def test_fit():
"""Test for fitting the model."""
X = rnd.randn(10, 2)
y = np.hstack((-np.ones((5, )), np.ones((5, ))))
Z = rnd.randn(10, 2) + 1
clf = SubspaceAlignedClassifier()
clf.fit(X, y, Z)
assert clf.is_trained
def test_subspace_alignment():
"""Test the alignment between datasets."""
X = rnd.randn(100, 10)
Z = np.dot(rnd.randn(100, 10), np.diag(np.arange(1, 11)))
clf = SubspaceAlignedClassifier()
V, CX, CZ = clf.subspace_alignment(X, Z, num_components=3)
assert not np.any(np.isnan(V))
assert CX.shape[1] == 3
assert CZ.shape[1] == 3
def main(source, target, model, target_train_ratio, random_state):
params = {
'source': source,
'target': target,
'target_train_ratio': target_train_ratio,
'max_features': 5000,
'random_state': random_state
}
params['partition'] = 'tr'
tr_X, tr_y = get_data(AmazonDatasetCombined(**params))
params['partition'] = 'te'
te_X, te_y = get_data(AmazonDatasetCombined(**params))
tr_y = tr_y.reshape(-1)
te_y = te_y.reshape(-1)
if model == 'lr':
C = 0.2
clf = LogisticRegression(solver='lbfgs', max_iter=1000, C=C)
clf.fit(tr_X, tr_y)
elif model == 'svm':
C = 0.2
clf = LinearSVC(C=C)
clf.fit(tr_X, tr_y)
elif model == 'kmm':
clf = ImportanceWeightedClassifier(iwe='kmm')
clf.fit(tr_X, tr_y, te_X)
elif model == 'suba-lr':
clf = SubspaceAlignedClassifier(loss='logistic')
clf.fit(tr_X, tr_y, te_X)
elif model == 'suba-hi':
clf = SubspaceAlignedClassifier(loss='hinge')
clf.fit(tr_X, tr_y, te_X)
elif model == 'tca-lr':
clf = TransferComponentClassifier(loss='logistic')
clf.fit(tr_X, tr_y, te_X)
elif model == 'tca-hi':
clf = TransferComponentClassifier(loss='hinge')
clf.fit(tr_X, tr_y, te_X)
else:
raise Exception('Unknown model called..')
tr_score = accuracy_score(tr_y, clf.predict(tr_X))
te_score = accuracy_score(te_y, clf.predict(te_X))
return tr_score, te_score
def test_predict():
"""Test for making predictions."""
X = rnd.randn(10, 2)
y = np.hstack((-np.ones((5, )), np.ones((5, ))))
Z = rnd.randn(10, 2) + 1
clf = SubspaceAlignedClassifier()
clf.fit(X, y, Z)
u_pred = clf.predict(Z)
labels = np.unique(y)
assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0
def apply_ENSEMBLE(trainX, trainY, testX, testY, window, source_pos, target_pos):
classifier_SA_DT = SubspaceAlignedClassifier(loss="dtree")
classifier_SA_LR = SubspaceAlignedClassifier(loss="logistic")
classifier_SA_NB = SubspaceAlignedClassifier(loss="berno")
classifier_TCA_DT = TransferComponentClassifier(loss="dtree")
classifier_TCA_LR = TransferComponentClassifier(loss="logistic")
classifier_TCA_NB = TransferComponentClassifier(loss="berno")
classifier_NN_DT = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier_NN_LR = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier_NN_NB = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier_KMM_DT = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier_KMM_LR = ImportanceWeightedClassifier(iwe='kmm', loss="logistic")
classifier_KMM_NB = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
#
eclf = EnsembleClassifier(clfs=[
#classifier_SA_DT,
#classifier_SA_LR,
#classifier_SA_NB,
#classifier_TCA_DT,
#classifier_TCA_LR,
classifier_TCA_NB,
classifier_NN_DT,
#classifier_NN_LR,
#classifier_NN_NB,
classifier_KMM_DT,
classifier_KMM_LR,
#classifier_KMM_NB
])
eclf.fit(trainX, trainY, testX)
pred = eclf.predict(testX)
acc_ENSEMBLE, acc_ENSEMBLE_INFO = check_accuracy(testY, pred)
#
return pd.DataFrame(
