSplit([0.5, 0.5], 0)
model = RandomForest.trainClassifier(training,
numClasses=7,
categoricalFeaturesInfo={},
numTrees=1000,
featureSubsetStrategy="auto",
impurity='gini',
maxBins=32)
predictions = model.predict(testing.map(lambda x: x.features))
labelsAndPredictions = testing.map(lambda lp: lp.label).zip(predictions)
accuracy = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(
testing.count())
print accuracy
#
# # https://books.google.com/books?id=syPHBgAAQBAJ&pg=PA166&lpg=PA166&dq=categorical+variables+labeledpoint+pyspark&source=bl&ots=X9VyTR348v&sig=cMf8rZlpbdWcyCl2jSPNU1Var6k&hl=en&sa=X&ved=0ahUKEwjPpofhh8XMAhVI1WMKHXoqCio4ChDoAQgbMAA#v=onepage&q=categorical%20variables%20labeledpoint%20pyspark&f=false
# # Page 166
# def get_mapping(rdd, idx):
# return rdd.map(lambda fields: fields[idx]).distinct().zipWithIndex().collectAsMap()
def train_random_forest(trainRDD, num_trees, max_depth):
return RandomForest.trainClassifier(trainRDD,
2, {},
num_trees,
maxDepth=max_depth)
from pyspark.mllib.evaluation import MulticlassMetrics
trainDataPath = "s3://cloudpa2/TrainingDataset.csv"
valDataPath = "s3://cloudpa2/ValidationDataset.csv"
sc = SparkContext.getOrCreate()
sc.getConf().setAppName('cloudpa2')
rawData = sc.textFile(trainDataPath)
records = rawData.filter(lambda str: "\"" not in str).map(
lambda str: str.split(";")).map(lambda strVal: [float(x) for x in strVal])
data = records.map(
lambda arr: LabeledPoint(int(arr[-1]) - 1, Vectors.dense(arr[:-1])))
valRawData = sc.textFile(valDataPath)
valRecords = valRawData.filter(lambda str: "\"" not in str).map(
lambda str: str.split(";")).map(lambda strVal: [float(x) for x in strVal])
valData = valRecords.map(lambda arr: (arr[:-1], int(arr[-1]) - 1))
rfModel = RandomForest.trainClassifier(data,
numClasses=10,
categoricalFeaturesInfo={},
numTrees=100)
rfModelPredictionAndLabels = rfModel.predict(
valData.map(lambda tp: tp[0])).zip(valData.map(lambda _: float(_[1])))
rfModelMetric = MulticlassMetrics(rfModelPredictionAndLabels)
print("F1Score : %s" % (rfModelMetric.accuracy))
rfModel.save(sc, "s3://myprogrambucket123/rfwine_model.model")
dataPath = 'train_svm'# 'data/mllib/sample_libsvm_data.txt'
if len(sys.argv) == 2:
dataPath = sys.argv[1]
if not os.path.isfile(dataPath):
sc.stop()
usage()
points = MLUtils.loadLibSVMFile(sc, dataPath)
# Re-index class labels if needed.
(reindexedData, origToNewLabels) = reindexClassLabels(points)
numClasses = len(origToNewLabels)
# Train a classifier.
categoricalFeaturesInfo = {} # no categorical features
#model = DecisionTree.trainClassifier(reindexedData, numClasses=numClasses,
# categoricalFeaturesInfo=categoricalFeaturesInfo)
model = RandomForest.trainClassifier(reindexedData, numClasses=numClasses,categoricalFeaturesInfo={},numTrees=30,featureSubsetStrategy='auto', impurity='gini', maxDepth=8, maxBins=40, )
