def main():
records = get_records()
records.cache()
# extract all the catgorical mappings
mappings = [get_mapping(records, i) for i in range(2,10)]
cat_len = sum(map(len, mappings))
num_len = len(records.first()[11:15])
data = records.map(lambda r: LabeledPoint(extract_label(r), extract_features(r, cat_len, mappings)))
data_dt = records.map(lambda r: LabeledPoint(extract_label(r), extract_features_dt(r)))
dt_model = DecisionTree.trainRegressor(data_dt, {})
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
data_dt_log = data_dt.map(lambda lp: LabeledPoint(np.log(lp.label), lp.features))
dt_model_log = DecisionTree.trainRegressor(data_dt_log, {})
preds_log = dt_model_log.predict(data_dt_log.map(lambda p: p.features))
actual_log = data_dt_log.map(lambda p: p.label)
true_vs_predicted_dt_log = actual_log.zip(preds_log).map(lambda (t, p): (np.exp(t), np.exp(p)))
calculate_print_metrics("Decision Tree Log", true_vs_predicted_dt_log)
def decisionTreeRegression(trainingData, testData, trainingSize, testSize):
'''
decision tree for regression
'''
# parameter range
maxDepthValList = [10, 20, 30]
maxBinsValList = [16, 24, 32]
# best parameters
bestMaxDepthVal = 5
bestMaxBinsVal = 16
bestTrainingRMSE = 1e10
for maxDepthVal, maxBinsVal in itertools.product(maxDepthValList,
maxBinsValList):
model = DecisionTree.trainRegressor(trainingData,
categoricalFeaturesInfo={},
impurity='variance',
maxDepth=maxDepthVal,
maxBins=maxBinsVal)
predictions = model.predict(trainingData.map(lambda x: x.features))
ValsAndPreds = trainingData.map(lambda x: x.label).zip(predictions)
trainingRMSE = math.sqrt(
ValsAndPreds.map(lambda (v, p):
(v - p)**2).reduce(lambda x, y: x + y) /
trainingSize)
if trainingRMSE:
if trainingRMSE < bestTrainingRMSE:
bestMaxDepthVal = maxDepthVal
bestMaxBinsVal = maxBinsVal
bestTrainingRMSE = trainingRMSE
print maxDepthVal, maxBinsVal, trainingRMSE
print bestMaxDepthVal, bestMaxBinsVal, bestTrainingRMSE
model = DecisionTree.trainRegressor(trainingData,
categoricalFeaturesInfo={},
impurity='variance',
maxDepth=bestMaxDepthVal,
maxBins=bestMaxBinsVal)
# evaluating the model on training data
predictions = model.predict(trainingData.map(lambda x: x.features))
ValsAndPreds = trainingData.map(lambda x: x.label).zip(predictions)
trainingRMSE = math.sqrt(
ValsAndPreds.map(lambda (v, p): (v - p)**2).reduce(lambda x, y: x + y)
/ trainingSize)
print trainingRMSE
# evaluating the model on test data
predictions = model.predict(testData.map(lambda x: x.features))
ValsAndPreds = testData.map(lambda x: x.label).zip(predictions)
testRMSE = math.sqrt(
ValsAndPreds.map(lambda (v, p): (v - p)**2).reduce(lambda x, y: x + y)
/ testSize)
print testRMSE
pass
def main():
records = get_records()
records.cache()
# extract all the catgorical mappings
mappings = [get_mapping(records, i) for i in range(2, 10)]
cat_len = sum(map(len, mappings))
num_len = len(records.first()[11:15])
total_len = num_len + cat_len
print "Feature vector length for categorical features: %d" % cat_len
print "Feature vector length for numerical features: %d" % num_len
print "Total feature vector length: %d" % total_len
data = records.map(lambda r: LabeledPoint(
extract_label(r), extract_features(r, cat_len, mappings)))
data_dt = records.map(
lambda r: LabeledPoint(extract_label(r), extract_features_dt(r)))
first_point_dt = data_dt.first()
print "Decision Tree feature vector: " + str(first_point_dt.features)
print "Decision Tree feature vector length: " + str(
len(first_point_dt.features))
dt_model = DecisionTree.trainRegressor(data_dt, {})
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print "Decision Tree predictions: " + str(true_vs_predicted_dt.take(5))
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
calculate_print_metrics("Decision Tree", true_vs_predicted_dt)
def trainEvaluateModel(trainData, validationData, impurityParm, maxDepthParm,
maxBinsParm):
'''
训练模型时会输入不同的参数。其中，DecisionTree参数有impurity、maxDepth、maxBins等的值都会影响准确率以及训练所需的时间。
我们以图表显示这些参数值、准确率与训练所需的时间。
我们每次只会评估单个参数的不同值，例如评估maxDepth参数的不同值[3, 5, 10, 15, 20, 25]，执行步骤如下：
（1）用DecisionTree.trainRegressor进行训练传入trainData与单个参数的不同数值；
（2）建立模型后，用validationData评估模型的RMES准确率；
（3）训练与评估模型重复执行多次，产生多个参数项的RMES与运行时间，并存储于metricsRDD中；
（4）全部执行完成后，将metricsRDD转换为Pandas DataFrame；
（5）Pandas DataFrame可绘制RMES与运行时间图表，用于显示不同参数的准确率与执行时间的关系。
:param trainData:
:param validationData:
:param impurityParm:
:param maxDepthParm:
:param maxBinsParm:
:return:
'''
print('======================= 训练评估模型 =======================')
startTime = time()
model = DecisionTree.trainRegressor(trainData,
categoricalFeaturesInfo={},
impurity=impurityParm,
maxDepth=maxDepthParm,
maxBins=maxBinsParm)
RMES = evaluateModel(model, validationData)
duration = time() - startTime
print('========== [trainEvaluateModel] >>>> 训练评估模型：使用参数：impurity=' +
str(impurityParm) + ', maxDepth=' + str(maxDepthParm) +
', maxBins=' + str(maxBinsParm) + '\n' + '\t\t==>> 所需时间=' +
str(duration) + ', 结果RMES=' + str(RMES))
return (RMES, duration, impurityParm, maxDepthParm, maxBinsParm, model)
def evaluate_dt(train,test,maxDepth,maxBins):
model = DecisionTree.trainRegressor(train,{},impurity = 'variance',maxDepth = maxDepth,maxBins = maxBins)
preds = model.predict(test.map(lambda p:p.features))
actual = test.map(lambda p:p.label)
tp = actual.zip(preds)
rmsle = np.sqrt(tp.map(lambda (t,p):squared_log_error(t,p)).mean())
