def test_rest(x, y):
print('Random under-sampling')
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
print('Tomek links')
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
print('Clustering centroids')
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
print('NearMiss-1')
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
print('NearMiss-2')
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
print('NearMiss-3')
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
print('Neighboorhood Cleaning Rule')
NCR = NeighbourhoodCleaningRule(verbose=verbose)
ncrx, ncry = NCR.fit_transform(x, y)
print('Random over-sampling')
OS = OverSampler(verbose=verbose)
ox, oy = OS.fit_transform(x, y)
print('SMOTE Tomek links')
STK = SMOTETomek(verbose=verbose)
stkx, stky = STK.fit_transform(x, y)
print('SMOTE ENN')
SENN = SMOTEENN(verbose=verbose)
sennx, senny = SENN.fit_transform(x, y)
print('EasyEnsemble')
EE = EasyEnsemble(verbose=verbose)
eex, eey = EE.fit_transform(x, y)
def clustering_centroids(self):
# 'Clustering centroids'
CC = ClusterCentroids(verbose=self.verbose)
ccx, ccy = CC.fit_transform(self.x, self.y)
print "Clustering Centroids Transformed"
return ccx, ccy
plt.scatter(x_vis[y==1, 0], x_vis[y==1, 1], label="Class #1", alpha=0.5,
edgecolor=almost_black, facecolor='blue', linewidth=0.15)
plt.legend()
plt.show()
# Generate the new dataset using under-sampling method
verbose = False
# 'Random under-sampling'
US = UnderSampler(verbose=verbose)
usx, usy = US.fit_transform(x, y)
# 'Tomek links'
TL = TomekLinks(verbose=verbose)
tlx, tly = TL.fit_transform(x, y)
# 'Clustering centroids'
CC = ClusterCentroids(verbose=verbose)
ccx, ccy = CC.fit_transform(x, y)
# 'NearMiss-1'
NM1 = NearMiss(version=1, verbose=verbose)
nm1x, nm1y = NM1.fit_transform(x, y)
# 'NearMiss-2'
NM2 = NearMiss(version=2, verbose=verbose)
nm2x, nm2y = NM2.fit_transform(x, y)
# 'NearMiss-3'
NM3 = NearMiss(version=3, verbose=verbose)
nm3x, nm3y = NM3.fit_transform(x, y)
# 'Condensed Nearest Neighbour'
CNN = CondensedNearestNeighbour(size_ngh=51, n_seeds_S=51, verbose=verbose)
cnnx, cnny = CNN.fit_transform(x, y)
# 'One-Sided Selection'
OSS = OneSidedSelection(size_ngh=51, n_seeds_S=51, verbose=verbose)
def main(argv):
X=np.load('numdata/epochFeats.npy')
Y=np.load('numdata/epochLabels.npy')
labels= np.load('numdata/LOO.npy')
print(X.shape,Y.shape)
X,Y = deleteClass(X,Y,330,2)
X,Y = deleteClass(X,Y,70,1)
if sys.argv[1]=='-first':
print(X.shape, Y.shape, labels.shape)
folds=10
#Pipeline stuff
forest = RandomForestRegressor(n_estimators=100, n_jobs = -1)
scaler = preprocessing.StandardScaler()
lolo = LeaveOneLabelOut(labels)
print(lolo,len(lolo))
acc = 0
us = UnderSampler(verbose=True)
#X,Y = us.fit_transform(X,Y)
kf = KFold(Y.shape[0],n_folds=folds)
for train_index,test_index in lolo:
print(len(train_index),len(test_index))
Xtrain,Xtest = X[train_index], X[test_index]
ytrain,ytest = Y[train_index], Y[test_index]
forest.fit(Xtrain,ytrain)
scores = forest.predict(Xtest)
#acc += tolAcc(ytest,scores)
print(acc/folds)
# Ensemble Random Forest Regressor stacked with Random Forest Classifier
elif sys.argv[1]=='-ensemble':
RF = []
outputRF = []
outRFtest=[]
us = UnderSampler(verbose=True)
cc = ClusterCentroids(verbose=True)
#X,Y = cc.fit_transform(X,Y)
print(X.shape,Y.shape)
# separating features into categories for Ensemble Training
activityData = X[:,0:3 ]
screenData = X[:,3:14]
conversationData = X[:,14:20 ]
colocationData = X[:,20:26]
audioData = X[:,26:X.shape[1]]
# Custom Nested Cross-Validation
# Indexes is used to split the dataset in a 40/40/20 manner
# NOTE: 30/30/40 seemed to produce very similar results
indexes = np.array([i for i in range(X.shape[0])])
np.random.shuffle(indexes)
lolo = LeaveOneLabelOut(labels)
# print(lolo,len(lolo))
# separating data to 3 subsets:
# 1) Train RF
# 2) Get RF outputs with which train NN
# 3) Test NN output on the rest
train_index = indexes[0: int(0.5*X.shape[0])]
train_index2 = indexes[int(0.5*X.shape[0]):int(0.8*X.shape[0])]
test_index = indexes[int(0.8*X.shape[0]):X.shape[0]]
print(len(train_index),len(train_index2),len(test_index ))
# Training 5 regressors on 5 types of features
i=0
for data in [activityData,screenData,conversationData,colocationData,audioData]:
RF.append(RandomForestRegressor(n_estimators=300,max_features=data.shape[1],n_jobs=-1))
RF[i].fit(data[train_index],Y[train_index])
outputRF.append( RF[i].predict(data[train_index2]) )
outRFtest.append(RF[i].predict(data[test_index]))
i += 1
middleTrainMat = np.transpose(np.array(outputRF))
testMat = np.transpose(np.array(outRFtest))
# RF classifier to combine regressors
class_weights={0 : 1, 1 : 0.5 , 2 : 0.1 , 3 : 0.6, 4 :1}
print(class_weights)
rfr= ExtraTreesClassifier(n_estimators=300,class_weight=class_weights,n_jobs=-1)
rfr.fit(middleTrainMat,Y[train_index2])
print(middleTrainMat.shape)
pred = rfr.predict(testMat)
# Print to screen mean error and Tolerance Score
print(tolAcc(Y[test_index],pred,testMat))