# Print learned tree and stats.
print origToNewLabels
print "Trained DecisionTree for classification:"
# print " Model numNodes: %d" % model.numNodes()
# print " Model depth: %d" % model.depth()
print " Training accuracy: %g" % getAccuracy(model, reindexedData)
# if model.numNodes() < 20:
# print model.toDebugString()
# else:
# print model
print model
# testdata = MLUtils.loadLibSVMFile(sc, 'test_svm')
#reuben
predictions = model.predict(testdata.map(lambda x: x.features))
# labels = testdata.map(lambda l:l.label)
def test_classification(self):
from pyspark.mllib.classification import LogisticRegressionWithSGD, SVMWithSGD, NaiveBayes
from pyspark.mllib.tree import DecisionTree, DecisionTreeModel, RandomForest,\
RandomForestModel, GradientBoostedTrees, GradientBoostedTreesModel
data = [
LabeledPoint(0.0, [1, 0, 0]),
LabeledPoint(1.0, [0, 1, 1]),
LabeledPoint(0.0, [2, 0, 0]),
LabeledPoint(1.0, [0, 2, 1])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
temp_dir = tempfile.mkdtemp()
lr_model = LogisticRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
svm_model = SVMWithSGD.train(rdd, iterations=10)
self.assertTrue(svm_model.predict(features[0]) <= 0)
self.assertTrue(svm_model.predict(features[1]) > 0)
self.assertTrue(svm_model.predict(features[2]) <= 0)
self.assertTrue(svm_model.predict(features[3]) > 0)
nb_model = NaiveBayes.train(rdd)
self.assertTrue(nb_model.predict(features[0]) <= 0)
self.assertTrue(nb_model.predict(features[1]) > 0)
self.assertTrue(nb_model.predict(features[2]) <= 0)
self.assertTrue(nb_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 3} # feature 0 has 3 categories
dt_model = DecisionTree.trainClassifier(
rdd, numClasses=2, categoricalFeaturesInfo=categoricalFeaturesInfo, maxBins=4)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
dt_model_dir = os.path.join(temp_dir, "dt")
dt_model.save(self.sc, dt_model_dir)
same_dt_model = DecisionTreeModel.load(self.sc, dt_model_dir)
self.assertEqual(same_dt_model.toDebugString(), dt_model.toDebugString())
rf_model = RandomForest.trainClassifier(
rdd, numClasses=2, categoricalFeaturesInfo=categoricalFeaturesInfo, numTrees=10,
maxBins=4, seed=1)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
rf_model_dir = os.path.join(temp_dir, "rf")
rf_model.save(self.sc, rf_model_dir)
same_rf_model = RandomForestModel.load(self.sc, rf_model_dir)
self.assertEqual(same_rf_model.toDebugString(), rf_model.toDebugString())
gbt_model = GradientBoostedTrees.trainClassifier(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
gbt_model_dir = os.path.join(temp_dir, "gbt")
gbt_model.save(self.sc, gbt_model_dir)
same_gbt_model = GradientBoostedTreesModel.load(self.sc, gbt_model_dir)
self.assertEqual(same_gbt_model.toDebugString(), gbt_model.toDebugString())
try:
rmtree(temp_dir)
except OSError:
pass
df = spark.read.format('com.databricks.spark.csv').csv(
's3://cs643-wine/TrainingDataset.csv', header=True, sep=";")
# def parsePoint(line):
# # values = [float(x) for x in line.split(';')]
# return LabeledPoint(values[11], values[0:10])
parsedTData = df.rdd.map(
lambda row: LabeledPoint(row[-1], Vectors.dense(row[:11])))
#Training data using Random Forest
model = RandomForest.trainClassifier(parsedTData,
numClasses=11,
categoricalFeaturesInfo={},
numTrees=3,
impurity='gini',
maxDepth=4,
maxBins=32)
# vData = sc.textFile("ValidationDataset.csv")
# header = vData.first()
# rows = vData.filter(lambda x: x != header)
vdf = spark.read.format('com.databricks.spark.csv').csv(
's3://cs643-wine/ValidationDataset.csv', header=True, sep=";")
parsedVData = vdf.rdd.map(
lambda row: LabeledPoint(row[-1], Vectors.dense(row[:11])))
predictions = model.predict(parsedVData.map(lambda x: x.features))
# Class 18.0 precision = 0.0
# Class 18.0 recall = 0.0
# Class 18.0 F1 Measure = 0.0
# Class 19.0 precision = 0.0
# Class 19.0 recall = 0.0
# Class 19.0 F1 Measure = 0.0
# Class 20.0 precision = 0.0
# Class 20.0 recall = 0.0
# Class 20.0 F1 Measure = 0.0
training = training_random.rdd.map(lambda row: LabeledPoint(row['label'], row['raw_Features'].toArray()))
test = test_random.rdd.map(lambda row: LabeledPoint(row['label'], row['raw_Features'].toArray()))
#======== RandomForest
rf_model = RandomForest.trainClassifier(training,21,{}, 50, seed=1000)
rf_model.totalNumNodes()#402
## Compute raw scores on the test set
# predictionAndLabels = test.map(lambda lp: (float(rf_model.predict(lp.features)), lp.label)) #doesnot work
# an other way
predictions = rf_model.predict(test.map(lambda x: x.features))
labelsAndPredictions = test.map(lambda lp: lp.label).zip(predictions)
predictionAndLabels=labelsAndPredictions.map(lambda x: (x[1],x[0] )) #infact , there is no need to switch
metrics = MulticlassMetrics(predictionAndLabels)
#metrics = MulticlassMetrics(labelsAndPredictions) # the same as above
#predictionAndLabels – an RDD of (prediction, label) pairs.