return rmsle
def main():
records = get_records()
records.cache()
print "Mapping of first categorical feature column: %s" % get_mapping(
records, 2)
# extract all the catgorical mappings
mappings = [get_mapping(records, i) for i in range(2, 10)]
cat_len = sum(map(len, mappings))
num_len = len(records.first()[11:15])
total_len = num_len + cat_len
data = records.map(lambda r: LabeledPoint(
extract_label(r), extract_features(r, cat_len, mappings)))
data_dt = records.map(
lambda r: LabeledPoint(extract_label(r), extract_features_dt(r)))
cat_features = dict([(i - 2, len(get_mapping(records, i)) + 1)
for i in range(2, 10)])
print "Categorical feature size mapping %s" % cat_features
# train the model again
dt_model = DecisionTree.trainRegressor(
data_dt, categoricalFeaturesInfo=cat_features)
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
calculate_print_metrics("Decision Tree Categorical Features",
true_vs_predicted_dt)
def evaluate_final(description, data, maxDepth, maxBins):
data_with_idx = data.zipWithIndex().map(lambda (k, v): (v, k))
test = data_with_idx.sample(False, 0.13, 63) #.13 WAS working to get 10..., for 10% ..., 63 is the seed
train = data_with_idx.subtractByKey(test)
train_data = train.map(lambda (idx, p): p) #train_size = train_data.count()
test_data = test.map(lambda (idx, p) : p) #test_size = test_data.count()
dt_model = DecisionTree.trainRegressor(train_data,{}, maxDepth=maxDepth, maxBins=maxBins)
preds = dt_model.predict(test_data.map(lambda p: p.features))
actual = test_data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print '\r\n-------- ' + description + ' ---------'
print "Decision Tree predictions: " + str(true_vs_predicted_dt.take(5))
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
mse_dt = true_vs_predicted_dt.map(lambda (t, p): squared_error(t, p)).mean()
mae_dt = true_vs_predicted_dt.map(lambda (t, p): abs_error(t, p)).mean()
rmsle_dt = np.sqrt(true_vs_predicted_dt.map(lambda (t, p): squared_log_error(t, p)).mean())
print 'Decision Tree -Mean Squared Error: {0:2.4f}'.format(mse_dt)
print 'Decision Tree -Root Mean Squared Error: {0:2.4f}'.format(np.sqrt(mse_dt))
print 'Decision Tree -Mean Absolute Error: {0:2.4f}'.format(mae_dt)
print 'Decision Tree -Root Mean Squared Log Error: {0:2.4f}'.format(rmsle_dt)
def trainEvaluateModel(trainData,validationData,impurityParm, maxDepthParm, maxBinsParm):
model = DecisionTree.trainRegressor(trainData,
categoricalFeaturesInfo={},
impurity=impurityParm,
maxDepth=maxDepthParm,
maxBins=maxBinsParm)
return model
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 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, 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)
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]))
LassoWithSGD.train(rdd, initialWeights=array([1.0, 1.0]))
RidgeRegressionWithSGD.train(rdd, initialWeights=array([1.0, 1.0]))
except ValueError:
self.fail()
def Regression_Model(filename):
open_price, close_price, open_price_train, close_price_train, True_price, True_price_train, Date = get_csv_data(
filename)
output = []
for i in range(1, len(Date)):
tmp = LabeledPoint(label=True_price_train[i],
features=[close_price_train[i]])
output.append(tmp)
output_train_RDD = sc.parallelize(output).cache()
lrm = LinearRegressionWithSGD.train(output_train_RDD,
step=0.001,
iterations=100000)
tree = DecisionTree.trainRegressor(output_train_RDD,
categoricalFeaturesInfo={},
impurity='variance',
maxDepth=5,
maxBins=30)
forest = RandomForest.trainRegressor(output_train_RDD,
categoricalFeaturesInfo={},
numTrees=3,
featureSubsetStrategy="auto",
impurity='variance',
maxDepth=5,
maxBins=30)
gradient = GradientBoostedTrees.trainRegressor(output_train_RDD,
categoricalFeaturesInfo={},
numIterations=10)
print("\n============MODEL Evaluation=============\n")
model_name = [
'LinearRegression', 'DecisionTree', 'RandomForest',
'GradientBoostedTrees'
]
es_modelname = ['lrm', 'tree', 'forest', 'gradient']
result = ''
x = 0
err = 1000
test_model = 'LinearRegression'
#此处更换不同的RDD
output_model_RDD = lrm
for model in [lrm, tree, forest, gradient]:
predictions = model.predict(output_train_RDD.map(lambda x: x.features))
labelsAndPredictions = output_train_RDD.map(lambda lp: lp.label).zip(
predictions)
MSE = (
labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() /
float(output_train_RDD.count()))**0.5
#print ("Predictions: ", valuesAndPreds.take(10))
result += model_name[x] + "\tMean Squared Error\t=" + str(MSE) + "\n"
if (err > MSE):
err = MSE
output_model = model
es_model = es_modelname[x]
x += 1
print(result)
print(es_model)
return Date, True_price, output_model_RDD, open_price, close_price, es_model
def evaluate_dt(train, test, maxDepth, maxBins):
model = DecisionTree.trainRegressor(train, {},
impurity='variance',
maxDepth=maxDepth,
maxBins=maxBins)
preds = model.predict(test.map(lambda p: p.features))
actual = test.map(lambda p: p.label)
tp = actual.zip(preds)
rmsle = np.sqrt(tp.map(lambda (t, p): squared_log_error(t, p)).mean())
return rmsle
def trainEvaluateModel(trainData, validationData, impurityParam, maxDepthParam,
maxBinsParam):
startTime = time()
model = DecisionTree.trainRegressor(trainData, categoricalFeaturesInfo={}, \
impurity=impurityParam, maxDepth=maxDepthParam, maxBins=maxBinsParam)
RMSE = evaluateModel(model, validationData)
