def run_debuging_tests():
inf = open(sys.argv[1])
data = np.array(
[map(float,
s.strip().split(',')) for s in inf.readlines()])
# print data.shape[0]
data = np.random.permutation(data)
# compute how much of the data is training and testing
np.random.shuffle(data)
train_rows = int(0.6 * data.shape[0])
test_rows = data.shape[0] - train_rows
# separate out training and testing data
trainX = data[:train_rows, 0:-1]
trainY = data[:train_rows, -1]
testX = data[train_rows:, 0:-1]
testY = data[train_rows:, -1]
# create a learner and train it
learner = lrl.LinRegLearner(verbose=True) # create a LinRegLearner
run_learner(learner, trainX, trainY, testX, testY) # training step
learner = dt.DTLearner(leaf_size=1, verbose=False) # constructor
run_learner(learner, trainX, trainY, testX, testY) # training step
learner = rt.RTLearner(leaf_size=1, verbose=False) # constructor
run_learner(learner, trainX, trainY, testX, testY)
learner = bl.BagLearner(learner=lrl.LinRegLearner,
kwargs={},
bags=10,
boost=False,
verbose=False)
run_learner(learner, trainX, trainY, testX, testY)
learner = il.InsaneLearner(verbose=False)
run_learner(learner, trainX, trainY, testX, testY)
def insane():
import InsaneLearner as it
learner = it.InsaneLearner(verbose=False)
learner.addEvidence(trainX, trainY)
Y = learner.query(testX)
# create a learner and train it
if ltype == 0:
learner = lrl.LinRegLearner(verbose = True) # create a LinRegLearner
elif ltype == 1:
print ('Creating DTLearner')
learner = dtl.DTLearner(1,verbose=False)
elif ltype == 2:
print ('Creating RTLearner')
learner = rtl.RTLearner(1, verbose=False)
elif ltype == 3:
print ('Creating BAGLearner')
learner = bagl.BagLearner(dtl.DTLearner,kwargs = {"leaf_size":1},bags=15,verbose=False)
elif ltype == 4:
print ('Creating InsaneLearner')
learner = itl.InsaneLearner(verbose=False)
elif ltype == 5:
print ('Creating plot for DTlearner for overfitting vs leaf size')
leafSizePlot(dtl.DTLearner,trainX,trainY,testX,testY,"DTLearner",data,100)
elif ltype == 6:
print ('Creating plot for BagLearner for overfitting vs leaf size')
leafSizePlot(bagl.BagLearner,trainX,trainY,testX,testY,"BagLearner",data,25)
elif ltype == 7:
print('Calculating metrics')
calculateMetrics(data)
if(ltype in range(0,5)):
learner.addEvidence(trainX, trainY) # train it
print learner.author()
# evaluate in sample
# compute how much of the data is training and testing
train_rows = int(0.6 * data.shape[0])
#train_rows = int(data.shape[0])
test_rows = data.shape[0] - train_rows
# separate out training and testing data
trainX = data[:train_rows, 0:-1]
trainY = data[:train_rows, -1]
testX = data[train_rows:, 0:-1]
testY = data[train_rows:, -1]
print trainX.shape
#trainY = trainY.reshape(8,1)
# create a learner and train it
learner = il.InsaneLearner()
learner.addEvidence(trainX, trainY)
print learner.author()
# evaluate in sample
predY = learner.query(trainX) # get the predictions
print "PRED Y Shape: " + str(predY.shape)
print "TRAINX SHAPE: " + str(trainX.shape)
rmse = math.sqrt(((trainY - predY)**2).sum() / trainY.shape[0])
print
print "In sample results"
print "RMSE: ", rmse
c = np.corrcoef(predY, y=trainY)
print "corr: ", c[0, 1]
# evaluate out of sample
# compute how much of the data is training and testing
train_rows = int(0.6* data.shape[0])
test_rows = data.shape[0] - train_rows
# separate out training and testing data
trainX = data[:train_rows,0:-1]
trainY = data[:train_rows,-1]
testX = data[train_rows:,0:-1]
testY = data[train_rows:,-1]
print testX.shape
print testY.shape
# create a learner and train it; API for BagLearner
learner = it.InsaneLearner(verbose = False) # create a InsaneLearner
learner.addEvidence(trainX, trainY) # train it
print learner.author()
# evaluate in sample
predY = learner.query(trainX) # get the predictions
rmse = math.sqrt(((trainY - predY) ** 2).sum()/trainY.shape[0])
print
print "In sample results"
print "RMSE: ", rmse
c = np.corrcoef(predY, y=trainY)
print "corr: ", c[0,1]
# evaluate out of sample
predY = learner.query(testX) # get the predictions
rmse = math.sqrt(((testY - predY) ** 2).sum()/testY.shape[0])
import numpy as np
import InsaneLearner as it
if __name__ == '__main__':
data = np.genfromtxt('Data/best4lrr_data.csv', delimiter=',')
# np.random.shuffle(data) # Don't shuffle to compare output with single linreglearner
split = int(0.6 * data.shape[0]) # 60-40 break into train-test sets
trainX = data[:split, :-1]
trainY = data[:split, -1] # last column is labels
testX = data[split:, :-1]
testY = data[split:, -1] # last column is labels
learner = it.InsaneLearner(verbose=False) # constructor for InsaneLearner
learner.add_Evidence(trainX, trainY)
Y = learner.query(trainX) # get the predictions
rmse = np.sqrt(((Y - trainY)**2).sum() / trainY.shape[0])
corr = np.corrcoef(Y, trainY)
print("In sample results")
print("RMSE: ", rmse)
print("corr: ", corr[0, 1])
Y = learner.query(testX) # get the predictions
rmse = np.sqrt(((Y - testY)**2).sum() / testY.shape[0])
corr = np.corrcoef(Y, testY)
print
print("Out of sample results")
print("RMSE: ", rmse)
print("corr: ", corr[0, 1])
# DTlearner
# compute how much of the data is training and testing
train_rows = int(0.6 * data.shape[0])
test_rows = data.shape[0] - train_rows
# separate out training and testing data
trainX = data[:train_rows, 0:-1]
trainY = data[:train_rows, -1]
testX = data[train_rows:, 0:-1]
testY = data[train_rows:, -1]
print testX.shape
print testY.shape
# create a learner and train it
learner = it.InsaneLearner() # constructor
learner.addEvidence(trainX, trainY) # training step
Y = learner.query(testX) # query
print learner.author()
learner = lrl.LinRegLearner(verbose=True) # create a LinRegLearner
learner.addEvidence(trainX, trainY) # train it
pred = learner.query(trainX)
print learner.author()
# evaluate in sample
# predY = dt_learner.query(trainX) # get the predictions
rmse = math.sqrt(((trainY - pred)**2).sum() / trainY.shape[0])
print
print "In sample results"
print "RMSE: ", rmse
c = np.corrcoef(pred, y=trainY)