def cross_validation_lr(Data_1,Data_2,Data_3,regType, num_iter):
# Training the model using Logistic Regression Classifier
model_train_1 =LogisticRegressionWithLBFGS.train(Data_1.union(Data_2),
regType =regType, iterations=num_iter, numClasses=5)
# Evaluate model on test instances and compute test error
predictions_1 = model_train_1.predict(Data_3.map(lambda x: x.features))
labelsAndPredictions_1 = Data_3.map(lambda lp: lp.label).zip(predictions_1)
testMSE_1 = labelsAndPredictions_1.map(lambda (v, p): (v +0.5 - p) * (v +0.5- p )).sum() /\
float(Data_3.count())
model_train_2 =LogisticRegressionWithLBFGS.train(Data_2.union(Data_3),
regType =regType, iterations=num_iter, numClasses=5)
# Evaluate model on test instances and compute test error
predictions_2 = model_train_2.predict(Data_1.map(lambda x: x.features))
labelsAndPredictions_2 = Data_1.map(lambda lp: lp.label).zip(predictions_2)
testMSE_2 = labelsAndPredictions_2.map(lambda (v, p): (v +0.5- p) * (v +0.5- p )).sum() /\
float(Data_1.count())
model_train_3 =LogisticRegressionWithLBFGS.train(Data_3.union(Data_1),
regType =regType, iterations=num_iter, numClasses=5)
# Evaluate model on test instances and compute test error
predictions_3 = model_train_3.predict(Data_2.map(lambda x: x.features))
labelsAndPredictions_3 = Data_2.map(lambda lp: lp.label).zip(predictions_3)
testMSE_3 = labelsAndPredictions_3.map(lambda (v, p): (v +0.5- p ) * (v +0.5- p)).sum() /\
float(Data_2.count())
return (testMSE_1+testMSE_2+testMSE_3)/3
def training(model_directory, libsvm, scaler):
sc = SparkContext(appName="PythonLinearRegressionWithSGDExample")
training_rdd = MLUtils.loadLibSVMFile(sc, libsvm)
training_rdd.cache()
if scaler == '1':
label = training_rdd.map(lambda x: x.label)
features = training_rdd.map(lambda x: x.features)
scaler1 = StandardScaler().fit(features)
data1 = label.zip(scaler1.transform(features))
# convert into labeled point
data2 = data1.map(lambda x: LabeledPoint(x[0], x[1]))
model_logistic = LogisticRegressionWithLBFGS.train(data2)
else:
model_logistic = LogisticRegressionWithLBFGS.train(training_rdd)
model_logistic.save(sc, model_directory)
def train(self, df, target, regularization=None, num_of_iterations=100):
try:
LOGGER.info("Generation logistic regression")
spark_df = self.sql_context.createDataFrame(df)
feature_columns = spark_df.columns
feature_columns.remove(target)
X_train = spark_df.select(*feature_columns).map(lambda x: list(x))
y_train = spark_df.select(target).map(lambda x: x[0])
zipped = y_train.zip(X_train)
train_data = zipped.map(lambda x: LabeledPoint(x[0], x[1]))
numOfClasses = len(df[target].unique())
logistic_model = LogisticRegressionWithLBFGS.train(
train_data,
numClasses=numOfClasses,
regParam=0,
regType=regularization,
intercept=True,
iterations=num_of_iterations,
validateData=False)
self.model = logistic_model
except Exception as e:
raise e
def lrTest(sqlContext,dataset_rdd,positive_negotive_rate): 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 = LogisticRegressionWithLBFGS.train(trainset,iterations = 100) predict = testset.map(lambda p:(p.label,model.predict(p.features))) 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 seg_model_lr(train_data, test_data, regType, num_iter):
removelist_train= set(['stars', 'business_id', 'bus_id', 'b_id','review_id', 'user_id'])
newlist_train = [v for i, v in enumerate(train_data.columns) if v not in removelist_train]
# Putting data in vector assembler form
assembler_train = VectorAssembler(inputCols=newlist_train, outputCol="features")
transformed_train = assembler_train.transform(train_data.fillna(0))
# Creating input dataset in the form of labeled point for training the model
data_train= (transformed_train.select("features", "stars")).map(lambda row: LabeledPoint(row.stars, row.features))
# Training the model using Logistic regression Classifier
model_train = LogisticRegressionWithLBFGS.train(sc.parallelize(data_train.collect(),5),
regType =regType, iterations=num_iter, numClasses=5)
# Creating a list of features to be used for predictions
removelist_final = set(['business_id', 'bus_id', 'b_id','review_id', 'user_id'])
newlist_final = [v for i, v in enumerate(test_data.columns) if v not in removelist_final]
# Putting data in vector assembler form
assembler_final = VectorAssembler(inputCols=newlist_final,outputCol="features")
transformed_final= assembler_final.transform(test_data.fillna(0))
# Creating input dataset to be used for predictions
data_final = transformed_final.select("features", "review_id")
# Predicting ratings using the developed model
predictions = model_train.predict(data_final.map(lambda x: x.features))
labelsAndPredictions = data_final.map(lambda data_final: data_final.review_id).zip(predictions)
return labelsAndPredictions
def main():
training_rdd = sc.textFile(train_inputs).map(to_LP_training).filter(lambda lp: lp!=None)
testing_rdd = sc.textFile(test_inputs).map(to_LP_testing).filter(lambda lp: lp!=None)
# # Logistic Regression with SGD
# lg_model = LogisticRegressionWithSGD.train(training_rdd, step = 0.1, regType = 'l1')
# lg_prediction = testing_rdd.map(lambda (qt, sv): (qt, lg_model.predict(sv)))
#
#
# Logistic Regression with LBFGS
lg_model2 = LogisticRegressionWithLBFGS.train(training_rdd)
lg_prediction2 = testing_rdd.map(lambda (qt, sv): (qt, lg_model2.predict(sv)))
#
#
# # SVM with SGD
# svm_model = SVMWithSGD.train(training_rdd, step = 0.01)
# svm_prediction = testing_rdd.map(lambda (qt, sv): (qt, svm_model.predict(sv)))
# print 'Logistic Regression with SGD results: ', len(lg_prediction.filter(lambda (idx, p):p!=0).collect())
result = lg_prediction2.collect()
# print 'SVM with SGD', len(svm_prediction.filter(lambda (idx, p):p!=0).collect())
with open('[your result.csv path]', 'w') as csvfile:
fieldnames = ['QuoteNumber', 'QuoteConversion_Flag']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for l in result:
writer.writerow({'QuoteNumber': l[0], 'QuoteConversion_Flag': l[1]})