[{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_ENSEMBLE': acc_ENSEMBLE,
'acc_ENSEMBLE_INFO': acc_ENSEMBLE_INFO,
}]
)
def model_build(classifier, trian_features, train_labels, test_features):
if classifier == "IW":
# Call an importance-weighted classifier
# pipe = make_pipeline(StandardScaler(), ImportanceWeightedClassifier(iwe='nn'))
# param_grid = [{}]
# model = GridSearchCV(pipe, param_grid, cv=3)
# model.fit(trian_features, train_labels, test_features)
# print(model.best_params_)
model = ImportanceWeightedClassifier(iwe='kmm')
model.fit(preprocessing.scale(trian_features), train_labels,
preprocessing.scale(test_features))
elif classifier == "SUBA":
# Classifier based on subspace alignment
model = SubspaceAlignedClassifier(loss_function='logistic')
model.fit(preprocessing.scale(trian_features), train_labels,
preprocessing.scale(test_features))
elif classifier == "TCPR":
# Target Contrastive Pessimistic Classifier
model = TargetContrastivePessimisticClassifier(l2=0.1)
model.fit(preprocessing.scale(trian_features), train_labels,
preprocessing.scale(test_features))
else:
if classifier == "LR":
pipe = make_pipeline(StandardScaler(), LogisticRegression())
param_grid = [{'logisticregression__C': [1, 10, 100]}]
elif classifier == "SVM":
# pipe = make_pipeline(StandardScaler(), LinearSVC(random_state=0, tol=1e-5)) SVC(kernel='linear',probability=True)
pipe = make_pipeline(StandardScaler(),
SVC(kernel='linear', probability=True))
param_grid = [{'svc__C': [0.01, 0.1, 1]}]
elif classifier == "RF":
pipe = make_pipeline(StandardScaler(),
RandomForestClassifier(max_features='sqrt'))
param_grid = {
'randomforestclassifier__n_estimators': range(230, 300, 10),
'randomforestclassifier__max_depth': range(8, 12, 1),
'randomforestclassifier__min_samples_leaf': range(1, 5, 1),
'randomforestclassifier__max_features': range(1, 20, 1)
# 'learning_rate': np.linspace(0.01, 2, 20),
# 'subsample': np.linspace(0.7, 0.9, 20),
# 'colsample_bytree': np.linspace(0.5, 0.98, 10),
# 'min_child_weight': range(1, 9, 1)
}
model = GridSearchCV(pipe, param_grid, cv=3)
model.fit(trian_features, train_labels)
print(model.best_params_)
# save the model
model_file_name = classifier + time.strftime("%m%d-%H%M%S") + ".model"
joblib.dump(filename=model_file_name, value=model)
return model
def apply_SA(trainX, trainY, testX, testY, window, source_pos, target_pos):
# Decision Tree
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_SA, acc_DT_SA_INFO = check_accuracy(testY, pred_naive)
# Logistic Regression
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_SA, acc_LR_SA_INFO = check_accuracy(testY, pred_naive)
# Naive Bayes Bernoulli
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_SA, acc_NB_SA_INFO = check_accuracy(testY, pred_naive)
#
return pd.DataFrame(
[{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_LR_SA': acc_LR_SA,
'acc_LR_SA_INFO': str(acc_LR_SA_INFO),
'acc_DT_SA': acc_DT_SA,
'acc_DT_SA_INFO': str(acc_DT_SA_INFO),
'acc_NB_SA': acc_NB_SA,
'acc_NB_SA_INFO': str(acc_NB_SA_INFO),
}]
)
def build_models(trainX, trainY, testX, testY, source_pos, target_pos, window):
#######################
### SEMI-SUPERVISED ###
########################
# Label Propagation
label_prop_model = LabelPropagation(kernel='knn')
label_prop_model.fit(trainX, trainY)
Y_Pred = label_prop_model.predict(testX)
acc_ss_propagation, acc_ss_propagation_INFO = checkAccuracy(testY, Y_Pred)