duration = time() - startTime
print("训练评估：impurity->", impurityParam, ", maxDepth->", maxDepthParam,
", maxBins->", maxBinsParam)
print("==> 所需时间:", duration, "s , RMSE=", RMSE)
return (RMSE, duration, impurityParam, maxDepthParam, maxBinsParam, model)
def evaluate_dt(train, test, maxDepth, maxBins):
dtModel = DecisionTree.trainRegressor(train, {},
impurity='variance',
maxDepth=maxDepth,
maxBins=maxBins)
preds = dtModel.predict(test.map(lambda p: p.features))
actual = test.map(lambda p: p.label)
actual_vs_pred = actual.zip(preds)
#print actual_vs_pred.take(10)
#print "decision tree depth: %d" % dtModel.depth()
#print "decision tree number of nodes: %d" % dtModel.numNodes()
return actual_pred_error(actual_vs_pred)
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 trainEvaluationModel(trainData, validationData, impurityParm, maxDepthParm, maxBinsParm):
startTime = time()
model = DecisionTree.trainRegressor(trainData, categoricalFeaturesInfo={},
impurity=impurityParm, maxDepth=maxDepthParm, maxBins=maxBinsParm)
RMSE = evaluateModel(model, validationData)
duration = time() - startTime
print("训练评估：使用参数 " + \
" impurity = " + str(impurityParm) + \
" maxDepth = " + str(maxDepthParm) + \
" maxBins = " + str(maxBinsParm) + \
" ==> 所需时间 = " + str(duration) + " 秒"\
" 结果 RMSE = %f" %RMSE)
return RMSE, duration, impurityParm, maxDepthParm, maxBinsParm, model
def trainEvaluateModel(trainData, validationData, impurtyParam, maxDepthParam,
maxBinsParam):
starttime = time()
model = DecisionTree.trainRegressor(data=trainData,
categoricalFeaturesInfo={},
impurity=impurtyParam,
maxDepth=maxDepthParam,
maxBins=maxBinsParam)
RMSE = evaluateModel(model, validationData) #均方根误差
duration = time() - starttime
print("训练评估使用参数：\n", "impurity=", impurtyParam, "\n maxDepth=",
maxDepthParam, "\n maxBins=", maxBinsParam, "====>用时=", duration,
"\n 结果AUC=", RMSE)
return (RMSE, duration, impurtyParam, maxDepthParam, maxBinsParam, model)
def regression(sc, sample):
traindata = sc.parallelize(sample)
traindata = traindata.map(lambda x: LabeledPoint(x[1], x[0]))
testdata = [8.2]
#####
# linear_model = LinearRegressionWithSGD.train(traindata,iterations=10)
# prediction = linear_model.predict(testdata)
# print prediction
#####
decision_model = DecisionTree.trainRegressor(traindata, {})
prediction = decision_model.predict(testdata)
print prediction
def TrainEvaluateModel(trainData,validationData,
impurityParm,maxDepthParm,maxBinsParm):
startTime = time()
model = DecisionTree.trainRegressor(trainData,
categoricalFeaturesInfo={}, impurity=impurityParm, maxDepth=maxDepthParm,
maxBins=maxBinsParm)
RMSE = EvaluateModel(model, validationData)
duration = time() - startTime
print("Evaluate the model: use the params: " + \
"impurity=" + str(impurityParm) + \
" maxDepthParm=" + str(maxDepthParm) + \
" maxBinsParm=" + str(maxBinsParm) + "\n" + \
"====> duration time = " + str(duration) + \
" result RMSE = " + str(RMSE))
return (RMSE, duration, impurityParm, maxDepthParm, maxBinsParm, model)
def regression(sc, sample):
traindata = sc.parallelize(sample)
traindata = traindata.map(lambda x:LabeledPoint(x[1],x[0]))
testdata = [8.2]
#####
# linear_model = LinearRegressionWithSGD.train(traindata,iterations=10)
# prediction = linear_model.predict(testdata)
# print prediction
#####
decision_model = DecisionTree.trainRegressor(traindata,{})
prediction = decision_model.predict(testdata)
print prediction
def train_evaluate_model(train_data, valid_data, impurity, max_depth,
max_bins):
start_time = time()
# 训练
model = DecisionTree.trainRegressor(train_data,
categoricalFeaturesInfo={},
impurity=impurity,
maxDepth=max_depth,
maxBins=max_bins)
# 评估
# y_pred y_true
RMSE = evaluate_model(model, valid_data)
duration = time() - start_time
print(f"训练评估：使用参数 impurity={impurity}, maxDepth={max_depth},"\
f"maxBins={max_bins},==>所需时间={duration} 结果RMSE = {RMSE}")
return RMSE, duration, impurity, max_depth, max_bins, model
def test_all(self, measure_columns=None, dimension_columns=None):
measures = measure_columns[0]
self._target_column = measures
#dimension = dimension_columns[0]
all_dimensions = self._dimension_columns
all_measures = list(x for x in self._measure_columns if x != measures)
cat_feature_info = []
#columns_without_dimension = list(x for x in all_dimensions if x != dimension)
columns_without_dimension = all_dimensions
mapping_dict = {}
masterMappingDict = {}
decision_tree_result = DecisionTreeResult()
for column in all_dimensions:
mapping_dict[column] = dict(enumerate(self._data_frame.select(column).distinct().rdd.map(lambda x: str(x[0])).collect()))
# for c in mapping_dict:
# name = c
# reverseMap = {v: k for k, v in mapping_dict[c].iteritems()}
# udf = UserDefinedFunction(lambda x: reverseMap[x], StringType())
# self._data_frame = self._data_frame.select(*[udf(column).alias(name) if column == name else column for column in self._data_frame.columns])
# converting spark dataframe to pandas for transformation and then back to spark dataframe
pandasDataFrame = self._data_frame.toPandas()
for key in mapping_dict:
pandasDataFrame[key] = pandasDataFrame[key].apply(lambda x: 'None' if x==None else x)
reverseMap = {v: k for k, v in mapping_dict[key].items()}
pandasDataFrame[key] = pandasDataFrame[key].apply(lambda x: reverseMap[x])
# sqlCtx = SQLContext(self._spark)
self._data_frame = self._spark.createDataFrame(pandasDataFrame)