#Preparing the training data
from pyspark.mllib.regression import LabeledPoint
from numpy import array
data_raw = train_data.rdd.map(lambda x: LabeledPoint(x[12], array((x[0], x[1], x[2], x[3], x[4], x[5], x[6], x[7], x[8] ,x[9], x[10], x[11]), dtype=float)))
(trainingData, testData) = data_raw.randomSplit([0.7, 0.3])
# In[ ]:
#Training the random forest model
from pyspark.mllib.tree import RandomForest, RandomForestModel
model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={0:13, 1:13, 5:13, 11:14},
numTrees=4, featureSubsetStrategy="auto",
impurity='gini', maxDepth=7, maxBins=15)
# In[ ]:
#Testing the trained model on the test data and evaluating error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda lp: lp[0] != lp[1]).count() / float(testData.count())
print('Test Error = ' + str(testErr))
print('Learned classification forest model:')
print(model.toDebugString())
for country_from in country_list:
for country_to in country_list:
print("Country from: ", country_from, " Country to: ", country_to)
try:
df2 = df.filter(df.Country_from == country_from).filter(
df.Country_to == country_to)
df_temp = df2.select(df2.Scrap_time.cast("float"),'Airline1_Back','Airline2_There','Airline2_Back'\
,'Airline1_There',df2.Days.cast("float"),df2.Journey_time.cast("float"), df2.Full_Price.cast("float"))
for nazwa in nazwy:
indexer = StringIndexer(inputCol=nazwa,
outputCol=nazwa + "Index")
df_temp = indexer.fit(df_temp).transform(df_temp)
df_temp = df_temp.select('Airline1_BackIndex','Airline2_ThereIndex','Airline2_BackIndex','Airline1_ThereIndex','Scrap_time',\
'Days','Journey_time', 'Full_Price')
transformed = transData(df_temp)
test = transformed.rdd.map(lambda row: LabeledPoint(
row['label'], row['features'].toArray()))
model = RandomForest.trainRegressor(test,
categoricalFeaturesInfo={},
numTrees=30,
featureSubsetStrategy="auto",
impurity='variance',
maxDepth=4,
maxBins=32)
model.save(sc, "modele/" + country_from + "_" + country_to)
except:
print("Puść jeszcze raz ", country_from, " ", country_to)
# MLUtils.saveAsLibSVMFile(data, "hdfs:///hndata/spam_docvecs")
# Split the data into training and test sets
(trainingData, testData) = data.randomSplit([0.7, 0.3])
# Train a RandomForest model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
rr = RandomForest.trainClassifier(
trainingData,
numClasses=2,
categoricalFeaturesInfo={},
numTrees=3,
featureSubsetStrategy="auto",
impurity="gini",
maxDepth=4,
maxBins=32,
)
predictions = rr.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
posErr = (
float(labelsAndPredictions.filter(lambda (v, p): v == 0.0 and v != p).count())
/ testData.filter(lambda lp: lp.label == 0.0).count()
)
negErr = (
float(labelsAndPredictions.filter(lambda (v, p): v == 1.0 and v != p).count())
/ testData.filter(lambda lp: lp.label == 1.0).count()
)
} # feature 1 has 53 categories, 0 ..to .. 52 (corresponding to week 1 .. 53)
# [(crimes, [beat, week, temp])]
# feature 0: beat
# feature 1: week
# feature 2: temp
# featuresDic = {} # for all continuous predictors
maxBins = max(
len(beatsDic), len(weekDic)
) # ecisionTree requires maxBins >= max categories in categorical features (304)
### Fit
model = RandomForest.trainRegressor(trainingData,
categoricalFeaturesInfo=featuresDic,
numTrees=10,
featureSubsetStrategy="auto",
impurity='variance',
maxDepth=5,
maxBins=maxBins)
### Evalute
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testMSE = labelsAndPredictions.map(lambda v_p1: (v_p1[0] - v_p1[1]) * (v_p1[0] - v_p1[1]))\
.sum() / float(testData.count())
print('Test Mean Squared Error = ' + str(testMSE))
print('Learned regression forest model:')
# print(model.toDebugString())
### Compute R2
SSE = labelsAndPredictions.map(lambda v_p1: (v_p1[0] - v_p1[1]) *
labeled_data = labeled_indices.leftOuterJoin(keyfirst_train).map(
lambda _: (_[1][1], _[0]))
unlabeled_data = unlabeled_indices.leftOuterJoin(keyfirst_train).map(
lambda _: (_[1][1], _[0]))
print('labeled = ', labeled_indices.count(), ' unlabeled = ',
unlabeled_indices.count())
if unlabeled_indices.isEmpty():
break
n_estimators = 10
model = RandomForest.trainClassifier(labeled_data.map(lambda _: _[0]),
numClasses=2,
categoricalFeaturesInfo={},
numTrees=n_estimators,
featureSubsetStrategy="auto",
impurity='gini')
''' accuracy test on testset here'''
predictions = model.predict(test.map(lambda x: x.features))
labelsAndPredictions = test.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda _: _[0] != _[1])
n_unlabeled = unlabeled_data.count()
rdd = sc.parallelize([])
for tree in model._java_model.trees():
predX = DecisionTreeModel(tree).predict(unlabeled_data.map(lambda _ : _[0].features))\
.zipWithIndex()\
.map(lambda _: (_[1], _[0]))
rdd = rdd.union(predX)
features_modeled_train, features_categorical_indexed_vec_train)
