def experiment(train_file, test_file, predictor, ntrees, mtry, sample, ignores, parser_header, cpu_cores):
# Load train data
trainDataX = pandas.read_csv(train_file,header=0)
fmap = preprocessFrame(trainDataX)
predictorCol = trainDataX.columns[predictor]
trainDataY = array(trainDataX.pop(predictorCol))
trainDataX = array(popIgnores(trainDataX,ignores))
timeTrainRF = time()
rf = WiseRF(n_estimators=ntrees, n_jobs=cpu_cores)
rf.fit(trainDataX, trainDataY)
timeTrainRF = time() - timeTrainRF
# Validation
testDataX = pandas.read_csv(test_file,header=0)
preprocessFrame(testDataX,fmap)
predictorCol = testDataX.columns[predictor]
testDataY = array(testDataX.pop(predictorCol))
testDataX = array(popIgnores(testDataX,ignores))
timeTestRF = time()
predict = rf.predict(testDataX)
print predict
testScore = rf.score(testDataX,testDataY)
timeTestRF = time() - timeTestRF
print """
Train time: {0}
Test time: {1}
Err. rate: {2} %
Trees,Sample,Mtry,TrainTime,TestTime,OOB,ClassErr
{3},NA,NA,{0},{1},NA,{4}""".format(timeTrainRF, timeTestRF, 100*(1-testScore),ntrees,1-testScore)
def experiment(train_file, test_file, predictor, ntrees, mtry, sample, ignores,
parser_header, cpu_cores):
# Load train data
trainDataX = pandas.read_csv(train_file, header=0)
fmap = preprocessFrame(trainDataX)
predictorCol = trainDataX.columns[predictor]
trainDataY = array(trainDataX.pop(predictorCol))
trainDataX = array(popIgnores(trainDataX, ignores))
timeTrainRF = time()
rf = WiseRF(n_estimators=ntrees, n_jobs=cpu_cores)
rf.fit(trainDataX, trainDataY)
timeTrainRF = time() - timeTrainRF
# Validation
testDataX = pandas.read_csv(test_file, header=0)
preprocessFrame(testDataX, fmap)
predictorCol = testDataX.columns[predictor]
testDataY = array(testDataX.pop(predictorCol))
testDataX = array(popIgnores(testDataX, ignores))
timeTestRF = time()
predict = rf.predict(testDataX)
print predict
testScore = rf.score(testDataX, testDataY)
timeTestRF = time() - timeTestRF
print """
Train time: {0}
Test time: {1}
Err. rate: {2} %
Trees,Sample,Mtry,TrainTime,TestTime,OOB,ClassErr
{3},NA,NA,{0},{1},NA,{4}""".format(timeTrainRF, timeTestRF,
100 * (1 - testScore), ntrees,
1 - testScore)
X = np.concatenate([X] +
[np.apply_along_axis(rotate, 1, X, angle)
for angle in angles])
Y = np.concatenate([Y for _ in range(3)], axis=0)
return X, Y
train = np.genfromtxt('train.csv', delimiter=',')[1:]
target = train[:,0]
train = train[:,1:]
test = np.genfromtxt('test.csv', delimiter=',')[1:]
#%% Rotates and nudges dataset, trains predictor
ntrain,ntarget = rotate_dataset(train,target)
ntrain,ntarget = nudge_dataset(ntrain,ntarget)
wtrees = WiseRF(n_jobs=-1,n_estimators=512)
wtrees.fit(ntrain,ntarget)
wtrees.score(ntrain,ntarget)
result_svm_rbm = wtrees.predict(test)
#%%
f=open('result_wtrees.csv','w')
f.write('ImageId,Label\n')
count=1
for x in result_svm_rbm:
f.write('%d,%d\n' % (count,x))
count += 1