self._mapping_dict = mapping_dict
for c in columns_without_dimension:
cat_feature_info.append(self._data_frame.select(c).distinct().count())
if len(cat_feature_info)>0:
max_length = max(cat_feature_info)
else:
max_length=32
cat_feature_info = dict(enumerate(cat_feature_info))
#dimension_classes = self._data_frame.select(dimension).distinct().count()
self._data_frame = self._data_frame[[measures] + columns_without_dimension + all_measures]
data = self._data_frame.rdd.map(lambda x: LabeledPoint(x[0], x[1:]))
(trainingData, testData) = data.randomSplit([1.0, 0.0])
# TO DO : set maxBins at least equal to the max level of categories in dimension column
model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo=cat_feature_info, impurity='variance', maxDepth=3, maxBins=max_length)
output_result = model.toDebugString()
decision_tree = self.tree_json(output_result, self._data_frame)
self.generate_probabilities(decision_tree, measures)
decision_tree_result.set_params(self._new_tree, self._new_rules, self._total, self._success, self._probability)
return decision_tree_result
def trainEvaluateModel(trainData, validationData,
impurityParm, maxDepthParm, maxBinsParm):
startTime = time()
model = DecisionTree.trainRegressor(trainData,
categoricalFeaturesInfo={},
impurity=impurityParm,
maxDepth=maxDepthParm,
maxBins=maxBinsParm)
RMSE = evaluateModel(model, validationData)
duration = time() - startTime
print "訓練評估：使用參數" + \
" impurityParm= %s" % impurityParm + \
" maxDepthParm= %s" % maxDepthParm + \
" maxBinsParm = %d." % maxBinsParm + \
" 所需時間=%d" % duration + \
" 結果RMSE = %f " % RMSE
return (RMSE, duration, impurityParm, maxDepthParm, maxBinsParm, model)
def dealData(path):
rawData = sc.textFile(path + 'hour.csv')
header = rawData.first()
rData = rawData.filter(lambda x: x != header)
lines = rData.map(lambda x: x.split(","))
labelpointRDD = lines.map(
lambda r: LabeledPoint(process_label(r), process_features(r)))
print(labelpointRDD.first())
# 划分训练集、验证集和测试集
(trainData, validationData,
testData) = labelpointRDD.randomSplit([7, 1, 2])
print("训练集样本个数：" + str(trainData.count()) + " 验证集样本个数：" +
str(validationData.count()) + " 测试集样本个数：" + str(testData.count()))
# 将数据暂存在内存中，加快后续运算效率
trainData.persist()
validationData.persist()
testData.persist()
model = DecisionTree.trainRegressor(trainData,
categoricalFeaturesInfo={},
impurity="variance",
maxDepth=5,
maxBins=32,
minInstancesPerNode=1,
minInfoGain=0.0)
rmse = RMSE(model, validationData)
print("均方误差RMSE=" + str(rmse))
## 评估参数 maxDepth
maxDepthList = [3, 5, 10, 15, 20, 25]
maxBinsList = [10]
minInstancesPerNodeList = [1]
minInfoGainList = [0.0]
## 返回结果存放至metries中
metrics = [
trainEvaluateModel(trainData, validationData, maxDepth, maxBins,
minInstancesPerNode, minInfoGain)
for maxDepth in maxDepthList for maxBins in maxBinsList
for minInstancesPerNode in minInstancesPerNodeList
for minInfoGain in minInfoGainList
]
def test_regression(self):
from pyspark.mllib.regression import (
LinearRegressionWithSGD,
LassoWithSGD,
RidgeRegressionWithSGD,
)
from pyspark.mllib.tree import DecisionTree
data = [
LabeledPoint(-1.0, self.scipy_matrix(2, {1: -1.0})),
LabeledPoint(1.0, self.scipy_matrix(2, {1: 1.0})),
LabeledPoint(-1.0, self.scipy_matrix(2, {1: -2.0})),
LabeledPoint(1.0, self.scipy_matrix(2, {1: 2.0})),
]
rdd = self.sc.parallelize(data)
features = [p.features 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)
def trainEvaluateModel(trainData, validationData, maxDepthParm, maxBinsParm,
minInstancesPerNodeParm, minInfoGainParm):
startTime = time.time()
# 创建并训练模型
model = DecisionTree.trainRegressor(
trainData,
categoricalFeaturesInfo={},
impurity="variance",
maxDepth=maxDepthParm,
maxBins=maxBinsParm,
minInstancesPerNode=minInstancesPerNodeParm,
minInfoGain=minInfoGainParm)
# 计算RMSE
rmse = RMSE(model, validationData)
duration = time.time() - startTime # 持续时间
print("训练评估：参数" + ", maxDepth=" + str(maxDepthParm) + ", maxBins=" +
str(maxBinsParm) + ", minInstancesPerNode=" +
str(minInstancesPerNodeParm) + ", minInfoGainParm=" +
str(minInfoGainParm) + "\n"
"===>消耗时间=" + str(duration) + ", 均方误差RMSE=" + str(rmse))
return rmse, duration, maxDepthParm, maxBinsParm, minInstancesPerNodeParm, minInfoGainParm, model
def train_model():
data = get_dataset()
(trainingData, testData) = data.randomSplit([0.7, 0.3])
metrics_combos = []
bins = [x for x in range(50, 500, 10)]
depths = [x for x in range(4, 12)]
for numBin in bins:
for depth in depths:
model = DecisionTree.trainRegressor(trainingData,
categoricalFeaturesInfo={},
impurity='variance',
maxDepth=depth,
maxBins=numBin)
predictions = model.predict(testData.map(lambda x: x.features))
labelsAndPredictions = testData.map(lambda lp: lp.label).zip(
predictions)
metrics = RegressionMetrics(labelsAndPredictions)
metrics_combos.append(((numBin, depth), metrics.meanSquaredError))
print(sorted(metrics_combos, key=lambda s: s[1]))
def test_regression(self):
from pyspark.mllib.regression import LinearRegressionWithSGD, LassoWithSGD, \
RidgeRegressionWithSGD
from pyspark.mllib.tree import DecisionTree
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)
def test_regression(self):
from pyspark.mllib.regression import LinearRegressionWithSGD, LassoWithSGD, \
RidgeRegressionWithSGD
from pyspark.mllib.tree import DecisionTree
data = [