## select the one-hot-encoded categorical features along with numerical features as well as label to contrust the modeling dataset
df_train_modeling = df_train.select(features_modeled_train)
## df_train_modeling_rdd for mllib package
df_train_modeling_rdd = df_train_modeling.map(
lambda p: convert_sparsevec_to_vec_df(
p, features_categorical_indexed_vec_index_train))
df_train_modeling_rdd = df_train_modeling_rdd.map(
lambda l: LabeledPoint(l[0], l[1:]))
################################################## 5: train random forest regression model
## random forest
## train model
rfModel = RandomForest.trainRegressor(df_train_modeling_rdd,
categoricalFeaturesInfo={},
numTrees=100,
featureSubsetStrategy="auto",
impurity='variance',
maxDepth=10,
maxBins=32)
# Predict on train data
predictions = rfModel.predict(
df_train_modeling_rdd.map(lambda l: l.features))
## Evaluation of the model
predictionAndObservations = predictions.zip(
df_train_modeling_rdd.map(lambda l: l.label))
testMetrics = RegressionMetrics(predictionAndObservations)
model_time = str(model_time[0][0])
df_model_performance = sqlContext.createDataFrame(
sc.parallelize(
[[model_time, testMetrics.rootMeanSquaredError, testMetrics.r2]]),
["model_time", "RMSE", "R2"])
print("Number of training set rows: %d" % training_data.count())
print("Number of test set rows: %d" % test_data.count())
# COMMAND ----------
from pyspark.mllib.tree import RandomForest
from time import *
start_time = time()
model = RandomForest.trainClassifier(training_data,
numClasses=2,
categoricalFeaturesInfo={},
numTrees=25,
featureSubsetStrategy="auto",
impurity="gini",
maxDepth=4,
maxBins=32,
seed=13579)
end_time = time()
elapsed_time = end_time - start_time
print("Time to train model: %.3f seconds" % elapsed_time)
# COMMAND ----------
predictions = model.predict(test_data.map(lambda x: x.features))
labels_and_predictions = test_data.map(lambda x: x.label).zip(predictions)
acc = labels_and_predictions.filter(lambda x: x[0] == x[1]).count() / float(
test_data.count())
l2.extend([float(a[j])])
test_features.append(l2)
l = f.readline()
f.close()
# Random Forest
# C14 - C21
# Build the Model
rf_trees = [25, 50, 100, 150, 200, 250, 300]
for i in range(0, len(rf_trees), 1):
num_rf_trees = rf_trees[i]
# Build the Model
model = RandomForest.trainClassifier(train_data, 2, {}, num_rf_trees)
rf_train_predict_label = []
rf_test_predict_label = []
# Predict Labels
for j in range(0, len(test_features), 1):
p_l = model.predict(test_features[j])
rf_test_predict_label.extend([p_l])
for j in range(0, len(train_features), 1):
p_l = model.predict(train_features[j])
rf_train_predict_label.extend([p_l])
# Append Labels
appendColumn(ensemble_test, rf_test_predict_label)
# from pyspark.mllib.tree import RandomForest, RandomForestModel
# model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
# numTrees=3, featureSubsetStrategy="auto",
# impurity='gini', maxDepth=4, maxBins=32)
# evaluate(model,trainingData,testData)
# In[16]:
import pandas as pd
from pyspark.mllib.tree import RandomForest, RandomForestModel
for n in [1, 2, 4, 8, 16, 32, 64, 100]:
start = time.time()
model = RandomForest.trainClassifier(parsedData,
numClasses=2,
categoricalFeaturesInfo={},
numTrees=n,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=30,
maxBins=32)
taken = time.time() - start
taken
pd.DataFrame([[filename, taken, n]]).to_csv('rf_spark.txt',
mode='a',
index=False,
header=False)
#from pyspark.mllib.classification import SVMWithSGD, SVMModel
#model = SVMWithSGD.train(trainingData, iterations=100)
#evaluate(model,trainingData,testData)
# Gradient Boosted Trees
# ------------------------------------------------------------------------------
# Step 5(a):
# Parameters for the Random Forest model
# ------------------------------------------------------------------------------
RANDOM_SEED = 10904
RF_NUM_TREES = 100
RF_MAX_DEPTH = 4
RF_MAX_BINS = 100
# ------------------------------------------------------------------------------
# Step 5(b):
# Training a Random Forest model on the dataset
# ------------------------------------------------------------------------------
model = RandomForest.trainClassifier(transformed_train_df, numClasses=2, categoricalFeaturesInfo={}, \
numTrees=RF_NUM_TREES, featureSubsetStrategy="log2", impurity="entropy", \
maxDepth=RF_MAX_DEPTH, maxBins=RF_MAX_BINS, seed=RANDOM_SEED)
# ------------------------------------------------------------------------------
# Step 5©:
# Make predictions and compute accuracy
# ------------------------------------------------------------------------------
predictions = model.predict(transformed_test_df.map(lambda x: x.features))
labels_and_predictions = transformed_test_df.map(lambda x: x.label).zip(predictions)