def test_train(self, df, target, train_split, test_split, regularization=None, num_of_iterations=100):
try:
LOGGER.info("Generation logistic regression")
spark_df = self.sql_context.createDataFrame(df)
feature_columns = spark_df.columns
feature_columns.remove(target)
train, test = spark_df.randomSplit([train_split, test_split], seed=1000000)
X_train = train.select(*feature_columns).map(lambda x: list(x))
y_train = train.select(target).map(lambda x: x[0])
zipped = y_train.zip(X_train)
train_data = zipped.map(lambda x: LabeledPoint(x[0], x[1]))
numOfClasses = len(df[target].unique())
logistic_model = LogisticRegressionWithLBFGS.train(train_data,
numClasses=numOfClasses, regParam=0,
regType=regularization, intercept=True,
iterations=num_of_iterations, validateData=False)
X_test = test.select(*feature_columns).map(lambda x: list(x))
y_test = test.select(target).map(lambda x: x[0])
prediction = X_test.map(lambda lp: (float(logistic_model.predict(lp))))
prediction_and_label = prediction.zip(y_test)
LOGGER.info(prediction_and_label.map(lambda labelAndPred: labelAndPred[0] == labelAndPred[1]).mean())
except Exception as e:
raise e
def logistic_regression(sc, in1, **params):
temp = in1.map(lambda x: LabeledPoint(
x[int(params['label'])], x[:int(params['label'])] + x[int(params[
'label']) + 1:]))
temp = LogisticRegressionWithLBFGS.train(
temp,
iterations=int(params['iterations']),
numClasses=int(params['numClasses']))
return True, temp
def train(self, input_data, parameters):
iterations = parameters.get('iterations', None)
weights = parameters.get('weights', None)
intercept = parameters.get('intercept', None)
numFeatures = parameters.get('numFeatures', None)
numClasses = parameters.get('numClasses', None)
data = self._sc.parallelize(self._parser.parse(input_data))
self._model = LogisticRegressionWithLBFGS.train(data,\
iterations=iterations,\
numClasses=numClasses)
def RunLogit(tf): rdd = tf.map(parseAsLabeledPoints) train, test = rdd.randomSplit([.8, .2]) numCat = len(genCats) model = LogisticRegressionWithLBFGS.train(train, numClasses=numCat, iterations=100) predictionAndLabel = test.map(lambda p: (model.predict(p.features), p.label)) accuracy = 1.0 * predictionAndLabel.filter(lambda (x, v): x == v).count() / test.count() print 'Accuracy of Logit = ', accuracy * 100 print "Test Error = ", (1.0 - accuracy) * 100
def get_error(training, test):
model = LogisticRegressionWithLBFGS.train(training, numClasses=18)
# Evaluating the model on training data
labelsAndPreds = test.map(lambda p: (p.label, model.predict(p.features)))
ERR = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(
test.count())
print("Training Error = " + str(ERR))
return ERR
def main():
conf = SparkConf().setMaster("local").setAppName("Assignment 1")
sc = SparkContext(conf=conf)
sqlContext = SQLContext(sc)
sc.setLogLevel("ERROR")
#part 1
data = sc.textFile('/home/disha/Downloads/MSD.txt', 2)
dc = data.count()
#print data.count()
#print data.take(40)
sdata = data.take(40)
#part 2
lp = [parse_line(p) for p in sdata]
#part 3
x1 = list(lp[i].features[3] for i in range(40))
x2 = list(lp[i].features[4] for i in range(40))
dataFrame = sqlContext.createDataFrame([(Vectors.dense(x1), ),
(Vectors.dense(x2), )],
["features"])
scaler = MinMaxScaler(inputCol="features", outputCol="scaledFeatures")
scalerModel = scaler.fit(dataFrame)
scaledData = scalerModel.transform(dataFrame)
x = scaledData.select("scaledFeatures").map(list).collect()
xdf = pd.DataFrame({'1': x[0][0], '2': x[1][0]})
'''
fig, ax = plt.subplots()
heatmap = ax.pcolor(xdf, cmap=plt.cm.Greys, alpha=0.8)
fig = plt.gcf()
fig.set_size_inches(8, 11)
ax.set_frame_on(False)
ax.invert_yaxis()
ax.xaxis.tick_top()'''
#plt.show()
#part 4
onlyLabels = data.map(parse_line).map(
lambda point: int(point.label)).collect()
minYear = min(onlyLabels)
maxYear = max(onlyLabels)
print maxYear, minYear
lp_rdd = data.map(parse_line).map(
lambda l: LabeledPoint(int(l.label) - minYear, l.features))
#print lp_rdd.take(10)
#part 5
train, test = lp_rdd.randomSplit([0.8, 0.2])
model = LogisticRegressionWithLBFGS.train(train,
iterations=10,
numClasses=maxYear - minYear + 1)
vp = test.map(lambda p: (model.predict(p.features), p.label))
rmse = getrmse(vp)
print rmse
a1 = test.map(lambda p: model.predict(p.features)).collect()
a2 = test.map(lambda p: int(p.label)).collect()
plt.scatter(a1, a2)
plt.show()
def train_model(training_rdd, **kwargs):
"""
Train a classifier model using an rdd training dataset
:param training_rdd: the rdd of the training dataset
:param kwargs: additional key-value params for the training (if any)
:return:
"""
return LogisticRegressionWithLBFGS.train(training_rdd,
regType=_REGULARIZATION,
intercept=_INTERCEPT,
**kwargs)
def train_model(training_rdd, **kwargs):
"""
Train a classifier model using an rdd training dataset
:param training_rdd: the rdd of the training dataset
:param kwargs: additional key-value params for the training (if any)
:return:
"""
return LogisticRegressionWithLBFGS.train(training_rdd,
regType=_REGULARIZATION,
intercept=_INTERCEPT,
**kwargs)
def regression(reg_data):
(trainingData, testData) = reg_data.randomSplit([0.7, 0.3])
lrmodel = LogisticRegressionWithLBFGS.train(trainingData)
labelsAndPreds = testData.map(lambda p: (p.label, lrmodel.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(testData.count())
falsePos = labelsAndPreds.filter(lambda (v, p): v != p and v == 0.0).count() / float(testData.filter(lambda lp: lp.label == 0.0).count())
falseNeg = labelsAndPreds.filter(lambda (v, p): v != p and v == 1.0).count() / float(testData.filter(lambda lp: lp.label == 1.0).count())
print "*** Error Rate: %f ***" % trainErr
print "*** False Positive Rate: %f ***" % falsePos
print "*** False Negative Rate: %f ***" % falseNeg
def __init__(self, sc):
"""Init the engine and train the model
"""
logger.info("Starting up the GeneLearn Engine: ")
self.sc = sc
logger.info("Loading training data...")