LabeledPoint(-1.0, self.scipy_matrix(2, {1: -1.0})),
LabeledPoint(1.0, self.scipy_matrix(2, {1: 1.0})),
LabeledPoint(-1.0, self.scipy_matrix(2, {1: -2.0})),
LabeledPoint(1.0, self.scipy_matrix(2, {1: 2.0}))
]
rdd = self.sc.parallelize(data)
features = [p.features 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)
def getPredictionsLabels(model, test):
predictions = model.predict(test.map(lambda r: r.features))
return predictions.zip(test.map(lambda r: r.label))
def printMetrics(predictions_and_labels):
metrics = RegressionMetrics(predictions_and_labels)
f.write('Explained Variance:{0}\n'.format(metrics.explainedVariance))
f.write('Mean Absolute Error:{0}\n'.format(metrics.meanAbsoluteError))
f.write('Mean Squared Error:{0}\n'.format(metrics.meanSquaredError))
f.write('Root Mean Squared Error:{0}\n'.format(
metrics.rootMeanSquaredError))
f.write('R^2 :{0}\n'.format(metrics.r2))
for j in range(numModels):
regp = paramGrid[j]['regParam']
iters = paramGrid[j]['iterations']
regt = paramGrid[j]['regType']
con = paramGrid[j]['convergenceTol']
#f.write('Model{0}: regParam = {1}, iterations = {2}, regType = {3}, convergenceTol = {4}\n'.format(str(j), regp, iters, regt, con))
# Train decision tree regression model with hypermarameter set
model = DecisionTree.trainRegressor(training, categoricalFeaturesInfo = {}, impurity='variance', \
maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0)
predictions_and_labels = getPredictionsLabels(model, test)
printMetrics(predictions_and_labels)
f.close()
sc.stop()
#ArrDelay is our response
#ArrDelay becomes the 8tth column now, and total columns in the data = 12
label = clean_line_split[0]
nonLable = clean_line_split[1:]
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])
#start timer at this point
startTime = datetime.now()
#build the model
#empty categoricalFeaturesInfo indicates all features are continuous.
model = DecisionTree.trainRegressor (training, categoricalFeaturesInfo={},
impurity='variance', maxDepth=5, maxBins=32)
#evaluate model on test instances and compute test error
predictions = model.predict (test.map (lambda x: x.features))
labelsAndPredictions = test.map (lambda lp: lp.label).zip (predictions)
testMSE = labelsAndPredictions.map (lambda (v, p): (v - p) * (v - p)).sum() /\
float(testData.count())
print ('Time consumed = '), (datetime.now() - startTime)
print ('Test Mean Squared Error = ' + str (testMSE))
print ('Learned regression tree model:')
print (model.toDebugString())
#save and load model
model.save (sc, "DTR-Narrow-2008")
# get 90% train and 10% test data
data_with_idx = data_dt.zipWithIndex().map(lambda (k, v): (v, k))
test = data_with_idx.sample(False, 0.1)
train = data_with_idx.subtractByKey(test)
train_data = train.map(lambda (idx, p): p)
test_data = test.map(lambda (idx, p): p)
train_size = train_data.count()
test_size = test_data.count()
print "Training data size: %d" % train_size
print "Test data size: %d" % test_size
print "Total data size: %d " % num_data
print "Train + Test size : %d" % (train_size + test_size)
# make decision tree model
dt_model = DecisionTree.trainRegressor(train_data, {})
# make predictions and measure error
preds = dt_model.predict(test_data.map(lambda p: p.features))
actual = test_data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print "Decision Tree predictions: " + str(true_vs_predicted_dt.take(5))
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
def squared_error(actual, pred):
return (pred - actual)**2
def squared_log_error(pred, actual):
from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
from pyspark.mllib.util import MLUtils
sc = SparkContext(appName="PythonWordCount")
data = MLUtils.loadLibSVMFile(sc, '/usr/hadoop/para_avg_halfsqrsum.txt')
traindata = MLUtils.loadLibSVMFile(sc, '/usr/hadoop/train_para.txt')
data_720 = MLUtils.loadLibSVMFile(sc,
'/usr/hadoop/para_avg_halfsqrsum_720.txt')
data_540 = MLUtils.loadLibSVMFile(sc,
'/usr/hadoop/para_avg_halfsqrsum_540.txt')
data_360 = MLUtils.loadLibSVMFile(sc,
'/usr/hadoop/para_avg_halfsqrsum_360.txt')
model = DecisionTree.trainRegressor(traindata,
categoricalFeaturesInfo={},
impurity='variance',
maxDepth=5,
maxBins=32)
predictions = model.predict(data.map(lambda x: x.features))
labelsandpredictions = data.map(lambda lp: lp.label).zip(predictions)
MSE = labelsandpredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(
data.count())
print("training MSE = " + str(MSE))
#labelsandpredictions.saveAsTextFile("/usr/hadoop/hf_dt")
predictions_720 = model.predict(data_720.map(lambda x: x.features))
labelsandpredictions_720 = data_720.map(lambda lp: lp.label).zip(
predictions_720)
MSE_720 = labelsandpredictions_720.map(lambda (v, p): (v - p) *
(v - p)).sum() / float(data_720.count())
print("training MSE_720 = " + str(MSE_720))
data_dt = records.map(lambda r: LabeledPoint(extract_label(r), extract_features_dt(r)))
first_point_dt = data_dt.first()
first_point_dt.label
first_point_dt.features
len(first_point_dt.features)
from pyspark.mllib.regression import LinearRegressionWithSGD
from pyspark.mllib.tree import DecisionTree
linear_model = LinearRegressionWithSGD.train(data, iterations=10, step=0.1, intercept=False)
true_vs_predicted = data.map(lambda p: (p.label, linear_model.predict(p.features)))
true_vs_predicted.take(5)
dt_model = DecisionTree.trainRegressor(data_dt, {})