model_accuracy = labels_and_predictions.filter(lambda x: x[0] == x[1]).count() / float(transformed_test_df.count())
print("Model accuracy: %.3f%%" % (model_accuracy * 100))
# ------------------------------------------------------------------------------
# Step 5(d):
sc = spark.sparkContext
# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLibSVMFile(sc, 'data/diamonds.data')
# Split the data into training and test sets (30% held out for testing)
(trainingData, testData) = data.randomSplit([0.7, 0.3], seed=123)
# Train a RandomForest model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainClassifier(trainingData,
numClasses=9,
categoricalFeaturesInfo={},
numTrees=25,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=15,
maxBins=32,
seed=123)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(
lambda lp: lp[0] != lp[1]).count() / float(testData.count())
result = testData.zip(predictions).collect()
# Print the predictions to output file
with open('machine_learning/results/predicted_cut.txt', 'w') as f:
for i in result:
target_data = keyed_data.join(keyed_target)
labled_point_data = target_data.map(lambda tup: LabeledPoint(tup[1][1][0], tup[1][0][0].split(',')))
#map(lambda line: line.split(",")).map(lambda line: tuple((feature for feature in line)))
# Split the data into training and test sets (30% held out for testing)
print("Creating Training and Test Data Split")
(trainingData, testData) = labled_point_data.randomSplit([0.7, 0.3])
# Train a RandomForest model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo={},
numTrees=5, featureSubsetStrategy="auto",
impurity='variance', maxDepth=8, maxBins=32)
# # Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(testData.count())
print('Test Mean Squared Error = ' + str(testMSE))
testAccuracy = labelsAndPredictions.map(lambda (v, p): 1 if (abs(v - p) < 10) else 0).sum() / float(testData.count())
print('Total Accuracy = ' + str(testAccuracy))
# print('Learned regression forest model:')
# print(model.toDebugString())
# # Save and load model
def test_classification(self):
from pyspark.mllib.classification import LogisticRegressionWithSGD, SVMWithSGD, NaiveBayes
from pyspark.mllib.tree import DecisionTree, DecisionTreeModel, RandomForest,\
RandomForestModel, GradientBoostedTrees, GradientBoostedTreesModel
data = [
LabeledPoint(0.0, [1, 0, 0]),
LabeledPoint(1.0, [0, 1, 1]),
LabeledPoint(0.0, [2, 0, 0]),
LabeledPoint(1.0, [0, 2, 1])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
temp_dir = tempfile.mkdtemp()
lr_model = LogisticRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
svm_model = SVMWithSGD.train(rdd, iterations=10)
self.assertTrue(svm_model.predict(features[0]) <= 0)
self.assertTrue(svm_model.predict(features[1]) > 0)
self.assertTrue(svm_model.predict(features[2]) <= 0)
self.assertTrue(svm_model.predict(features[3]) > 0)
nb_model = NaiveBayes.train(rdd)
self.assertTrue(nb_model.predict(features[0]) <= 0)
self.assertTrue(nb_model.predict(features[1]) > 0)
self.assertTrue(nb_model.predict(features[2]) <= 0)
self.assertTrue(nb_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 3} # feature 0 has 3 categories
dt_model = DecisionTree.trainClassifier(
rdd,
numClasses=2,
categoricalFeaturesInfo=categoricalFeaturesInfo,
maxBins=4)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
dt_model_dir = os.path.join(temp_dir, "dt")
dt_model.save(self.sc, dt_model_dir)
same_dt_model = DecisionTreeModel.load(self.sc, dt_model_dir)
self.assertEqual(same_dt_model.toDebugString(),
dt_model.toDebugString())
rf_model = RandomForest.trainClassifier(
rdd,
numClasses=2,
categoricalFeaturesInfo=categoricalFeaturesInfo,
numTrees=10,
maxBins=4,
seed=1)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
rf_model_dir = os.path.join(temp_dir, "rf")
rf_model.save(self.sc, rf_model_dir)
same_rf_model = RandomForestModel.load(self.sc, rf_model_dir)
self.assertEqual(same_rf_model.toDebugString(),
rf_model.toDebugString())
gbt_model = GradientBoostedTrees.trainClassifier(
rdd,
categoricalFeaturesInfo=categoricalFeaturesInfo,
numIterations=4)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
gbt_model_dir = os.path.join(temp_dir, "gbt")
gbt_model.save(self.sc, gbt_model_dir)
same_gbt_model = GradientBoostedTreesModel.load(self.sc, gbt_model_dir)
self.assertEqual(same_gbt_model.toDebugString(),
gbt_model.toDebugString())
try:
os.removedirs(temp_dir)
except OSError:
pass
test_lp_arr = []
sample_data = all_data[train_indexes]
test_data = all_data[test_indexes]
for survived, record in sample_data:
lp = LabeledPoint(survived, tuple(record))
lparr.append(lp)
for survived, record in test_data:
lp = LabeledPoint(survived, tuple(record))
test_lp_arr.append(lp)
training_data = sc.parallelize(lparr).cache()
test_data_rdd = sc.parallelize(test_lp_arr).cache()