dataset_path = "/Users/qingpeng/Dropbox/Development/Bitbucket/jgi-genelearn/scripts/Flask"
training_file_path = os.path.join(dataset_path, 'training.svmlib')
training = MLUtils.loadLibSVMFile(sc, training_file_path)
self.model = LogisticRegressionWithLBFGS.train(training)
def TrainLRCModel(trainingData, testData): print(type(trainingData)) print(trainingData.take(2)) model = LogisticRegressionWithLBFGS.train(trainingData, numClasses=5) print(type(model)) exit(); predictions = testData.map(lambda p: (p.label, model.predict(p.features))) correct = predictions.filter(lambda (x, p): x == p) ### Calculate the accuracy of the model using custom method accuracy = round((correct.count() / float(testData.count())) * 100, 3) # return the final accuracy return accuracy
def sim_function(isim, patsim, dataset, ss_ori):
#select patients in each simulation from patsim
valsimid = patsim.filter(patsim.simid == isim)
sssim = ss_ori\
.join(valsimid,valsimid.matched_positive_id==ss_ori.matched_positive_id,'inner')\
.select(ss_ori.matched_positive_id, ss_ori.label, ss_ori.patid,ss_ori.features)
#select corresponding trainning and test set
valsim = dataset\
.join(valsimid, valsimid.matched_positive_id==dataset.matched_positive_id,
'inner')\
.select(dataset.matched_positive_id, dataset.label, dataset.patid,dataset.features)
trsim = dataset.subtract(valsim)
#get LabeledandPoint rdd data
trsimrdd = trsim.map(parsePoint)
valsimrdd = valsim.map(parsePoint)
sssimrdd = sssim.map(parsePoint)
# Build the model
sim_model = LogisticRegressionWithLBFGS.train(trsimrdd,
intercept=True,
regType=None)
#clear the threshold
sim_model.clearThreshold()
#output model
sim_model.save(sc, resultDir_s3 + "model_sim" + str(isim))
#load model
#model = LogisticRegressionModel.load(sc, resultDir_s3+"model_sim"+str(isim))
#predict on test data
scoreAndLabels_val = valsimrdd.map(
lambda p: (float(sim_model.predict(p.features)), p.label))
scoreAndLabels_ss = sssimrdd.map(
lambda p: (float(sim_model.predict(p.features)), p.label))
#Identify the probility of response
pred_score_val = scoreAndLabels_val.toDF()\
.withColumnRenamed('_1', 'prob_1')\
.withColumnRenamed('_2', 'label')
pred_score_ss = scoreAndLabels_ss.toDF()\
.withColumnRenamed('_1', 'prob_1')\
.withColumnRenamed('_2', 'label')
return [pred_score_val, pred_score_ss]
def validation_lr(trainingData,testData, regType, num_iter):
# Training the model using Logistic Regression Classifier
model_train =LogisticRegressionWithLBFGS.train(trainingData, regType =regType, iterations=num_iter, numClasses=5)
# Evaluate model on test instances and compute test error
predictions = model_train.predict(testData.map(lambda x: x.features))
testMSE_1 = labelsAndPredictions_1.map(lambda (v, p): (v - p) * (v - p)).sum() /\
float(testData.count())
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(predictions)
testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() /\
float(testData.count())
return testMSE_1,testMSE
def main(input_file_path):
print('=====>>>>>')
print('ddd')
data = sc.textFile(input_file_path)
traning_data_RDD = data.filter(lambda line: line.split(',')[4] != '' and
line.split(',')[0] != 'INDEX')
unseen_data_RDD = data.filter(lambda line: line.split(',')[4] == '')
traning_data_pddf = create_pddf(traning_data_RDD)
traning_data_df = sqlContext.createDataFrame(traning_data_pddf)
print(traning_data_df.head())
parsed_data = rdd_to_labeled_point(traning_data_df.rdd)
parsed_data.persist()
# Correct print: [LabeledPoint(1.0, [1.0,8.6662186586,6.98047693487])]
logisticRegressionWithLBFGS = LogisticRegressionWithLBFGS.train(
parsed_data, iterations=500, numClasses=100)
labels_and_preds = parsed_data.map(
lambda lp:
[lp.label, logisticRegressionWithLBFGS.predict(lp.features)])
Accuracy = float(
labels_and_preds.filter(lambda ele: (int(ele[0]) - int(ele[1]))**2).
reduce(lambda x, y: x + y)[0]) / float(parsed_data.count())
print("Training Accuracy on training data = " + str(Accuracy))
unseen_data_pddf = create_pddf(unseen_data_RDD)
unseen_data_df = sqlContext.createDataFrame(unseen_data_pddf)
unseen_parsed_data = rdd_to_index_featurs(unseen_data_df.rdd)
unseen_parsed_data.persist()
file = open(
'/Users/1002720/Documents/workspace/SNU-project/data/BDA2Project/1-GenderPrediction/result2.csv',
'w',
encoding='utf-8')
file.write('INDEX,AGE\n')
for data in unseen_parsed_data.collect():
file.write(
str(data[0]) + ',' +
str(logisticRegressionWithLBFGS.predict(data[1])) + '\n')
# print(labels_and_preds.collect())
parsed_data.unpersist()
unseen_parsed_data.unpersist()
print('=====>>>>>')
print('=====>>>>>')
print('=====>>>>>')
print('=====>>>>>')
def train_evaluate_model(train_data, valid_data, iterations, regParam):
start_time = time()
# 训练
model = LogisticRegressionWithLBFGS.train(train_data,
numClasses=2,
iterations=iterations,
regParam=regParam)
# 评估
# y_pred y_true
AUC = evaluate_model(model, valid_data)
duration = time() - start_time
print(
f"训练评估：使用参数 iterations={iterations}, regParam={regParam} ==>所需时间={duration} 结果AUC = {AUC}"
)
return AUC, duration, iterations, regParam, model
def regression(reg_data):
train_data, test_data = reg_data.randomSplit([0.7, 0.3])
model = LogisticRegressionWithLBFGS.train(train_data)
labels_predictions = test_data.map(lambda p: (p.label, model.predict(p.features)))
train_error = labels_predictions.filter(lambda (v, p): v != p).count() / float(test_data.count())
false_pos = labels_predictions.filter(lambda (v, p): v != p and v == 0.0).count() / float(
test_data.filter(lambda lp: lp.label == 0.0).count())
false_neg = labels_predictions.filter(lambda (v, p): v != p and v == 1.0).count() / float(
test_data.filter(lambda lp: lp.label == 1.0).count())
print "*** Error Rate: %f ***" % train_error
print "*** False Positive Rate: %f ***" % false_pos
print "*** False Negative Rate: %f ***" % false_neg
def main():
#parameters
num_features = 400 #vocabulary size
#load data
print "loading 20 newsgroups dataset..."
categories = [
'rec.autos', 'rec.sport.hockey', 'comp.graphics', 'sci.space'
]
tic = time()
dataset = fetch_20newsgroups(shuffle=True,
random_state=0,
categories=categories,
remove=('headers', 'footers', 'quotes'))
train_corpus = dataset.data # a list of 11314 documents / entries
train_labels = dataset.target
toc = time()
print "elapsed time: %.4f sec" % (toc - tic)
#tf-idf vectorizer
tfidf = TfidfVectorizer(max_df=0.5, max_features=num_features, \
min_df=2, stop_words='english', use_idf=True)
X_tfidf = tfidf.fit_transform(train_corpus).toarray()
#append document labels
train_labels = train_labels.reshape(-1, 1)
X_all = np.hstack([train_labels, X_tfidf])
#distribute the data
sc = SparkContext('local', 'log_reg')
rdd = sc.parallelize(X_all)
labeled_corpus = rdd.map(parse_doc)
train_RDD, test_RDD = labeled_corpus.randomSplit([8, 2], seed=0)
#distributed logistic regression
print "training logistic regression..."