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data_dt.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
true_vs_predicted_dt.take(5)
dt_model.depth()
dt_model.numNodes()
def squared_error(actual, pred):
return (pred - actual) ** 2
def abs_error(actual, pred):
return np.abs(pred - actual)
def squared_log_error(actual, pred):
return (np.log(pred + 1) - np.log(actual + 1)) ** 2
true_vs_predicted.map(lambda t: squared_error(t[0], t[1])).mean()
def learn(examples,depth,bin):
global model
model = DecisionTree.trainRegressor(examples, categoricalFeaturesInfo={},
impurity='variance', maxDepth=depth, maxBins=bin)
def evaluate_dt(train, test, maxDepth, maxBins):
dt_model = DecisionTree.trainRegressor(train, categoricalFeaturesInfo={0:4},impurity='variance', maxDepth=maxDepth, maxBins=maxBins)
dt_predictions = dt_model.predict(test.map(lambda x: x.features))
dt_labelsAndPredictions = test.map(lambda lp: lp.label).zip(dt_predictions)
dt_testMSE = dt_labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(testData.count())
return dt_testMSE
# get 90% train and 10% test data
data_with_idx = data_dt.zipWithIndex().map(lambda (k, v): (v, k))
test = data_with_idx.sample(False, 0.1)
train = data_with_idx.subtractByKey(test)
train_data = train.map(lambda (idx, p): p)
test_data = test.map(lambda (idx, p) : p)
train_size = train_data.count()
test_size = test_data.count()
print "Training data size: %d" % train_size
print "Test data size: %d" % test_size
print "Total data size: %d " % num_data
print "Train + Test size : %d" % (train_size + test_size)
# make decision tree model
dt_model = DecisionTree.trainRegressor(train_data,{})
# make predictions and measure error
preds = dt_model.predict(test_data.map(lambda p: p.features))
actual = test_data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print "Decision Tree predictions: " + str(true_vs_predicted_dt.take(5))
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
def squared_error(actual, pred):
return (pred - actual)**2
def squared_log_error(pred, actual):
return (np.log(pred + 1) - np.log(actual + 1))**2
# MAGIC %md DecisionTree performs best when it is told which features are categorical. We constructor a map categoricalFeaturesInfo to pass this information to DecisionTree.
# MAGIC If DecisionTree is not given this info, then it will treat all features as continuous.
# COMMAND ----------
# Construct a map for categorical features:
# categoricalFeaturesInfo[column index] = number of categories
categoricalFeaturesInfo = {}
for j in xrange(numFeatures):
col = featureCols[j]
if col in categoryIndexes:
categoricalFeaturesInfo[j] = len(categoryIndexes[col])
# COMMAND ----------
initialModel = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo)
initialModel
# COMMAND ----------
# We can print the full model, but it can be hard to parse when the tree is large.
print initialModel.toDebugString()
# COMMAND ----------
# MAGIC %md We now compute the error of the DecisionTreeModel on the training dataset. We use Root Mean Squared Error (RMSE) as our error metric.
# MAGIC
# MAGIC Denote (y_i, x_i) as the (label, feature vector) for instance i, and write model.predict(x_i) as our model's predicted label for instance i. RMSE is defined as:
# MAGIC
# MAGIC %[ RMSE(dataset) = \left[ \mathbf{avg}_{(y_i, x_i) \in dataset} \left( y_i - model.predict(x_i) \right)^2 \right]^{1/2} ]%
def run_decision_tree(userid):
conf = SparkConf().setMaster("local[1]").setAppName("heart-disease-prediction-descision-tree")
sc = SparkContext(conf=conf)
print "Running Spark Version %s" % (sc.version)
# https://archive.ics.uci.edu/ml/machine-learning-databases/heart-disease/processed.cleveland.data
path = "/home/raju/Documents/hdp_proj"
heartdf_tr = pd.read_csv(path+"processed.cleveland.data.csv",header=None)
heartdf_test = pd.read_csv(path+"testdata.csv",header=None)
print "Original training Dataset (Rows:Colums): "
print heartdf_tr.shape
print heartdf_test.shaperead_csvread_csvread_csv
print "Categories of Diagnosis of heart disease (angiographic disease status) that we are predicting"
print "-- Value 0: < 50% diameter narrowing"
print "-- Value 1: > 50% diameter narrowing "
print heartdf_tr.ix[:,13].unique() #Column containing the Diagnosis of heart disease
print heartdf_test.ix[:,13].unique() #Column containing the Diagnosis of heart disease
newheartdf = pd.concat([heartdf_tr.ix[:,13], heartdf_tr.ix[:,0:12]],axis=1, join_axes=[heartdf_tr.index])
newheartdf_test = pd.concat([heartdf_test.ix[:,13], heartdf_test.ix[:,0:12]],axis=1, join_axes=[heartdf_test.index])
newheartdf.replace('?', np.nan, inplace=True) # Replace ? values
newheartdf_test.replace('?', np.nan, inplace=True) # Replace ? values
print "After dropping rows with anyone empty value (Rows:Columns): "
ndf2 = newheartdf.dropna()
ndf_test = newheartdf_test.dropna()
ndf2.to_csv(path+"new-heart-disease-cleaveland.txt",sep=",",index=False,header=None,na_rep=np.nan)
ndf_test.to_csv(path+"new-heart-disease-cleaveland-test.txt",sep=",",index=False,header=None,na_rep=np.nan)
print ndf2.shape
print ndf_test.shape
print ndf2.ix[:5,:]
print ndf_test.ix[:5,:]
print "Create a Labeled point which is a local vector, associated with a label/response"
points = sc.textFile(path+'new-heart-disease-cleaveland.txt')
points_test = sc.textFile(path+'new-heart-disease-cleaveland-test.txt')
