def main(sc, sql_context, is_hive=True):
lp_train = MLUtils.loadLabeledPoints(sc,
"bintrade.ml.diff.label_point.train")
lp_check = MLUtils.loadLabeledPoints(sc,
"bintrade.ml.diff.label_point.check")
model = GradientBoostedTrees.trainRegressor(lp_train, {},
numIterations=50,
maxDepth=10)
preds = model.predict(lp_check.map(lambda x: x.features))
labels_and_preds = lp_check.map(lambda x: x.label).zip(preds).sortBy(
lambda x: x[1], ascending=False)
for each in labels_and_preds.take(100):
print each
labels_and_preds = lp_check.map(lambda x: x.label).zip(preds).sortBy(
lambda x: x[1], ascending=True)
for each in labels_and_preds.take(100):
print each
mse = labels_and_preds.map(
lambda x: math.pow(x[0] - x[1], 2)).sum() / labels_and_preds.count()
print mse
mse = labels_and_preds.map(
lambda x: math.pow(x[0] - 1.0, 2)).sum() / labels_and_preds.count()
print mse
def do_POST(self):
response_code = 200
response = ""
var_len = int(self.headers.get('Content-Length'))
content = self.rfile.read(var_len)
payload = json.loads(content)
# 如果是训练请求，训练然后保存训练完的神经网络
if payload.get('train'):
# 转化数据格式
TrainData = ""
for d in payload['trainArray'][0]['y0']:
TrainData = TrainData + " " + ('%d' % d)
TrainData = '%d' % (payload['trainArray'][0]['label']
) + "," + TrainData.lstrip() + "\n"
print(TrainData)
Addoutput = open('LabeledPointsdata.txt', 'a')
Addoutput.write(TrainData)
Addoutput.close()
# 如果是预测请求，返回预测值
elif payload.get('predict'):
try:
training = MLUtils.loadLabeledPoints(sc,
"LabeledPointsdata.txt")
print('Begin NaiveBayes tranning!')
model = NaiveBayes.train(training, 1.0)
print('Trainning over!')
print(payload['image'])
response = {
"type": "test",
"result": str(model.predict(payload['image']))
}
except:
response_code = 500
else:
response_code = 400
self.send_response(response_code)
self.send_header("Content-type", "application/json")
self.send_header("Access-Control-Allow-Origin", "*")
self.end_headers()
if response:
self.wfile.write(json.dumps(response))
return
def main(input_file):
sc = pyspark.SparkContext(appName="DecisionTree")
data = MLUtils.loadLabeledPoints(sc, input_file)
trainingData, testData = data.randomSplit([0.70, 0.3])
# Cache in memory for faster training
trainingData.cache()
model = DecisionTree.trainClassifier(trainingData, numClasses=4, impurity='gini',
categoricalFeaturesInfo={}, maxDepth=16, maxBins=10)
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 tree_model.toDebugString()
print ""
print ""
print "Test Erros: {}".format(round(testErr,4))
import pyspark
from pyspark.mllib.tree import RandomForest, RandomForestModel
from pyspark.mllib.util import MLUtils
sc = pyspark.SparkContext(appName="RandomForest")
# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLabeledPoints(sc, 'gs://cs123data/Output/AmountVectors2/')
# Split the data into training and test sets
trainingData, testData = data.randomSplit([0.7, 0.3])
trainingData.cache()
testData.cache()
model = RandomForest.trainRegressor(trainingData, categoricalFeaturesInfo={},
numTrees=20, featureSubsetStrategy="auto",
impurity='variance', maxDepth=3, 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))
print('Learned regression forest model:')
print(model.toDebugString())
import pyspark
from pyspark.mllib.tree import RandomForest, RandomForestModel
from pyspark.mllib.util import MLUtils
sc = pyspark.SparkContext(appName="RandomForest")
# Load and parse the data file into an RDD of LabeledPoint.
data = MLUtils.loadLabeledPoints(sc, 'gs://cs123data/Output/PartyVectors/')
# Split the data into training and test sets
trainingData, testData = data.randomSplit([0.7, 0.3])
trainingData.cache()
# The depth of the tree proved to be a significant bottle neck
model = RandomForest.trainClassifier(trainingData, numClasses=4, categoricalFeaturesInfo={},
numTrees=700, featureSubsetStrategy="auto",
impurity='gini', maxDepth=8, maxBins=12)
# 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("")
print("")
print('Test Error: ' + str(testErr))
from __future__ import print_function
import sys
import math
from pyspark import SparkContext
from pyspark.mllib.classification import SVMWithSGD, SVMModel
from pyspark.mllib.util import MLUtils
if __name__ == "__main__":
sc = SparkContext(appName="BloodTestReportPythonSVMExample")
# 读取数据.
print('Begin Load Data File!')
sexData = MLUtils.loadLabeledPoints(sc, "LabeledPointsdata_sex.txt")
print('Data File has been Loaded!')
accuracySex = []
for i in range(0,100):
# 将数据随机分割为9:1，分别作为训练数据（training）和预测数据（test）.
sexTraining, sexTest = sexData.randomSplit([0.9, 0.1])
# 训练线性支持向量机模型.
#print('Begin SVM tranning!')
sexModel = SVMWithSGD.train(sexTraining, iterations=100)
#print('Trainning over!')
# 对test数据进行预测，输出预测准确度.
sexPredictionAndLabel = sexTest.map(lambda p: (sexModel.predict(p.features), p.label))
accuracySex.append(1.0 * sexPredictionAndLabel.filter(lambda (x, v): x == v).count() / sexTest.count())