model = LogisticRegressionWithLBFGS.train(train_RDD,
regParam=1,
regType='l1',
numClasses=len(categories))
#evaluated the model on test data
labels_and_preds = test_RDD.map(lambda p:
(p.label, model.predict(p.features)))
test_err = labels_and_preds.filter(lambda (v, p): v != p).count() / float(
test_RDD.count())
print "log-reg test error: ", test_err
def training(path): #import dataset into RDD raw_data = sc.textFile(path) #parse raw data into label bag-of-words pairs parsed_data = raw_data.map(lambda line: parse_line(line)) #separate into training set and test set training_set, test_set = parsed_data.randomSplit([0.6, 0.4], 17) #get features for model training features = feature_extraction(training_set) labeled_points_training = training_set.map(lambda line: construct_labeled_point(line, features)) labeled_points_test = test_set.map(lambda line: construct_labeled_point(line, features)) #train logistic regression model lrModel = LogisticRegressionWithLBFGS.train(labeled_points_training) #train naive bayes model nbModel = NaiveBayes.train(labeled_points_training) return lrModel, nbModel, labeled_points_test
def regression(reg_data):
(trainingData, testData) = reg_data.randomSplit([0.7, 0.3])
lrmodel = LogisticRegressionWithLBFGS.train(trainingData)
labelsAndPreds = testData.map(lambda p:
(p.label, lrmodel.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda v, p: v != p).count() / float(
testData.count())
falsePos = labelsAndPreds.filter(lambda v, p: v != p and v == 0.0).count(
) / float(testData.filter(lambda lp: lp.label == 0.0).count())
falseNeg = labelsAndPreds.filter(lambda v, p: v != p and v == 1.0).count(
) / float(testData.filter(lambda lp: lp.label == 1.0).count())
print("*** Error Rate: %f ***" % trainErr)
print("*** False Positive Rate: %f ***" % falsePos)
print("*** False Negative Rate: %f ***" % falseNeg)
def trainModel(lpRDD):
""" Train 3 classifier models on the given RDD with LabeledPoint objects. A list of trained model is returned. """
lpRDD.persist(
StorageLevel.MEMORY_ONLY
) # not really needed as the Spark implementations ensure caching themselves. Other implementations might not, however.
# Train a classifier model.
print('Starting to train the model') #give some immediate feedback
model1 = LogisticRegressionWithLBFGS.train(lpRDD) # this is the best model
print('Trained LR (model1)')
#print(type(model1))
model2 = NaiveBayes.train(lpRDD) # doesn't work well
print('Trained NB (model2)')
print(type(model2))
model3 = SVMWithSGD.train(lpRDD) # or this ...
print('Trained SVM (model3)')
return [model1, model2, model3]
def main():
#spark = SparkSession.builder.master("yarn").appName("spark_demo").getOrCreate()
spark = SparkSession.builder.getOrCreate()
print "Session created!"
sc = spark.sparkContext
print "The url to track the job: http://namenode-01:8088/proxy/" + sc.applicationId
print sys.argv
sampleHDFS_1 = sys.argv[1]
sampleHDFS_2 = sys.argv[2]
outputHDFS = sys.argv[3]
sampleRDD = sc.textFile(sampleHDFS_1).map(parse)
predictRDD = sc.textFile(sampleHDFS_2).map(lambda x: parse(x, True))
# 训练
model = LogisticRegressionWithLBFGS.train(sampleRDD)
model.clearThreshold() #删除默认阈值（否则后面直接输出0、1）
# 预测，保存结果
labelsAndPreds = predictRDD.map(
lambda p: (p[0], p[1].label, model.predict(p[1].features)))
labelsAndPreds.map(lambda p: '\t'.join(map(str, p))).saveAsTextFile(
outputHDFS + "/target/output")
# 评估不同阈值下的准确率、召回率
labelsAndPreds_label_1 = labelsAndPreds.filter(lambda lp: int(lp[1]) == 1)
labelsAndPreds_label_0 = labelsAndPreds.filter(lambda lp: int(lp[1]) == 0)
t_cnt = labelsAndPreds_label_1.count()
f_cnt = labelsAndPreds_label_0.count()
print "thre\ttp\ttn\tfp\tfn\taccuracy\trecall"
for thre in [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]:
tp = labelsAndPreds_label_1.filter(lambda lp: lp[2] > thre).count()
tn = t_cnt - tp
fp = labelsAndPreds_label_0.filter(lambda lp: lp[2] > thre).count()
fn = f_cnt - fp
print("%.1f\t%d\t%d\t%d\t%d\t%.4f\t%.4f" %
(thre, tp, tn, fp, fn, float(tp) / (tp + fp), float(tp) /
(t_cnt)))
# 保存模型、加载模型
model.save(
sc, outputHDFS + "/target/tmp/pythonLogisticRegressionWithLBFGSModel")
sameModel = LogisticRegressionModel.load(
sc, outputHDFS + "/target/tmp/pythonLogisticRegressionWithLBFGSModel")
print "output:", outputHDFS
def create_or_load_model(sc: SparkContext,
train_dataset_path: str) -> LogisticRegressionModel:
if not os.path.exists(MODEL_PATH):
print('training model...')
dataset_rdd = sc.textFile(train_dataset_path)
table_rdd = dataset_rdd.map(lambda line: line.split(','))
labeled_features = rdd_to_feature(table_rdd)
# labeled_features.foreach(lambda lp: print(lp))
labeled_features.cache()
model = LogisticRegressionWithLBFGS.train(labeled_features,
numClasses=NUM_CLASSES)
model.setThreshold(0.5)
model.save(sc, MODEL_PATH)
return model
else:
model = LogisticRegressionModel.load(sc, MODEL_PATH)
return model
def logistic_model(sc):
# global conf
# conf.setAppName("data analyse")
# sc = SparkContext(conf=conf)
# print ("Successfully started SparkContext")
data = sc.textFile("file://" + ROOTDIR + "/sample_svm_data.txt")
parsedData = data.map(parsePoint)
# Build the model
model = LogisticRegressionWithLBFGS.train(parsedData)
# Evaluating the model on training data
labelsAndPreds = parsedData.map(lambda p:
(p.label, model.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(
parsedData.count())
print("Training Error = " + str(trainErr))
def test_train(self,
df,
target,
train_split,
test_split,
regularization=None,
num_of_iterations=100):
try:
LOGGER.info("Generation logistic regression")
spark_df = self.sql_context.createDataFrame(df)
feature_columns = spark_df.columns
feature_columns.remove(target)
train, test = spark_df.randomSplit([train_split, test_split],
seed=1000000)
X_train = train.select(*feature_columns).map(lambda x: list(x))
y_train = train.select(target).map(lambda x: x[0])
zipped = y_train.zip(X_train)
train_data = zipped.map(lambda x: LabeledPoint(x[0], x[1]))
numOfClasses = len(df[target].unique())
logistic_model = LogisticRegressionWithLBFGS.train(
train_data,
numClasses=numOfClasses,
regParam=0,
regType=regularization,
intercept=True,
iterations=num_of_iterations,
validateData=False)
X_test = test.select(*feature_columns).map(lambda x: list(x))
y_test = test.select(target).map(lambda x: x[0])
prediction = X_test.map(lambda lp:
(float(logistic_model.predict(lp))))
prediction_and_label = prediction.zip(y_test)
LOGGER.info(
prediction_and_label.map(lambda labelAndPred: labelAndPred[0]
== labelAndPred[1]).mean())
except Exception as e:
raise e
def Train_Model(trainingRDD, method, parameter_Iterations, parameter_stepSize,
parameter_reqParam):
# model load in.
if method == 'Logistic':
Logistic_Model = LogisticRegressionWithLBFGS.train(
trainingRDD,
iterations=parameter_Iterations,
regParam=parameter_reqParam)
return Logistic_Model
elif method == 'SVM':
SVM_Model = SVMWithSGD.train(trainingRDD,
iterations=parameter_Iterations,
step=parameter_stepSize,
regParam=parameter_reqParam)
return SVM_Model
else:
return "No this method."