print "###############################Something"
parsed_data = points.map(parsePoint)
parsed_data_test = points_test.map(parsePoint)
print 'After parsing, number of training lines: %s' %parsed_data.take(5) #parsed_data.count()
print 'After parsing, number of test data lines: %s' %parsed_data_test.take(5) #parsed_data.count()
#####Perform Classification using a Decision Tree#####
# Split the data into training and test sets (30% held out for testing)
(trainingData, trainingData1) = parsed_data.randomSplit([1,0])
(testData , testData1) = parsed_data_test.randomSplit([1,0])
# Train a DecisionTree model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
print "+++++++++++++++++++++++++++++++++ Perform Classification using a Decision Tree +++++++++++++++++++++++++++++++++"
model = DecisionTree.trainClassifier(trainingData, numClasses=5, categoricalFeaturesInfo={}, 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))
print('=================== Learned classification tree model ====================')
print(model.toDebugString())
print "+++++++++++++++++++++++++++++++++ Perform Regression using a Decision Tree +++++++++++++++++++++++++++++++++"
model1 = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={}, impurity='variance', maxDepth=4, maxBins=32)
####### Evaluate model on test instances and compute test error########
predictions = model1.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 tree model ====================')
print(model1.toDebugString())
print(userid)
input_data = get_input_data(userid[-20:-2])
#features = vector.dense(result)
prediction_value = model1.predict(input_data)
print(prediction_value)
post_prediction(userid[-20:-2],prediction_value)
from pyspark.mllib.tree import DecisionTree
def loadRecord(line):
input = StringIO.StringIO(line)
reader = csv.reader(input)
row = map(float, reader.next())
return LabeledPoint(row[-1],row[:-1])
chf = open('data/CAhousing.csv','r')
header = chf.next().rstrip("\n").split(",")
for i,j in enumerate(header):
print "%d: %s" % (i,j)
chrdd = sc.parallelize(chf).map(lambda line: loadRecord(line))
chrdd.persist()
(trainingData, testData) = chrdd.randomSplit([0.7, 0.3])
model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={},
impurity='variance', minInstancesPerNode=2500)
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())
with open("trunk.txt", "w") as f:
f.write('Test Mean Squared Error = ' + str(testMSE))
f.write('Learned regression tree model:')
f.write( model.toDebugString() )
data = records.map(
lambda r: LabeledPoint(extract_label(r), extract_features(r)))
first_point = data.first()
print("Raw data :")
print(first[2:])
print("Label")
print(first_point.label)
print("decision tree model feature vector :")
print(first_point.features)
print("decision tree model feature vector length :" +
str(len(first_point.features)))
#
dt_model = DecisionTree.trainRegressor(data, {})
preds = dt_model.predict(data.map(lambda d: d.features))
actual = data.map(lambda d: d.label)
true_vs_predicted = actual.zip(preds)
print("decision tree prediction :" + str(true_vs_predicted.take(5)))
print("decision tree depth :" + str(dt_model.depth()))
print("decision tree number of nodes :" + str(dt_model.numNodes()))
#
def squared_error(actual, prediction):
return (actual - prediction)**2
def abs_error(actual, prediction):
return np.abs(actual - prediction)
from sklearn.cross_validation import LeaveOneOut
from sklearn.cross_validation import KFold
# Kfold
if __name__ == "__main__":
sc = SparkContext('local',appName="Prediction")
import fileinput
data_y1, data_y2 = [], []
for line in fileinput.input("data/feature_extracted_class3.txt"):
data_y1.append(LabeledPoint(float(1 if int(line.split("\t")[2])!=0 else 0), [float(i) for i in line.split("\t")[3:]]))
data_y2.append(LabeledPoint(int(line.split("\t")[2]), [float(i) for i in line.split("\t")[3:]]))
total, right, mse = 0, 0, []
for t in xrange(10):
kf = KFold(32*40, n_folds=10)
for train, test in kf:
data_train_y1, data_train_y2 = [], []
for i in train:
data_train_y1.append(data_y1[i])
data_train_y2.append(data_y2[i])
clf1 = DecisionTree.trainClassifier(sc.parallelize(data_train_y1), numClasses=2, categoricalFeaturesInfo={}, impurity='gini', maxDepth=5, maxBins=100)
clf2 = DecisionTree.trainRegressor(sc.parallelize(data_train_y2), categoricalFeaturesInfo={}, impurity='variance', maxDepth=5, maxBins=100)
for i in test:
data_test_y1, data_test_y2 = data_y1[i], data_y2[i]
r1 = clf1.predict(data_test_y1.features)
r2 = clf2.predict(data_test_y2.features)
if r1 == data_test_y1.label:
right += 1
mse.append(abs(r2-data_test_y2.label))
total += 1
print float(right)/total, sum(mse)/len(mse)
print "Decision Tree feature vector length: " + str(
len(first_point_tree.features))
# In[167]:
from pyspark.mllib.tree import DecisionTree
#from the RDD sample 20% for training and rest for test
records_tree_with_idx = data_tree.zipWithIndex().map(lambda (k, v): (v, k))
test_tree_idx = records_tree_with_idx.sample(False, 0.2, 42)
training_tree_idx = records_tree_with_idx.subtractByKey(test_tree_idx)
test_tree = test_tree_idx.map(lambda (idx, p): p)
training_tree = training_tree_idx.map(lambda (idx, p): p)
model_tree = DecisionTree.trainRegressor(training_tree, {})
preds_tree = model_tree.predict(test_tree.map(lambda p: p.features))
actual_tree = test_tree.map(lambda p: p.label)