# Label Spreading
label_prop_models_spr = LabelSpreading(kernel='knn')
label_prop_models_spr.fit(trainX, trainY)
Y_Pred = label_prop_models_spr.predict(testX)
acc_ss_spreading, acc_ss_spreading_INFO = checkAccuracy(testY, Y_Pred)
########################
#### WITHOUT TL ########
########################
# LogisticRegression
modelLR = LogisticRegression()
modelLR.fit(trainX, trainY)
predLR = modelLR.predict(testX)
accLR, acc_LR_INFO = checkAccuracy(testY, predLR)
# DecisionTreeClassifier
modelDT = tree.DecisionTreeClassifier()
modelDT.fit(trainX, trainY)
predDT = modelDT.predict(testX)
accDT, acc_DT_INFO = checkAccuracy(testY, predDT)
# BernoulliNB
modelNB = BernoulliNB()
modelNB.fit(trainX, trainY)
predND = modelNB.predict(testX)
accNB, acc_NB_INFO = checkAccuracy(testY, predND)
#
print("WITHOUT TL ACC_LR:", accLR, " ACC_DT:", accDT, " ACC_NB:", accNB)
########################
#### WITH TL ########
########################
####################################################
### Kernel Mean Matching (Huang et al., 2006)
###
# Decision Tree
print("\n Kernel Mean Matching (Huang et al., 2006) ")
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_KMM, acc_DT_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_KMM)
# Logistic Regression
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_KMM, acc_LR_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_KMM)
# Naive Bayes Bernoulli
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_KMM, acc_NB_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_KMM)
####################################################
### Nearest-neighbour-based weighting (Loog, 2015)
###
# Decision Tree
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_NN, acc_DT_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_NN)
# Logistic Regression
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_NN, acc_LR_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_NN)
# Naive Bayes Bernoulli
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_NN, acc_NB_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_NN)
####################################################
### Transfer Component Analysis (Pan et al, 2009)
###
# Decision Tree
print("\n Transfer Component Analysis (Pan et al, 2009)")
classifier = TransferComponentClassifier(loss="dtree", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_TCA, acc_DT_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_TCA)
# Logistic Regression
classifier = TransferComponentClassifier(loss="logistic", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_TCA, acc_LR_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_TCA)
# Naive Bayes Bernoulli
classifier = TransferComponentClassifier(loss="berno", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_TCA, acc_NB_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_TCA)
####################################################
### Subspace Alignment (Fernando et al., 2013)
###
# Decision Tree
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_SA, acc_DT_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_SA)
# Logistic Regression
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_SA, acc_LR_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_SA)
# Naive Bayes Bernoulli
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_SA, acc_NB_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_SA)