def predictions(train_data_labeled,test_data_labeled):
time_start=time.time()
model_lrm = LogisticRegressionWithLBFGS.train(train_data_labeled,
iterations=100, initialWeights=None, regParam=0.01,
regType='l2', intercept=False, corrections=10, tolerance=0.0001,
validateData=True, numClasses=10)
predictions = model_lrm.predict(test_data_labeled.map(lambda x: x.features))
predict_label = test_data_labeled.map(lambda x: x.label).repartition(1).saveAsTextFile("hdfs://soit-hdp-pro-1.ucc.usyd.edu.au/user/czho9311/stage3")
labels_and_predictions = test_data_labeled.map(lambda x: x.label).zip(predictions)
lrAccuracy = labels_and_predictions.filter(lambda x: x[0] == x[1]).count() / float(test_data_labeled.count())
time_end=time.time()
time_lrm=(time_end - time_start)
print("=========================================================================================================")
print("run time: {},LogisticRegression accuracy: {}".format(time_lrm,lrAccuracy))
def fit_and_predict(rdd):
'''
Fits a logistic regression model.
Parameters
----------
rdd: A pyspark.rdd.RDD instance.
Returns
-------
An RDD of (label, prediction) pairs.
'''
#Creates logistical regression model with 10 iterations that predicts on entire data
model=LogisticRegressionWithLBFGS.train(rdd, iterations=10)
#makes RDD with label and predictions
rdd=rdd.map(lambda x: (x.label, float(model.predict(x.features))))
return rdd
def logisticRegression(features,sc,output_n): features_and_label = features.collect() training_features_labels = features_and_label[0:70] testing_features_labels = features_and_label[70:] labeled_training = [] labeled_testing = [] for x in training_features_labels: labeled_training.append(LabeledPoint(x[0],x[1])) for y in testing_features_labels: labeled_testing.append(LabeledPoint(y[0],y[1])) test = sc.parallelize(labeled_testing) logregression_model = LogisticRegressionWithLBFGS.train(labeled_training) predictions = test.map(lambda line: (line.label, float(logregression_model.predict(line.features)))) return predictions
def TrainLRCModel(trainingData, testData):
print(type(trainingData))
print(trainingData.take(2))
# Map the training and testing dataset into Labeled Point
trainingData = trainingData.map(lambda row:[LabeledPoint(row.label,row.features)])
print('After changing the dataset type to labeled Point')
print(type(trainingData))
print(trainingData.take(2))
model = LogisticRegressionWithLBFGS.train(trainingData, numClasses=5)
print(type(model))
exit();
predictions = testData.map(lambda p: (p.label, model.predict(p.features)))
correct = predictions.filter(lambda (x, p): x == p)
### Calculate the accuracy of the model using custom method
accuracy = round((correct.count() / float(testData.count())) * 100, 3)
# return the final accuracy
return accuracy
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 main(input_file_path):
print('=====>>>>>')
print('ddd')
data = sc.textFile(input_file_path)
traning_data_RDD = data.filter(lambda line: line.split(',')[4] != '' and line.split(',')[0] != 'INDEX')
unseen_data_RDD = data.filter(lambda line: line.split(',')[4] == '')
traning_data_pddf = create_pddf(traning_data_RDD)
traning_data_df = sqlContext.createDataFrame(traning_data_pddf)
print(traning_data_df.head())
parsed_data = rdd_to_labeled_point(traning_data_df.rdd)
parsed_data.persist()
# Correct print: [LabeledPoint(1.0, [1.0,8.6662186586,6.98047693487])]
logisticRegressionWithLBFGS = LogisticRegressionWithLBFGS.train(parsed_data, iterations=500, numClasses=100)
labels_and_preds = parsed_data.map(lambda lp: [lp.label, logisticRegressionWithLBFGS.predict(lp.features)])
Accuracy = float(labels_and_preds.filter(lambda ele: (int(ele[0]) - int(ele[1])) ** 2).reduce(lambda x, y: x + y)[0]) / float(parsed_data.count())
print("Training Accuracy on training data = " + str(Accuracy))
unseen_data_pddf = create_pddf(unseen_data_RDD)
unseen_data_df = sqlContext.createDataFrame(unseen_data_pddf)
unseen_parsed_data = rdd_to_index_featurs(unseen_data_df.rdd)
unseen_parsed_data.persist()
file = open('/Users/1002720/Documents/workspace/SNU-project/data/BDA2Project/1-GenderPrediction/result2.csv', 'w',
encoding='utf-8')
file.write('INDEX,AGE\n')
for data in unseen_parsed_data.collect():
file.write(str(data[0]) + ',' + str(logisticRegressionWithLBFGS.predict(data[1])) + '\n')
# print(labels_and_preds.collect())
parsed_data.unpersist()
unseen_parsed_data.unpersist()
print('=====>>>>>')
print('=====>>>>>')
print('=====>>>>>')
print('=====>>>>>')
def train(self, feat='tfidf'):
"""
Trains a multinomal NaiveBayes classifier on TFIDF features.
Parameters
---------
Spark DataFrame with columns:
key: (label, filepath) tuple
tf: Term-frequency Sparse Vector.
IDF: TFIDF Sparse Vector.
Returns
---------
model: MLLib NaiveBayesModel object, trained.
test_score: Accuracy of the model on test dataset.