classificationModel = RandomForest.trainClassifier(training_data, numClasses=2, categoricalFeaturesInfo={},
numTrees=3)
result = classificationModel.predict(test_data_rdd.map(lambda x: x.features))
print classificationModel
print classificationModel.toDebugString()
print "==============================="
predicted_data = result.collect()
actual_data = test_data_rdd.map(lambda x: float(x.label)).collect()
print mean_absolute_error(actual_data, predicted_data)
print accuracy_score(actual_data,predicted_data)
print(classificationModel)
#for p in predicted_data:
# print p
break
def test_regression(self):
from pyspark.mllib.regression import LinearRegressionWithSGD, LassoWithSGD, \
RidgeRegressionWithSGD
from pyspark.mllib.tree import DecisionTree, RandomForest, GradientBoostedTrees
data = [
LabeledPoint(-1.0, [0, -1]),
LabeledPoint(1.0, [0, 1]),
LabeledPoint(-1.0, [0, -2]),
LabeledPoint(1.0, [0, 2])
]
rdd = self.sc.parallelize(data)
features = [p.features.tolist() for p in data]
lr_model = LinearRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(lr_model.predict(features[0]) <= 0)
self.assertTrue(lr_model.predict(features[1]) > 0)
self.assertTrue(lr_model.predict(features[2]) <= 0)
self.assertTrue(lr_model.predict(features[3]) > 0)
lasso_model = LassoWithSGD.train(rdd, iterations=10)
self.assertTrue(lasso_model.predict(features[0]) <= 0)
self.assertTrue(lasso_model.predict(features[1]) > 0)
self.assertTrue(lasso_model.predict(features[2]) <= 0)
self.assertTrue(lasso_model.predict(features[3]) > 0)
rr_model = RidgeRegressionWithSGD.train(rdd, iterations=10)
self.assertTrue(rr_model.predict(features[0]) <= 0)
self.assertTrue(rr_model.predict(features[1]) > 0)
self.assertTrue(rr_model.predict(features[2]) <= 0)
self.assertTrue(rr_model.predict(features[3]) > 0)
categoricalFeaturesInfo = {0: 2} # feature 0 has 2 categories
dt_model = DecisionTree.trainRegressor(
rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, maxBins=4)
self.assertTrue(dt_model.predict(features[0]) <= 0)
self.assertTrue(dt_model.predict(features[1]) > 0)
self.assertTrue(dt_model.predict(features[2]) <= 0)
self.assertTrue(dt_model.predict(features[3]) > 0)
rf_model = RandomForest.trainRegressor(
rdd,
categoricalFeaturesInfo=categoricalFeaturesInfo,
numTrees=10,
maxBins=4,
seed=1)
self.assertTrue(rf_model.predict(features[0]) <= 0)
self.assertTrue(rf_model.predict(features[1]) > 0)
self.assertTrue(rf_model.predict(features[2]) <= 0)
self.assertTrue(rf_model.predict(features[3]) > 0)
gbt_model = GradientBoostedTrees.trainRegressor(
rdd,
categoricalFeaturesInfo=categoricalFeaturesInfo,
numIterations=4)
self.assertTrue(gbt_model.predict(features[0]) <= 0)
self.assertTrue(gbt_model.predict(features[1]) > 0)
self.assertTrue(gbt_model.predict(features[2]) <= 0)
self.assertTrue(gbt_model.predict(features[3]) > 0)
try:
LinearRegressionWithSGD.train(rdd,
initialWeights=array([1.0, 1.0]),
iterations=10)
LassoWithSGD.train(rdd,
initialWeights=array([1.0, 1.0]),
iterations=10)
RidgeRegressionWithSGD.train(rdd,
initialWeights=array([1.0, 1.0]),
iterations=10)
except ValueError:
self.fail()
def train(self, trainingData):
self.model = RandomForest.trainClassifier(trainingData, numClasses=2, categoricalFeaturesInfo={},
numTrees=10, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
from pyspark.ml.classification import RandomForestClassifier
from pyspark.mllib.tree import RandomForestModel
from pyspark.mllib.evaluation import MulticlassMetrics
from prettytable import PrettyTable
sc = SparkContext()
spark = SparkSession(sc)
inputDF = spark.read.csv('TrainingDataset.csv',
header='true', inferSchema='true', sep=';')
featureColumns = [c for c in inputDF.columns if c != 'quality']
transformed_df = inputDF.rdd.map(
lambda row: LabeledPoint(row[-1], Vectors.dense(row[0:-1])))
model = RandomForest.trainClassifier(transformed_df, numClasses=10, categoricalFeaturesInfo={
}, numTrees=50, maxBins=64, maxDepth=20, seed=33)
# model.save(sc,"s3://wineprediction/model_created.model")
validDF = spark.read.csv(
'/testdata/*.csv', header='true', inferSchema='true', sep=';')
datadf = validDF.rdd.map(lambda row: LabeledPoint(
row[-1], Vectors.dense(row[0:-1])))
predictions = model.predict(datadf.map(lambda x: x.features))
labels_and_predictions = datadf.map(lambda x: x.label).zip(predictions)
acc = labels_and_predictions.filter(
lambda x: x[0] == x[1]).count() / float(datadf.count())
def main():
options = parse_args()
sc = SparkContext(appName="PythonRandomForestClassificationExample")
pm.init(sc)
# $example on$
# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLibSVMFile(sc, options.data_file)
# 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.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# Note: Use larger numTrees in practice.