#################################
############# ENSEMBLE ##########
#################################
classifier_SA_DT = SubspaceAlignedClassifier(loss="dtree")
classifier_SA_LR = SubspaceAlignedClassifier(loss="logistic")
classifier_SA_NB = SubspaceAlignedClassifier(loss="berno")
classifier_TCA_DT = TransferComponentClassifier(loss="dtree")
classifier_TCA_LR = TransferComponentClassifier(loss="logistic")
classifier_TCA_NB = TransferComponentClassifier(loss="berno")
classifier_NN_DT = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier_NN_LR = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier_NN_NB = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier_KMM_DT = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier_KMM_LR = ImportanceWeightedClassifier(iwe='kmm',
loss="logistic")
classifier_KMM_NB = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
#
eclf = EnsembleClassifier(
clfs=[classifier_TCA_DT, classifier_NN_DT, classifier_KMM_DT])
eclf.fit(trainX, trainY, testX)
pred = eclf.predict_v2(testX)
acc_ENSEMBLE, acc_ENSEMBLE_INFO = checkAccuracy(testY, pred)
########################
#### RETURN ########
########################
return pd.DataFrame([{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_SS_propagation': acc_ss_propagation,
'acc_SS_propagation_INFO': acc_ss_propagation_INFO,
'acc_SS_spreading': acc_ss_spreading,
'acc_SS_spreading_INFO': acc_ss_spreading_INFO,
'acc_ENSEMBLE': acc_ENSEMBLE,
'acc_LR': accLR,
'acc_LR_INFO': str(acc_LR_INFO),
'acc_DT': accDT,
'acc_DT_INFO': str(acc_DT_INFO),
'acc_NB': accNB,
'acc_NB_INFO': str(acc_NB_INFO),
'acc_LR_KMM': acc_LR_KMM,
'acc_LR_KMM_INFO': str(acc_LR_KMM_INFO),
'acc_LR_NN': acc_LR_NN,
'acc_LR_NN_INFO': str(acc_LR_NN_INFO),
'acc_LR_TCA': acc_LR_TCA,
'acc_LR_TCA_INFO': str(acc_LR_TCA_INFO),
'acc_LR_SA': acc_LR_SA,
'acc_LR_SA_INFO': str(acc_LR_SA_INFO),
'acc_DT_KMM': acc_DT_KMM,
'acc_DT_KMM_INFO': str(acc_DT_KMM_INFO),
'acc_DT_NN': acc_DT_NN,
'acc_DT_NN_INFO': str(acc_DT_NN_INFO),
'acc_DT_TCA': acc_DT_TCA,
'acc_DT_TCA_INFO': str(acc_DT_TCA_INFO),
'acc_DT_SA': acc_DT_SA,
'acc_DT_SA_INFO': str(acc_DT_SA_INFO),
'acc_NB_KMM': acc_NB_KMM,
'acc_NB_KMM_INFO': str(acc_NB_KMM_INFO),
'acc_NB_NN': acc_NB_NN,
'acc_NB_NN_INFO': str(acc_NB_NN_INFO),
'acc_NB_TCA': acc_NB_TCA,
'acc_NB_TCA_INFO': str(acc_NB_TCA_INFO),
'acc_NB_SA': acc_NB_SA,
'acc_NB_SA_INFO': str(acc_NB_SA_INFO)
}])
X_s_t = np.vstack([X_s, X_t_init]) y_s_t = np.concatenate([y_s, y_t_init]) clf_sup = RandomForestClassifier().fit(X_s_t, y_s_t) pred = clf_sup.predict(X_test) print(accuracy_score(y_test, pred)) clf_sup = MLPClassifier().fit(X_s_t, y_s_t) pred = clf_sup.predict(X_test) print(accuracy_score(y_test, pred)) clf_sup = DecisionTreeClassifier().fit(X_s_t, y_s_t) pred = clf_sup.predict(X_test) print(accuracy_score(y_test, pred)) clf_sup = SVC().fit(X_s_t, y_s_t) pred = clf_sup.predict(X_test) print(accuracy_score(y_test, pred)) # ENCO learning clf_sup = encolearning.EnCoLearning(iteration=20).fit(X_s_t, y_s_t, X_t) pred = clf_sup.predict(X_test) print(accuracy_score(y_test, pred)) #%% TCA clf_tca = SubspaceAlignedClassifier(num_components=10) clf_tca.fit(X_s, y_s.reshape(len(y_s), ), X_t) pred = clf_tca.predict(X_test) acc = accuracy_score(y_test, pred) print(acc)
def test_init():
"""Test for object type."""
clf = SubspaceAlignedClassifier()
assert type(clf) == SubspaceAlignedClassifier
assert not clf.is_trained