"""
if not self.lp_path:
self.labeled_points = self.make_labeled_points(self.extract_features())
self.make_train_test(self.test_size)
train_rdd = self.labeled_points.join(self.y_train) \
.map(lambda (key, (lp, label)): lp) \
.repartition(self.n_part).cache()
if self.model_type == 'naive_bayes':
nb = NaiveBayes()
self.model = nb.train(train_rdd)
elif self.model_type == 'log_reg':
n_classes = len(self.unique_ratings())
features = train_rdd.map(lambda lp: LabeledPoint(lp.label, lp.features.toArray()))
logreg = LogisticRegressionWithLBFGS.train(features, numClasses=n_classes)
self.model = logreg
# elif self
return self
def processData(sc):
#load and parse the data
raw_data = sc.textFile(DATA_FILE)
raw_data.persist()
print "Train data size {}".format(raw_data.count())
# map data to a format needed for logistic regression
parsedData = raw_data.map(mapper)
print "Sample of input to algorithm ", parsedData.take(10)
# Train model
t0 = time()
model = LogisticRegressionWithLBFGS.train(parsedData)
t1 = time() - t0
print "Classifier trained in {} seconds".format(round(t1, 3))
labelsAndPreds = parsedData.map(lambda point: (point.label, model.predict(point.features)))
# Evaluating the model on training data
trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count())
# Print some stuff
print("Training Error = " + str(trainErr))
"""
# Imports
# The L-BFGS method approximates the objective function locally
# as a quadratic without evaluating the second partial derivatives of the objective function to construct the Hessian matrix.
# LogBFGS over mini-batch gradient descent for faster convergence.
from pyspark.mllib.classification import LogisticRegressionWithLBFGS
from pyspark.mllib.regression import LabeledPoint
from pyspark import SparkContext
from numpy import array
sc = SparkContext("local", "SVM")
# Loading and parsing data
def parsePoint(line):
vals = [float(i) for i in line.split(' ')]
return LabeledPoint(vals[0], vals[1:])
# Sample data provided by Spark 1.3.1 folder
data = sc.textFile("jingrong/sample_svm_data.txt")
parsedData = data.map(parsePoint)
# Building the model
model = LogisticRegressionWithLBFGS.train(parsedData)
# Evaluate the model based on training data
labelAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
trainingError = labelAndPreds.filter(lambda (v,p): v!=p).count() / float(parsedData.count())
print "Training Error: ", str(trainingError)
def logsreg(loadTrainingFilePath, sc):
# Load training data in LIBSVM format
loadTrainingFilePath = '/Users/Jacob/repository/SparkService/data/sample_libsvm_data.txt'
data = MLUtils.loadLibSVMFile(sc, loadTrainingFilePath)
# Split data into training (60%) and test (40%)
traindata, testdata = data.randomSplit([0.6, 0.4], seed = 11L)
traindata.cache()
# Load testing data in LIBSVM format
#testdata = MLUtils.loadLibSVMFile(sc, loadTestingFilePath)
# Run training algorithm to build the model
model = LogisticRegressionWithLBFGS.train(traindata, numClasses=3)
# Compute raw scores on the test set
predictionAndLabels = testdata.map(lambda lp: (float(model.predict(lp.features)), lp.label))
Json.generateJson("LogisticRegression", "12345678", traindata, predictionAndLabels);
print 'Completed.'
# Instantiate metrics object
# metrics = MulticlassMetrics(predictionAndLabels)
# # Overall statistics
# precision = metrics.precision()
# recall = metrics.recall()
# f1Score = metrics.fMeasure()
# #confusion_matrix = metrics.confusionMatrix().toArray()
# print("Summary Stats")
# print("Precision = %s" % precision)
# print("Recall = %s" % recall)
# print("F1 Score = %s" % f1Score)
# # Statistics by class
# labels = traindata.map(lambda lp: lp.label).distinct().collect()
# for label in sorted(labels):
# print("Class %s precision = %s" % (label, metrics.precision(label)))
# print("Class %s recall = %s" % (label, metrics.recall(label)))
# print("Class %s F1 Measure = %s" % (label, metrics.fMeasure(label, beta=1.0)))
# # Weighted stats
# print("Weighted recall = %s" % metrics.weightedRecall)
# print("Weighted precision = %s" % metrics.weightedPrecision)
# print("Weighted F(1) Score = %s" % metrics.weightedFMeasure())
# print("Weighted F(0.5) Score = %s" % metrics.weightedFMeasure(beta=0.5))
# print("Weighted false positive rate = %s" % metrics.weightedFalsePositiveRate)
# #return model parameters
# res = [('1','Yes','TP Rate', metrics.truePositiveRate(0.0)),
# ('2','Yes','FP Rate', metrics.falsePositiveRate(0.0)),
# ('3','Yes','Precision', metrics.precision(0.0)),
# ('4','Yes','Recall', metrics.recall(0.0)),
# ('5','Yes','F-Measure', metrics.fMeasure(0.0, beta=1.0)),
# ('1','Yes','TP Rate', metrics.truePositiveRate(1.0)),
# ('2','Yes','FP Rate', metrics.falsePositiveRate(1.0)),
# ('3','Yes','Precision', metrics.precision(1.0)),
# ('4','Yes','Recall', metrics.recall(1.0)),
# ('5','Yes','F-Measure', metrics.fMeasure(1.0, beta=1.0)),
# ('1','Yes','TP Rate', metrics.truePositiveRate(2.0)),
# ('2','Yes','FP Rate', metrics.falsePositiveRate(2.0)),
# ('3','Yes','Precision', metrics.precision(2.0)),
# ('4','Yes','Recall', metrics.recall(2.0)),
# ('5','Yes','F-Measure', metrics.fMeasure(2.0, beta=1.0))]
# #save output file path as JSON and dump into dumpFilePath
# rdd = sc.parallelize(res)
# SQLContext.createDataFrame(rdd).collect()
# df = SQLContext.createDataFrame(rdd,['Order','CLass','Name', 'Value'])
#tempDumpFilePath = dumpFilePath + "/part-00000"
#if os.path.exists(tempDumpFilePath):
# os.remove(tempDumpFilePath)
#df.toJSON().saveAsTextFile(hdfsFilePath)
#tmpHdfsFilePath = hdfsFilePath + "/part-00000"
#subprocess.call(["hadoop","fs","-copyToLocal", tmpHdfsFilePath, dumpFilePath])
# Save and load model
#clusters.save(sc, "myModel")
#sameModel = KMeansModel.load(sc, "myModel")
def train(self, num_iterations=10):
model = LogisticRegressionWithLBFGS.train(
self._labeled_feature_vector_rdd(),
num_iterations)
return LogisticRegressionModel(model, self.feature_cols)
regParams = [1e-3]
corrections = [30]
tolerances = [1e-4]
bestReg = 0
bestCor = 0
bestTol = 0
from pyspark.mllib.classification import LogisticRegressionWithLBFGS
for reg in regParams:
for cor in corrections:
for tol in tolerances:
model = LogisticRegressionWithLBFGS.train(hashedTrainData, iterations=100, initialWeights=None, regParam=reg, regType='l2',
intercept=False, corrections=cor, tolerance=tol, validateData=True, numClasses=2)
logLossVa = (hashedValidationData.map(lambda p: (p.label, getCTRProb(p.features, model.weights, model.intercept)))
.map(lambda p: computeLogLoss(p[1], p[0]))
.reduce(lambda a,b: a+b))/hashedValidationData.count()
# logLossVa = evaluateModel(model, hashedValidationData)
print logLossVa, reg, cor, tol
if (logLossVa < bestLogLoss):
bestModel = model
bestLogLoss = logLossVa
bestReg = reg
bestCor = cor
bestTol = tol
print bestLogLoss, bestReg, bestCor, bestTol
traindays = set(traindays.collect()) # for fast searching
# read the data, filtering it to keep only traindays and non-cancels
# the header is organically removed because FL_DATE is not a trainday
#allfields = sc.textFile('gs://cloud-training-demos/flights/201501.csv') \
allfields = sc.textFile('gs://cloud-training-demos/flights/2015*.csv') \
.map(lambda line : line.split(',')) \
.filter(lambda fields: fields[0] in traindays and \
fields[22] != '')