true_vs_predicted_tree = actual_tree.zip(preds_tree)
print "Decision Tree predictions: " + str(true_vs_predicted_tree.take(5))
print "Decision Tree depth: " + str(model_tree.depth())
print "Decision Tree number of nodes: " + str(model_tree.numNodes())
# In[177]:
mse_tree = true_vs_predicted_tree.map(lambda
(t, p): squared_error(t, p)).mean()
mae_tree = true_vs_predicted_tree.map(lambda (t, p): abs_error(t, p)).mean()
help(DecisionTree.trainRegressor)
# ## Train a Regression Model on the Bike Sharing Dataset
# In[9]:
linear_model = LinearRegressionWithSGD.train(data, iterations=10, step=0.1, intercept=False)
true_vs_predicted = data.map(lambda p: (p.label, linear_model.predict(p.features)))
print "Linear Model predictions: " + str(true_vs_predicted.take(5))
# In[10]:
# we pass in an mepty mapping for categorical feature size {}
dt_model = DecisionTree.trainRegressor(data_dt, {})
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print "Decision Tree predictions: " + str(true_vs_predicted_dt.take(5))
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
# ## Perfomance Metrics
# In[11]:
# set up performance metrics functions
def squared_error(actual, pred):
def extract_label(record):
return float(record[17])
data_dt = RDD.map(lambda r: LabeledPoint(extract_label(r),extract_features_dt(r)))
first_point_dt = data_dt.first()
print "Decision Tree feature vector: " + str(first_point_dt.features)
print "Decision Tree feature vector length: " + str(len(first_point_dt.features))
training_dt, test_dt = data_dt.randomSplit([0.9, 0.1])
print "trainging_dt count = ", training_dt.count()
print "test_dt count = ", test_dt.count()
print "###########Start decision tree using Spark MLLib ################"
from pyspark.mllib.tree import DecisionTree
dt_model = DecisionTree.trainRegressor(training_dt,{})
preds = dt_model.predict(test_dt.map(lambda p: p.features))
actual = test_dt.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print "Decision Tree predictions: " + str(true_vs_predicted_dt.collect())
print "Decision Tree depth: " + str(dt_model.depth())
print "Decision Tree number of nodes: " + str(dt_model.numNodes())
# data_dt.saveAsTextFile("file:///home/cloudera/MMZ/FinalProject/temp/temp_training_data_dt")
def squared_error(actual, pred): # Mean Squared Error (MSE)
return (pred - actual)**2
def abs_error(actual, pred): # Mean Absolute Error (MAE)
return np.abs(pred - actual)
def squared_log_error(pred, actual): # Root Mean Squared Log Error (RMSE)
return (np.log(pred + 1) - np.log(actual + 1))**2
mse_dt = true_vs_predicted_dt.map(lambda (t, p): squared_error(t, p)).mean()
summary = Statistics.colStats(testvecData)
variance = summary.variance()[0]
# compute the pseudo R-square
test_Rsqr1 = 1 - testMSE1/float(variance)
# Train a DecisionTree model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
# use variance as impurity for regression
# maxDepth is the maximum number of level for each tree
model2 = DecisionTree.trainRegressor(trainparsedData
, categoricalFeaturesInfo={}
, impurity='variance'
, maxDepth=8
, maxBins=32)
# evaluate the training error
# first make the prediction and create a new "vector" of all the predictions
trainpredictions = model2.predict(trainparsedData.map(lambda x: x.features))
# then you column bind the prediction and actual values into a new RDD
trainlabelsAndPredictions = trainparsedData.map(lambda lp: lp.label).zip(trainpredictions)
# use map operation to compute MSE
trainMSE2 = trainlabelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(trainparsedData.count())
# use the the Statistics library to obtain the variance
summary = Statistics.colStats(trainvecData)
variance = summary.variance()[0]
# In[22]:
for i,x in enumerate(features): print i,x
# In[23]:
# Split the data into training and test sets (30% held out for testing)
(trainingData, testData) = d2.randomSplit([0.7, 0.3])
# Train a DecisionTree model.
# Empty categoricalFeaturesInfo indicates all features are continuous.
model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={},
impurity="variance", maxDepth=6, 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)
testMSE = labelsAndPredictions.map(lambda (v, p): (v - p) * (v - p)).sum() / float(testData.count())
print('Test Mean Squared Error = ' + str(testMSE))
print('Learned regression tree model:')
print(model.toDebugString())
# In[24]:
#
plt.xlabel("response")
plt.ylabel("prediction")
print '决策树特征向量长度: ' + str(len(first_point_dt.features))
from pyspark.mllib.regression import LinearRegressionWithSGD
from pyspark.mllib.tree import DecisionTree
help(LinearRegressionWithSGD.train)
linear_model = LinearRegressionWithSGD.train(data,
iterations=10,
step=0.1,
intercept=False)
true_vs_predicted = data.map(
lambda point: (point.label, linear_model.predict(point.features)))
print '线性回归模型对前5个样本的预测值: ' + str(true_vs_predicted.take(5))
dt_model = DecisionTree.trainRegressor(data_dt, {})
preds = dt_model.predict(data_dt.map(lambda p: p.features))
actual = data.map(lambda p: p.label)
true_vs_predicted_dt = actual.zip(preds)
print '决策树回归模型对前5个样本的预测值: ' + str(true_vs_predicted_dt.take(5))
print '决策树模型的深度: ' + str(dt_model.depth())
print '决策树模型的叶子节点个数: ' + str(dt_model.numNodes())
def squared_error(actual, pred):
return (pred - actual)**2
def abs_error(actual, pred):
return np.abs(pred - actual)