# Setting featureSubsetStrategy="auto" lets the algorithm choose.
model = RandomForest.trainClassifier(trainingData,
numClasses=options.num_classes,
categoricalFeaturesInfo={},
numTrees=options.num_trees,
featureSubsetStrategy="auto",
impurity='gini',
maxDepth=options.max_depth,
maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(
lambda lp: lp[0] != lp[1]).count() / float(testData.count())
print('Test Error = ' + str(testErr))
print('Learned classification forest model:')
print(model.toDebugString())
print("Using mlops to report statistics")
# Adding multiple points (to see a graph in the ui)
pm.set_stat("numTrees", options.num_trees, st.TIME_SERIES)
pm.set_stat("numClasses", options.num_classes, st.TIME_SERIES)
pm.set_stat("maxDepth", options.max_depth, st.TIME_SERIES)
pm.set_stat("testError", testErr, st.TIME_SERIES)
# TODO: this should be removed once we have better tests for mlops
pm.set_stat("stat1", 1.0, st.TIME_SERIES)
pm.set_stat("stat1", 2.0, st.TIME_SERIES)
pm.set_stat("stat1", 3.0, st.TIME_SERIES)
pm.set_stat("stat1", 4.0, st.TIME_SERIES)
pm.set_stat("stat1", 5.0, st.TIME_SERIES)
pm.set_stat("stat1", 6.0, st.TIME_SERIES)
pm.set_stat("stat1", 7.0, st.TIME_SERIES)
pm.set_stat("stat1", 8.0, st.TIME_SERIES)
# String
pm.set_stat("stat2", "str-value", st.TIME_SERIES)
# Vec
pm.set_stat("statvec", [4.5, 5.5, 6.6], st.TIME_SERIES)
list_of_strings = []
for x in range(1, 10000):
list_of_strings.append("{},{},{}".format(x, x + 1, x + 2))
rdd_of_str = sc.parallelize(list_of_strings)
rdd = rdd_of_str.map(lambda line: Vectors.dense(line.split(",")))
# Histograms and any input stats
pm.set_stat("input", rdd, st.INPUT)
print("Done reporting statistics")
# Save and load model
model.save(sc, options.output_model)
print("Done saving model to {}".format(options.output_model))
sameModel = RandomForestModel.load(sc, options.output_model)
# $example off$
sc.stop()
pm.done()
test_lp_arr = []
sample_data = all_data[train_indexes]
test_data = all_data[test_indexes]
for survived, record in sample_data:
lp = LabeledPoint(survived, tuple(record))
lparr.append(lp)
for survived, record in test_data:
lp = LabeledPoint(survived, tuple(record))
test_lp_arr.append(lp)
training_data = sc.parallelize(lparr).cache()
test_data_rdd = sc.parallelize(test_lp_arr).cache()
classificationModel = RandomForest.trainClassifier(
training_data, numClasses=2, categoricalFeaturesInfo={}, numTrees=3)
result = classificationModel.predict(
test_data_rdd.map(lambda x: x.features))
print classificationModel
print classificationModel.toDebugString()
print "==============================="
predicted_data = result.collect()
actual_data = test_data_rdd.map(lambda x: float(x.label)).collect()
print mean_absolute_error(actual_data, predicted_data)
print accuracy_score(actual_data, predicted_data)
print(classificationModel)
#for p in predicted_data:
# print p
break
# categorical = range(0,30) + range(35,39) + range(41,46) + range(48,57)
# data.cache()
# mappings = [get_mapping(data, i) for i in categorical]
labelpoints = data.map(lambda x: LabeledPoint(x[-1], x[:-1]))
return labelpoints
data = label_points(data_raw)
training, testing = data.randomSplit([0.5, 0.5], 0)
model = RandomForest.trainClassifier(training, numClasses=7, categoricalFeaturesInfo={},
numTrees=1000, featureSubsetStrategy="auto",
impurity='gini', maxBins=32)
predictions = model.predict(testing.map(lambda x: x.features))
labelsAndPredictions = testing.map(lambda lp: lp.label).zip(predictions)
accuracy = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(testing.count())
print accuracy
#
# # https://books.google.com/books?id=syPHBgAAQBAJ&pg=PA166&lpg=PA166&dq=categorical+variables+labeledpoint+pyspark&source=bl&ots=X9VyTR348v&sig=cMf8rZlpbdWcyCl2jSPNU1Var6k&hl=en&sa=X&ved=0ahUKEwjPpofhh8XMAhVI1WMKHXoqCio4ChDoAQgbMAA#v=onepage&q=categorical%20variables%20labeledpoint%20pyspark&f=false
# # Page 166
# def get_mapping(rdd, idx):
# return rdd.map(lambda fields: fields[idx]).distinct().zipWithIndex().collectAsMap()
#
# # cat_len = sum(map(len, mappings))
testFinal.count()