# these are the fields we'll use in the regression
# format is LabeledPoint(label, [x1, x2, ...])
flights = allfields.map(lambda fields: LabeledPoint(\
float(float(fields[22]) < 15), #ontime \
[ \
float(fields[15]), # DEP_DELAY \
float(fields[16]), # TAXI_OUT \
float(fields[26]), # DISTANCE \
]))
#flights.saveAsTextFile('gs://cloud-training-demos/flights/sparkoutput/train')
lrmodel = LogisticRegressionWithLBFGS.train(flights, intercept=True)
print lrmodel.weights,lrmodel.intercept
lrmodel.setThreshold(0.7) # cancel if prob-of-ontime < 0.7
#print lrmodel.predict([36.0,12.0,594.0])
lrmodel.save(sc, 'gs://cloud-training-demos/flights/sparkoutput/model')
Err = 0.0
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 = LogisticRegressionWithLBFGS.train(sc.parallelize(parsedData))
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))
def main():
appName = "BadOrGood;zl"
conf = (SparkConf()
.setAppName(appName)
.set("spark.executor.memory", "5g")
.set("spark.executor.cores","3")
.set("spark.executor.instance", "3")
)
sc = SparkContext(conf = conf)
hc = HiveContext(sc)
#fetch data
#filepath = '/sshomework_zl/BadOrGood/AllDataRowrdd'
#fetchDataToFile(hc, filepath)
#load data
# AllDataRawrdd = sc.pickleFile(filepath) \
# .map( lambda _: {'label':int(_.status), 'feature':extractFeature(_)} ) \
# .repartition(10)
AllDataRawrdd = sc.pickleFile('/pickleData').repartition(10)
#standardizer for train and test data
model = StandardScaler(True, True) \
.fit( AllDataRawrdd \
.map( lambda _: Vectors.dense(_['feature']) )
)
labels = AllDataRawrdd.map(lambda _: _['label'])
featureTransformed = model.transform( AllDataRawrdd.map(lambda _: _['feature']) )
AllDataRawrdd = labels \
.zip(featureTransformed) \
.map( lambda _: { 'label':_[0], 'feature':_[1] } )
#sampling
trainDataRawrdd, testDataRawrdd = AllDataRawrdd.randomSplit(weights=[0.7, 0.3], seed=100)
trainDatardd = trainDataRawrdd.map( lambda _: LabeledPoint( _['label'], _['feature'] ) ).persist()
testDatardd = testDataRawrdd.map( lambda _: {'label': _['label'], 'feature': list(_['feature']) } ).persist()
#prediction & test
lrmLBFGS = LogisticRegressionWithLBFGS.train(trainDatardd, iterations=3000, regParam=0.01, regType="l1")
resultrdd = test(lrmLBFGS, testDatardd)
lrmLBFGSFone = fone(resultrdd)
lrmLBFGSac = accuracy(resultrdd)
lrmSGD = LogisticRegressionWithSGD.train(trainDatardd, iterations=3000, step=0.1, regParam=0.01, regType="l1")
resultrdd = test(lrmSGD, testDatardd)
lrmSGDFone = fone(resultrdd)
lrmSGDac = accuracy(resultrdd)
dt = DecisionTree.trainClassifier(trainDatardd, 2, {}, maxDepth=10)
resultrdd = test(dt, testDatardd)
dtFone = fone(resultrdd)
dtac = accuracy(resultrdd)
rf = RandomForest.trainClassifier(trainDatardd, 2, {}, 10)
resultrdd = test(rf, testDatardd)
rfFone = fone(resultrdd)
rfac = accuracy(resultrdd)
print "LR_LBFGS f1 is : %f, ac is : %f" % (lrmLBFGSFone, lrmLBFGSac)
print "LR_SGD f1 is : %f, ac is : %f" % (lrmSGDFone, lrmSGDac)
print "Decision Tree f1 is: %f, ac is : %f" % (dtFone, dtac)
print "Random Forest f1 is: %f, ac is : %f" % (rfFone, rfac)
print lrmLBFGS.weights
print lrmSGD.weights
sc.stop()
#creating RDD of reviews
review = parts.map(lambda p: Row(id=p[0], label=float(p[1]),
sentence=paragraph_to_wordlist(p[2])))
#creating the dataframe
reviewDF = sqlContext.createDataFrame(review)
#transforming the words to vectors using the trained model
transformDF = wvModel.transform(reviewDF)
#segregating the labels and features
selectData = transformDF.select("label","features","id")
#Creating RDD of LabeledPoints
lpSelectData = selectData.map(lambda x : (x.id, LabeledPoint(x.label,x.features)))
#Spliting the data for training and test
(trainingData, testData) = lpSelectData.randomSplit([0.9, 0.1])
# training the Logistic regression with LBFGS model
lrm = LogisticRegressionWithLBFGS.train(trainingData.map(lambda x: x[1]), iterations=10)
#fetching the labels and predictions for test data
labelsAndPreds = testData.map(lambda p: (p[0],p[1].label, lrm.predict(p[1].features)))
#calculating the accuracy and printing it.
accuracy = labelsAndPreds.filter(lambda (i, v, p): v == p).count() / float(testData.count())
print("Accuracy = " + str(accuracy))
#initializing Streming context with a window of 10 secs
ssc = StreamingContext(sc, 10)
#fetching the input statement from S3
lines = ssc.textFileStream("s3://spark-sentimentanalysis/")
#calculating a wordcount
counts = lines.flatMap(lambda line: line.split(" "))\
.map(lambda x: (x, 1))\
.reduceByKey(lambda a, b: a+b)
# Evaluate the model on training data
model2 = RandomForest.trainClassifier(trainingData, numClasses=2,
categoricalFeaturesInfo={},
numTrees=3, featureSubsetStrategy="auto",
impurity='gini', maxDepth=4, maxBins=32)
# Build the model
model3 = LogisticRegressionWithLBFGS.train(trainingData)
model4 = GradientBoostedTrees.trainClassifier(trainingData,
categoricalFeaturesInfo={}, numIterations=3)
#model.setThreshold(0.07)
model.clearThreshold()
# 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())
j=0
return LabeledPoint(float(int(hashlib.md5(datapoints[3]).hexdigest(), 16)/pow(10,38)), datapoints[1:3])
working_directory = os.getcwd()
working_directory = working_directory+"/"
configuartion=py.SparkConf() # setting the Spark Configuration
sContext=py.SparkContext(conf=configuartion) # setting the Spark context
sContext.defaultParallelism
data = sContext.textFile(working_directory+"Test-TrainingData_SVM.csv")
testdata = sContext.textFile("/media/vyassu/OS/Users/vyas/Documents/Assigments/BigData/AudioData/KL/")
print testdata.take(1)
parsedData = data.map(parsePoint)
print parsedData.take(10)
# Build the modelLogisticRegressionWithLBFGS
model = LogisticRegressionWithLBFGS.train(parsedData, iterations=10,numClasses=7)
# Evaluating the model on training data
labelsAndPreds = parsedData.map(lambda p: (p.label, model.predict(p.features)))
trainErr = labelsAndPreds.filter(lambda (v, p): v != p).count() / float(parsedData.count())
print("Training Error = " + str(trainErr))
# # Save and load model
# model.save(sc, "myModelPath")
# sameModel = SVMModel.load(sc, "myModelPath")
#Cancelled becomes the 8th column now, and total columns in the data = 8
label = clean_line_split[7]
nonLable = clean_line_split[0:7]
return LabeledPoint (label, nonLable)
parsedData = raw_data.map (parsePoint)
#divide training and test data by 70-30 rule
(training, test) = parsedData.randomSplit ([0.7, 0.3], seed=11L)
training.cache ()
#start timer at this point
startTime = datetime.now()
#build the model
model = LogisticRegressionWithLBFGS.train (training, numClasses=3)
#evaluate the model on training data
labelAndPreds = test.map (lambda x: (x.label, model.predict (x.features)))
#labelAndPreds = testData.map (lambda x: (x.label, model.predict (x.features)))
trainErr = labelAndPreds.filter (lambda (w, x): w != x).count () / float (test.count ())
print ('Time consumed = '), (datetime.now() - startTime)
print ("Training error = " + str (trainErr))
#save and load model
model.save(sc, "LRW-95-08")
sameModel = LogisticRegressionModel.load(sc, "LRW-95-08")
sc.stop ()
#NB_socredLabel = numpy.array(test_set.map(lambda lp: (NBmodel.predict(lp.features), lp.label)).sortByKey(ascending=False).map(lambda (k,v): v).collect()) #findCoveragePercent(NB_socredLabel, 0.4) SVMSGDmodel = SVMWithSGD.train(train_set) SVMSGDmodel.clearThreshold() SVM_scoredLabel = numpy.array(test_set.map(lambda lp: (SVMSGDmodel.predict(lp.features), lp.label)).sortByKey(ascending=False).map(lambda (k,v): v).collect()) SVM_percent.append(findCoveragePercent(SVM_scoredLabel, 0.4)) SVM_percent.append(findCoveragePercent(SVM_scoredLabel, 0.8)) SVM_percent.append(findCoveragePercent(SVM_scoredLabel, 1.0)) LRSGDmodel = LogisticRegressionWithSGD.train(train_set) LRSGDmodel.clearThreshold() LRSGD_scoedLabel = numpy.array(test_set.map(lambda lp: (LRSGDmodel.predict(lp.features), lp.label)).sortByKey(ascending=False).map(lambda (k,v): v).collect()) LRSGD_percent.append(findCoveragePercent(LRSGD_scoedLabel, 0.4)) LRSGD_percent.append(findCoveragePercent(LRSGD_scoedLabel, 0.8)) LRSGD_percent.append(findCoveragePercent(LRSGD_scoedLabel, 1.0)) LRLBFGSmodel = LogisticRegressionWithLBFGS.train(train_set) LRLBFGSmodel.clearThreshold() LRLBFGS_scoredLabel = numpy.array(test_set.map(lambda lp: (LRLBFGSmodel.predict(lp.features), lp.label)).sortByKey(ascending=False).map(lambda (k,v): v).collect()) LRLBFGS_percent.append(findCoveragePercent(LRLBFGS_scoredLabel, 0.4)) LRLBFGS_percent.append(findCoveragePercent(LRLBFGS_scoredLabel, 0.8)) LRLBFGS_percent.append(findCoveragePercent(LRLBFGS_scoredLabel, 1.0)) def getAccumulatedPercentage(socredLabel): result = [] total = socredLabel.sum() accum = 0 for i in range(socredLabel.size): accum += socredLabel[i] result.append(accum/total) return result SVM_accum = getAccumulatedPercentage(SVM_socredLabel)
# $example off$
if __name__ == "__main__":
sc = SparkContext(appName="BinaryClassificationMetricsExample")
sqlContext = SQLContext(sc)
# $example on$
# Several of the methods available in scala are currently missing from pyspark
# Load training data in LIBSVM format
data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")
# Split data into training (60%) and test (40%)
training, test = data.randomSplit([0.6, 0.4], seed=11L)
training.cache()
# Run training algorithm to build the model
model = LogisticRegressionWithLBFGS.train(training)
# Compute raw scores on the test set
predictionAndLabels = test.map(lambda lp: (float(model.predict(lp.features)), lp.label))
# Instantiate metrics object
metrics = BinaryClassificationMetrics(predictionAndLabels)
# Area under precision-recall curve
print("Area under PR = %s" % metrics.areaUnderPR)
# Area under ROC curve
print("Area under ROC = %s" % metrics.areaUnderROC)
# $example off$
def train(self,data,**kwargs):
model = LogisticRegressionWithLBFGS.train(data=data,**kwargs)
model.clearThreshold()
self.model = model
print irisTrainRDD.take(2)
print irisTestRDD.take(2)
# COMMAND ----------
# MAGIC %md
# MAGIC Now, we can use MLlib's logistic regression on our `RDD` of `LabeledPoints`. Note that we'll use `LogisticRegressionWithLBFGS` as it tends to converge faster than `LogisticRegressionWithSGD`.
# COMMAND ----------
from pyspark.mllib.classification import LogisticRegressionWithLBFGS
help(LogisticRegressionWithLBFGS)
# COMMAND ----------
mllibModel = LogisticRegressionWithLBFGS.train(irisTrainRDD, iterations=1000, regParam=0.0)
# COMMAND ----------
# MAGIC %md
# MAGIC Let's calculate our accuracy using `RDDs`.
# COMMAND ----------
rddPredictions = mllibModel.predict(irisTestRDD.values())
predictAndLabels = rddPredictions.zip(irisTestRDD.keys())
mllibAccuracy = predictAndLabels.map(lambda (p, l): p == l).mean()
print 'MLlib model accuracy: {0:.3f}'.format(mllibAccuracy)
def train(self, df, target, regularization=None, num_of_iterations=100):
try:
LOGGER.info("Generation logistic regression")
spark_df = self.sql_context.createDataFrame(df)
feature_columns = spark_df.columns
feature_columns.remove(target)
X_train = spark_df.select(*feature_columns).map(lambda x: list(x))
y_train = spark_df.select(target).map(lambda x: x[0])
zipped = y_train.zip(X_train)
train_data = zipped.map(lambda x: LabeledPoint(x[0], x[1]))
numOfClasses = len(df[target].unique())
logistic_model = LogisticRegressionWithLBFGS.train(train_data,
numClasses=numOfClasses, regParam=0,
regType=regularization, intercept=True,
iterations=num_of_iterations, validateData=False)
self.model = logistic_model
except Exception as e:
raise e