testFinal.collect()
#For Getting the threshold limit, Using Train dataset
(training1, training2) = trainFinal.randomSplit([0.7, 0.3])
training1.collect()
model_1 = RandomForest.trainRegressor(training1, categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto",
impurity='variance', maxDepth=4, maxBins=32)
model_2 = GradientBoostedTrees.trainRegressor(training1,
categoricalFeaturesInfo={}, numIterations=3)
model_3 = DecisionTree.trainRegressor(training1, categoricalFeaturesInfo={},
impurity='variance', maxDepth=5, maxBins=32)
predictionsRFTrain = model_1.predict(training1.map(lambda x: x.features))
predictionsGBTTrain = model_2.predict(training1.map(lambda x: x.features))
predictionsDTTrain = model_3.predict(training1.map(lambda x: x.features))
predictionsRFTrain.collect()
predictionsGBTTrain.collect()
numFeatures = parsed_data.map(lambda x:-1 if x[1].size==0 else x[1][-1]).reduce(max)+1
labeled_data = parsed_data.map(lambda x: LabeledPoint(x[0], Vectors.sparse(numFeatures, x[1],x[2])))
unbalance_test = data_ans_0827.map(feature_char_to_num).cache()
l_unbal_te = unbalance_test.map(lambda x: LabeledPoint(x[0], Vectors.sparse(numFeatures, x[1], x[2])))
#splite data to trainData and testData
(trianData, testData) = labeled_data.randomSplit([0.9, 0.1])
len_list = [len(i) for i in fe]
col_na_l = [i-1 for i in col_na] #because slice out the first data in vector [1:-2]
col_na_l = [i-1 for i in col_na_l if i >= 83] #for drop out the 85th col
features_dict = dict(zip(col_na_l, len_list)) #feature dict eg. {1:3, 5:8}
model = RandomForest.trainClassifier(trianData, numClasses=2, categoricalFeaturesInfo={},
numTrees=50, featureSubsetStrategy="auto",
impurity='gini', maxDepth=5, maxBins=32)
# Evaluate model on test instances and compute test error
predictions = model.predict(l_unbal_te.map(lambda x: x.features))
labelsAndPredictions = l_unbal_te.map(lambda lp: lp.label).zip(predictions)
testErr = labelsAndPredictions.filter(lambda (v, p): v != p).count() / float(l_unbal_te.count())
print('Test Error = ' + str(testErr) +"$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$")
true_positive = labelsAndPredictions.filter(lambda (v,p):v==p and p==1).count()/float(labelsAndPredictions.filter(lambda (v,p):v==1).count())
print "true_positive", true_positive, "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%"
f_true = labelsAndPredictions.filter(lambda (v,p):v==p and v==1).count()/float(labelsAndPredictions.filter(lambda (v,p):p==1).count())
print "precision=TP/(TP+Fp)", f_true, "&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&"
print "1/0",labelsAndPredictions.filter(lambda (v,p):v==1).count()/float(labelsAndPredictions.filter(lambda (v,p):v==0).count()), "##############################################################################################"
#print "False", labeled_data.filter(lambda p:p.label==0).count(), "@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@2"
#print "Positive", labeled_data.filter(lambda p:p.label==1).count(),"!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
split = Tokenizer(inputCol="text", outputCol="words")
wordsData = split.transform(train_hive_info)
my_print('分词完成.......')
# 增加TF特征列
hashingTF = HashingTF(inputCol="words",
outputCol="rawFeatures",
numFeatures=2**10)
TF_data = hashingTF.transform(wordsData)
my_print('TF特征构造完成.......')
# 增加IDF特征列
idf = IDF(inputCol="rawFeatures", outputCol="features").fit(TF_data)
final_input_data = idf.transform(TF_data)
my_print('IDF特征构造完成.......')
train_rdd = final_input_data.select("label", "features") \
.rdd.map(lambda (label, features): (LabeledPoint(label, features.toArray())))
if model_name == 'LogisticRegression':
model = LogisticRegressionWithLBFGS.train(train_rdd, numClasses=10)
model.save(sc, model_path)
elif model_name == 'NaiveBayes':
model = NaiveBayes.train(train_rdd)
model.save(sc, model_path)
else:
model = RandomForest.trainClassifier(train_rdd, 10, {}, 10, seed=42)
model.save(sc, model_path)
my_print('模型训练完成.......')
